size of train loader is: 90
torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6200, 0.4070, 0.8938, 0.4183, 0.3538, 0.4567, 0.6175, 0.5400],
[0.6197, 0.3986, 0.8800, 0.4617, 0.4188, 0.4783, 0.5687, 0.5550],
[0.6276, 0.4002, 0.8800, 0.5533, 0.3575, 0.4400, 0.6132, 0.4672],
[0.6162, 0.4014, 0.8800, 0.5333, 0.3750, 0.4817, 0.5988, 0.5283],
[0.6346, 0.4165, 0.9138, 0.3983, 0.3875, 0.4317, 0.7469, 0.5471],
[0.6325, 0.4165, 0.9000, 0.4617, 0.3813, 0.4900, 0.7485, 0.5447],
[0.6175, 0.4013, 0.7734, 0.2783, 0.4475, 0.1786, 0.5790, 0.5351],
[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[-0.0584, 0.2115, -0.0577, -0.0264, 0.6124, -0.3884, 0.2870, 0.4973],
[-0.0186, 0.2038, -0.0694, -0.0212, 0.5656, -0.3732, 0.2786, 0.4981],
[-0.0844, 0.2453, -0.0447, -0.0736, 0.6318, -0.3736, 0.2809, 0.5259],
[-0.0908, 0.2592, -0.0879, -0.0383, 0.5870, -0.3843, 0.3103, 0.4775],
[-0.0545, 0.2420, -0.0500, -0.0258, 0.6162, -0.3611, 0.2940, 0.5109],
[-0.0442, 0.2109, -0.0649, -0.0483, 0.5915, -0.3324, 0.2890, 0.5157],
[-0.0514, 0.2363, -0.0713, -0.0051, 0.6292, -0.3114, 0.2788, 0.4927],
[-0.0822, 0.2308, -0.0656, -0.0090, 0.6174, -0.3896, 0.2823, 0.5259]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6200, 0.4070, 0.8938, 0.4183, 0.3537, 0.4567, 0.6175, 0.5400],
[0.6197, 0.3986, 0.8800, 0.4617, 0.4187, 0.4783, 0.5688, 0.5550],
[0.6276, 0.4002, 0.8800, 0.5533, 0.3575, 0.4400, 0.6132, 0.4672],
[0.6162, 0.4014, 0.8800, 0.5333, 0.3750, 0.4817, 0.5987, 0.5283],
[0.6346, 0.4165, 0.9137, 0.3983, 0.3875, 0.4317, 0.7469, 0.5471],
[0.6325, 0.4165, 0.9000, 0.4617, 0.3812, 0.4900, 0.7485, 0.5447],
[0.6175, 0.4013, 0.7734, 0.2783, 0.4475, 0.1786, 0.5790, 0.5351],
[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383]]],
device='cuda:0')
loss_train_step before backward: tensor(0.2998, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.2998, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.2997697591781616
step: 1
running loss: 0.2997697591781616
Train Steps: 1/90 Loss: 0.2998 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6234, 0.4023, 0.8888, 0.4633, 0.3975, 0.5767, 0.6400, 0.5183],
[0.6226, 0.4125, 0.8800, 0.4900, 0.4512, 0.5600, 0.6275, 0.5517],
[0.6236, 0.3977, 0.8985, 0.4806, 0.3835, 0.5216, 0.6613, 0.5166],
[0.6143, 0.4055, 0.8150, 0.2767, 0.3825, 0.2567, 0.5173, 0.4901],
[0.6150, 0.3949, 0.8800, 0.4033, 0.3825, 0.4900, 0.5875, 0.5483],
[0.6214, 0.3982, 0.8938, 0.4517, 0.3663, 0.4083, 0.5863, 0.5050],
[0.6200, 0.3993, 0.8519, 0.4923, 0.3962, 0.4717, 0.6013, 0.5433],
[0.6165, 0.4106, 0.7575, 0.1733, 0.3838, 0.2650, 0.5680, 0.5116]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.1958, 0.3088, 0.2890, 0.1878, 0.4821, -0.0499, 0.4648, 0.5882],
[ 0.2268, 0.3071, 0.2562, 0.1235, 0.4270, -0.0543, 0.4471, 0.5042],
[ 0.2150, 0.3346, 0.2953, 0.1354, 0.4465, -0.0666, 0.4839, 0.5662],
[ 0.2461, 0.2619, 0.2592, 0.1226, 0.4609, -0.0660, 0.4270, 0.4831],
[ 0.1998, 0.3029, 0.2570, 0.1213, 0.4600, -0.0628, 0.4580, 0.5487],
[ 0.2079, 0.2926, 0.2190, 0.1779, 0.4371, -0.0531, 0.4744, 0.5373],
[ 0.2588, 0.2846, 0.2885, 0.1383, 0.4450, -0.0381, 0.4251, 0.5413],
[ 0.1834, 0.2973, 0.3002, 0.1576, 0.4539, -0.0788, 0.4260, 0.5624]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6234, 0.4023, 0.8888, 0.4633, 0.3975, 0.5767, 0.6400, 0.5183],
[0.6226, 0.4125, 0.8800, 0.4900, 0.4512, 0.5600, 0.6275, 0.5517],
[0.6236, 0.3977, 0.8985, 0.4806, 0.3835, 0.5216, 0.6613, 0.5166],
[0.6143, 0.4055, 0.8150, 0.2767, 0.3825, 0.2567, 0.5173, 0.4901],
[0.6150, 0.3949, 0.8800, 0.4033, 0.3825, 0.4900, 0.5875, 0.5483],
[0.6214, 0.3982, 0.8938, 0.4517, 0.3663, 0.4083, 0.5863, 0.5050],
[0.6200, 0.3993, 0.8519, 0.4923, 0.3963, 0.4717, 0.6012, 0.5433],
[0.6165, 0.4106, 0.7575, 0.1733, 0.3837, 0.2650, 0.5680, 0.5116]]],
device='cuda:0')
loss_train_step before backward: tensor(0.1120, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.1120, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.4117617905139923
step: 2
running loss: 0.20588089525699615
Train Steps: 2/90 Loss: 0.2059 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6133, 0.4094, 0.8495, 0.4028, 0.3588, 0.3200, 0.5003, 0.5407],
[0.6164, 0.3956, 0.8757, 0.5088, 0.4300, 0.5320, 0.6022, 0.5202],
[0.6286, 0.4078, 0.8063, 0.2267, 0.4788, 0.1533, 0.5953, 0.4913],
[0.6059, 0.4002, 0.7562, 0.2767, 0.3538, 0.3033, 0.5529, 0.5455],
[0.6227, 0.4193, 0.8838, 0.4933, 0.3663, 0.3733, 0.5637, 0.5633],
[0.6223, 0.4130, 0.8100, 0.2983, 0.3525, 0.3900, 0.5694, 0.5103],
[0.6229, 0.4107, 0.8137, 0.2883, 0.4750, 0.1717, 0.5813, 0.5400],
[ nan, nan, 0.7612, 0.3250, 0.4037, 0.2533, 0.5438, 0.5767]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4055, 0.3739, 0.5440, 0.2942, 0.3808, 0.2197, 0.5719, 0.5390],
[0.4301, 0.4093, 0.5301, 0.2674, 0.3338, 0.2265, 0.5864, 0.5637],
[0.3896, 0.3546, 0.4938, 0.2991, 0.3735, 0.1760, 0.5180, 0.5417],
[0.3896, 0.3833, 0.5534, 0.3136, 0.3577, 0.1936, 0.5783, 0.5552],
[0.4145, 0.4122, 0.5246, 0.2921, 0.3729, 0.2434, 0.5558, 0.5490],
[0.3705, 0.3855, 0.5324, 0.3042, 0.3832, 0.1809, 0.5555, 0.5525],
[0.3739, 0.3511, 0.5211, 0.2681, 0.3678, 0.1772, 0.5384, 0.5119],
[0.3903, 0.3680, 0.5187, 0.2795, 0.3428, 0.1927, 0.5294, 0.5423]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6133, 0.4094, 0.8495, 0.4028, 0.3587, 0.3200, 0.5003, 0.5407],
[0.6164, 0.3956, 0.8757, 0.5088, 0.4300, 0.5320, 0.6022, 0.5202],
[0.6286, 0.4078, 0.8062, 0.2267, 0.4787, 0.1533, 0.5953, 0.4913],
[0.6059, 0.4002, 0.7563, 0.2767, 0.3537, 0.3033, 0.5529, 0.5455],
[0.6227, 0.4193, 0.8838, 0.4933, 0.3663, 0.3733, 0.5638, 0.5633],
[0.6223, 0.4130, 0.8100, 0.2983, 0.3525, 0.3900, 0.5694, 0.5103],
[0.6229, 0.4107, 0.8138, 0.2883, 0.4750, 0.1717, 0.5813, 0.5400],
[0.0000, 0.0000, 0.7613, 0.3250, 0.4038, 0.2533, 0.5437, 0.5767]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0267, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0267, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.43846603110432625
step: 3
running loss: 0.1461553437014421
Train Steps: 3/90 Loss: 0.1462 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6095, 0.4002, 0.8533, 0.5168, 0.5031, 0.5094, 0.5125, 0.5433],
[0.6230, 0.4152, 0.7588, 0.2283, 0.4012, 0.2883, 0.6200, 0.5767],
[0.6164, 0.3956, 0.8757, 0.5088, 0.4300, 0.5320, 0.6022, 0.5202],
[0.6075, 0.4000, 0.8513, 0.5183, 0.4510, 0.5329, 0.5180, 0.5280],
[0.6177, 0.4086, 0.8738, 0.3950, 0.3775, 0.5600, 0.6225, 0.5700],
[0.6201, 0.4029, 0.8776, 0.4602, 0.3683, 0.4203, 0.5938, 0.5450],
[0.6212, 0.4171, 0.7875, 0.3633, 0.3813, 0.2933, 0.5675, 0.5700],
[0.6204, 0.4091, 0.8950, 0.4783, 0.3613, 0.4617, 0.6063, 0.5617]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5931, 0.4201, 0.7860, 0.3801, 0.3459, 0.3958, 0.5810, 0.5520],
[0.5350, 0.4044, 0.8002, 0.3776, 0.3409, 0.3038, 0.6013, 0.5565],
[0.5821, 0.4141, 0.8026, 0.3910, 0.3213, 0.3766, 0.6106, 0.5469],
[0.5523, 0.3895, 0.7907, 0.4043, 0.3298, 0.3388, 0.6085, 0.5748],
[0.5915, 0.4425, 0.8049, 0.4194, 0.3449, 0.4237, 0.6408, 0.5606],
[0.6064, 0.4165, 0.7978, 0.3757, 0.3294, 0.4055, 0.6155, 0.5291],
[0.5497, 0.3888, 0.7902, 0.3943, 0.3422, 0.3726, 0.6113, 0.5332],
[0.5783, 0.4244, 0.8106, 0.3968, 0.2945, 0.3802, 0.6230, 0.5543]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6095, 0.4002, 0.8533, 0.5168, 0.5031, 0.5094, 0.5125, 0.5433],
[0.6230, 0.4152, 0.7588, 0.2283, 0.4013, 0.2883, 0.6200, 0.5767],
[0.6164, 0.3956, 0.8757, 0.5088, 0.4300, 0.5320, 0.6022, 0.5202],
[0.6075, 0.4000, 0.8512, 0.5183, 0.4510, 0.5329, 0.5180, 0.5280],
[0.6177, 0.4085, 0.8737, 0.3950, 0.3775, 0.5600, 0.6225, 0.5700],
[0.6201, 0.4029, 0.8776, 0.4602, 0.3683, 0.4203, 0.5938, 0.5450],
[0.6212, 0.4171, 0.7875, 0.3633, 0.3812, 0.2933, 0.5675, 0.5700],
[0.6204, 0.4091, 0.8950, 0.4783, 0.3613, 0.4617, 0.6062, 0.5617]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0052, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0052, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.4436452961526811
step: 4
running loss: 0.11091132403817028
Train Steps: 4/90 Loss: 0.1109 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6264, 0.4071, 0.9038, 0.3867, 0.3663, 0.3917, 0.6338, 0.5283],
[0.6275, 0.4071, 0.8075, 0.2100, 0.4700, 0.1533, 0.6148, 0.4834],
[0.6229, 0.4107, 0.8137, 0.2883, 0.4750, 0.1717, 0.5813, 0.5400],
[0.6115, 0.3998, 0.7063, 0.2383, 0.4037, 0.1950, 0.5320, 0.4993],
[0.6160, 0.4093, 0.8314, 0.4417, 0.3675, 0.4583, 0.5250, 0.5808],
[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459],
[0.6064, 0.4019, 0.8650, 0.4517, 0.4037, 0.5367, 0.5703, 0.5609],
[0.6353, 0.4128, 0.9138, 0.3533, 0.4688, 0.3250, 0.7145, 0.5991]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6595, 0.4149, 0.9635, 0.4405, 0.3608, 0.5043, 0.6468, 0.5533],
[0.6573, 0.4416, 0.9378, 0.4602, 0.3851, 0.4643, 0.6446, 0.5442],
[0.6465, 0.3929, 0.9284, 0.3990, 0.3773, 0.3864, 0.6122, 0.5066],
[0.6654, 0.4107, 0.9472, 0.4188, 0.3765, 0.4518, 0.6117, 0.5490],
[0.6871, 0.4540, 0.9970, 0.4859, 0.3264, 0.5708, 0.6297, 0.5511],
[0.6877, 0.4320, 0.9677, 0.5030, 0.3692, 0.5202, 0.6485, 0.5374],
[0.6752, 0.4174, 1.0047, 0.5007, 0.3579, 0.5584, 0.6603, 0.5398],
[0.6805, 0.4097, 0.9533, 0.4593, 0.3685, 0.4398, 0.6234, 0.5440]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6264, 0.4071, 0.9038, 0.3867, 0.3663, 0.3917, 0.6338, 0.5283],
[0.6275, 0.4071, 0.8075, 0.2100, 0.4700, 0.1533, 0.6148, 0.4834],
[0.6229, 0.4107, 0.8138, 0.2883, 0.4750, 0.1717, 0.5813, 0.5400],
[0.6115, 0.3998, 0.7063, 0.2383, 0.4038, 0.1950, 0.5320, 0.4993],
[0.6160, 0.4092, 0.8314, 0.4417, 0.3675, 0.4583, 0.5250, 0.5808],
[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459],
[0.6064, 0.4019, 0.8650, 0.4517, 0.4038, 0.5367, 0.5703, 0.5609],
[0.6353, 0.4128, 0.9137, 0.3533, 0.4688, 0.3250, 0.7145, 0.5991]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0123, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0123, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.455948734190315
step: 5
running loss: 0.091189746838063
Train Steps: 5/90 Loss: 0.0912 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6111, 0.3995, 0.8788, 0.4567, 0.3813, 0.4833, 0.5450, 0.5700],
[0.6304, 0.4029, 0.8413, 0.5217, 0.4125, 0.5617, 0.7089, 0.5679],
[0.6203, 0.4056, 0.8942, 0.4086, 0.3643, 0.3617, 0.5917, 0.5482],
[0.6204, 0.4049, 0.7975, 0.2700, 0.3937, 0.2567, 0.5700, 0.5183],
[0.6154, 0.4112, 0.7037, 0.2317, 0.4238, 0.1833, 0.5350, 0.5600],
[0.6204, 0.4055, 0.8438, 0.5733, 0.4574, 0.4801, 0.5487, 0.5617],
[0.6207, 0.4081, 0.7662, 0.2067, 0.3962, 0.3200, 0.6312, 0.5300],
[0.6200, 0.4071, 0.7338, 0.1917, 0.4200, 0.2450, 0.6150, 0.5517]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7639, 0.4666, 1.0737, 0.5197, 0.4200, 0.6167, 0.6571, 0.5344],
[0.7446, 0.4824, 1.0979, 0.4950, 0.4316, 0.6142, 0.6310, 0.5616],
[0.7546, 0.4313, 1.0392, 0.4391, 0.4339, 0.5028, 0.6431, 0.5494],
[0.7280, 0.4014, 1.0350, 0.3954, 0.4080, 0.4104, 0.6010, 0.5530],
[0.7477, 0.4200, 1.0253, 0.4783, 0.4805, 0.4765, 0.5870, 0.5082],
[0.7686, 0.4448, 1.0690, 0.4399, 0.4344, 0.5180, 0.6374, 0.5681],
[0.7443, 0.4067, 1.0424, 0.4304, 0.4043, 0.5326, 0.6042, 0.5293],
[0.7320, 0.4131, 1.0113, 0.4355, 0.3841, 0.4534, 0.6299, 0.5128]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6111, 0.3995, 0.8788, 0.4567, 0.3812, 0.4833, 0.5450, 0.5700],
[0.6304, 0.4029, 0.8413, 0.5217, 0.4125, 0.5617, 0.7089, 0.5679],
[0.6203, 0.4056, 0.8942, 0.4086, 0.3643, 0.3617, 0.5917, 0.5482],
[0.6204, 0.4049, 0.7975, 0.2700, 0.3938, 0.2567, 0.5700, 0.5183],
[0.6154, 0.4112, 0.7038, 0.2317, 0.4238, 0.1833, 0.5350, 0.5600],
[0.6204, 0.4055, 0.8438, 0.5733, 0.4574, 0.4801, 0.5487, 0.5617],
[0.6207, 0.4081, 0.7663, 0.2067, 0.3963, 0.3200, 0.6313, 0.5300],
[0.6200, 0.4071, 0.7337, 0.1917, 0.4200, 0.2450, 0.6150, 0.5517]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0178, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0178, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.4737188364379108
step: 6
running loss: 0.07895313940631847
Train Steps: 6/90 Loss: 0.0790 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6350, 0.4043, 0.8738, 0.5650, 0.3850, 0.4750, 0.6401, 0.4950],
[0.6276, 0.4095, 0.8237, 0.2250, 0.4662, 0.1783, 0.6171, 0.4869],
[0.6131, 0.4037, 0.6907, 0.2819, 0.3688, 0.2700, 0.5217, 0.5680],
[0.6202, 0.4066, 0.8398, 0.2648, 0.3925, 0.2627, 0.5845, 0.5124],
[0.6196, 0.4088, 0.8888, 0.4583, 0.4500, 0.5683, 0.6138, 0.5883],
[0.6267, 0.4065, 0.8313, 0.2467, 0.4788, 0.1733, 0.6312, 0.5133],
[0.6282, 0.4092, 0.8000, 0.2183, 0.4500, 0.2383, 0.6787, 0.5364],
[0.6282, 0.4029, 0.8988, 0.3000, 0.4250, 0.4183, 0.7042, 0.5575]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7992, 0.4712, 1.0351, 0.5252, 0.4813, 0.6162, 0.6746, 0.5770],
[0.7076, 0.4036, 0.9749, 0.3386, 0.4551, 0.3386, 0.5951, 0.5499],
[0.7864, 0.4010, 1.0021, 0.3990, 0.4437, 0.4824, 0.5861, 0.5256],
[0.6992, 0.3757, 0.9816, 0.3626, 0.4514, 0.2998, 0.5664, 0.5662],
[0.8054, 0.4612, 1.0290, 0.4557, 0.4737, 0.5697, 0.6536, 0.5601],
[0.7407, 0.4508, 0.9957, 0.4088, 0.4786, 0.4903, 0.6357, 0.5672],
[0.7307, 0.4101, 1.0154, 0.4157, 0.4688, 0.3993, 0.5921, 0.5474],
[0.7518, 0.3969, 1.0725, 0.4365, 0.4336, 0.5652, 0.6162, 0.5677]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6350, 0.4043, 0.8737, 0.5650, 0.3850, 0.4750, 0.6401, 0.4950],
[0.6276, 0.4095, 0.8238, 0.2250, 0.4663, 0.1783, 0.6171, 0.4869],
[0.6131, 0.4036, 0.6907, 0.2819, 0.3688, 0.2700, 0.5217, 0.5680],
[0.6202, 0.4066, 0.8398, 0.2648, 0.3925, 0.2627, 0.5845, 0.5124],
[0.6196, 0.4088, 0.8888, 0.4583, 0.4500, 0.5683, 0.6137, 0.5883],
[0.6266, 0.4065, 0.8313, 0.2467, 0.4787, 0.1733, 0.6313, 0.5133],
[0.6282, 0.4092, 0.8000, 0.2183, 0.4500, 0.2383, 0.6787, 0.5364],
[0.6282, 0.4029, 0.8988, 0.3000, 0.4250, 0.4183, 0.7042, 0.5575]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0135, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0135, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.48724996810778975
step: 7
running loss: 0.06960713830111283
Train Steps: 7/90 Loss: 0.0696 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6134, 0.4090, 0.6926, 0.2819, 0.3538, 0.3233, 0.5563, 0.5667],
[0.6246, 0.4028, 0.8738, 0.4867, 0.4088, 0.5667, 0.6362, 0.5200],
[0.6307, 0.4060, 0.8950, 0.5183, 0.3750, 0.3850, 0.6338, 0.4938],
[0.6226, 0.4001, 0.8438, 0.5733, 0.3862, 0.4250, 0.5750, 0.5283],
[ nan, nan, 0.8213, 0.2700, 0.3775, 0.2817, 0.5425, 0.5533],
[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.6329, 0.4175, 0.8550, 0.2333, 0.5425, 0.2250, 0.7398, 0.5609],
[0.6296, 0.3989, 0.9000, 0.4150, 0.3613, 0.3867, 0.6400, 0.5100]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7125, 0.4141, 0.9276, 0.3407, 0.4545, 0.3371, 0.6088, 0.5133],
[0.7724, 0.4321, 0.9407, 0.3951, 0.4934, 0.5374, 0.6366, 0.5840],
[0.7000, 0.4080, 0.9320, 0.3456, 0.4463, 0.3606, 0.5961, 0.5657],
[0.7373, 0.4212, 0.9778, 0.3996, 0.4907, 0.4384, 0.6298, 0.5426],
[0.6694, 0.3810, 0.9105, 0.2660, 0.4332, 0.2168, 0.5700, 0.5416],
[0.7486, 0.4425, 0.9655, 0.4365, 0.4873, 0.4980, 0.6413, 0.5653],
[0.6991, 0.4299, 0.9115, 0.3282, 0.5000, 0.3444, 0.6179, 0.5303],
[0.7601, 0.4259, 0.9607, 0.4066, 0.4690, 0.5100, 0.6555, 0.5402]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6134, 0.4090, 0.6926, 0.2819, 0.3537, 0.3233, 0.5562, 0.5667],
[0.6246, 0.4028, 0.8737, 0.4867, 0.4087, 0.5667, 0.6363, 0.5200],
[0.6307, 0.4060, 0.8950, 0.5183, 0.3750, 0.3850, 0.6338, 0.4938],
[0.6226, 0.4001, 0.8438, 0.5733, 0.3862, 0.4250, 0.5750, 0.5283],
[0.0000, 0.0000, 0.8213, 0.2700, 0.3775, 0.2817, 0.5425, 0.5533],
[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.6329, 0.4175, 0.8550, 0.2333, 0.5425, 0.2250, 0.7398, 0.5609],
[0.6296, 0.3989, 0.9000, 0.4150, 0.3613, 0.3867, 0.6400, 0.5100]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0159, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0159, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.503159002866596
step: 8
running loss: 0.0628948753583245
Train Steps: 8/90 Loss: 0.0629 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6257, 0.4024, 0.8612, 0.5352, 0.4361, 0.5253, 0.6680, 0.5166],
[0.6193, 0.4034, 0.7757, 0.2347, 0.3733, 0.2919, 0.5930, 0.4926],
[0.6332, 0.4128, 0.9200, 0.3517, 0.4400, 0.3833, 0.7461, 0.5494],
[0.6223, 0.4171, 0.8750, 0.5500, 0.4050, 0.4817, 0.5675, 0.5600],
[0.6329, 0.4196, 0.9238, 0.4583, 0.4263, 0.2933, 0.7343, 0.5748],
[0.6230, 0.4152, 0.7588, 0.2283, 0.4012, 0.2883, 0.6200, 0.5767],
[0.6277, 0.4013, 0.8888, 0.4767, 0.3600, 0.3567, 0.6148, 0.4672],
[0.6111, 0.4033, 0.8300, 0.3267, 0.3588, 0.3333, 0.5444, 0.5637]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6310, 0.4255, 0.8500, 0.3970, 0.4594, 0.4231, 0.6480, 0.5211],
[0.5883, 0.3990, 0.8303, 0.3005, 0.4513, 0.3195, 0.6211, 0.5154],
[0.6312, 0.3964, 0.8382, 0.3922, 0.4255, 0.4006, 0.6227, 0.4975],
[0.6345, 0.4232, 0.8789, 0.3901, 0.4579, 0.4217, 0.6088, 0.5509],
[0.5915, 0.3512, 0.8164, 0.3049, 0.4660, 0.2282, 0.5638, 0.5399],
[0.6027, 0.3788, 0.8326, 0.2586, 0.4733, 0.2217, 0.6128, 0.5120],
[0.6407, 0.4505, 0.8766, 0.4017, 0.4244, 0.4355, 0.6682, 0.5646],
[0.6337, 0.3537, 0.8414, 0.3109, 0.4235, 0.2654, 0.6164, 0.5033]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6257, 0.4024, 0.8612, 0.5352, 0.4361, 0.5253, 0.6680, 0.5166],
[0.6193, 0.4034, 0.7757, 0.2347, 0.3733, 0.2919, 0.5930, 0.4926],
[0.6332, 0.4128, 0.9200, 0.3517, 0.4400, 0.3833, 0.7461, 0.5494],
[0.6223, 0.4171, 0.8750, 0.5500, 0.4050, 0.4817, 0.5675, 0.5600],
[0.6329, 0.4196, 0.9237, 0.4583, 0.4263, 0.2933, 0.7343, 0.5748],
[0.6230, 0.4152, 0.7588, 0.2283, 0.4013, 0.2883, 0.6200, 0.5767],
[0.6277, 0.4013, 0.8888, 0.4767, 0.3600, 0.3567, 0.6148, 0.4672],
[0.6111, 0.4033, 0.8300, 0.3267, 0.3587, 0.3333, 0.5444, 0.5637]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0041, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0041, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.5072252913378179
step: 9
running loss: 0.05635836570420199
Train Steps: 9/90 Loss: 0.0564 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6300, 0.4013, 0.8938, 0.5350, 0.3675, 0.4600, 0.6456, 0.4973],
[0.6250, 0.4116, 0.8700, 0.4850, 0.4650, 0.5567, 0.6088, 0.5183],
[0.6128, 0.4084, 0.8738, 0.4683, 0.3613, 0.3700, 0.4960, 0.5397],
[0.6195, 0.4101, 0.8650, 0.3917, 0.3575, 0.4033, 0.5800, 0.5650],
[0.6122, 0.4048, 0.7506, 0.3014, 0.3475, 0.3333, 0.5487, 0.5749],
[0.6146, 0.4124, 0.8800, 0.4867, 0.3800, 0.4500, 0.5106, 0.5524],
[0.6101, 0.3977, 0.8550, 0.5667, 0.3862, 0.4417, 0.5128, 0.4869],
[ nan, nan, 0.8850, 0.3000, 0.5363, 0.2250, 0.7343, 0.5771]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5854, 0.4194, 0.7982, 0.4484, 0.3842, 0.4339, 0.6975, 0.4881],
[0.5636, 0.3870, 0.7519, 0.3707, 0.4280, 0.3838, 0.6772, 0.5203],
[0.5463, 0.3677, 0.7634, 0.3431, 0.3938, 0.2582, 0.6202, 0.5056],
[0.5107, 0.3751, 0.7688, 0.3725, 0.3725, 0.3147, 0.6341, 0.5228],
[0.5468, 0.3651, 0.7660, 0.3440, 0.3912, 0.2587, 0.6207, 0.5004],
[0.5300, 0.3686, 0.7474, 0.3380, 0.3827, 0.3088, 0.6002, 0.5400],
[0.5577, 0.3624, 0.7734, 0.3745, 0.3982, 0.3396, 0.6820, 0.4983],
[0.5084, 0.3917, 0.7298, 0.2798, 0.4158, 0.2044, 0.6265, 0.4828]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6300, 0.4013, 0.8938, 0.5350, 0.3675, 0.4600, 0.6456, 0.4973],
[0.6251, 0.4116, 0.8700, 0.4850, 0.4650, 0.5567, 0.6087, 0.5183],
[0.6127, 0.4084, 0.8737, 0.4683, 0.3613, 0.3700, 0.4960, 0.5397],
[0.6195, 0.4101, 0.8650, 0.3917, 0.3575, 0.4033, 0.5800, 0.5650],
[0.6122, 0.4048, 0.7506, 0.3014, 0.3475, 0.3333, 0.5487, 0.5749],
[0.6146, 0.4124, 0.8800, 0.4867, 0.3800, 0.4500, 0.5106, 0.5524],
[0.6101, 0.3977, 0.8550, 0.5667, 0.3862, 0.4417, 0.5128, 0.4869],
[0.0000, 0.0000, 0.8850, 0.3000, 0.5362, 0.2250, 0.7343, 0.5771]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0133, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0133, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.5205279276706278
step: 10
running loss: 0.05205279276706278
Train Steps: 10/90 Loss: 0.0521 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6193, 0.4108, 0.7438, 0.2700, 0.3650, 0.3683, 0.6238, 0.5717],
[0.6216, 0.4099, 0.7225, 0.2033, 0.4188, 0.2217, 0.5975, 0.5283],
[0.6274, 0.4270, 0.8938, 0.4967, 0.3550, 0.4283, 0.5700, 0.5733],
[0.6236, 0.3966, 0.8850, 0.4967, 0.3638, 0.4017, 0.5850, 0.5183],
[0.6310, 0.4017, 0.8563, 0.5800, 0.3688, 0.4750, 0.6326, 0.5006],
[0.6260, 0.4120, 0.8013, 0.2350, 0.4888, 0.1533, 0.6281, 0.4895],
[0.6201, 0.4055, 0.7717, 0.1919, 0.4250, 0.2079, 0.5871, 0.5044],
[0.6357, 0.4139, 0.8450, 0.5883, 0.3775, 0.4950, 0.6488, 0.5297]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4604, 0.3238, 0.7617, 0.3943, 0.3457, 0.3056, 0.6460, 0.4995],
[0.4523, 0.3381, 0.6931, 0.3316, 0.3268, 0.2285, 0.6105, 0.5138],
[0.4482, 0.3509, 0.7564, 0.4134, 0.3853, 0.3224, 0.5696, 0.5136],
[0.5103, 0.3802, 0.7495, 0.4832, 0.3225, 0.3799, 0.6293, 0.5123],
[0.5484, 0.3973, 0.7444, 0.5327, 0.3770, 0.5066, 0.6837, 0.5201],
[0.4322, 0.3602, 0.7118, 0.3229, 0.3856, 0.1895, 0.5927, 0.5381],
[0.4152, 0.3308, 0.6963, 0.2808, 0.3751, 0.1732, 0.5842, 0.4984],
[0.4961, 0.3820, 0.7515, 0.4521, 0.3516, 0.3834, 0.6456, 0.5185]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6193, 0.4108, 0.7437, 0.2700, 0.3650, 0.3683, 0.6237, 0.5717],
[0.6216, 0.4099, 0.7225, 0.2033, 0.4187, 0.2217, 0.5975, 0.5283],
[0.6274, 0.4270, 0.8938, 0.4967, 0.3550, 0.4283, 0.5700, 0.5733],
[0.6236, 0.3965, 0.8850, 0.4967, 0.3638, 0.4017, 0.5850, 0.5183],
[0.6310, 0.4017, 0.8562, 0.5800, 0.3688, 0.4750, 0.6326, 0.5006],
[0.6259, 0.4120, 0.8012, 0.2350, 0.4888, 0.1533, 0.6281, 0.4895],
[0.6202, 0.4055, 0.7717, 0.1919, 0.4250, 0.2079, 0.5871, 0.5044],
[0.6357, 0.4139, 0.8450, 0.5883, 0.3775, 0.4950, 0.6488, 0.5297]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0071, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0071, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.5276685687713325
step: 11
running loss: 0.04796986988830296
Train Steps: 11/90 Loss: 0.0480 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6150, 0.4097, 0.7468, 0.3194, 0.3825, 0.2633, 0.5463, 0.5800],
[0.6361, 0.4076, 0.8862, 0.5350, 0.3713, 0.4650, 0.6654, 0.5297],
[0.6203, 0.4096, 0.8862, 0.4267, 0.3538, 0.4117, 0.6025, 0.5650],
[0.6109, 0.4015, 0.7668, 0.3639, 0.3513, 0.3667, 0.5200, 0.5641],
[0.6201, 0.4064, 0.8688, 0.5050, 0.4225, 0.5100, 0.6138, 0.5500],
[0.6136, 0.4060, 0.8025, 0.3217, 0.3650, 0.3000, 0.5060, 0.5646],
[0.6261, 0.4131, 0.8938, 0.3550, 0.4000, 0.2683, 0.6188, 0.5283],
[ nan, nan, 0.6469, 0.1943, 0.4025, 0.2000, 0.5125, 0.5533]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4242, 0.3276, 0.7231, 0.3277, 0.3530, 0.2147, 0.5563, 0.5227],
[0.5232, 0.4021, 0.7501, 0.5769, 0.3382, 0.5162, 0.6495, 0.5368],
[0.4466, 0.3568, 0.7542, 0.4222, 0.3525, 0.2569, 0.5686, 0.5441],
[0.4663, 0.3350, 0.7140, 0.4204, 0.3233, 0.3100, 0.5935, 0.5369],
[0.5148, 0.3751, 0.7542, 0.5413, 0.3297, 0.4700, 0.6317, 0.5378],
[0.4329, 0.3714, 0.7269, 0.3483, 0.3543, 0.2071, 0.5617, 0.5350],
[0.4669, 0.3490, 0.7035, 0.3924, 0.3518, 0.2807, 0.5944, 0.5369],
[0.4827, 0.3401, 0.7154, 0.3492, 0.3307, 0.2902, 0.5846, 0.5344]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6150, 0.4097, 0.7468, 0.3194, 0.3825, 0.2633, 0.5462, 0.5800],
[0.6361, 0.4076, 0.8863, 0.5350, 0.3713, 0.4650, 0.6654, 0.5297],
[0.6203, 0.4096, 0.8863, 0.4267, 0.3537, 0.4117, 0.6025, 0.5650],
[0.6109, 0.4015, 0.7668, 0.3639, 0.3512, 0.3667, 0.5200, 0.5641],
[0.6201, 0.4064, 0.8687, 0.5050, 0.4225, 0.5100, 0.6137, 0.5500],
[0.6136, 0.4060, 0.8025, 0.3217, 0.3650, 0.3000, 0.5060, 0.5646],
[0.6261, 0.4131, 0.8938, 0.3550, 0.4000, 0.2683, 0.6187, 0.5283],
[0.0000, 0.0000, 0.6469, 0.1943, 0.4025, 0.2000, 0.5125, 0.5533]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0119, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0119, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.5395649061538279
step: 12
running loss: 0.044963742179485656
Train Steps: 12/90 Loss: 0.0450 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6203, 0.4096, 0.8862, 0.4267, 0.3538, 0.4117, 0.6025, 0.5650],
[0.6203, 0.4076, 0.8611, 0.2878, 0.4050, 0.2554, 0.5907, 0.5496],
[0.6250, 0.4054, 0.8770, 0.4723, 0.4662, 0.5367, 0.6162, 0.5433],
[0.6350, 0.4043, 0.8738, 0.5650, 0.3850, 0.4750, 0.6401, 0.4950],
[0.6277, 0.4036, 0.8688, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742],
[0.6082, 0.4024, 0.8738, 0.4017, 0.3688, 0.3950, 0.5306, 0.5136],
[0.6040, 0.4002, 0.7338, 0.2267, 0.3975, 0.2100, 0.5231, 0.4778],
[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4855, 0.3495, 0.7835, 0.4110, 0.3501, 0.2785, 0.5376, 0.5742],
[0.4499, 0.3128, 0.7569, 0.3151, 0.3372, 0.1992, 0.5607, 0.5833],
[0.5349, 0.3750, 0.7566, 0.4635, 0.3470, 0.4020, 0.6041, 0.5436],
[0.5596, 0.3703, 0.7619, 0.5797, 0.3526, 0.4759, 0.5958, 0.5680],
[0.5413, 0.3735, 0.7778, 0.4743, 0.3496, 0.4225, 0.5655, 0.5585],
[0.4563, 0.3362, 0.7333, 0.3678, 0.3327, 0.2827, 0.5468, 0.5548],
[0.4906, 0.3384, 0.7265, 0.3375, 0.3288, 0.2491, 0.5441, 0.5544],
[0.5201, 0.3942, 0.7543, 0.4075, 0.3626, 0.3394, 0.5407, 0.5594]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6203, 0.4096, 0.8863, 0.4267, 0.3537, 0.4117, 0.6025, 0.5650],
[0.6203, 0.4076, 0.8611, 0.2878, 0.4050, 0.2554, 0.5907, 0.5496],
[0.6250, 0.4054, 0.8770, 0.4723, 0.4663, 0.5367, 0.6162, 0.5433],
[0.6350, 0.4043, 0.8737, 0.5650, 0.3850, 0.4750, 0.6401, 0.4950],
[0.6277, 0.4036, 0.8687, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742],
[0.6082, 0.4024, 0.8737, 0.4017, 0.3688, 0.3950, 0.5306, 0.5136],
[0.6040, 0.4002, 0.7337, 0.2267, 0.3975, 0.2100, 0.5231, 0.4778],
[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0066, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0066, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.5461384528316557
step: 13
running loss: 0.042010650217819676
Train Steps: 13/90 Loss: 0.0420 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6339, 0.4149, 0.8800, 0.5000, 0.3900, 0.5283, 0.7541, 0.5424],
[0.6205, 0.4016, 0.8350, 0.2717, 0.3987, 0.2550, 0.5787, 0.5133],
[0.6160, 0.4093, 0.8314, 0.4417, 0.3675, 0.4583, 0.5250, 0.5808],
[0.6273, 0.4143, 0.8750, 0.5700, 0.3987, 0.4717, 0.6013, 0.5467],
[0.6064, 0.4019, 0.8650, 0.4517, 0.4037, 0.5367, 0.5703, 0.5609],
[0.6284, 0.4093, 0.8900, 0.4700, 0.3650, 0.3850, 0.6212, 0.5167],
[0.6274, 0.4117, 0.8100, 0.5801, 0.4000, 0.4583, 0.5582, 0.6118],
[0.6205, 0.4004, 0.8938, 0.4883, 0.3663, 0.5000, 0.6357, 0.4947]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6138, 0.4089, 0.8334, 0.4689, 0.3602, 0.4501, 0.5896, 0.5509],
[0.5220, 0.3308, 0.7897, 0.2446, 0.3819, 0.1887, 0.5110, 0.5884],
[0.5544, 0.3636, 0.8083, 0.4162, 0.3470, 0.3582, 0.5382, 0.5543],
[0.5467, 0.3849, 0.8156, 0.3669, 0.3635, 0.3404, 0.5649, 0.5676],
[0.5364, 0.3596, 0.8030, 0.4386, 0.3820, 0.3932, 0.5638, 0.5476],
[0.5485, 0.3434, 0.7971, 0.3553, 0.3534, 0.2809, 0.5138, 0.5525],
[0.5894, 0.3773, 0.8297, 0.4457, 0.3587, 0.4137, 0.5796, 0.5698],
[0.5982, 0.4032, 0.8306, 0.4746, 0.3600, 0.4449, 0.5974, 0.5406]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6339, 0.4149, 0.8800, 0.5000, 0.3900, 0.5283, 0.7541, 0.5424],
[0.6205, 0.4015, 0.8350, 0.2717, 0.3988, 0.2550, 0.5788, 0.5133],
[0.6160, 0.4092, 0.8314, 0.4417, 0.3675, 0.4583, 0.5250, 0.5808],
[0.6273, 0.4143, 0.8750, 0.5700, 0.3988, 0.4717, 0.6012, 0.5467],
[0.6064, 0.4019, 0.8650, 0.4517, 0.4038, 0.5367, 0.5703, 0.5609],
[0.6284, 0.4092, 0.8900, 0.4700, 0.3650, 0.3850, 0.6212, 0.5167],
[0.6274, 0.4117, 0.8100, 0.5801, 0.4000, 0.4583, 0.5582, 0.6118],
[0.6205, 0.4004, 0.8938, 0.4883, 0.3663, 0.5000, 0.6357, 0.4947]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0045, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0045, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.5506306039169431
step: 14
running loss: 0.03933075742263879
Train Steps: 14/90 Loss: 0.0393 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.6992, 0.2791, 0.3950, 0.2383, 0.5483, 0.5819],
[ nan, nan, 0.6512, 0.1717, 0.4100, 0.1983, 0.5253, 0.5240],
[0.6239, 0.4123, 0.8313, 0.2550, 0.4500, 0.2050, 0.6175, 0.5400],
[0.6111, 0.3995, 0.8788, 0.4567, 0.3813, 0.4833, 0.5450, 0.5700],
[0.6308, 0.3990, 0.8688, 0.5183, 0.3950, 0.4983, 0.6388, 0.5133],
[0.6260, 0.4133, 0.8800, 0.5117, 0.3713, 0.3283, 0.6223, 0.4967],
[0.6353, 0.4128, 0.8488, 0.2600, 0.5525, 0.1616, 0.6694, 0.5540],
[0.6299, 0.4008, 0.8450, 0.5350, 0.4213, 0.5000, 0.6350, 0.5100]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5937, 0.3509, 0.8326, 0.3062, 0.3551, 0.3064, 0.5233, 0.5584],
[0.5701, 0.3368, 0.8274, 0.2523, 0.3597, 0.2419, 0.5122, 0.5743],
[0.5733, 0.3884, 0.8194, 0.2436, 0.4069, 0.2326, 0.5367, 0.5481],
[0.6927, 0.4126, 0.8742, 0.5447, 0.3724, 0.5729, 0.6022, 0.5212],
[0.6857, 0.4112, 0.8971, 0.5565, 0.3780, 0.5510, 0.5959, 0.5286],
[0.6102, 0.3915, 0.8287, 0.3693, 0.3949, 0.3350, 0.5436, 0.5626],
[0.5731, 0.3627, 0.8294, 0.3020, 0.4315, 0.2867, 0.5511, 0.5545],
[0.6631, 0.4388, 0.8668, 0.5153, 0.3947, 0.5607, 0.6025, 0.5215]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.6992, 0.2791, 0.3950, 0.2383, 0.5483, 0.5819],
[0.0000, 0.0000, 0.6513, 0.1717, 0.4100, 0.1983, 0.5253, 0.5240],
[0.6239, 0.4123, 0.8313, 0.2550, 0.4500, 0.2050, 0.6175, 0.5400],
[0.6111, 0.3995, 0.8788, 0.4567, 0.3812, 0.4833, 0.5450, 0.5700],
[0.6308, 0.3990, 0.8687, 0.5183, 0.3950, 0.4983, 0.6388, 0.5133],
[0.6260, 0.4133, 0.8800, 0.5117, 0.3713, 0.3283, 0.6223, 0.4967],
[0.6353, 0.4128, 0.8487, 0.2600, 0.5525, 0.1616, 0.6694, 0.5540],
[0.6299, 0.4008, 0.8450, 0.5350, 0.4212, 0.5000, 0.6350, 0.5100]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0177, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0177, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.5683316038921475
step: 15
running loss: 0.03788877359280984
Train Steps: 15/90 Loss: 0.0379 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6271, 0.4024, 0.9000, 0.3517, 0.3700, 0.4517, 0.6931, 0.5285],
[0.6219, 0.4089, 0.8938, 0.4800, 0.3825, 0.4450, 0.5850, 0.5200],
[0.6275, 0.4071, 0.8075, 0.2100, 0.4700, 0.1533, 0.6148, 0.4834],
[0.6200, 0.3993, 0.8519, 0.4923, 0.3962, 0.4717, 0.6013, 0.5433],
[ nan, nan, 0.8938, 0.2850, 0.4662, 0.3117, 0.7406, 0.5528],
[0.6266, 0.4101, 0.8350, 0.2333, 0.3950, 0.2950, 0.6264, 0.4921],
[0.6182, 0.3967, 0.8263, 0.3065, 0.3526, 0.4161, 0.6192, 0.5290],
[0.6086, 0.4019, 0.7782, 0.4278, 0.3625, 0.4350, 0.5150, 0.5285]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6547, 0.4026, 0.9127, 0.4880, 0.4210, 0.5077, 0.6168, 0.5180],
[0.6555, 0.3753, 0.8744, 0.4401, 0.4125, 0.4705, 0.6017, 0.5382],
[0.5861, 0.3916, 0.8767, 0.2952, 0.4540, 0.3381, 0.5853, 0.5346],
[0.6865, 0.4021, 0.9131, 0.5099, 0.3946, 0.5068, 0.6111, 0.5421],
[0.6070, 0.3931, 0.8990, 0.3118, 0.4520, 0.3536, 0.5994, 0.5259],
[0.6044, 0.3817, 0.8638, 0.2735, 0.4256, 0.2824, 0.5731, 0.5519],
[0.6471, 0.3808, 0.8958, 0.4194, 0.4224, 0.4481, 0.5902, 0.5492],
[0.6469, 0.3749, 0.8770, 0.3937, 0.4066, 0.3749, 0.5731, 0.5123]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6271, 0.4024, 0.9000, 0.3517, 0.3700, 0.4517, 0.6931, 0.5285],
[0.6219, 0.4089, 0.8938, 0.4800, 0.3825, 0.4450, 0.5850, 0.5200],
[0.6275, 0.4071, 0.8075, 0.2100, 0.4700, 0.1533, 0.6148, 0.4834],
[0.6200, 0.3993, 0.8519, 0.4923, 0.3963, 0.4717, 0.6012, 0.5433],
[0.0000, 0.0000, 0.8938, 0.2850, 0.4663, 0.3117, 0.7406, 0.5528],
[0.6266, 0.4101, 0.8350, 0.2333, 0.3950, 0.2950, 0.6264, 0.4921],
[0.6182, 0.3967, 0.8263, 0.3065, 0.3526, 0.4161, 0.6192, 0.5290],
[0.6086, 0.4019, 0.7782, 0.4278, 0.3625, 0.4350, 0.5150, 0.5285]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0110, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0110, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.5793465515598655
step: 16
running loss: 0.03620915947249159
Train Steps: 16/90 Loss: 0.0362 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6198, 0.3997, 0.8582, 0.5361, 0.4117, 0.5016, 0.5942, 0.5134],
[ nan, nan, 0.6992, 0.2791, 0.3950, 0.2383, 0.5483, 0.5819],
[0.6346, 0.4144, 0.9088, 0.4667, 0.3850, 0.4333, 0.7121, 0.5899],
[0.6225, 0.4191, 0.8500, 0.4167, 0.3688, 0.3233, 0.5650, 0.5650],
[0.6072, 0.4029, 0.7037, 0.2150, 0.3912, 0.2267, 0.5516, 0.5507],
[0.6269, 0.4073, 0.8900, 0.4933, 0.3625, 0.4183, 0.6288, 0.5150],
[0.6272, 0.4045, 0.8538, 0.5900, 0.3750, 0.4417, 0.5989, 0.4649],
[0.6273, 0.4143, 0.8750, 0.5700, 0.3987, 0.4717, 0.6013, 0.5467]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6627, 0.4136, 0.9392, 0.5165, 0.4523, 0.5500, 0.6682, 0.4953],
[0.5376, 0.3240, 0.8913, 0.2640, 0.4416, 0.3313, 0.5895, 0.5246],
[0.6395, 0.3805, 0.9361, 0.4163, 0.4485, 0.4339, 0.6147, 0.5254],
[0.5680, 0.3594, 0.9200, 0.2960, 0.4363, 0.3497, 0.5919, 0.5198],
[0.5743, 0.3581, 0.8822, 0.2888, 0.4754, 0.3589, 0.6170, 0.5224],
[0.6266, 0.3792, 0.9241, 0.3970, 0.4373, 0.4108, 0.6244, 0.4996],
[0.6290, 0.3848, 0.9422, 0.4540, 0.4268, 0.4926, 0.6146, 0.5069],
[0.6318, 0.4059, 0.9420, 0.4500, 0.4560, 0.4884, 0.6553, 0.5268]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6198, 0.3997, 0.8582, 0.5361, 0.4117, 0.5016, 0.5942, 0.5134],
[0.0000, 0.0000, 0.6992, 0.2791, 0.3950, 0.2383, 0.5483, 0.5819],
[0.6346, 0.4144, 0.9087, 0.4667, 0.3850, 0.4333, 0.7121, 0.5899],
[0.6225, 0.4191, 0.8500, 0.4167, 0.3688, 0.3233, 0.5650, 0.5650],
[0.6072, 0.4029, 0.7038, 0.2150, 0.3913, 0.2267, 0.5516, 0.5507],
[0.6269, 0.4073, 0.8900, 0.4933, 0.3625, 0.4183, 0.6288, 0.5150],
[0.6271, 0.4045, 0.8537, 0.5900, 0.3750, 0.4417, 0.5989, 0.4649],
[0.6273, 0.4143, 0.8750, 0.5700, 0.3988, 0.4717, 0.6012, 0.5467]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0105, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0105, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.5897985212504864
step: 17
running loss: 0.034694030661793315
Train Steps: 17/90 Loss: 0.0347 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6139, 0.4019, 0.7137, 0.2150, 0.4375, 0.1533, 0.5293, 0.5006],
[0.6147, 0.4107, 0.8137, 0.3333, 0.3750, 0.2683, 0.5006, 0.5412],
[0.6189, 0.3911, 0.8800, 0.4917, 0.3713, 0.4800, 0.6038, 0.4833],
[0.6213, 0.4131, 0.8438, 0.3550, 0.3513, 0.4400, 0.5716, 0.5123],
[0.6187, 0.4104, 0.7126, 0.2069, 0.3950, 0.2517, 0.5913, 0.5683],
[0.6109, 0.4003, 0.8650, 0.4883, 0.4775, 0.4867, 0.5175, 0.5683],
[0.6302, 0.4007, 0.8850, 0.5500, 0.3613, 0.4517, 0.6335, 0.5012],
[0.6169, 0.4052, 0.8742, 0.4779, 0.4288, 0.4917, 0.5763, 0.5617]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4989, 0.3019, 0.8501, 0.2146, 0.4736, 0.2612, 0.5998, 0.5084],
[0.5352, 0.3228, 0.8733, 0.2890, 0.4420, 0.2892, 0.5881, 0.5260],
[0.6540, 0.3960, 0.9527, 0.5137, 0.4338, 0.5415, 0.6720, 0.5053],
[0.5784, 0.3489, 0.9258, 0.4035, 0.4336, 0.4318, 0.6304, 0.5092],
[0.5422, 0.3244, 0.9022, 0.2565, 0.4607, 0.3007, 0.6357, 0.5141],
[0.5923, 0.3676, 0.9305, 0.4436, 0.4626, 0.4719, 0.6405, 0.5138],
[0.6616, 0.3972, 0.9572, 0.5468, 0.4315, 0.5406, 0.6886, 0.4973],
[0.6289, 0.3807, 0.9102, 0.4968, 0.4496, 0.4921, 0.6804, 0.4749]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6139, 0.4019, 0.7138, 0.2150, 0.4375, 0.1533, 0.5293, 0.5006],
[0.6147, 0.4107, 0.8138, 0.3333, 0.3750, 0.2683, 0.5006, 0.5412],
[0.6189, 0.3911, 0.8800, 0.4917, 0.3713, 0.4800, 0.6037, 0.4833],
[0.6213, 0.4131, 0.8438, 0.3550, 0.3512, 0.4400, 0.5716, 0.5123],
[0.6187, 0.4103, 0.7126, 0.2069, 0.3950, 0.2517, 0.5913, 0.5683],
[0.6109, 0.4003, 0.8650, 0.4883, 0.4775, 0.4867, 0.5175, 0.5683],
[0.6302, 0.4007, 0.8850, 0.5500, 0.3613, 0.4517, 0.6335, 0.5012],
[0.6169, 0.4052, 0.8742, 0.4779, 0.4288, 0.4917, 0.5763, 0.5617]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0042, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0042, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.59402234852314
step: 18
running loss: 0.03300124158461889
Train Steps: 18/90 Loss: 0.0330 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6257, 0.4034, 0.8287, 0.2333, 0.3925, 0.2717, 0.6330, 0.4901],
[0.6266, 0.4101, 0.8350, 0.2333, 0.3950, 0.2950, 0.6264, 0.4921],
[0.6229, 0.4086, 0.7538, 0.2600, 0.4775, 0.1617, 0.5900, 0.5383],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3788, 0.4900, 0.7121, 0.5864],
[0.6109, 0.3943, 0.8525, 0.4950, 0.4338, 0.4800, 0.5449, 0.5383],
[0.6302, 0.4007, 0.8850, 0.5500, 0.3613, 0.4517, 0.6335, 0.5012],
[0.6265, 0.4091, 0.8950, 0.3533, 0.3600, 0.3967, 0.6295, 0.4901],
[0.6339, 0.4123, 0.8638, 0.5367, 0.4075, 0.5467, 0.7517, 0.5436]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5489, 0.3691, 0.8602, 0.3525, 0.4167, 0.3724, 0.6237, 0.5266],
[0.5204, 0.3422, 0.8550, 0.2708, 0.4328, 0.2782, 0.6180, 0.5341],
[0.4912, 0.3260, 0.8521, 0.2680, 0.4374, 0.2647, 0.6071, 0.5039],
[0.6073, 0.3701, 0.8993, 0.4969, 0.4102, 0.4751, 0.6399, 0.5054],
[0.5643, 0.3735, 0.8997, 0.4671, 0.4200, 0.4458, 0.6410, 0.5132],
[0.6377, 0.3858, 0.9165, 0.5669, 0.4071, 0.5251, 0.6724, 0.4992],
[0.5725, 0.3525, 0.8803, 0.3685, 0.4274, 0.3686, 0.6311, 0.5081],
[0.6164, 0.3833, 0.9266, 0.5551, 0.4389, 0.5435, 0.6636, 0.5159]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6257, 0.4034, 0.8288, 0.2333, 0.3925, 0.2717, 0.6330, 0.4901],
[0.6266, 0.4101, 0.8350, 0.2333, 0.3950, 0.2950, 0.6264, 0.4921],
[0.6229, 0.4086, 0.7538, 0.2600, 0.4775, 0.1617, 0.5900, 0.5383],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3787, 0.4900, 0.7121, 0.5864],
[0.6109, 0.3943, 0.8525, 0.4950, 0.4338, 0.4800, 0.5449, 0.5383],
[0.6302, 0.4007, 0.8850, 0.5500, 0.3613, 0.4517, 0.6335, 0.5012],
[0.6265, 0.4091, 0.8950, 0.3533, 0.3600, 0.3967, 0.6295, 0.4901],
[0.6339, 0.4123, 0.8637, 0.5367, 0.4075, 0.5467, 0.7517, 0.5436]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0027, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0027, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.5967375976033509
step: 19
running loss: 0.03140724197912373
Train Steps: 19/90 Loss: 0.0314 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6149, 0.4054, 0.6713, 0.2333, 0.4025, 0.2017, 0.5213, 0.5695],
[0.6070, 0.3979, 0.8575, 0.5083, 0.4350, 0.5400, 0.5180, 0.5466],
[0.6129, 0.4114, 0.6950, 0.2467, 0.4050, 0.2133, 0.5363, 0.5550],
[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150],
[0.6200, 0.3978, 0.8900, 0.4550, 0.3775, 0.5200, 0.6150, 0.5367],
[0.6258, 0.4038, 0.8750, 0.4883, 0.3900, 0.5500, 0.6375, 0.5217],
[0.6307, 0.4029, 0.8650, 0.5200, 0.3763, 0.4017, 0.7311, 0.5366],
[0.6357, 0.4159, 0.8788, 0.5583, 0.3638, 0.4433, 0.6488, 0.5297]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5002, 0.3322, 0.7828, 0.2725, 0.3797, 0.2560, 0.5804, 0.5275],
[0.6001, 0.3807, 0.8608, 0.4400, 0.3863, 0.4352, 0.6208, 0.5364],
[0.5115, 0.3182, 0.8096, 0.2736, 0.3886, 0.2493, 0.6107, 0.5172],
[0.5968, 0.4046, 0.8681, 0.5250, 0.4023, 0.4724, 0.6819, 0.5299],
[0.6252, 0.3984, 0.8836, 0.5122, 0.4340, 0.4717, 0.6479, 0.5141],
[0.6535, 0.4172, 0.8849, 0.5469, 0.3984, 0.5496, 0.6890, 0.4915],
[0.5809, 0.3773, 0.8423, 0.3697, 0.3968, 0.3501, 0.6085, 0.5313],
[0.5965, 0.3755, 0.8642, 0.4635, 0.3780, 0.3989, 0.6192, 0.5332]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6149, 0.4054, 0.6712, 0.2333, 0.4025, 0.2017, 0.5213, 0.5695],
[0.6070, 0.3979, 0.8575, 0.5083, 0.4350, 0.5400, 0.5180, 0.5466],
[0.6129, 0.4114, 0.6950, 0.2467, 0.4050, 0.2133, 0.5362, 0.5550],
[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150],
[0.6199, 0.3978, 0.8900, 0.4550, 0.3775, 0.5200, 0.6150, 0.5367],
[0.6258, 0.4038, 0.8750, 0.4883, 0.3900, 0.5500, 0.6375, 0.5217],
[0.6307, 0.4029, 0.8650, 0.5200, 0.3762, 0.4017, 0.7311, 0.5366],
[0.6357, 0.4159, 0.8788, 0.5583, 0.3638, 0.4433, 0.6488, 0.5297]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0033, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0033, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.6000654962845147
step: 20
running loss: 0.030003274814225732
Train Steps: 20/90 Loss: 0.0300 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6273, 0.4105, 0.8988, 0.4517, 0.3912, 0.2550, 0.5894, 0.4811],
[0.6227, 0.4193, 0.8838, 0.4933, 0.3663, 0.3733, 0.5637, 0.5633],
[0.6280, 0.4055, 0.8600, 0.5317, 0.3800, 0.4700, 0.6275, 0.5133],
[0.6206, 0.4123, 0.7175, 0.2400, 0.3887, 0.2933, 0.6225, 0.5750],
[0.6084, 0.3981, 0.8588, 0.5233, 0.4600, 0.5367, 0.5680, 0.5006],
[0.6271, 0.4040, 0.9000, 0.3250, 0.4938, 0.2300, 0.7192, 0.5413],
[ nan, nan, 0.6512, 0.1717, 0.4100, 0.1983, 0.5253, 0.5240],
[0.6284, 0.4029, 0.8838, 0.3783, 0.3975, 0.2850, 0.6335, 0.5090]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5916, 0.3844, 0.7633, 0.3877, 0.3732, 0.3227, 0.6046, 0.5243],
[0.6335, 0.4340, 0.7941, 0.4725, 0.3441, 0.4270, 0.6307, 0.5186],
[0.6787, 0.4430, 0.8263, 0.5454, 0.3485, 0.4909, 0.6363, 0.4990],
[0.5771, 0.3782, 0.7535, 0.3500, 0.3570, 0.3527, 0.6062, 0.5452],
[0.6281, 0.4197, 0.8233, 0.5323, 0.3730, 0.4784, 0.6468, 0.5321],
[0.5682, 0.4123, 0.8094, 0.3721, 0.4299, 0.3495, 0.6410, 0.5398],
[0.4449, 0.3098, 0.7400, 0.2139, 0.3699, 0.2040, 0.5648, 0.5597],
[0.6228, 0.4093, 0.8242, 0.4646, 0.3890, 0.4224, 0.6368, 0.5439]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6273, 0.4105, 0.8988, 0.4517, 0.3913, 0.2550, 0.5894, 0.4811],
[0.6227, 0.4193, 0.8838, 0.4933, 0.3663, 0.3733, 0.5638, 0.5633],
[0.6280, 0.4055, 0.8600, 0.5317, 0.3800, 0.4700, 0.6275, 0.5133],
[0.6206, 0.4123, 0.7175, 0.2400, 0.3887, 0.2933, 0.6225, 0.5750],
[0.6084, 0.3981, 0.8587, 0.5233, 0.4600, 0.5367, 0.5680, 0.5006],
[0.6271, 0.4040, 0.9000, 0.3250, 0.4938, 0.2300, 0.7192, 0.5413],
[0.0000, 0.0000, 0.6513, 0.1717, 0.4100, 0.1983, 0.5253, 0.5240],
[0.6284, 0.4029, 0.8838, 0.3783, 0.3975, 0.2850, 0.6335, 0.5090]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0075, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0075, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.6075229728594422
step: 21
running loss: 0.028929665374259155
Train Steps: 21/90 Loss: 0.0289 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6159, 0.4085, 0.6900, 0.2283, 0.4088, 0.1950, 0.5123, 0.5397],
[0.6272, 0.4045, 0.8538, 0.5900, 0.3750, 0.4417, 0.5989, 0.4649],
[0.6224, 0.3964, 0.8225, 0.5717, 0.4150, 0.4617, 0.5775, 0.5267],
[0.6257, 0.4167, 0.8775, 0.3433, 0.3563, 0.4133, 0.6200, 0.5667],
[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.6100, 0.4071, 0.7601, 0.3444, 0.3400, 0.4117, 0.5625, 0.5617],
[0.6277, 0.4103, 0.8087, 0.5717, 0.4188, 0.4750, 0.5663, 0.6083],
[0.6124, 0.4083, 0.6954, 0.3069, 0.3650, 0.2750, 0.5163, 0.5485]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5361, 0.3473, 0.7224, 0.2576, 0.3896, 0.2200, 0.5687, 0.5548],
[0.6341, 0.4344, 0.8141, 0.4878, 0.3341, 0.4040, 0.5881, 0.5413],
[0.6328, 0.4104, 0.7829, 0.5221, 0.3337, 0.4532, 0.6095, 0.5360],
[0.6438, 0.4458, 0.8056, 0.4583, 0.3897, 0.4038, 0.6523, 0.5541],
[0.6684, 0.4341, 0.8065, 0.5662, 0.3743, 0.4831, 0.6147, 0.5662],
[0.5448, 0.4118, 0.7564, 0.3263, 0.3703, 0.3139, 0.5909, 0.5578],
[0.6425, 0.4230, 0.8266, 0.5468, 0.3626, 0.4794, 0.6113, 0.5741],
[0.5344, 0.3745, 0.7279, 0.2517, 0.3772, 0.2505, 0.5578, 0.5618]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6159, 0.4085, 0.6900, 0.2283, 0.4087, 0.1950, 0.5123, 0.5397],
[0.6271, 0.4045, 0.8537, 0.5900, 0.3750, 0.4417, 0.5989, 0.4649],
[0.6224, 0.3964, 0.8225, 0.5717, 0.4150, 0.4617, 0.5775, 0.5267],
[0.6257, 0.4167, 0.8775, 0.3433, 0.3562, 0.4133, 0.6200, 0.5667],
[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.6100, 0.4071, 0.7601, 0.3444, 0.3400, 0.4117, 0.5625, 0.5617],
[0.6277, 0.4103, 0.8087, 0.5717, 0.4187, 0.4750, 0.5663, 0.6083],
[0.6123, 0.4083, 0.6954, 0.3069, 0.3650, 0.2750, 0.5163, 0.5485]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0018, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0018, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.6093606404028833
step: 22
running loss: 0.027698210927403787
Train Steps: 22/90 Loss: 0.0277 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6332, 0.4118, 0.9238, 0.4267, 0.4012, 0.4733, 0.7525, 0.5436],
[0.6128, 0.4118, 0.8638, 0.5333, 0.4625, 0.5267, 0.5193, 0.5475],
[0.6245, 0.4115, 0.8700, 0.4883, 0.4625, 0.5517, 0.6100, 0.5217],
[0.6276, 0.4120, 0.8738, 0.3133, 0.4225, 0.2217, 0.6203, 0.4892],
[0.6277, 0.4013, 0.8888, 0.4767, 0.3600, 0.3567, 0.6148, 0.4672],
[0.6086, 0.3940, 0.8712, 0.4783, 0.4025, 0.4900, 0.5498, 0.5390],
[0.6257, 0.4167, 0.8775, 0.3433, 0.3563, 0.4133, 0.6200, 0.5667],
[0.6064, 0.3953, 0.8738, 0.4417, 0.3663, 0.4683, 0.5511, 0.5416]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6037, 0.4042, 0.7861, 0.4525, 0.3799, 0.4002, 0.5853, 0.5947],
[0.6158, 0.3983, 0.7456, 0.4208, 0.3749, 0.3494, 0.5616, 0.5747],
[0.5826, 0.3949, 0.7472, 0.4460, 0.3831, 0.4107, 0.5832, 0.5636],
[0.5835, 0.4133, 0.7313, 0.3065, 0.4241, 0.2709, 0.5836, 0.5425],
[0.6116, 0.4081, 0.7711, 0.4174, 0.3359, 0.3233, 0.5526, 0.5699],
[0.6512, 0.4110, 0.7677, 0.5061, 0.3607, 0.4228, 0.5736, 0.5367],
[0.6322, 0.4209, 0.7510, 0.4096, 0.3741, 0.3559, 0.6041, 0.5573],
[0.6771, 0.3982, 0.7817, 0.4814, 0.3504, 0.4184, 0.5547, 0.5450]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6332, 0.4118, 0.9237, 0.4267, 0.4013, 0.4733, 0.7525, 0.5436],
[0.6128, 0.4118, 0.8637, 0.5333, 0.4625, 0.5267, 0.5193, 0.5475],
[0.6245, 0.4115, 0.8700, 0.4883, 0.4625, 0.5517, 0.6100, 0.5217],
[0.6276, 0.4120, 0.8737, 0.3133, 0.4225, 0.2217, 0.6203, 0.4892],
[0.6277, 0.4013, 0.8888, 0.4767, 0.3600, 0.3567, 0.6148, 0.4672],
[0.6086, 0.3940, 0.8712, 0.4783, 0.4025, 0.4900, 0.5498, 0.5390],
[0.6257, 0.4167, 0.8775, 0.3433, 0.3562, 0.4133, 0.6200, 0.5667],
[0.6064, 0.3952, 0.8737, 0.4417, 0.3663, 0.4683, 0.5511, 0.5416]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0047, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0047, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.6140206111595035
step: 23
running loss: 0.02669654831128276
Train Steps: 23/90 Loss: 0.0267 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6107, 0.4050, 0.8700, 0.4850, 0.4470, 0.4848, 0.5043, 0.5431],
[ nan, nan, 0.6488, 0.1817, 0.4325, 0.1867, 0.5475, 0.5733],
[0.6164, 0.4066, 0.6625, 0.3033, 0.3775, 0.2967, 0.5725, 0.5833],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533],
[0.6189, 0.4029, 0.8375, 0.5767, 0.4745, 0.4829, 0.5551, 0.5598],
[0.6199, 0.4102, 0.8950, 0.4417, 0.4012, 0.5367, 0.6112, 0.5967],
[0.6200, 0.4118, 0.8287, 0.4017, 0.3775, 0.2833, 0.5391, 0.5799],
[ nan, nan, 0.7512, 0.2117, 0.4288, 0.2000, 0.5600, 0.5617]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6534, 0.4442, 0.7870, 0.5273, 0.3688, 0.4122, 0.5606, 0.5491],
[0.4899, 0.3300, 0.6995, 0.1907, 0.4047, 0.1847, 0.5049, 0.5413],
[0.5462, 0.3605, 0.7138, 0.3059, 0.3777, 0.2765, 0.5254, 0.5580],
[0.6595, 0.4666, 0.8279, 0.5287, 0.3715, 0.4721, 0.6088, 0.5316],
[0.6401, 0.4335, 0.7881, 0.5154, 0.3938, 0.4018, 0.5882, 0.5655],
[0.7212, 0.4738, 0.8581, 0.6698, 0.3993, 0.5994, 0.6318, 0.5457],
[0.5917, 0.3890, 0.7234, 0.3395, 0.3801, 0.2883, 0.5364, 0.5730],
[0.5050, 0.3630, 0.7010, 0.2187, 0.3996, 0.2131, 0.5094, 0.5673]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6107, 0.4050, 0.8700, 0.4850, 0.4470, 0.4848, 0.5043, 0.5431],
[0.0000, 0.0000, 0.6488, 0.1817, 0.4325, 0.1867, 0.5475, 0.5733],
[0.6164, 0.4066, 0.6625, 0.3033, 0.3775, 0.2967, 0.5725, 0.5833],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533],
[0.6189, 0.4029, 0.8375, 0.5767, 0.4745, 0.4829, 0.5551, 0.5598],
[0.6199, 0.4102, 0.8950, 0.4417, 0.4013, 0.5367, 0.6112, 0.5967],
[0.6200, 0.4118, 0.8288, 0.4017, 0.3775, 0.2833, 0.5391, 0.5799],
[0.0000, 0.0000, 0.7513, 0.2117, 0.4288, 0.2000, 0.5600, 0.5617]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0145, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0145, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.628472588956356
step: 24
running loss: 0.026186357873181503
Train Steps: 24/90 Loss: 0.0262 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383],
[0.6286, 0.4055, 0.9000, 0.4717, 0.3763, 0.4683, 0.7018, 0.5494],
[ nan, nan, 0.7335, 0.2569, 0.3788, 0.2667, 0.5066, 0.5578],
[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586],
[ nan, nan, 0.6935, 0.1930, 0.4150, 0.2250, 0.5450, 0.5650],
[0.6307, 0.4029, 0.8988, 0.4817, 0.3937, 0.3500, 0.7311, 0.5378],
[0.6153, 0.4117, 0.8688, 0.5167, 0.4895, 0.5647, 0.5524, 0.5136],
[0.6149, 0.4054, 0.6713, 0.2333, 0.4025, 0.2017, 0.5213, 0.5695]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6083, 0.4021, 0.8504, 0.4506, 0.4062, 0.4482, 0.5526, 0.5495],
[0.6550, 0.4405, 0.8656, 0.6100, 0.3859, 0.5233, 0.5851, 0.5481],
[0.4780, 0.3301, 0.7199, 0.2762, 0.4161, 0.2419, 0.4989, 0.5769],
[0.5234, 0.3830, 0.8144, 0.3121, 0.4428, 0.3014, 0.5504, 0.5798],
[0.4204, 0.3060, 0.7255, 0.2233, 0.4225, 0.1847, 0.5139, 0.5718],
[0.6194, 0.4022, 0.8339, 0.4905, 0.4203, 0.3756, 0.5566, 0.5277],
[0.5894, 0.4061, 0.8469, 0.5381, 0.4337, 0.5094, 0.5568, 0.5652],
[0.4978, 0.3319, 0.7075, 0.3023, 0.4139, 0.2716, 0.4750, 0.5493]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383],
[0.6286, 0.4055, 0.9000, 0.4717, 0.3762, 0.4683, 0.7018, 0.5494],
[0.0000, 0.0000, 0.7335, 0.2569, 0.3787, 0.2667, 0.5066, 0.5578],
[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586],
[0.0000, 0.0000, 0.6935, 0.1930, 0.4150, 0.2250, 0.5450, 0.5650],
[0.6307, 0.4029, 0.8988, 0.4817, 0.3938, 0.3500, 0.7311, 0.5378],
[0.6154, 0.4117, 0.8687, 0.5167, 0.4895, 0.5647, 0.5524, 0.5136],
[0.6149, 0.4054, 0.6712, 0.2333, 0.4025, 0.2017, 0.5213, 0.5695]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0125, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0125, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.6410121768712997
step: 25
running loss: 0.02564048707485199
Train Steps: 25/90 Loss: 0.0256 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6268, 0.4102, 0.8938, 0.3667, 0.4025, 0.2833, 0.6275, 0.5183],
[ nan, nan, 0.9050, 0.3500, 0.5138, 0.2300, 0.7359, 0.5702],
[0.6286, 0.4078, 0.8063, 0.2267, 0.4788, 0.1533, 0.5953, 0.4913],
[0.6111, 0.4019, 0.8350, 0.3867, 0.3500, 0.4283, 0.5480, 0.5719],
[0.6199, 0.4071, 0.7600, 0.2117, 0.4037, 0.2767, 0.6138, 0.5550],
[0.6134, 0.4090, 0.6926, 0.2819, 0.3538, 0.3233, 0.5563, 0.5667],
[0.6199, 0.4102, 0.8950, 0.4417, 0.4012, 0.5367, 0.6112, 0.5967],
[0.6278, 0.4253, 0.8875, 0.5017, 0.4113, 0.2750, 0.5413, 0.6196]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5108, 0.3604, 0.8390, 0.3908, 0.4406, 0.3910, 0.5886, 0.5432],
[0.4525, 0.3217, 0.8464, 0.3252, 0.4609, 0.3114, 0.5518, 0.5576],
[0.3797, 0.2495, 0.7300, 0.1931, 0.4586, 0.1687, 0.5035, 0.5400],
[0.5461, 0.3603, 0.8976, 0.4546, 0.4051, 0.4570, 0.5562, 0.5573],
[0.4287, 0.3064, 0.7561, 0.2479, 0.4488, 0.2206, 0.5375, 0.5389],
[0.4644, 0.2900, 0.7424, 0.2811, 0.3841, 0.3158, 0.4938, 0.5445],
[0.6190, 0.3835, 0.9274, 0.5857, 0.4378, 0.6095, 0.5924, 0.5434],
[0.5422, 0.3625, 0.8487, 0.4538, 0.4157, 0.4287, 0.5251, 0.5353]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6268, 0.4102, 0.8938, 0.3667, 0.4025, 0.2833, 0.6275, 0.5183],
[0.0000, 0.0000, 0.9050, 0.3500, 0.5138, 0.2300, 0.7359, 0.5702],
[0.6286, 0.4078, 0.8062, 0.2267, 0.4787, 0.1533, 0.5953, 0.4913],
[0.6111, 0.4019, 0.8350, 0.3867, 0.3500, 0.4283, 0.5480, 0.5719],
[0.6199, 0.4071, 0.7600, 0.2117, 0.4038, 0.2767, 0.6137, 0.5550],
[0.6134, 0.4090, 0.6926, 0.2819, 0.3537, 0.3233, 0.5562, 0.5667],
[0.6199, 0.4102, 0.8950, 0.4417, 0.4013, 0.5367, 0.6112, 0.5967],
[0.6278, 0.4253, 0.8875, 0.5017, 0.4112, 0.2750, 0.5413, 0.6196]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0109, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0109, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.6518932655453682
step: 26
running loss: 0.025072817905591085
Train Steps: 26/90 Loss: 0.0251 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6196, 0.4090, 0.8450, 0.3900, 0.3575, 0.3933, 0.5975, 0.5583],
[0.6214, 0.4040, 0.8838, 0.3500, 0.3600, 0.5183, 0.6362, 0.5200],
[0.6214, 0.4175, 0.7300, 0.2883, 0.4338, 0.2167, 0.5698, 0.5773],
[0.6311, 0.3998, 0.7975, 0.5767, 0.3838, 0.4850, 0.7327, 0.5343],
[ nan, nan, 0.7850, 0.2700, 0.4288, 0.1717, 0.5199, 0.4999],
[0.6213, 0.4001, 0.7712, 0.2117, 0.4338, 0.1800, 0.5850, 0.5183],
[0.6286, 0.4274, 0.8500, 0.4500, 0.4525, 0.2583, 0.5440, 0.6209],
[0.6189, 0.4049, 0.8888, 0.4417, 0.4213, 0.5200, 0.5988, 0.5633]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5346, 0.3361, 0.9201, 0.4234, 0.4331, 0.4263, 0.5722, 0.5859],
[0.5568, 0.3413, 0.9471, 0.4525, 0.4453, 0.4915, 0.5743, 0.5571],
[0.3841, 0.2736, 0.8017, 0.2267, 0.4508, 0.2552, 0.5554, 0.5411],
[0.4868, 0.3168, 0.9052, 0.4018, 0.4096, 0.3981, 0.5696, 0.5464],
[0.3279, 0.2467, 0.8089, 0.1724, 0.4432, 0.1667, 0.5400, 0.5439],
[0.3911, 0.2765, 0.7820, 0.1967, 0.4317, 0.2572, 0.5715, 0.5536],
[0.4877, 0.3180, 0.8559, 0.3810, 0.4573, 0.3899, 0.5876, 0.5489],
[0.5775, 0.3616, 0.9427, 0.5111, 0.4411, 0.5220, 0.6233, 0.5373]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6196, 0.4090, 0.8450, 0.3900, 0.3575, 0.3933, 0.5975, 0.5583],
[0.6214, 0.4040, 0.8838, 0.3500, 0.3600, 0.5183, 0.6363, 0.5200],
[0.6214, 0.4175, 0.7300, 0.2883, 0.4338, 0.2167, 0.5698, 0.5773],
[0.6311, 0.3998, 0.7975, 0.5767, 0.3837, 0.4850, 0.7327, 0.5343],
[0.0000, 0.0000, 0.7850, 0.2700, 0.4288, 0.1717, 0.5199, 0.4999],
[0.6213, 0.4001, 0.7713, 0.2117, 0.4338, 0.1800, 0.5850, 0.5183],
[0.6286, 0.4274, 0.8500, 0.4500, 0.4525, 0.2583, 0.5440, 0.6209],
[0.6189, 0.4049, 0.8888, 0.4417, 0.4212, 0.5200, 0.5987, 0.5633]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0092, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0092, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.6610878705978394
step: 27
running loss: 0.024484735948068125
Train Steps: 27/90 Loss: 0.0245 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6132, 0.4066, 0.7259, 0.2402, 0.3588, 0.3300, 0.6000, 0.5600],
[0.6085, 0.4008, 0.8588, 0.5200, 0.4959, 0.4977, 0.5175, 0.5283],
[0.6286, 0.4034, 0.8191, 0.2414, 0.4262, 0.2393, 0.6365, 0.5356],
[0.6200, 0.4039, 0.8880, 0.4799, 0.3625, 0.4285, 0.5866, 0.5148],
[0.6272, 0.4045, 0.8538, 0.5900, 0.3750, 0.4417, 0.5989, 0.4649],
[0.6211, 0.3993, 0.7650, 0.1933, 0.4575, 0.1550, 0.5965, 0.4895],
[0.6350, 0.4144, 0.9250, 0.4100, 0.4125, 0.3750, 0.7129, 0.5945],
[0.6136, 0.4060, 0.8025, 0.3217, 0.3650, 0.3000, 0.5060, 0.5646]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4143, 0.2747, 0.8007, 0.2348, 0.4075, 0.2985, 0.5870, 0.5697],
[0.4828, 0.2987, 0.9111, 0.4216, 0.4440, 0.4238, 0.6115, 0.5584],
[0.3344, 0.2688, 0.8159, 0.2095, 0.4573, 0.1910, 0.6030, 0.5582],
[0.5427, 0.3206, 0.9698, 0.4371, 0.4166, 0.4546, 0.6427, 0.5454],
[0.5437, 0.3577, 0.9476, 0.4925, 0.3931, 0.4746, 0.6047, 0.5349],
[0.3526, 0.2414, 0.7833, 0.1797, 0.4681, 0.2100, 0.6073, 0.5477],
[0.4671, 0.3069, 0.9184, 0.3883, 0.4627, 0.3664, 0.6575, 0.5600],
[0.4275, 0.2836, 0.8408, 0.2699, 0.4258, 0.3069, 0.5922, 0.5463]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6132, 0.4066, 0.7259, 0.2402, 0.3587, 0.3300, 0.6000, 0.5600],
[0.6084, 0.4008, 0.8587, 0.5200, 0.4959, 0.4977, 0.5175, 0.5283],
[0.6286, 0.4034, 0.8191, 0.2414, 0.4262, 0.2393, 0.6365, 0.5356],
[0.6201, 0.4039, 0.8880, 0.4799, 0.3625, 0.4285, 0.5866, 0.5148],
[0.6271, 0.4045, 0.8537, 0.5900, 0.3750, 0.4417, 0.5989, 0.4649],
[0.6211, 0.3993, 0.7650, 0.1933, 0.4575, 0.1550, 0.5965, 0.4895],
[0.6350, 0.4144, 0.9250, 0.4100, 0.4125, 0.3750, 0.7129, 0.5945],
[0.6136, 0.4060, 0.8025, 0.3217, 0.3650, 0.3000, 0.5060, 0.5646]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0080, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0080, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.6691014468669891
step: 28
running loss: 0.023896480245249613
Train Steps: 28/90 Loss: 0.0239 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6109, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117],
[0.6206, 0.4123, 0.7175, 0.2400, 0.3887, 0.2933, 0.6225, 0.5750],
[0.6136, 0.4060, 0.8025, 0.3217, 0.3650, 0.3000, 0.5060, 0.5646],
[0.6042, 0.3990, 0.6831, 0.2875, 0.3500, 0.3133, 0.5143, 0.5510],
[0.6241, 0.4143, 0.8938, 0.4650, 0.4075, 0.5350, 0.6250, 0.5550],
[0.6203, 0.4078, 0.8800, 0.5083, 0.3900, 0.5000, 0.6100, 0.5583],
[0.6275, 0.4071, 0.8075, 0.2100, 0.4700, 0.1533, 0.6148, 0.4834],
[0.6031, 0.3986, 0.7462, 0.2833, 0.3638, 0.2717, 0.5253, 0.4726]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5390, 0.3826, 0.9603, 0.4170, 0.3944, 0.4088, 0.6443, 0.5350],
[0.4486, 0.2729, 0.8097, 0.2505, 0.4108, 0.2737, 0.6175, 0.5547],
[0.4647, 0.3007, 0.8495, 0.2775, 0.4124, 0.2690, 0.6329, 0.5355],
[0.4015, 0.2568, 0.7904, 0.2029, 0.3834, 0.2554, 0.5896, 0.5526],
[0.5965, 0.3690, 0.9675, 0.5167, 0.4347, 0.5499, 0.7048, 0.5469],
[0.6405, 0.3905, 0.9769, 0.5324, 0.3739, 0.5301, 0.6639, 0.5552],
[0.4013, 0.2692, 0.8289, 0.1844, 0.4672, 0.1578, 0.6531, 0.5266],
[0.4481, 0.2940, 0.8121, 0.2447, 0.4270, 0.2471, 0.6292, 0.5344]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6108, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117],
[0.6206, 0.4123, 0.7175, 0.2400, 0.3887, 0.2933, 0.6225, 0.5750],
[0.6136, 0.4060, 0.8025, 0.3217, 0.3650, 0.3000, 0.5060, 0.5646],
[0.6042, 0.3990, 0.6831, 0.2875, 0.3500, 0.3133, 0.5143, 0.5510],
[0.6241, 0.4142, 0.8938, 0.4650, 0.4075, 0.5350, 0.6250, 0.5550],
[0.6203, 0.4078, 0.8800, 0.5083, 0.3900, 0.5000, 0.6100, 0.5583],
[0.6275, 0.4071, 0.8075, 0.2100, 0.4700, 0.1533, 0.6148, 0.4834],
[0.6031, 0.3986, 0.7462, 0.2833, 0.3638, 0.2717, 0.5253, 0.4726]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0062, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0062, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.6753336312249303
step: 29
running loss: 0.02328736659396311
Train Steps: 29/90 Loss: 0.0233 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6161, 0.4099, 0.8738, 0.4383, 0.3788, 0.5483, 0.5605, 0.5019],
[0.6076, 0.3958, 0.8700, 0.4667, 0.4546, 0.5046, 0.5231, 0.4960],
[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837],
[0.6111, 0.4033, 0.8300, 0.3267, 0.3588, 0.3333, 0.5444, 0.5637],
[0.6250, 0.4106, 0.8700, 0.3717, 0.3588, 0.4967, 0.6038, 0.5167],
[0.6293, 0.3982, 0.8700, 0.5300, 0.3763, 0.4717, 0.7050, 0.5297],
[0.6261, 0.4131, 0.8938, 0.3550, 0.4000, 0.2683, 0.6188, 0.5283],
[0.6250, 0.4103, 0.8950, 0.4400, 0.3912, 0.5650, 0.6050, 0.5133]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6369, 0.4089, 0.8763, 0.3559, 0.3884, 0.3804, 0.6565, 0.5152],
[0.5575, 0.3820, 0.8672, 0.3558, 0.4400, 0.3587, 0.6304, 0.5472],
[0.4623, 0.2721, 0.7361, 0.2071, 0.3519, 0.1966, 0.6082, 0.5153],
[0.5630, 0.3509, 0.8418, 0.3172, 0.3521, 0.2707, 0.6689, 0.4976],
[0.5934, 0.3768, 0.8642, 0.3091, 0.4111, 0.3737, 0.6373, 0.5525],
[0.6304, 0.3884, 0.8941, 0.4007, 0.3824, 0.3954, 0.6342, 0.5111],
[0.5640, 0.3495, 0.8785, 0.3389, 0.4095, 0.2641, 0.7161, 0.5165],
[0.6403, 0.4074, 0.9030, 0.3953, 0.4031, 0.4607, 0.6779, 0.5264]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6161, 0.4099, 0.8737, 0.4383, 0.3787, 0.5483, 0.5605, 0.5019],
[0.6076, 0.3958, 0.8700, 0.4667, 0.4546, 0.5046, 0.5231, 0.4960],
[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837],
[0.6111, 0.4033, 0.8300, 0.3267, 0.3587, 0.3333, 0.5444, 0.5637],
[0.6250, 0.4105, 0.8700, 0.3717, 0.3587, 0.4967, 0.6037, 0.5167],
[0.6293, 0.3982, 0.8700, 0.5300, 0.3762, 0.4717, 0.7050, 0.5297],
[0.6261, 0.4131, 0.8938, 0.3550, 0.4000, 0.2683, 0.6187, 0.5283],
[0.6250, 0.4103, 0.8950, 0.4400, 0.3913, 0.5650, 0.6050, 0.5133]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0046, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0046, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.6799087165854871
step: 30
running loss: 0.022663623886182906
Train Steps: 30/90 Loss: 0.0227 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6223, 0.4028, 0.8988, 0.4200, 0.3763, 0.5733, 0.6375, 0.5167],
[ nan, nan, 0.6859, 0.2194, 0.4150, 0.1867, 0.5153, 0.5729],
[0.6240, 0.4217, 0.8150, 0.3133, 0.4425, 0.2650, 0.5650, 0.5817],
[0.6184, 0.4079, 0.8350, 0.3700, 0.3675, 0.2883, 0.5312, 0.5783],
[0.6214, 0.4116, 0.7750, 0.2317, 0.4487, 0.1883, 0.6200, 0.5400],
[0.6264, 0.4071, 0.9038, 0.3867, 0.3663, 0.3917, 0.6338, 0.5283],
[0.6188, 0.4099, 0.7400, 0.2433, 0.3962, 0.2750, 0.6162, 0.5467],
[0.6202, 0.3983, 0.8555, 0.5429, 0.3842, 0.4370, 0.5866, 0.5398]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.8508, 0.5153, 0.9209, 0.4967, 0.3942, 0.5981, 0.6709, 0.5179],
[0.4904, 0.3145, 0.7087, 0.2052, 0.3900, 0.1955, 0.5960, 0.5065],
[0.4885, 0.3282, 0.7663, 0.2554, 0.4071, 0.1947, 0.6204, 0.5186],
[0.6714, 0.4204, 0.7941, 0.3738, 0.3507, 0.3638, 0.6271, 0.5192],
[0.5495, 0.3321, 0.7264, 0.2246, 0.4070, 0.2041, 0.6100, 0.5103],
[0.6896, 0.4610, 0.8982, 0.4124, 0.3639, 0.4241, 0.6851, 0.5136],
[0.5575, 0.3861, 0.7116, 0.2491, 0.3762, 0.2665, 0.6054, 0.5234],
[0.7678, 0.4905, 0.9072, 0.5293, 0.3453, 0.4882, 0.6262, 0.4931]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6223, 0.4028, 0.8988, 0.4200, 0.3762, 0.5733, 0.6375, 0.5167],
[0.0000, 0.0000, 0.6859, 0.2194, 0.4150, 0.1867, 0.5153, 0.5729],
[0.6240, 0.4217, 0.8150, 0.3133, 0.4425, 0.2650, 0.5650, 0.5817],
[0.6184, 0.4079, 0.8350, 0.3700, 0.3675, 0.2883, 0.5312, 0.5783],
[0.6214, 0.4116, 0.7750, 0.2317, 0.4487, 0.1883, 0.6200, 0.5400],
[0.6264, 0.4071, 0.9038, 0.3867, 0.3663, 0.3917, 0.6338, 0.5283],
[0.6188, 0.4099, 0.7400, 0.2433, 0.3963, 0.2750, 0.6162, 0.5467],
[0.6202, 0.3983, 0.8555, 0.5429, 0.3842, 0.4370, 0.5866, 0.5398]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0089, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0089, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.6888156817294657
step: 31
running loss: 0.022219860700950507
Train Steps: 31/90 Loss: 0.0222 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6250, 0.4146, 0.8838, 0.3933, 0.3588, 0.4283, 0.6162, 0.5367],
[0.6201, 0.4027, 0.8029, 0.2728, 0.4042, 0.2310, 0.5980, 0.5391],
[0.6277, 0.4013, 0.8888, 0.4767, 0.3600, 0.3567, 0.6148, 0.4672],
[0.6183, 0.4076, 0.8838, 0.4517, 0.3813, 0.4483, 0.5775, 0.5633],
[0.6097, 0.3988, 0.8650, 0.5250, 0.4213, 0.5200, 0.5675, 0.5050],
[0.6104, 0.4029, 0.8738, 0.4900, 0.4088, 0.4533, 0.5070, 0.5510],
[0.6157, 0.4102, 0.8513, 0.3817, 0.3613, 0.3667, 0.5096, 0.5890],
[0.6196, 0.4090, 0.8450, 0.3900, 0.3575, 0.3933, 0.5975, 0.5583]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6710, 0.4203, 0.7945, 0.3961, 0.3727, 0.3562, 0.6165, 0.4802],
[0.5841, 0.3361, 0.7245, 0.2290, 0.3879, 0.2388, 0.5897, 0.5041],
[0.6982, 0.4584, 0.7993, 0.3879, 0.3324, 0.3598, 0.5931, 0.5174],
[0.7280, 0.4381, 0.8203, 0.4481, 0.3542, 0.4475, 0.6107, 0.5190],
[0.7076, 0.4717, 0.8278, 0.4338, 0.3845, 0.4404, 0.5895, 0.5367],
[0.7239, 0.4483, 0.8322, 0.4365, 0.3643, 0.4370, 0.5907, 0.5236],
[0.6941, 0.4412, 0.7852, 0.3663, 0.3613, 0.3664, 0.6066, 0.5027],
[0.7049, 0.4463, 0.7884, 0.3625, 0.3525, 0.3731, 0.6007, 0.5497]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6250, 0.4146, 0.8838, 0.3933, 0.3587, 0.4283, 0.6162, 0.5367],
[0.6201, 0.4027, 0.8029, 0.2728, 0.4042, 0.2310, 0.5980, 0.5391],
[0.6277, 0.4013, 0.8888, 0.4767, 0.3600, 0.3567, 0.6148, 0.4672],
[0.6183, 0.4076, 0.8838, 0.4517, 0.3812, 0.4483, 0.5775, 0.5633],
[0.6097, 0.3988, 0.8650, 0.5250, 0.4212, 0.5200, 0.5675, 0.5050],
[0.6104, 0.4029, 0.8737, 0.4900, 0.4087, 0.4533, 0.5070, 0.5510],
[0.6157, 0.4102, 0.8512, 0.3817, 0.3613, 0.3667, 0.5096, 0.5890],
[0.6196, 0.4090, 0.8450, 0.3900, 0.3575, 0.3933, 0.5975, 0.5583]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0029, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0029, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.6917505832388997
step: 32
running loss: 0.021617205726215616
Train Steps: 32/90 Loss: 0.0216 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6246, 0.4028, 0.8738, 0.4867, 0.4088, 0.5667, 0.6362, 0.5200],
[0.6122, 0.4048, 0.7506, 0.3014, 0.3475, 0.3333, 0.5487, 0.5749],
[0.6289, 0.4024, 0.9088, 0.4567, 0.3937, 0.5633, 0.7058, 0.5609],
[0.6156, 0.4125, 0.8850, 0.4833, 0.4550, 0.5817, 0.5765, 0.5084],
[0.6164, 0.3972, 0.7818, 0.3381, 0.3599, 0.3387, 0.5880, 0.5153],
[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466],
[0.6076, 0.3953, 0.8125, 0.3917, 0.3525, 0.4083, 0.5346, 0.4954],
[0.6292, 0.4010, 0.8988, 0.4800, 0.3638, 0.3817, 0.6357, 0.5051]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7848, 0.4827, 0.8367, 0.4659, 0.3955, 0.5450, 0.6055, 0.5506],
[0.6511, 0.3996, 0.7105, 0.3123, 0.3613, 0.2571, 0.5342, 0.5192],
[0.7224, 0.4844, 0.8538, 0.4692, 0.3898, 0.5190, 0.5744, 0.5551],
[0.7083, 0.4858, 0.8719, 0.4633, 0.4123, 0.4938, 0.5730, 0.5529],
[0.6830, 0.4370, 0.7286, 0.3365, 0.3475, 0.3186, 0.5642, 0.5397],
[0.6332, 0.4395, 0.7310, 0.3280, 0.3316, 0.2940, 0.5389, 0.5436],
[0.6753, 0.4355, 0.7696, 0.3689, 0.3314, 0.3119, 0.5551, 0.5516],
[0.7349, 0.4735, 0.8271, 0.4398, 0.3587, 0.3736, 0.5524, 0.5296]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6246, 0.4028, 0.8737, 0.4867, 0.4087, 0.5667, 0.6363, 0.5200],
[0.6122, 0.4048, 0.7506, 0.3014, 0.3475, 0.3333, 0.5487, 0.5749],
[0.6289, 0.4024, 0.9087, 0.4567, 0.3938, 0.5633, 0.7058, 0.5609],
[0.6155, 0.4124, 0.8850, 0.4833, 0.4550, 0.5817, 0.5765, 0.5084],
[0.6164, 0.3972, 0.7818, 0.3381, 0.3599, 0.3387, 0.5880, 0.5153],
[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466],
[0.6076, 0.3952, 0.8125, 0.3917, 0.3525, 0.4083, 0.5346, 0.4954],
[0.6292, 0.4010, 0.8988, 0.4800, 0.3638, 0.3817, 0.6357, 0.5051]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0031, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0031, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.694860020885244
step: 33
running loss: 0.021056364269249818
Train Steps: 33/90 Loss: 0.0211 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6175, 0.4091, 0.7863, 0.2800, 0.3638, 0.3583, 0.6188, 0.5433],
[0.6299, 0.4008, 0.8450, 0.5350, 0.4213, 0.5000, 0.6350, 0.5100],
[0.6150, 0.3949, 0.8800, 0.4033, 0.3825, 0.4900, 0.5875, 0.5483],
[0.6199, 0.4060, 0.8888, 0.4667, 0.3800, 0.5050, 0.6188, 0.5433],
[0.6229, 0.4198, 0.7662, 0.2700, 0.4700, 0.2133, 0.5675, 0.5783],
[0.6128, 0.4116, 0.8450, 0.4583, 0.3675, 0.4867, 0.5337, 0.5446],
[0.6275, 0.4111, 0.8463, 0.2617, 0.4487, 0.1983, 0.6211, 0.4904],
[0.6205, 0.4012, 0.8675, 0.3283, 0.3713, 0.3050, 0.5813, 0.5117]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6149, 0.4340, 0.7060, 0.3099, 0.3430, 0.3445, 0.5397, 0.5623],
[0.7183, 0.4977, 0.8231, 0.5166, 0.3665, 0.5264, 0.5438, 0.5380],
[0.7315, 0.4994, 0.8343, 0.4605, 0.3698, 0.5051, 0.5327, 0.5626],
[0.7524, 0.4987, 0.8748, 0.5025, 0.3540, 0.5581, 0.5317, 0.5548],
[0.5284, 0.3690, 0.6747, 0.3188, 0.3901, 0.2372, 0.5341, 0.5517],
[0.6771, 0.4421, 0.7946, 0.4589, 0.3322, 0.4516, 0.5312, 0.5619],
[0.6197, 0.4022, 0.7689, 0.3958, 0.3993, 0.2837, 0.6107, 0.5413],
[0.7074, 0.4393, 0.8183, 0.4463, 0.3742, 0.3971, 0.5818, 0.5478]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6175, 0.4091, 0.7862, 0.2800, 0.3638, 0.3583, 0.6187, 0.5433],
[0.6299, 0.4008, 0.8450, 0.5350, 0.4212, 0.5000, 0.6350, 0.5100],
[0.6150, 0.3949, 0.8800, 0.4033, 0.3825, 0.4900, 0.5875, 0.5483],
[0.6199, 0.4060, 0.8888, 0.4667, 0.3800, 0.5050, 0.6187, 0.5433],
[0.6229, 0.4198, 0.7663, 0.2700, 0.4700, 0.2133, 0.5675, 0.5783],
[0.6128, 0.4116, 0.8450, 0.4583, 0.3675, 0.4867, 0.5337, 0.5446],
[0.6275, 0.4111, 0.8462, 0.2617, 0.4487, 0.1983, 0.6211, 0.4904],
[0.6205, 0.4012, 0.8675, 0.3283, 0.3713, 0.3050, 0.5813, 0.5117]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0036, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0036, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.6984764796216041
step: 34
running loss: 0.02054342587122365
Train Steps: 34/90 Loss: 0.0205 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6055, 0.4015, 0.7425, 0.2033, 0.4113, 0.1883, 0.5217, 0.4823],
[0.6314, 0.4050, 0.8227, 0.5431, 0.4150, 0.5517, 0.7121, 0.5690],
[0.6151, 0.4058, 0.7068, 0.2680, 0.3400, 0.4083, 0.5775, 0.5733],
[0.6076, 0.3958, 0.8700, 0.4667, 0.4546, 0.5046, 0.5231, 0.4960],
[ nan, nan, 0.6859, 0.2194, 0.4150, 0.1867, 0.5153, 0.5729],
[0.6218, 0.4185, 0.7338, 0.2650, 0.4625, 0.1950, 0.5687, 0.5800],
[0.6321, 0.4048, 0.8738, 0.5617, 0.3875, 0.4417, 0.6361, 0.4927],
[0.6286, 0.4040, 0.8696, 0.3047, 0.3924, 0.2887, 0.6300, 0.5367]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5280, 0.3390, 0.7156, 0.3190, 0.3913, 0.2567, 0.5322, 0.5371],
[0.7018, 0.5026, 0.8817, 0.5279, 0.3719, 0.5954, 0.5577, 0.5688],
[0.6409, 0.4319, 0.7399, 0.3588, 0.3451, 0.4342, 0.5118, 0.5571],
[0.6910, 0.4941, 0.8952, 0.5139, 0.4234, 0.5669, 0.5235, 0.5712],
[0.5076, 0.3336, 0.7361, 0.3109, 0.3979, 0.2886, 0.5175, 0.5497],
[0.5446, 0.3609, 0.7134, 0.3174, 0.3978, 0.2716, 0.5157, 0.5486],
[0.7687, 0.5217, 0.9188, 0.5964, 0.3390, 0.5564, 0.5295, 0.5449],
[0.6559, 0.4589, 0.8268, 0.4680, 0.3728, 0.3424, 0.5794, 0.5420]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6055, 0.4015, 0.7425, 0.2033, 0.4112, 0.1883, 0.5217, 0.4823],
[0.6314, 0.4050, 0.8227, 0.5431, 0.4150, 0.5517, 0.7121, 0.5690],
[0.6151, 0.4058, 0.7068, 0.2680, 0.3400, 0.4083, 0.5775, 0.5733],
[0.6076, 0.3958, 0.8700, 0.4667, 0.4546, 0.5046, 0.5231, 0.4960],
[0.0000, 0.0000, 0.6859, 0.2194, 0.4150, 0.1867, 0.5153, 0.5729],
[0.6218, 0.4185, 0.7337, 0.2650, 0.4625, 0.1950, 0.5688, 0.5800],
[0.6321, 0.4048, 0.8737, 0.5617, 0.3875, 0.4417, 0.6361, 0.4927],
[0.6286, 0.4040, 0.8696, 0.3047, 0.3924, 0.2887, 0.6300, 0.5367]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0101, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0101, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.7085485982242972
step: 35
running loss: 0.020244245663551347
Train Steps: 35/90 Loss: 0.0202 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6236, 0.3967, 0.8675, 0.5400, 0.3862, 0.4517, 0.5825, 0.5200],
[0.6068, 0.3963, 0.8650, 0.4317, 0.4037, 0.5083, 0.5253, 0.4999],
[0.6236, 0.4081, 0.8575, 0.3000, 0.3713, 0.3033, 0.5550, 0.5633],
[0.6216, 0.4100, 0.7350, 0.2067, 0.4325, 0.2050, 0.5950, 0.5333],
[0.6357, 0.4097, 0.9038, 0.3883, 0.4213, 0.2950, 0.6686, 0.5390],
[0.6271, 0.4024, 0.9000, 0.3517, 0.3700, 0.4517, 0.6931, 0.5285],
[0.6193, 0.4079, 0.7288, 0.2500, 0.4250, 0.2550, 0.5989, 0.6266],
[0.6314, 0.4050, 0.8227, 0.5431, 0.4150, 0.5517, 0.7121, 0.5690]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6796, 0.4346, 0.9105, 0.5463, 0.3525, 0.5400, 0.5134, 0.5412],
[0.6602, 0.4432, 0.9022, 0.4741, 0.3960, 0.5250, 0.5403, 0.5289],
[0.6180, 0.4283, 0.8339, 0.4508, 0.4131, 0.3817, 0.5499, 0.5397],
[0.5023, 0.3241, 0.7431, 0.3296, 0.4211, 0.2222, 0.5520, 0.5293],
[0.5949, 0.3923, 0.8258, 0.4020, 0.4123, 0.3946, 0.5833, 0.5566],
[0.6230, 0.4350, 0.8654, 0.3879, 0.3692, 0.5040, 0.5558, 0.5466],
[0.5663, 0.3615, 0.7780, 0.3761, 0.4226, 0.2939, 0.5498, 0.5536],
[0.6266, 0.4297, 0.8683, 0.4994, 0.3981, 0.5438, 0.5580, 0.5618]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6236, 0.3967, 0.8675, 0.5400, 0.3862, 0.4517, 0.5825, 0.5200],
[0.6068, 0.3963, 0.8650, 0.4317, 0.4038, 0.5083, 0.5253, 0.4999],
[0.6236, 0.4081, 0.8575, 0.3000, 0.3713, 0.3033, 0.5550, 0.5633],
[0.6216, 0.4100, 0.7350, 0.2067, 0.4325, 0.2050, 0.5950, 0.5333],
[0.6357, 0.4097, 0.9038, 0.3883, 0.4212, 0.2950, 0.6686, 0.5390],
[0.6271, 0.4024, 0.9000, 0.3517, 0.3700, 0.4517, 0.6931, 0.5285],
[0.6193, 0.4078, 0.7287, 0.2500, 0.4250, 0.2550, 0.5989, 0.6266],
[0.6314, 0.4050, 0.8227, 0.5431, 0.4150, 0.5517, 0.7121, 0.5690]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0033, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0033, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.7118957417551428
step: 36
running loss: 0.019774881715420634
Train Steps: 36/90 Loss: 0.0198 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6175, 0.4091, 0.7863, 0.2800, 0.3638, 0.3583, 0.6188, 0.5433],
[0.6308, 0.3990, 0.8688, 0.5183, 0.3950, 0.4983, 0.6388, 0.5133],
[0.6226, 0.4125, 0.8800, 0.4900, 0.4512, 0.5600, 0.6275, 0.5517],
[0.6250, 0.4116, 0.8700, 0.4850, 0.4650, 0.5567, 0.6088, 0.5183],
[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.6195, 0.4101, 0.8650, 0.3917, 0.3575, 0.4033, 0.5800, 0.5650],
[0.6353, 0.4128, 0.9138, 0.3533, 0.4688, 0.3250, 0.7145, 0.5991],
[0.6212, 0.4033, 0.8938, 0.4167, 0.3813, 0.4267, 0.5613, 0.5583]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5292, 0.3872, 0.7569, 0.2700, 0.3864, 0.3128, 0.5665, 0.5585],
[0.6096, 0.4050, 0.8747, 0.4772, 0.4006, 0.4952, 0.5530, 0.5093],
[0.5875, 0.3963, 0.8670, 0.4399, 0.4564, 0.4967, 0.5858, 0.5465],
[0.5625, 0.3597, 0.8807, 0.4257, 0.4473, 0.4756, 0.5719, 0.5578],
[0.5999, 0.4131, 0.8598, 0.4714, 0.3961, 0.4890, 0.5484, 0.5499],
[0.5851, 0.3990, 0.8530, 0.4214, 0.3858, 0.4066, 0.5353, 0.5361],
[0.5423, 0.3711, 0.8811, 0.3812, 0.4638, 0.3094, 0.6062, 0.5717],
[0.5934, 0.3772, 0.9045, 0.4281, 0.3759, 0.4242, 0.5442, 0.5451]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6175, 0.4091, 0.7862, 0.2800, 0.3638, 0.3583, 0.6187, 0.5433],
[0.6308, 0.3990, 0.8687, 0.5183, 0.3950, 0.4983, 0.6388, 0.5133],
[0.6226, 0.4125, 0.8800, 0.4900, 0.4512, 0.5600, 0.6275, 0.5517],
[0.6251, 0.4116, 0.8700, 0.4850, 0.4650, 0.5567, 0.6087, 0.5183],
[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.6195, 0.4101, 0.8650, 0.3917, 0.3575, 0.4033, 0.5800, 0.5650],
[0.6353, 0.4128, 0.9137, 0.3533, 0.4688, 0.3250, 0.7145, 0.5991],
[0.6212, 0.4033, 0.8938, 0.4167, 0.3812, 0.4267, 0.5612, 0.5583]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.7136210562894121
step: 37
running loss: 0.019287055575389515
Train Steps: 37/90 Loss: 0.0193 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586],
[0.6226, 0.4098, 0.8912, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367],
[0.6311, 0.4008, 0.7935, 0.5746, 0.3900, 0.5033, 0.6955, 0.5366],
[0.6277, 0.4036, 0.8688, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742],
[0.6038, 0.3946, 0.8413, 0.4883, 0.3563, 0.4550, 0.5266, 0.4693],
[0.6175, 0.4091, 0.7863, 0.2800, 0.3638, 0.3583, 0.6188, 0.5433],
[0.6275, 0.4050, 0.9038, 0.3767, 0.3838, 0.3533, 0.7074, 0.5575],
[0.6221, 0.4107, 0.7788, 0.3033, 0.3950, 0.2817, 0.6075, 0.5517]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5222, 0.3515, 0.8506, 0.3014, 0.4592, 0.3052, 0.6338, 0.5594],
[0.5480, 0.3766, 0.8690, 0.4320, 0.4403, 0.4208, 0.6058, 0.5543],
[0.5488, 0.3863, 0.8739, 0.4569, 0.4179, 0.4869, 0.5889, 0.5529],
[0.5554, 0.3790, 0.8614, 0.3570, 0.4100, 0.4137, 0.6209, 0.5165],
[0.5769, 0.3792, 0.8886, 0.4361, 0.3942, 0.4907, 0.5784, 0.5046],
[0.5248, 0.3738, 0.7878, 0.2725, 0.3957, 0.3849, 0.6102, 0.5456],
[0.5949, 0.3894, 0.9011, 0.4044, 0.4239, 0.3835, 0.6411, 0.5413],
[0.5363, 0.3850, 0.8409, 0.3620, 0.4490, 0.2931, 0.6067, 0.5606]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586],
[0.6226, 0.4098, 0.8913, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367],
[0.6311, 0.4008, 0.7935, 0.5746, 0.3900, 0.5033, 0.6955, 0.5366],
[0.6277, 0.4036, 0.8687, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742],
[0.6038, 0.3946, 0.8413, 0.4883, 0.3562, 0.4550, 0.5266, 0.4693],
[0.6175, 0.4091, 0.7862, 0.2800, 0.3638, 0.3583, 0.6187, 0.5433],
[0.6275, 0.4050, 0.9038, 0.3767, 0.3837, 0.3533, 0.7074, 0.5575],
[0.6221, 0.4107, 0.7788, 0.3033, 0.3950, 0.2817, 0.6075, 0.5517]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0029, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0029, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.7165557543048635
step: 38
running loss: 0.018856730376443778
Train Steps: 38/90 Loss: 0.0189 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6215, 0.4119, 0.7688, 0.2300, 0.4200, 0.2283, 0.5925, 0.5317],
[0.6364, 0.4154, 0.8938, 0.3717, 0.4500, 0.2583, 0.6448, 0.5285],
[0.6201, 0.4004, 0.8786, 0.5043, 0.3833, 0.5138, 0.5997, 0.5092],
[0.6164, 0.4066, 0.6625, 0.3033, 0.3775, 0.2967, 0.5725, 0.5833],
[0.6082, 0.4024, 0.8738, 0.4017, 0.3688, 0.3950, 0.5306, 0.5136],
[0.6137, 0.4084, 0.8076, 0.3889, 0.3650, 0.3150, 0.5356, 0.5896],
[0.6125, 0.3974, 0.7725, 0.2517, 0.3538, 0.3317, 0.5887, 0.5500],
[0.6179, 0.3961, 0.8347, 0.6020, 0.3887, 0.4624, 0.5714, 0.5373]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4853, 0.3183, 0.7892, 0.2729, 0.4579, 0.1858, 0.6309, 0.5517],
[0.5639, 0.3632, 0.9041, 0.3791, 0.4606, 0.3558, 0.6677, 0.5591],
[0.5767, 0.3924, 0.9650, 0.4746, 0.4343, 0.5645, 0.6595, 0.5016],
[0.5177, 0.3271, 0.7849, 0.2934, 0.3936, 0.3067, 0.6365, 0.5375],
[0.5677, 0.3806, 0.8894, 0.3982, 0.4131, 0.4094, 0.6496, 0.5093],
[0.5819, 0.3677, 0.8950, 0.3920, 0.4091, 0.3712, 0.6272, 0.5226],
[0.5597, 0.3846, 0.8170, 0.2857, 0.4165, 0.3674, 0.6354, 0.5120],
[0.5893, 0.3831, 0.9125, 0.4968, 0.3887, 0.5205, 0.6712, 0.5350]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6215, 0.4119, 0.7688, 0.2300, 0.4200, 0.2283, 0.5925, 0.5317],
[0.6364, 0.4154, 0.8938, 0.3717, 0.4500, 0.2583, 0.6448, 0.5285],
[0.6201, 0.4004, 0.8786, 0.5043, 0.3833, 0.5138, 0.5997, 0.5092],
[0.6164, 0.4066, 0.6625, 0.3033, 0.3775, 0.2967, 0.5725, 0.5833],
[0.6082, 0.4024, 0.8737, 0.4017, 0.3688, 0.3950, 0.5306, 0.5136],
[0.6137, 0.4084, 0.8076, 0.3889, 0.3650, 0.3150, 0.5356, 0.5896],
[0.6125, 0.3974, 0.7725, 0.2517, 0.3537, 0.3317, 0.5888, 0.5500],
[0.6179, 0.3961, 0.8347, 0.6020, 0.3887, 0.4624, 0.5714, 0.5373]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0032, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0032, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.7197442847536877
step: 39
running loss: 0.018454981660350967
Train Steps: 39/90 Loss: 0.0185 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6200, 0.4086, 0.8414, 0.2974, 0.4117, 0.2274, 0.5869, 0.5391],
[0.6277, 0.4013, 0.8888, 0.4767, 0.3600, 0.3567, 0.6148, 0.4672],
[0.6203, 0.4096, 0.8862, 0.4267, 0.3538, 0.4117, 0.6025, 0.5650],
[0.6086, 0.4019, 0.7782, 0.4278, 0.3625, 0.4350, 0.5150, 0.5285],
[0.6145, 0.3983, 0.8700, 0.5017, 0.4400, 0.4800, 0.5375, 0.5750],
[0.6361, 0.4165, 0.9038, 0.5017, 0.3750, 0.3783, 0.6448, 0.5309],
[0.6101, 0.4042, 0.7775, 0.2617, 0.3713, 0.2817, 0.5440, 0.5650],
[0.6160, 0.4086, 0.8775, 0.3983, 0.3750, 0.3783, 0.5128, 0.4882]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5669, 0.3682, 0.8350, 0.2945, 0.4606, 0.2369, 0.6672, 0.5693],
[0.5937, 0.3768, 0.8715, 0.4076, 0.3744, 0.4059, 0.6638, 0.4973],
[0.5738, 0.3461, 0.9497, 0.3841, 0.3975, 0.4007, 0.6788, 0.5481],
[0.5936, 0.3624, 0.8194, 0.3669, 0.3962, 0.3466, 0.6540, 0.5133],
[0.5639, 0.3757, 0.8873, 0.4276, 0.4282, 0.4881, 0.6677, 0.5097],
[0.6198, 0.4045, 0.8702, 0.4273, 0.4185, 0.3589, 0.6628, 0.5233],
[0.5214, 0.3388, 0.7650, 0.2842, 0.4229, 0.2296, 0.6664, 0.5563],
[0.6124, 0.3885, 0.8598, 0.3752, 0.3879, 0.3847, 0.6683, 0.5288]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6199, 0.4086, 0.8414, 0.2974, 0.4117, 0.2274, 0.5869, 0.5391],
[0.6277, 0.4013, 0.8888, 0.4767, 0.3600, 0.3567, 0.6148, 0.4672],
[0.6203, 0.4096, 0.8863, 0.4267, 0.3537, 0.4117, 0.6025, 0.5650],
[0.6086, 0.4019, 0.7782, 0.4278, 0.3625, 0.4350, 0.5150, 0.5285],
[0.6145, 0.3983, 0.8700, 0.5017, 0.4400, 0.4800, 0.5375, 0.5750],
[0.6361, 0.4165, 0.9038, 0.5017, 0.3750, 0.3783, 0.6448, 0.5309],
[0.6101, 0.4042, 0.7775, 0.2617, 0.3713, 0.2817, 0.5440, 0.5650],
[0.6160, 0.4086, 0.8775, 0.3983, 0.3750, 0.3783, 0.5128, 0.4882]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0029, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0029, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.7226116416277364
step: 40
running loss: 0.01806529104069341
Train Steps: 40/90 Loss: 0.0181 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6207, 0.4110, 0.8738, 0.5000, 0.4800, 0.5633, 0.6300, 0.5433],
[0.6239, 0.4061, 0.8850, 0.4600, 0.4225, 0.5200, 0.6138, 0.5450],
[0.6184, 0.4079, 0.8350, 0.3700, 0.3675, 0.2883, 0.5312, 0.5783],
[0.6122, 0.3993, 0.8738, 0.4667, 0.4517, 0.4879, 0.5155, 0.4927],
[0.6203, 0.4072, 0.8892, 0.3523, 0.3783, 0.3017, 0.5898, 0.5478],
[0.6200, 0.3913, 0.8788, 0.5217, 0.4075, 0.5100, 0.6060, 0.4913],
[0.6275, 0.4008, 0.8047, 0.2484, 0.4037, 0.2777, 0.6506, 0.5212],
[0.6264, 0.3972, 0.8853, 0.4771, 0.3853, 0.4511, 0.6293, 0.5334]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6079, 0.3684, 0.8767, 0.4069, 0.4390, 0.4066, 0.6747, 0.5424],
[0.5971, 0.3870, 0.9012, 0.4236, 0.3968, 0.4451, 0.6842, 0.5146],
[0.6840, 0.4018, 0.8202, 0.3566, 0.3806, 0.2903, 0.6120, 0.5582],
[0.6218, 0.3943, 0.8632, 0.3988, 0.4154, 0.3771, 0.6226, 0.5125],
[0.6515, 0.3961, 0.8786, 0.3728, 0.3809, 0.2942, 0.6653, 0.5429],
[0.6099, 0.3804, 0.8950, 0.4180, 0.4207, 0.4285, 0.6519, 0.5324],
[0.5717, 0.3496, 0.7514, 0.2635, 0.4039, 0.1859, 0.6216, 0.5170],
[0.5850, 0.3603, 0.8961, 0.3972, 0.3829, 0.3713, 0.6643, 0.5443]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6207, 0.4110, 0.8737, 0.5000, 0.4800, 0.5633, 0.6300, 0.5433],
[0.6239, 0.4061, 0.8850, 0.4600, 0.4225, 0.5200, 0.6137, 0.5450],
[0.6184, 0.4079, 0.8350, 0.3700, 0.3675, 0.2883, 0.5312, 0.5783],
[0.6122, 0.3993, 0.8737, 0.4667, 0.4517, 0.4879, 0.5155, 0.4927],
[0.6203, 0.4072, 0.8892, 0.3523, 0.3783, 0.3017, 0.5898, 0.5478],
[0.6199, 0.3913, 0.8788, 0.5217, 0.4075, 0.5100, 0.6060, 0.4913],
[0.6275, 0.4008, 0.8047, 0.2484, 0.4037, 0.2777, 0.6506, 0.5212],
[0.6264, 0.3972, 0.8853, 0.4771, 0.3853, 0.4511, 0.6293, 0.5334]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0025, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0025, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.7251194597920403
step: 41
running loss: 0.01768584048273269
Train Steps: 41/90 Loss: 0.0177 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395],
[0.6336, 0.4191, 0.8938, 0.5167, 0.3937, 0.3517, 0.7343, 0.5748],
[0.6268, 0.4061, 0.8350, 0.2433, 0.4575, 0.2283, 0.6350, 0.5300],
[0.6200, 0.4049, 0.8638, 0.5617, 0.4125, 0.5100, 0.6013, 0.5317],
[0.6236, 0.4081, 0.8575, 0.3000, 0.3713, 0.3033, 0.5550, 0.5633],
[0.6058, 0.3986, 0.8324, 0.4626, 0.3838, 0.4983, 0.5147, 0.5466],
[0.6107, 0.4050, 0.8700, 0.4850, 0.4470, 0.4848, 0.5043, 0.5431],
[0.6203, 0.4021, 0.8780, 0.5031, 0.3667, 0.3882, 0.5842, 0.5405]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6478, 0.3852, 0.8580, 0.4518, 0.3584, 0.3141, 0.5976, 0.5479],
[0.6389, 0.3808, 0.8447, 0.3671, 0.3886, 0.2617, 0.6178, 0.5360],
[0.6121, 0.3714, 0.8291, 0.2746, 0.4025, 0.2104, 0.6777, 0.5752],
[0.6169, 0.3722, 0.8361, 0.4941, 0.3821, 0.4507, 0.6206, 0.5253],
[0.6501, 0.3987, 0.8182, 0.3100, 0.4028, 0.2576, 0.6209, 0.5517],
[0.5819, 0.3600, 0.8697, 0.4064, 0.3736, 0.3797, 0.6058, 0.5259],
[0.6105, 0.3602, 0.8543, 0.4191, 0.4216, 0.3745, 0.6147, 0.5200],
[0.6841, 0.4008, 0.8740, 0.4576, 0.3594, 0.3333, 0.6435, 0.5299]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395],
[0.6336, 0.4191, 0.8938, 0.5167, 0.3938, 0.3517, 0.7343, 0.5748],
[0.6268, 0.4060, 0.8350, 0.2433, 0.4575, 0.2283, 0.6350, 0.5300],
[0.6199, 0.4049, 0.8637, 0.5617, 0.4125, 0.5100, 0.6012, 0.5317],
[0.6236, 0.4081, 0.8575, 0.3000, 0.3713, 0.3033, 0.5550, 0.5633],
[0.6058, 0.3986, 0.8324, 0.4626, 0.3837, 0.4983, 0.5147, 0.5466],
[0.6107, 0.4050, 0.8700, 0.4850, 0.4470, 0.4848, 0.5043, 0.5431],
[0.6203, 0.4020, 0.8780, 0.5031, 0.3667, 0.3882, 0.5842, 0.5405]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0026, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0026, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.7277624051785097
step: 42
running loss: 0.017327676313774038
Train Steps: 42/90 Loss: 0.0173 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6214, 0.4112, 0.7838, 0.2117, 0.3650, 0.3133, 0.5675, 0.5083],
[0.6125, 0.4076, 0.8488, 0.3883, 0.3700, 0.3683, 0.5026, 0.5505],
[0.6198, 0.4114, 0.8263, 0.3283, 0.3550, 0.3583, 0.5813, 0.5667],
[0.6225, 0.4116, 0.8662, 0.3517, 0.3663, 0.3233, 0.5837, 0.5317],
[0.6258, 0.4143, 0.8525, 0.2617, 0.4950, 0.1667, 0.6219, 0.4967],
[0.6106, 0.4022, 0.7125, 0.2650, 0.3713, 0.2700, 0.5431, 0.5123],
[0.6073, 0.3932, 0.8363, 0.5817, 0.4425, 0.5117, 0.5204, 0.4817],
[0.6275, 0.4157, 0.8337, 0.5800, 0.3763, 0.4200, 0.5547, 0.6125]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6859, 0.4183, 0.8201, 0.3667, 0.3846, 0.2885, 0.6160, 0.5481],
[0.6493, 0.3851, 0.8564, 0.4168, 0.3520, 0.3721, 0.5779, 0.5315],
[0.6808, 0.4184, 0.8806, 0.4314, 0.3619, 0.3917, 0.6199, 0.5227],
[0.6688, 0.3939, 0.8313, 0.3791, 0.3818, 0.2768, 0.5978, 0.5413],
[0.6302, 0.3876, 0.8173, 0.2933, 0.4438, 0.1975, 0.6074, 0.5589],
[0.6045, 0.3703, 0.7571, 0.3427, 0.3783, 0.2547, 0.5605, 0.5320],
[0.6031, 0.4094, 0.8788, 0.5251, 0.4059, 0.4233, 0.5849, 0.5355],
[0.6389, 0.4025, 0.8686, 0.5786, 0.3450, 0.4725, 0.6304, 0.4850]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6214, 0.4112, 0.7837, 0.2117, 0.3650, 0.3133, 0.5675, 0.5083],
[0.6125, 0.4076, 0.8487, 0.3883, 0.3700, 0.3683, 0.5026, 0.5505],
[0.6198, 0.4114, 0.8263, 0.3283, 0.3550, 0.3583, 0.5813, 0.5667],
[0.6225, 0.4116, 0.8662, 0.3517, 0.3663, 0.3233, 0.5838, 0.5317],
[0.6258, 0.4143, 0.8525, 0.2617, 0.4950, 0.1667, 0.6219, 0.4967],
[0.6106, 0.4022, 0.7125, 0.2650, 0.3713, 0.2700, 0.5431, 0.5123],
[0.6073, 0.3932, 0.8363, 0.5817, 0.4425, 0.5117, 0.5204, 0.4817],
[0.6275, 0.4157, 0.8338, 0.5800, 0.3762, 0.4200, 0.5547, 0.6125]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0022, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0022, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.7299826672533527
step: 43
running loss: 0.01697634109891518
Train Steps: 43/90 Loss: 0.0170 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6332, 0.4128, 0.9200, 0.3517, 0.4400, 0.3833, 0.7461, 0.5494],
[0.6250, 0.4103, 0.8950, 0.4400, 0.3912, 0.5650, 0.6050, 0.5133],
[0.6182, 0.3967, 0.8263, 0.3065, 0.3526, 0.4161, 0.6192, 0.5290],
[0.6262, 0.4085, 0.8438, 0.3150, 0.4025, 0.2633, 0.6339, 0.4810],
[0.6314, 0.4050, 0.8227, 0.5431, 0.4150, 0.5517, 0.7121, 0.5690],
[0.6202, 0.3983, 0.8555, 0.5429, 0.3842, 0.4370, 0.5866, 0.5398],
[0.6042, 0.3990, 0.6831, 0.2875, 0.3500, 0.3133, 0.5143, 0.5510],
[0.6200, 0.3913, 0.8788, 0.5217, 0.4075, 0.5100, 0.6060, 0.4913]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6318, 0.4200, 0.8345, 0.3732, 0.4057, 0.3183, 0.5886, 0.5354],
[0.6617, 0.4213, 0.8959, 0.4752, 0.4035, 0.5062, 0.5819, 0.5257],
[0.6774, 0.3981, 0.8371, 0.3690, 0.3556, 0.3575, 0.5416, 0.5478],
[0.6886, 0.4337, 0.8427, 0.3384, 0.4122, 0.2879, 0.5650, 0.5443],
[0.6776, 0.4242, 0.8516, 0.5299, 0.3947, 0.4612, 0.6092, 0.5451],
[0.7017, 0.4519, 0.8956, 0.5708, 0.3654, 0.4416, 0.5562, 0.5274],
[0.6478, 0.4055, 0.7656, 0.3337, 0.3684, 0.2613, 0.5162, 0.5638],
[0.6874, 0.4252, 0.9035, 0.5301, 0.4162, 0.4708, 0.5566, 0.5378]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6332, 0.4128, 0.9200, 0.3517, 0.4400, 0.3833, 0.7461, 0.5494],
[0.6250, 0.4103, 0.8950, 0.4400, 0.3913, 0.5650, 0.6050, 0.5133],
[0.6182, 0.3967, 0.8263, 0.3065, 0.3526, 0.4161, 0.6192, 0.5290],
[0.6262, 0.4085, 0.8438, 0.3150, 0.4025, 0.2633, 0.6339, 0.4810],
[0.6314, 0.4050, 0.8227, 0.5431, 0.4150, 0.5517, 0.7121, 0.5690],
[0.6202, 0.3983, 0.8555, 0.5429, 0.3842, 0.4370, 0.5866, 0.5398],
[0.6042, 0.3990, 0.6831, 0.2875, 0.3500, 0.3133, 0.5143, 0.5510],
[0.6199, 0.3913, 0.8788, 0.5217, 0.4075, 0.5100, 0.6060, 0.4913]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0022, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0022, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.7321775729069486
step: 44
running loss: 0.01664039938424883
Train Steps: 44/90 Loss: 0.0166 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.6469, 0.1943, 0.4025, 0.2000, 0.5125, 0.5533],
[0.6246, 0.4028, 0.8738, 0.4867, 0.4088, 0.5667, 0.6362, 0.5200],
[0.6275, 0.4071, 0.8075, 0.2100, 0.4700, 0.1533, 0.6148, 0.4834],
[0.6185, 0.4067, 0.8838, 0.4450, 0.4037, 0.4733, 0.5213, 0.5142],
[0.6202, 0.4054, 0.8892, 0.4428, 0.3642, 0.3249, 0.5840, 0.5426],
[0.6201, 0.4098, 0.8575, 0.3617, 0.3700, 0.3550, 0.5988, 0.5667],
[0.6113, 0.4104, 0.8650, 0.4250, 0.3925, 0.5967, 0.5787, 0.5116],
[0.6243, 0.4128, 0.7762, 0.2717, 0.3825, 0.3133, 0.6212, 0.5417]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5502, 0.3357, 0.6939, 0.2983, 0.3869, 0.2363, 0.4876, 0.5458],
[0.6379, 0.4245, 0.8473, 0.5687, 0.3954, 0.6164, 0.5743, 0.4970],
[0.6755, 0.4439, 0.7752, 0.2956, 0.4185, 0.2184, 0.5482, 0.5289],
[0.6546, 0.4260, 0.8546, 0.4950, 0.3709, 0.4749, 0.5239, 0.5447],
[0.6950, 0.4629, 0.8671, 0.4698, 0.3533, 0.4084, 0.5627, 0.5403],
[0.7052, 0.4755, 0.8520, 0.4392, 0.3554, 0.3897, 0.5525, 0.5459],
[0.6257, 0.4419, 0.8624, 0.4957, 0.3983, 0.5694, 0.5611, 0.5239],
[0.6736, 0.4606, 0.7992, 0.3360, 0.4000, 0.2437, 0.5425, 0.5643]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.6469, 0.1943, 0.4025, 0.2000, 0.5125, 0.5533],
[0.6246, 0.4028, 0.8737, 0.4867, 0.4087, 0.5667, 0.6363, 0.5200],
[0.6275, 0.4071, 0.8075, 0.2100, 0.4700, 0.1533, 0.6148, 0.4834],
[0.6185, 0.4067, 0.8838, 0.4450, 0.4038, 0.4733, 0.5213, 0.5142],
[0.6202, 0.4054, 0.8892, 0.4428, 0.3642, 0.3249, 0.5840, 0.5426],
[0.6201, 0.4098, 0.8575, 0.3617, 0.3700, 0.3550, 0.5987, 0.5667],
[0.6113, 0.4104, 0.8650, 0.4250, 0.3925, 0.5967, 0.5787, 0.5116],
[0.6243, 0.4128, 0.7763, 0.2717, 0.3825, 0.3133, 0.6212, 0.5417]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0085, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0085, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.7407123452285305
step: 45
running loss: 0.01646027433841179
Train Steps: 45/90 Loss: 0.0165 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6308, 0.3990, 0.8688, 0.5183, 0.3950, 0.4983, 0.6388, 0.5133],
[0.6192, 0.3980, 0.7078, 0.2750, 0.4250, 0.2100, 0.5450, 0.5783],
[0.6260, 0.4120, 0.8013, 0.2350, 0.4888, 0.1533, 0.6281, 0.4895],
[0.6164, 0.3972, 0.7818, 0.3381, 0.3599, 0.3387, 0.5880, 0.5153],
[0.6199, 0.4093, 0.7913, 0.2533, 0.4288, 0.2467, 0.5975, 0.5700],
[0.6064, 0.3953, 0.8738, 0.4417, 0.3663, 0.4683, 0.5511, 0.5416],
[0.6249, 0.4138, 0.9038, 0.4517, 0.3862, 0.4917, 0.6138, 0.5333],
[0.6200, 0.4112, 0.8862, 0.4100, 0.3638, 0.4917, 0.6088, 0.6050]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6275, 0.4261, 0.8645, 0.5512, 0.3968, 0.5612, 0.5912, 0.4915],
[0.5661, 0.3730, 0.7460, 0.2466, 0.4075, 0.2641, 0.5022, 0.5740],
[0.6225, 0.4330, 0.7935, 0.2694, 0.4527, 0.2330, 0.5499, 0.5673],
[0.6655, 0.4337, 0.7820, 0.3664, 0.3560, 0.4036, 0.5483, 0.5219],
[0.6356, 0.4358, 0.8026, 0.3195, 0.4113, 0.3123, 0.5415, 0.5637],
[0.6347, 0.4366, 0.8743, 0.5053, 0.3707, 0.5440, 0.5326, 0.5076],
[0.6398, 0.4466, 0.8624, 0.5047, 0.3825, 0.5448, 0.5553, 0.5348],
[0.6460, 0.4478, 0.9060, 0.5175, 0.3901, 0.5797, 0.5691, 0.5219]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6308, 0.3990, 0.8687, 0.5183, 0.3950, 0.4983, 0.6388, 0.5133],
[0.6192, 0.3980, 0.7078, 0.2750, 0.4250, 0.2100, 0.5450, 0.5783],
[0.6259, 0.4120, 0.8012, 0.2350, 0.4888, 0.1533, 0.6281, 0.4895],
[0.6164, 0.3972, 0.7818, 0.3381, 0.3599, 0.3387, 0.5880, 0.5153],
[0.6198, 0.4093, 0.7912, 0.2533, 0.4288, 0.2467, 0.5975, 0.5700],
[0.6064, 0.3952, 0.8737, 0.4417, 0.3663, 0.4683, 0.5511, 0.5416],
[0.6249, 0.4138, 0.9038, 0.4517, 0.3862, 0.4917, 0.6137, 0.5333],
[0.6200, 0.4112, 0.8863, 0.4100, 0.3638, 0.4917, 0.6087, 0.6050]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.7426065595354885
step: 46
running loss: 0.01614362085946714
Train Steps: 46/90 Loss: 0.0161 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6037, 0.4020, 0.8300, 0.4033, 0.3575, 0.4883, 0.5647, 0.5631],
[0.6267, 0.4080, 0.8438, 0.2633, 0.4763, 0.1800, 0.6259, 0.5240],
[0.6224, 0.3964, 0.8225, 0.5717, 0.4150, 0.4617, 0.5775, 0.5267],
[ nan, nan, 0.8037, 0.2483, 0.3975, 0.2517, 0.5575, 0.5600],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533],
[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334],
[0.6124, 0.4083, 0.6954, 0.3069, 0.3650, 0.2750, 0.5163, 0.5485],
[0.6268, 0.4094, 0.9038, 0.4300, 0.3700, 0.3483, 0.6262, 0.5167]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5601, 0.4024, 0.8080, 0.4328, 0.3650, 0.5411, 0.5782, 0.5040],
[0.6328, 0.4254, 0.8367, 0.2879, 0.4258, 0.3150, 0.5593, 0.5436],
[0.5882, 0.4032, 0.8208, 0.5737, 0.3746, 0.5384, 0.5297, 0.5168],
[0.5995, 0.4132, 0.7947, 0.2517, 0.4077, 0.3107, 0.5249, 0.5769],
[0.5679, 0.4346, 0.8613, 0.4552, 0.4261, 0.5152, 0.5542, 0.5333],
[0.5830, 0.4047, 0.7621, 0.3065, 0.3942, 0.3711, 0.5540, 0.5240],
[0.5902, 0.4203, 0.7136, 0.2819, 0.3937, 0.3589, 0.5246, 0.5339],
[0.6296, 0.4507, 0.8701, 0.4186, 0.4044, 0.4399, 0.5818, 0.5159]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6037, 0.4020, 0.8300, 0.4033, 0.3575, 0.4883, 0.5647, 0.5631],
[0.6267, 0.4080, 0.8438, 0.2633, 0.4762, 0.1800, 0.6259, 0.5240],
[0.6224, 0.3964, 0.8225, 0.5717, 0.4150, 0.4617, 0.5775, 0.5267],
[0.0000, 0.0000, 0.8037, 0.2483, 0.3975, 0.2517, 0.5575, 0.5600],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533],
[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334],
[0.6123, 0.4083, 0.6954, 0.3069, 0.3650, 0.2750, 0.5163, 0.5485],
[0.6268, 0.4094, 0.9038, 0.4300, 0.3700, 0.3483, 0.6263, 0.5167]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0098, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0098, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.7524001447018236
step: 47
running loss: 0.016008513717060077
Train Steps: 47/90 Loss: 0.0160 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6258, 0.4143, 0.8525, 0.2617, 0.4950, 0.1667, 0.6219, 0.4967],
[0.6210, 0.4164, 0.7202, 0.2930, 0.4025, 0.2483, 0.5687, 0.5567],
[0.6124, 0.4030, 0.8650, 0.4867, 0.4999, 0.5106, 0.5137, 0.5773],
[0.6182, 0.3982, 0.7541, 0.2379, 0.3959, 0.2792, 0.6079, 0.5389],
[0.6286, 0.4060, 0.9188, 0.4333, 0.3675, 0.4167, 0.7034, 0.5528],
[0.6193, 0.3930, 0.8949, 0.4437, 0.3852, 0.5435, 0.6263, 0.5263],
[0.6293, 0.3982, 0.8700, 0.5300, 0.3763, 0.4717, 0.7050, 0.5297],
[0.6225, 0.4191, 0.8500, 0.4167, 0.3688, 0.3233, 0.5650, 0.5650]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5769, 0.4040, 0.7802, 0.1991, 0.4471, 0.2531, 0.5674, 0.5500],
[0.5461, 0.3844, 0.7615, 0.2243, 0.4086, 0.2583, 0.5673, 0.5589],
[0.5276, 0.3678, 0.8232, 0.4573, 0.4060, 0.5099, 0.5400, 0.5218],
[0.5709, 0.4187, 0.7707, 0.2387, 0.3961, 0.2889, 0.5726, 0.5709],
[0.5552, 0.3937, 0.8630, 0.3850, 0.4013, 0.4375, 0.5807, 0.5623],
[0.5481, 0.3639, 0.8349, 0.4752, 0.3836, 0.5852, 0.5817, 0.4908],
[0.5516, 0.3764, 0.8259, 0.5291, 0.3828, 0.5496, 0.5861, 0.5209],
[0.5723, 0.4223, 0.8104, 0.3714, 0.3790, 0.3846, 0.5357, 0.5459]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6258, 0.4143, 0.8525, 0.2617, 0.4950, 0.1667, 0.6219, 0.4967],
[0.6210, 0.4164, 0.7202, 0.2930, 0.4025, 0.2483, 0.5688, 0.5567],
[0.6124, 0.4030, 0.8650, 0.4867, 0.4999, 0.5106, 0.5137, 0.5773],
[0.6182, 0.3982, 0.7541, 0.2379, 0.3959, 0.2792, 0.6079, 0.5389],
[0.6286, 0.4060, 0.9187, 0.4333, 0.3675, 0.4167, 0.7034, 0.5528],
[0.6193, 0.3930, 0.8949, 0.4437, 0.3852, 0.5435, 0.6263, 0.5263],
[0.6293, 0.3982, 0.8700, 0.5300, 0.3762, 0.4717, 0.7050, 0.5297],
[0.6225, 0.4191, 0.8500, 0.4167, 0.3688, 0.3233, 0.5650, 0.5650]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0024, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0024, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.7547844997607172
step: 48
running loss: 0.015724677078348275
Train Steps: 48/90 Loss: 0.0157 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.6859, 0.2194, 0.4150, 0.1867, 0.5153, 0.5729],
[0.6201, 0.4050, 0.7757, 0.2234, 0.4459, 0.1798, 0.5975, 0.5426],
[0.6266, 0.4101, 0.8350, 0.2333, 0.3950, 0.2950, 0.6264, 0.4921],
[0.6203, 0.4078, 0.8800, 0.5083, 0.3900, 0.5000, 0.6100, 0.5583],
[0.6165, 0.4106, 0.7575, 0.1733, 0.3838, 0.2650, 0.5680, 0.5116],
[0.6087, 0.3976, 0.8337, 0.3867, 0.3713, 0.3117, 0.5938, 0.5300],
[0.6277, 0.4036, 0.8688, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742],
[0.6275, 0.4008, 0.8047, 0.2484, 0.4037, 0.2777, 0.6506, 0.5212]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4047, 0.2704, 0.7542, 0.2308, 0.4533, 0.2697, 0.5537, 0.5551],
[0.5581, 0.3529, 0.7849, 0.2889, 0.4571, 0.3005, 0.5780, 0.5572],
[0.6089, 0.4270, 0.8583, 0.2296, 0.4496, 0.3126, 0.6338, 0.5481],
[0.5649, 0.3624, 0.9076, 0.5557, 0.3788, 0.6005, 0.5847, 0.5724],
[0.5639, 0.3667, 0.7899, 0.3049, 0.3963, 0.3105, 0.6038, 0.5304],
[0.5850, 0.4091, 0.8458, 0.3845, 0.3912, 0.4504, 0.5918, 0.5393],
[0.5680, 0.3801, 0.8733, 0.4001, 0.4094, 0.3984, 0.6094, 0.5167],
[0.5417, 0.3740, 0.7820, 0.2999, 0.4156, 0.3376, 0.5991, 0.5239]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.6859, 0.2194, 0.4150, 0.1867, 0.5153, 0.5729],
[0.6201, 0.4050, 0.7757, 0.2234, 0.4459, 0.1798, 0.5975, 0.5426],
[0.6266, 0.4101, 0.8350, 0.2333, 0.3950, 0.2950, 0.6264, 0.4921],
[0.6203, 0.4078, 0.8800, 0.5083, 0.3900, 0.5000, 0.6100, 0.5583],
[0.6165, 0.4106, 0.7575, 0.1733, 0.3837, 0.2650, 0.5680, 0.5116],
[0.6087, 0.3976, 0.8338, 0.3867, 0.3713, 0.3117, 0.5938, 0.5300],
[0.6277, 0.4036, 0.8687, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742],
[0.6275, 0.4008, 0.8047, 0.2484, 0.4037, 0.2777, 0.6506, 0.5212]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0062, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0062, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.760986584238708
step: 49
running loss: 0.015530338453851184
Train Steps: 49/90 Loss: 0.0155 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6070, 0.3979, 0.8575, 0.5083, 0.4350, 0.5400, 0.5180, 0.5466],
[0.6308, 0.3990, 0.8688, 0.5183, 0.3950, 0.4983, 0.6388, 0.5133],
[0.6102, 0.4001, 0.7738, 0.3583, 0.3463, 0.3800, 0.5524, 0.5689],
[0.6246, 0.4126, 0.8850, 0.4833, 0.4200, 0.5350, 0.6112, 0.5250],
[0.6125, 0.3974, 0.7725, 0.2517, 0.3538, 0.3317, 0.5887, 0.5500],
[0.6275, 0.4050, 0.9038, 0.3767, 0.3838, 0.3533, 0.7074, 0.5575],
[0.6299, 0.4008, 0.8450, 0.5350, 0.4213, 0.5000, 0.6350, 0.5100],
[0.6073, 0.3932, 0.8363, 0.5817, 0.4425, 0.5117, 0.5204, 0.4817]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5269, 0.3406, 0.8398, 0.3721, 0.4167, 0.4091, 0.5909, 0.5420],
[0.5514, 0.3257, 0.8563, 0.4422, 0.3974, 0.4406, 0.6472, 0.5195],
[0.5518, 0.3459, 0.7828, 0.2487, 0.3847, 0.2868, 0.6127, 0.5394],
[0.5655, 0.3462, 0.8768, 0.3768, 0.4197, 0.4672, 0.6450, 0.5594],
[0.5349, 0.3501, 0.7877, 0.2137, 0.3759, 0.2686, 0.5964, 0.5461],
[0.5685, 0.3744, 0.9011, 0.2612, 0.4193, 0.2459, 0.6702, 0.5458],
[0.5460, 0.3551, 0.8509, 0.4093, 0.3993, 0.4086, 0.6418, 0.5202],
[0.5323, 0.3448, 0.8462, 0.3966, 0.4335, 0.3736, 0.5903, 0.5409]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6070, 0.3979, 0.8575, 0.5083, 0.4350, 0.5400, 0.5180, 0.5466],
[0.6308, 0.3990, 0.8687, 0.5183, 0.3950, 0.4983, 0.6388, 0.5133],
[0.6102, 0.4001, 0.7738, 0.3583, 0.3462, 0.3800, 0.5524, 0.5689],
[0.6246, 0.4126, 0.8850, 0.4833, 0.4200, 0.5350, 0.6112, 0.5250],
[0.6125, 0.3974, 0.7725, 0.2517, 0.3537, 0.3317, 0.5888, 0.5500],
[0.6275, 0.4050, 0.9038, 0.3767, 0.3837, 0.3533, 0.7074, 0.5575],
[0.6299, 0.4008, 0.8450, 0.5350, 0.4212, 0.5000, 0.6350, 0.5100],
[0.6073, 0.3932, 0.8363, 0.5817, 0.4425, 0.5117, 0.5204, 0.4817]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0044, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0044, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.765395499765873
step: 50
running loss: 0.015307909995317458
Train Steps: 50/90 Loss: 0.0153 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6137, 0.4038, 0.8563, 0.4050, 0.3813, 0.2550, 0.5106, 0.4954],
[0.6239, 0.4061, 0.8850, 0.4600, 0.4225, 0.5200, 0.6138, 0.5450],
[0.6159, 0.4085, 0.6900, 0.2283, 0.4088, 0.1950, 0.5123, 0.5397],
[0.6149, 0.4054, 0.6713, 0.2333, 0.4025, 0.2017, 0.5213, 0.5695],
[0.6127, 0.4119, 0.8650, 0.5300, 0.4512, 0.5250, 0.5260, 0.5461],
[0.6126, 0.3954, 0.8538, 0.4983, 0.4250, 0.4700, 0.5355, 0.5350],
[0.6115, 0.4081, 0.6725, 0.2433, 0.4088, 0.1933, 0.5167, 0.5544],
[0.6169, 0.4052, 0.8742, 0.4779, 0.4288, 0.4917, 0.5763, 0.5617]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5544, 0.3628, 0.8616, 0.2909, 0.4169, 0.2274, 0.6133, 0.5377],
[0.5905, 0.3875, 0.9099, 0.4365, 0.3978, 0.4963, 0.6773, 0.5268],
[0.4808, 0.2976, 0.7408, 0.1998, 0.4108, 0.1856, 0.6188, 0.5373],
[0.4906, 0.3093, 0.7173, 0.2025, 0.3813, 0.2083, 0.5842, 0.5237],
[0.5996, 0.3735, 0.8806, 0.4638, 0.4183, 0.4209, 0.6550, 0.5542],
[0.5829, 0.3653, 0.9094, 0.4636, 0.4024, 0.4556, 0.6436, 0.5377],
[0.4791, 0.3142, 0.7376, 0.1940, 0.3909, 0.1909, 0.5938, 0.5389],
[0.5878, 0.3725, 0.8417, 0.4316, 0.4024, 0.4445, 0.6350, 0.5331]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6137, 0.4038, 0.8562, 0.4050, 0.3812, 0.2550, 0.5106, 0.4954],
[0.6239, 0.4061, 0.8850, 0.4600, 0.4225, 0.5200, 0.6137, 0.5450],
[0.6159, 0.4085, 0.6900, 0.2283, 0.4087, 0.1950, 0.5123, 0.5397],
[0.6149, 0.4054, 0.6712, 0.2333, 0.4025, 0.2017, 0.5213, 0.5695],
[0.6127, 0.4119, 0.8650, 0.5300, 0.4512, 0.5250, 0.5260, 0.5461],
[0.6126, 0.3954, 0.8537, 0.4983, 0.4250, 0.4700, 0.5355, 0.5350],
[0.6115, 0.4081, 0.6725, 0.2433, 0.4087, 0.1933, 0.5167, 0.5544],
[0.6169, 0.4052, 0.8742, 0.4779, 0.4288, 0.4917, 0.5763, 0.5617]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0035, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0035, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.7689229550305754
step: 51
running loss: 0.015076920686874027
Train Steps: 51/90 Loss: 0.0151 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6199, 0.4060, 0.8888, 0.4667, 0.3800, 0.5050, 0.6188, 0.5433],
[0.6263, 0.4030, 0.9000, 0.4767, 0.3800, 0.5167, 0.6415, 0.4771],
[0.6371, 0.4092, 0.8337, 0.5850, 0.3950, 0.5117, 0.6559, 0.5262],
[0.6100, 0.4071, 0.7601, 0.3444, 0.3400, 0.4117, 0.5625, 0.5617],
[0.6286, 0.4055, 0.9000, 0.4717, 0.3763, 0.4683, 0.7018, 0.5494],
[0.6272, 0.4120, 0.9038, 0.4117, 0.3725, 0.3200, 0.6175, 0.5250],
[0.6183, 0.4076, 0.8838, 0.4517, 0.3813, 0.4483, 0.5775, 0.5633],
[0.6229, 0.4107, 0.8137, 0.2883, 0.4750, 0.1717, 0.5813, 0.5400]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5841, 0.3481, 0.8627, 0.4467, 0.4061, 0.4344, 0.6089, 0.5218],
[0.5990, 0.3450, 0.8709, 0.4506, 0.3757, 0.4238, 0.5918, 0.5000],
[0.5780, 0.3840, 0.8173, 0.4550, 0.3951, 0.3989, 0.6279, 0.5487],
[0.5716, 0.3701, 0.7407, 0.2549, 0.3653, 0.2957, 0.6200, 0.5060],
[0.6063, 0.3638, 0.8475, 0.3999, 0.3978, 0.3789, 0.6600, 0.5402],
[0.6086, 0.3748, 0.8693, 0.3564, 0.3924, 0.2627, 0.6464, 0.5142],
[0.5666, 0.3266, 0.8481, 0.4245, 0.3842, 0.3965, 0.6189, 0.5329],
[0.5406, 0.3473, 0.7894, 0.1998, 0.4322, 0.1229, 0.6078, 0.5353]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6199, 0.4060, 0.8888, 0.4667, 0.3800, 0.5050, 0.6187, 0.5433],
[0.6263, 0.4029, 0.9000, 0.4767, 0.3800, 0.5167, 0.6415, 0.4771],
[0.6371, 0.4092, 0.8338, 0.5850, 0.3950, 0.5117, 0.6559, 0.5262],
[0.6100, 0.4071, 0.7601, 0.3444, 0.3400, 0.4117, 0.5625, 0.5617],
[0.6286, 0.4055, 0.9000, 0.4717, 0.3762, 0.4683, 0.7018, 0.5494],
[0.6272, 0.4120, 0.9038, 0.4117, 0.3725, 0.3200, 0.6175, 0.5250],
[0.6183, 0.4076, 0.8838, 0.4517, 0.3812, 0.4483, 0.5775, 0.5633],
[0.6229, 0.4107, 0.8138, 0.2883, 0.4750, 0.1717, 0.5813, 0.5400]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0026, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0026, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.7715486923698336
step: 52
running loss: 0.01483747485326603
Train Steps: 52/90 Loss: 0.0148 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6277, 0.4083, 0.8350, 0.2717, 0.4562, 0.1800, 0.5918, 0.4878],
[0.6275, 0.4050, 0.9038, 0.3767, 0.3838, 0.3533, 0.7074, 0.5575],
[0.6222, 0.4172, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633],
[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334],
[0.6161, 0.4076, 0.8900, 0.4667, 0.4125, 0.5917, 0.6262, 0.5367],
[0.6205, 0.4016, 0.8350, 0.2717, 0.3987, 0.2550, 0.5787, 0.5133],
[0.6350, 0.4118, 0.8363, 0.2717, 0.4850, 0.1700, 0.6441, 0.5170],
[ nan, nan, 0.8625, 0.2550, 0.5487, 0.2200, 0.7335, 0.5737]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5546, 0.3509, 0.7689, 0.2416, 0.4326, 0.1638, 0.5948, 0.5102],
[0.6363, 0.4136, 0.8775, 0.4243, 0.3832, 0.2892, 0.6573, 0.5144],
[0.6187, 0.3739, 0.8605, 0.6347, 0.3554, 0.5029, 0.5993, 0.5492],
[0.5874, 0.3769, 0.7346, 0.3428, 0.3623, 0.3021, 0.6076, 0.5091],
[0.6045, 0.3746, 0.8653, 0.5789, 0.3946, 0.5484, 0.6011, 0.5000],
[0.6121, 0.3957, 0.7958, 0.3137, 0.3871, 0.2547, 0.6147, 0.5380],
[0.5961, 0.3638, 0.7663, 0.2782, 0.4365, 0.2224, 0.6491, 0.5104],
[0.5224, 0.3245, 0.8160, 0.2858, 0.4545, 0.2050, 0.6430, 0.5117]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6277, 0.4083, 0.8350, 0.2717, 0.4563, 0.1800, 0.5918, 0.4878],
[0.6275, 0.4050, 0.9038, 0.3767, 0.3837, 0.3533, 0.7074, 0.5575],
[0.6222, 0.4171, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633],
[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334],
[0.6161, 0.4076, 0.8900, 0.4667, 0.4125, 0.5917, 0.6263, 0.5367],
[0.6205, 0.4015, 0.8350, 0.2717, 0.3988, 0.2550, 0.5788, 0.5133],
[0.6350, 0.4118, 0.8363, 0.2717, 0.4850, 0.1700, 0.6441, 0.5170],
[0.0000, 0.0000, 0.8625, 0.2550, 0.5487, 0.2200, 0.7335, 0.5737]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0079, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0079, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.7794073515105993
step: 53
running loss: 0.014705799085105647
Train Steps: 53/90 Loss: 0.0147 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6259, 0.4156, 0.8812, 0.3183, 0.4775, 0.1867, 0.6219, 0.4960],
[0.6115, 0.4081, 0.6725, 0.2433, 0.4088, 0.1933, 0.5167, 0.5544],
[ nan, nan, 0.6793, 0.2110, 0.4012, 0.2167, 0.5112, 0.5583],
[0.6151, 0.4125, 0.8738, 0.4417, 0.3575, 0.3783, 0.5138, 0.5483],
[0.6236, 0.3967, 0.8675, 0.5400, 0.3862, 0.4517, 0.5825, 0.5200],
[0.6099, 0.4030, 0.8638, 0.5117, 0.4983, 0.4965, 0.5086, 0.5388],
[0.6279, 0.4008, 0.8600, 0.4883, 0.4325, 0.5283, 0.7010, 0.5378],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3513, 0.4050, 0.6112, 0.5500]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6415, 0.4262, 0.8866, 0.2842, 0.4599, 0.2407, 0.6511, 0.5367],
[0.5397, 0.3495, 0.7260, 0.2746, 0.3897, 0.2141, 0.5626, 0.5319],
[0.4686, 0.3070, 0.6932, 0.2379, 0.4155, 0.1864, 0.5605, 0.5481],
[0.6670, 0.4144, 0.8815, 0.4926, 0.3525, 0.4148, 0.5968, 0.5435],
[0.6459, 0.4183, 0.8974, 0.6042, 0.3895, 0.4822, 0.6102, 0.5310],
[0.6237, 0.3969, 0.8895, 0.5081, 0.4466, 0.4090, 0.6234, 0.5345],
[0.6468, 0.4130, 0.8978, 0.5317, 0.4216, 0.4910, 0.6532, 0.5334],
[0.6487, 0.4075, 0.7803, 0.3463, 0.3606, 0.3783, 0.6201, 0.5232]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6259, 0.4156, 0.8813, 0.3183, 0.4775, 0.1867, 0.6219, 0.4960],
[0.6115, 0.4081, 0.6725, 0.2433, 0.4087, 0.1933, 0.5167, 0.5544],
[0.0000, 0.0000, 0.6793, 0.2110, 0.4013, 0.2167, 0.5113, 0.5583],
[0.6151, 0.4125, 0.8737, 0.4417, 0.3575, 0.3783, 0.5138, 0.5483],
[0.6236, 0.3967, 0.8675, 0.5400, 0.3862, 0.4517, 0.5825, 0.5200],
[0.6098, 0.4030, 0.8637, 0.5117, 0.4983, 0.4965, 0.5086, 0.5388],
[0.6279, 0.4008, 0.8600, 0.4883, 0.4325, 0.5283, 0.7010, 0.5378],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3512, 0.4050, 0.6112, 0.5500]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0063, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0063, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.7857216421980411
step: 54
running loss: 0.014550400781445205
Train Steps: 54/90 Loss: 0.0146 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6228, 0.4004, 0.8750, 0.5250, 0.3825, 0.5233, 0.6362, 0.5000],
[0.6307, 0.4029, 0.8988, 0.4817, 0.3937, 0.3500, 0.7311, 0.5378],
[0.6251, 0.4163, 0.8662, 0.4467, 0.3625, 0.3567, 0.6038, 0.5533],
[0.6128, 0.4116, 0.8450, 0.4583, 0.3675, 0.4867, 0.5337, 0.5446],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3788, 0.4900, 0.7121, 0.5864],
[0.6263, 0.4065, 0.9038, 0.4317, 0.3588, 0.4550, 0.6325, 0.5250],
[0.6302, 0.4007, 0.8850, 0.5500, 0.3613, 0.4517, 0.6335, 0.5012],
[0.6273, 0.4100, 0.7137, 0.2133, 0.4000, 0.2650, 0.6075, 0.5633]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6358, 0.4032, 0.8800, 0.5148, 0.4160, 0.5419, 0.5985, 0.5544],
[0.6271, 0.4309, 0.8779, 0.4180, 0.4278, 0.2989, 0.6445, 0.5209],
[0.6354, 0.4176, 0.8796, 0.4386, 0.3965, 0.3395, 0.5999, 0.5642],
[0.5834, 0.3736, 0.8202, 0.4424, 0.3896, 0.4175, 0.5881, 0.5508],
[0.6109, 0.4081, 0.8717, 0.4947, 0.4118, 0.4414, 0.6274, 0.5529],
[0.6070, 0.4307, 0.8827, 0.4406, 0.4242, 0.4110, 0.6265, 0.5525],
[0.6422, 0.4216, 0.8492, 0.5282, 0.4020, 0.4422, 0.6189, 0.5158],
[0.5524, 0.3625, 0.7314, 0.2355, 0.4092, 0.1922, 0.5738, 0.5495]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6228, 0.4004, 0.8750, 0.5250, 0.3825, 0.5233, 0.6363, 0.5000],
[0.6307, 0.4029, 0.8988, 0.4817, 0.3938, 0.3500, 0.7311, 0.5378],
[0.6252, 0.4162, 0.8662, 0.4467, 0.3625, 0.3567, 0.6037, 0.5533],
[0.6128, 0.4116, 0.8450, 0.4583, 0.3675, 0.4867, 0.5337, 0.5446],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3787, 0.4900, 0.7121, 0.5864],
[0.6263, 0.4065, 0.9038, 0.4317, 0.3587, 0.4550, 0.6325, 0.5250],
[0.6302, 0.4007, 0.8850, 0.5500, 0.3613, 0.4517, 0.6335, 0.5012],
[0.6273, 0.4099, 0.7138, 0.2133, 0.4000, 0.2650, 0.6075, 0.5633]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.7869276243727654
step: 55
running loss: 0.014307774988595735
Train Steps: 55/90 Loss: 0.0143 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6164, 0.4066, 0.6625, 0.3033, 0.3775, 0.2967, 0.5725, 0.5833],
[0.6057, 0.4011, 0.8750, 0.4267, 0.4400, 0.5800, 0.5845, 0.5585],
[0.6286, 0.4078, 0.8063, 0.2267, 0.4788, 0.1533, 0.5953, 0.4913],
[0.6241, 0.4143, 0.8938, 0.4650, 0.4075, 0.5350, 0.6250, 0.5550],
[0.6200, 0.4118, 0.8287, 0.4017, 0.3775, 0.2833, 0.5391, 0.5799],
[0.6168, 0.4081, 0.8438, 0.3367, 0.3500, 0.4667, 0.6212, 0.5400],
[0.6272, 0.4071, 0.8738, 0.5600, 0.3675, 0.3783, 0.5926, 0.4742],
[0.6264, 0.4035, 0.8888, 0.4883, 0.4050, 0.5217, 0.6361, 0.4791]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5301, 0.3866, 0.7485, 0.3359, 0.3693, 0.2995, 0.5671, 0.5649],
[0.6037, 0.4085, 0.8429, 0.4616, 0.4316, 0.4904, 0.6046, 0.5223],
[0.5098, 0.3556, 0.8043, 0.2597, 0.4651, 0.1535, 0.5834, 0.5238],
[0.6246, 0.4276, 0.9140, 0.5233, 0.4322, 0.5490, 0.6235, 0.5671],
[0.5730, 0.4027, 0.8279, 0.3740, 0.3846, 0.2692, 0.5577, 0.5516],
[0.6058, 0.3992, 0.8399, 0.3735, 0.3873, 0.4737, 0.6092, 0.5630],
[0.6692, 0.4559, 0.9170, 0.5879, 0.3788, 0.4056, 0.6201, 0.5233],
[0.6449, 0.4282, 0.8855, 0.5277, 0.4079, 0.5283, 0.6165, 0.5521]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6164, 0.4066, 0.6625, 0.3033, 0.3775, 0.2967, 0.5725, 0.5833],
[0.6057, 0.4011, 0.8750, 0.4267, 0.4400, 0.5800, 0.5845, 0.5585],
[0.6286, 0.4078, 0.8062, 0.2267, 0.4787, 0.1533, 0.5953, 0.4913],
[0.6241, 0.4142, 0.8938, 0.4650, 0.4075, 0.5350, 0.6250, 0.5550],
[0.6200, 0.4118, 0.8288, 0.4017, 0.3775, 0.2833, 0.5391, 0.5799],
[0.6168, 0.4081, 0.8438, 0.3367, 0.3500, 0.4667, 0.6212, 0.5400],
[0.6272, 0.4071, 0.8737, 0.5600, 0.3675, 0.3783, 0.5926, 0.4742],
[0.6264, 0.4035, 0.8888, 0.4883, 0.4050, 0.5217, 0.6361, 0.4791]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.7881838389439508
step: 56
running loss: 0.014074711409713407
Train Steps: 56/90 Loss: 0.0141 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6117, 0.4019, 0.8538, 0.4067, 0.3513, 0.3583, 0.5663, 0.5133],
[0.6075, 0.4007, 0.8275, 0.4917, 0.4050, 0.5100, 0.5167, 0.5280],
[0.6162, 0.3949, 0.8838, 0.4517, 0.4250, 0.5183, 0.5837, 0.5500],
[0.6332, 0.4128, 0.9200, 0.3517, 0.4400, 0.3833, 0.7461, 0.5494],
[0.6202, 0.4079, 0.8025, 0.2500, 0.3763, 0.3217, 0.6125, 0.5533],
[0.6270, 0.4267, 0.7150, 0.3317, 0.4900, 0.1817, 0.5560, 0.6183],
[0.6132, 0.4066, 0.7259, 0.2402, 0.3588, 0.3300, 0.6000, 0.5600],
[0.6179, 0.4082, 0.6688, 0.2667, 0.3588, 0.3317, 0.5750, 0.5783]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6256, 0.4479, 0.9064, 0.4920, 0.3685, 0.3892, 0.6073, 0.5520],
[0.6175, 0.4390, 0.8795, 0.5274, 0.4236, 0.5354, 0.5843, 0.5512],
[0.6787, 0.4470, 0.9259, 0.5724, 0.4245, 0.5948, 0.5997, 0.5572],
[0.6151, 0.4132, 0.8721, 0.4313, 0.4208, 0.4392, 0.6534, 0.5397],
[0.6369, 0.4252, 0.8739, 0.3726, 0.4443, 0.3527, 0.6142, 0.5384],
[0.5044, 0.3321, 0.7214, 0.3021, 0.4216, 0.3138, 0.5538, 0.5532],
[0.5753, 0.4049, 0.7476, 0.3612, 0.3829, 0.3842, 0.6129, 0.5504],
[0.5940, 0.4013, 0.7566, 0.3702, 0.3730, 0.3629, 0.5568, 0.5448]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6116, 0.4019, 0.8537, 0.4067, 0.3512, 0.3583, 0.5663, 0.5133],
[0.6075, 0.4006, 0.8275, 0.4917, 0.4050, 0.5100, 0.5167, 0.5280],
[0.6162, 0.3949, 0.8838, 0.4517, 0.4250, 0.5183, 0.5838, 0.5500],
[0.6332, 0.4128, 0.9200, 0.3517, 0.4400, 0.3833, 0.7461, 0.5494],
[0.6202, 0.4079, 0.8025, 0.2500, 0.3762, 0.3217, 0.6125, 0.5533],
[0.6270, 0.4266, 0.7150, 0.3317, 0.4900, 0.1817, 0.5560, 0.6183],
[0.6132, 0.4066, 0.7259, 0.2402, 0.3587, 0.3300, 0.6000, 0.5600],
[0.6179, 0.4082, 0.6687, 0.2667, 0.3587, 0.3317, 0.5750, 0.5783]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0031, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0031, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.7912858905037865
step: 57
running loss: 0.013882208605329589
Train Steps: 57/90 Loss: 0.0139 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.8900, 0.3217, 0.5038, 0.2233, 0.6694, 0.5609],
[0.6162, 0.4134, 0.6700, 0.2467, 0.3962, 0.2533, 0.5737, 0.5467],
[0.6106, 0.4022, 0.7125, 0.2650, 0.3713, 0.2700, 0.5431, 0.5123],
[0.6305, 0.3983, 0.8950, 0.4833, 0.3688, 0.4683, 0.6375, 0.5117],
[0.6179, 0.4008, 0.8600, 0.4015, 0.3932, 0.2515, 0.5711, 0.5438],
[ nan, nan, 0.7725, 0.2611, 0.3675, 0.2733, 0.5413, 0.5167],
[0.6259, 0.4133, 0.8200, 0.2317, 0.5025, 0.1533, 0.6250, 0.4947],
[0.6118, 0.4052, 0.8463, 0.3917, 0.3538, 0.3450, 0.5053, 0.5593]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5422, 0.3630, 0.8784, 0.3457, 0.4616, 0.3802, 0.6294, 0.5449],
[0.5507, 0.3724, 0.7493, 0.3501, 0.3832, 0.3287, 0.5473, 0.5549],
[0.6227, 0.4195, 0.7417, 0.3306, 0.3928, 0.3698, 0.5464, 0.5404],
[0.7243, 0.4714, 0.9390, 0.5854, 0.3803, 0.6338, 0.6083, 0.5526],
[0.5849, 0.4123, 0.8004, 0.3820, 0.4038, 0.3513, 0.5566, 0.5422],
[0.5595, 0.3575, 0.7537, 0.3040, 0.3828, 0.3033, 0.5416, 0.5295],
[0.5844, 0.3820, 0.8241, 0.2918, 0.4535, 0.3019, 0.6126, 0.5243],
[0.6423, 0.4446, 0.8735, 0.4902, 0.3554, 0.5000, 0.5660, 0.5697]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.8900, 0.3217, 0.5038, 0.2233, 0.6694, 0.5609],
[0.6162, 0.4134, 0.6700, 0.2467, 0.3963, 0.2533, 0.5738, 0.5467],
[0.6106, 0.4022, 0.7125, 0.2650, 0.3713, 0.2700, 0.5431, 0.5123],
[0.6305, 0.3983, 0.8950, 0.4833, 0.3688, 0.4683, 0.6375, 0.5117],
[0.6179, 0.4008, 0.8600, 0.4015, 0.3932, 0.2515, 0.5711, 0.5438],
[0.0000, 0.0000, 0.7725, 0.2611, 0.3675, 0.2733, 0.5412, 0.5167],
[0.6259, 0.4132, 0.8200, 0.2317, 0.5025, 0.1533, 0.6250, 0.4947],
[0.6118, 0.4052, 0.8462, 0.3917, 0.3537, 0.3450, 0.5053, 0.5593]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0170, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0170, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.8083162078401074
step: 58
running loss: 0.013936486342070818
Train Steps: 58/90 Loss: 0.0139 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6115, 0.4005, 0.8838, 0.3867, 0.3763, 0.4700, 0.5800, 0.5550],
[0.6214, 0.4175, 0.7300, 0.2883, 0.4338, 0.2167, 0.5698, 0.5773],
[0.6133, 0.4094, 0.8495, 0.4028, 0.3588, 0.3200, 0.5003, 0.5407],
[ nan, nan, 0.6900, 0.1917, 0.3937, 0.2367, 0.5240, 0.5246],
[0.6134, 0.4090, 0.6926, 0.2819, 0.3538, 0.3233, 0.5563, 0.5667],
[0.6142, 0.3982, 0.8650, 0.4883, 0.3912, 0.4317, 0.5315, 0.5350],
[0.6182, 0.4058, 0.8738, 0.4350, 0.3563, 0.3400, 0.5290, 0.5822],
[0.6229, 0.4066, 0.8513, 0.5717, 0.4500, 0.5050, 0.6025, 0.5350]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6941, 0.4152, 0.8931, 0.4134, 0.3910, 0.5324, 0.5766, 0.5431],
[0.5465, 0.3455, 0.7323, 0.2617, 0.4144, 0.2806, 0.5498, 0.5433],
[0.5984, 0.3990, 0.8667, 0.3813, 0.4116, 0.3690, 0.5511, 0.5340],
[0.4598, 0.3009, 0.7508, 0.1999, 0.4238, 0.2400, 0.5251, 0.5418],
[0.6028, 0.3708, 0.7092, 0.2750, 0.3748, 0.3487, 0.5502, 0.5231],
[0.6448, 0.4068, 0.8794, 0.5131, 0.4047, 0.5059, 0.5803, 0.5123],
[0.6070, 0.3968, 0.8930, 0.4225, 0.3829, 0.4504, 0.5513, 0.5751],
[0.6185, 0.3836, 0.8760, 0.4788, 0.4527, 0.4987, 0.5625, 0.5476]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6115, 0.4005, 0.8838, 0.3867, 0.3762, 0.4700, 0.5800, 0.5550],
[0.6214, 0.4175, 0.7300, 0.2883, 0.4338, 0.2167, 0.5698, 0.5773],
[0.6133, 0.4094, 0.8495, 0.4028, 0.3587, 0.3200, 0.5003, 0.5407],
[0.0000, 0.0000, 0.6900, 0.1917, 0.3938, 0.2367, 0.5240, 0.5246],
[0.6134, 0.4090, 0.6926, 0.2819, 0.3537, 0.3233, 0.5562, 0.5667],
[0.6143, 0.3982, 0.8650, 0.4883, 0.3913, 0.4317, 0.5315, 0.5350],
[0.6182, 0.4058, 0.8737, 0.4350, 0.3562, 0.3400, 0.5290, 0.5822],
[0.6229, 0.4066, 0.8512, 0.5717, 0.4500, 0.5050, 0.6025, 0.5350]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0060, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0060, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.8143562333425507
step: 59
running loss: 0.013802648022755097
Train Steps: 59/90 Loss: 0.0138 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6300, 0.4102, 0.9088, 0.4433, 0.4088, 0.3067, 0.6820, 0.5540],
[0.6204, 0.4049, 0.7975, 0.2700, 0.3937, 0.2567, 0.5700, 0.5183],
[0.6236, 0.3966, 0.8850, 0.4967, 0.3638, 0.4017, 0.5850, 0.5183],
[0.6112, 0.4029, 0.8638, 0.4800, 0.4875, 0.5083, 0.5763, 0.5567],
[0.6109, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117],
[0.6068, 0.3963, 0.8650, 0.4317, 0.4037, 0.5083, 0.5253, 0.4999],
[0.6038, 0.3946, 0.8413, 0.4883, 0.3563, 0.4550, 0.5266, 0.4693],
[0.6132, 0.4037, 0.6963, 0.2217, 0.4100, 0.1950, 0.5395, 0.5175]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6058, 0.3606, 0.8605, 0.3885, 0.4073, 0.3083, 0.5800, 0.5317],
[0.5016, 0.3565, 0.7446, 0.2448, 0.4139, 0.2543, 0.5300, 0.5583],
[0.6240, 0.3779, 0.8711, 0.4626, 0.3618, 0.4597, 0.5244, 0.5394],
[0.5254, 0.3303, 0.8582, 0.3840, 0.4548, 0.4209, 0.5505, 0.5425],
[0.5991, 0.3819, 0.8540, 0.4017, 0.3868, 0.4029, 0.5255, 0.5292],
[0.6212, 0.3578, 0.8351, 0.3708, 0.3966, 0.4988, 0.5554, 0.5446],
[0.6145, 0.3990, 0.8441, 0.4090, 0.3736, 0.4491, 0.5455, 0.5312],
[0.4360, 0.2643, 0.6835, 0.1788, 0.4104, 0.1723, 0.5302, 0.5247]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6300, 0.4102, 0.9087, 0.4433, 0.4087, 0.3067, 0.6820, 0.5540],
[0.6204, 0.4049, 0.7975, 0.2700, 0.3938, 0.2567, 0.5700, 0.5183],
[0.6236, 0.3965, 0.8850, 0.4967, 0.3638, 0.4017, 0.5850, 0.5183],
[0.6112, 0.4029, 0.8637, 0.4800, 0.4875, 0.5083, 0.5763, 0.5567],
[0.6108, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117],
[0.6068, 0.3963, 0.8650, 0.4317, 0.4038, 0.5083, 0.5253, 0.4999],
[0.6038, 0.3946, 0.8413, 0.4883, 0.3562, 0.4550, 0.5266, 0.4693],
[0.6132, 0.4037, 0.6963, 0.2217, 0.4100, 0.1950, 0.5395, 0.5175]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0026, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0026, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.8169467503903434
step: 60
running loss: 0.01361577917317239
Train Steps: 60/90 Loss: 0.0136 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6234, 0.4179, 0.7825, 0.3450, 0.3813, 0.2867, 0.5675, 0.5617],
[0.6090, 0.4010, 0.7838, 0.3483, 0.3538, 0.3783, 0.5462, 0.5077],
[0.6109, 0.4015, 0.7668, 0.3639, 0.3513, 0.3667, 0.5200, 0.5641],
[0.6236, 0.3966, 0.8850, 0.4967, 0.3638, 0.4017, 0.5850, 0.5183],
[0.6198, 0.4105, 0.7950, 0.3267, 0.3675, 0.3767, 0.6038, 0.6167],
[0.6200, 0.4039, 0.8880, 0.4799, 0.3625, 0.4285, 0.5866, 0.5148],
[0.6261, 0.4045, 0.8865, 0.5369, 0.3895, 0.4859, 0.6683, 0.5249],
[0.6265, 0.4091, 0.8950, 0.3533, 0.3600, 0.3967, 0.6295, 0.4901]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4491, 0.2910, 0.7879, 0.2603, 0.4166, 0.1751, 0.5204, 0.5405],
[0.5714, 0.3382, 0.7695, 0.2836, 0.3397, 0.3514, 0.5478, 0.5101],
[0.5415, 0.3494, 0.7559, 0.2859, 0.3479, 0.3300, 0.5355, 0.5410],
[0.5705, 0.3587, 0.8571, 0.4829, 0.3522, 0.4165, 0.5035, 0.5268],
[0.5447, 0.3654, 0.8386, 0.2982, 0.4155, 0.3437, 0.5604, 0.5473],
[0.5558, 0.3338, 0.8648, 0.4201, 0.3983, 0.3573, 0.5427, 0.5397],
[0.6101, 0.3714, 0.8259, 0.4802, 0.3784, 0.4516, 0.5814, 0.5289],
[0.5437, 0.3351, 0.8664, 0.3020, 0.3978, 0.2938, 0.5660, 0.5327]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6234, 0.4179, 0.7825, 0.3450, 0.3812, 0.2867, 0.5675, 0.5617],
[0.6090, 0.4010, 0.7837, 0.3483, 0.3537, 0.3783, 0.5462, 0.5077],
[0.6109, 0.4015, 0.7668, 0.3639, 0.3512, 0.3667, 0.5200, 0.5641],
[0.6236, 0.3965, 0.8850, 0.4967, 0.3638, 0.4017, 0.5850, 0.5183],
[0.6198, 0.4105, 0.7950, 0.3267, 0.3675, 0.3767, 0.6037, 0.6167],
[0.6201, 0.4039, 0.8880, 0.4799, 0.3625, 0.4285, 0.5866, 0.5148],
[0.6261, 0.4045, 0.8865, 0.5369, 0.3895, 0.4859, 0.6683, 0.5249],
[0.6265, 0.4091, 0.8950, 0.3533, 0.3600, 0.3967, 0.6295, 0.4901]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0032, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0032, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.8201047728070989
step: 61
running loss: 0.013444340537821294
Train Steps: 61/90 Loss: 0.0134 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6168, 0.4055, 0.7575, 0.2950, 0.4050, 0.2717, 0.5938, 0.6167],
[ nan, nan, 0.7268, 0.2333, 0.4125, 0.1933, 0.5112, 0.5383],
[0.6236, 0.3966, 0.8850, 0.4967, 0.3638, 0.4017, 0.5850, 0.5183],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4012, 0.4633, 0.5338, 0.5767],
[0.6198, 0.4075, 0.8650, 0.5617, 0.4150, 0.4367, 0.5450, 0.5650],
[0.6128, 0.4116, 0.8450, 0.4583, 0.3675, 0.4867, 0.5337, 0.5446],
[0.6222, 0.4108, 0.8938, 0.4233, 0.3600, 0.3817, 0.5825, 0.5283],
[0.6218, 0.4098, 0.7238, 0.1850, 0.4238, 0.2517, 0.6288, 0.5350]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5500, 0.3635, 0.7813, 0.2577, 0.3925, 0.3167, 0.5751, 0.5632],
[0.3665, 0.2547, 0.7070, 0.2034, 0.3935, 0.1840, 0.5407, 0.5374],
[0.6265, 0.3912, 0.8983, 0.4880, 0.3373, 0.4178, 0.5388, 0.5015],
[0.5959, 0.3870, 0.8860, 0.4874, 0.3806, 0.4561, 0.5588, 0.5384],
[0.5975, 0.3805, 0.8572, 0.4717, 0.3760, 0.3946, 0.5776, 0.5321],
[0.6113, 0.3528, 0.8609, 0.4085, 0.3538, 0.4293, 0.5591, 0.5227],
[0.5645, 0.3679, 0.8989, 0.3874, 0.3639, 0.3078, 0.5889, 0.5240],
[0.4978, 0.3402, 0.7412, 0.1953, 0.4422, 0.2193, 0.5693, 0.5261]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6168, 0.4055, 0.7575, 0.2950, 0.4050, 0.2717, 0.5938, 0.6167],
[0.0000, 0.0000, 0.7268, 0.2333, 0.4125, 0.1933, 0.5113, 0.5383],
[0.6236, 0.3965, 0.8850, 0.4967, 0.3638, 0.4017, 0.5850, 0.5183],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4013, 0.4633, 0.5337, 0.5767],
[0.6198, 0.4075, 0.8650, 0.5617, 0.4150, 0.4367, 0.5450, 0.5650],
[0.6128, 0.4116, 0.8450, 0.4583, 0.3675, 0.4867, 0.5337, 0.5446],
[0.6222, 0.4108, 0.8938, 0.4233, 0.3600, 0.3817, 0.5825, 0.5283],
[0.6218, 0.4098, 0.7237, 0.1850, 0.4238, 0.2517, 0.6288, 0.5350]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0045, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0045, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.824571170960553
step: 62
running loss: 0.01329953501549279
Train Steps: 62/90 Loss: 0.0133 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6128, 0.4118, 0.8638, 0.5333, 0.4625, 0.5267, 0.5193, 0.5475],
[0.6197, 0.4118, 0.8688, 0.5517, 0.4037, 0.5233, 0.5875, 0.5600],
[0.6109, 0.4036, 0.7188, 0.1750, 0.3850, 0.2550, 0.5863, 0.5567],
[0.6161, 0.4040, 0.7525, 0.2133, 0.4125, 0.2067, 0.5787, 0.5117],
[0.6168, 0.4055, 0.7575, 0.2950, 0.4050, 0.2717, 0.5938, 0.6167],
[0.6336, 0.4086, 0.8900, 0.3950, 0.3900, 0.2950, 0.6504, 0.5066],
[0.6280, 0.4101, 0.9050, 0.4533, 0.3775, 0.3217, 0.6338, 0.4915],
[0.6276, 0.4095, 0.8237, 0.2250, 0.4662, 0.1783, 0.6171, 0.4869]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5856, 0.3832, 0.8667, 0.5038, 0.3929, 0.4306, 0.5876, 0.5351],
[0.6264, 0.3945, 0.8378, 0.5135, 0.3571, 0.5204, 0.6011, 0.5409],
[0.4624, 0.3228, 0.7371, 0.2446, 0.3710, 0.2221, 0.5621, 0.5435],
[0.4359, 0.2948, 0.7194, 0.2421, 0.3845, 0.2105, 0.5463, 0.5387],
[0.5081, 0.3626, 0.7719, 0.2733, 0.3700, 0.3125, 0.5887, 0.5739],
[0.5906, 0.3802, 0.8621, 0.3707, 0.3631, 0.3314, 0.6340, 0.4989],
[0.5955, 0.3969, 0.8825, 0.4975, 0.3163, 0.2913, 0.5767, 0.5016],
[0.4488, 0.3219, 0.8165, 0.2282, 0.4266, 0.1937, 0.6143, 0.5187]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6128, 0.4118, 0.8637, 0.5333, 0.4625, 0.5267, 0.5193, 0.5475],
[0.6197, 0.4118, 0.8687, 0.5517, 0.4038, 0.5233, 0.5875, 0.5600],
[0.6108, 0.4036, 0.7188, 0.1750, 0.3850, 0.2550, 0.5863, 0.5567],
[0.6161, 0.4040, 0.7525, 0.2133, 0.4125, 0.2067, 0.5788, 0.5117],
[0.6168, 0.4055, 0.7575, 0.2950, 0.4050, 0.2717, 0.5938, 0.6167],
[0.6336, 0.4086, 0.8900, 0.3950, 0.3900, 0.2950, 0.6504, 0.5066],
[0.6280, 0.4101, 0.9050, 0.4533, 0.3775, 0.3217, 0.6338, 0.4915],
[0.6276, 0.4095, 0.8238, 0.2250, 0.4663, 0.1783, 0.6171, 0.4869]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0030, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0030, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.8275592027930543
step: 63
running loss: 0.013135860361794512
Train Steps: 63/90 Loss: 0.0131 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6203, 0.4076, 0.8611, 0.2878, 0.4050, 0.2554, 0.5907, 0.5496],
[0.6164, 0.4066, 0.6625, 0.3033, 0.3775, 0.2967, 0.5725, 0.5833],
[0.6304, 0.4029, 0.8413, 0.5217, 0.4125, 0.5617, 0.7089, 0.5679],
[0.6258, 0.4143, 0.8525, 0.2617, 0.4950, 0.1667, 0.6219, 0.4967],
[0.6223, 0.4028, 0.8988, 0.4200, 0.3763, 0.5733, 0.6375, 0.5167],
[0.6224, 0.4061, 0.8988, 0.4300, 0.3838, 0.4750, 0.6112, 0.5483],
[0.6277, 0.4036, 0.8688, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742],
[0.6083, 0.3957, 0.8638, 0.4950, 0.4363, 0.5083, 0.5346, 0.4980]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4981, 0.3343, 0.8217, 0.2960, 0.3723, 0.1908, 0.6148, 0.5354],
[0.4779, 0.3498, 0.6806, 0.3148, 0.3164, 0.2243, 0.5684, 0.5736],
[0.5703, 0.4017, 0.8371, 0.4836, 0.3770, 0.4784, 0.6296, 0.5814],
[0.4624, 0.3337, 0.7966, 0.2725, 0.4403, 0.1343, 0.6080, 0.5010],
[0.6624, 0.4184, 0.8434, 0.4282, 0.3695, 0.5177, 0.6353, 0.5406],
[0.6169, 0.4147, 0.8715, 0.4719, 0.3306, 0.4530, 0.6164, 0.5171],
[0.5956, 0.3959, 0.8104, 0.3552, 0.3451, 0.2360, 0.6289, 0.5024],
[0.5393, 0.3685, 0.8544, 0.4550, 0.3720, 0.3635, 0.5987, 0.5363]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6203, 0.4076, 0.8611, 0.2878, 0.4050, 0.2554, 0.5907, 0.5496],
[0.6164, 0.4066, 0.6625, 0.3033, 0.3775, 0.2967, 0.5725, 0.5833],
[0.6304, 0.4029, 0.8413, 0.5217, 0.4125, 0.5617, 0.7089, 0.5679],
[0.6258, 0.4143, 0.8525, 0.2617, 0.4950, 0.1667, 0.6219, 0.4967],
[0.6223, 0.4028, 0.8988, 0.4200, 0.3762, 0.5733, 0.6375, 0.5167],
[0.6224, 0.4061, 0.8988, 0.4300, 0.3837, 0.4750, 0.6112, 0.5483],
[0.6277, 0.4036, 0.8687, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742],
[0.6083, 0.3957, 0.8637, 0.4950, 0.4363, 0.5083, 0.5346, 0.4980]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0028, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0028, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.830406641936861
step: 64
running loss: 0.012975103780263453
Train Steps: 64/90 Loss: 0.0130 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6229, 0.4066, 0.7612, 0.2967, 0.4250, 0.2167, 0.5925, 0.5350],
[0.6185, 0.4080, 0.8625, 0.3483, 0.3788, 0.2650, 0.5320, 0.5272],
[0.6279, 0.4008, 0.8600, 0.4883, 0.4325, 0.5283, 0.7010, 0.5378],
[0.6218, 0.4098, 0.7238, 0.1850, 0.4238, 0.2517, 0.6288, 0.5350],
[0.6201, 0.4050, 0.7757, 0.2234, 0.4459, 0.1798, 0.5975, 0.5426],
[0.6135, 0.3994, 0.7913, 0.3050, 0.3625, 0.3050, 0.5837, 0.5050],
[0.6159, 0.4085, 0.6900, 0.2283, 0.4088, 0.1950, 0.5123, 0.5397],
[0.6214, 0.4040, 0.8838, 0.3500, 0.3600, 0.5183, 0.6362, 0.5200]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5603, 0.4120, 0.7911, 0.3092, 0.4101, 0.2705, 0.6473, 0.5467],
[0.5694, 0.3968, 0.8457, 0.4254, 0.3745, 0.2732, 0.5703, 0.5492],
[0.6512, 0.4446, 0.9230, 0.5599, 0.3967, 0.4851, 0.6733, 0.5388],
[0.5368, 0.4146, 0.7461, 0.2814, 0.4314, 0.2485, 0.6166, 0.5398],
[0.5517, 0.3704, 0.7644, 0.3018, 0.4405, 0.2130, 0.5926, 0.5472],
[0.6188, 0.4373, 0.8200, 0.3571, 0.3411, 0.3280, 0.6295, 0.5389],
[0.4397, 0.3159, 0.7076, 0.2952, 0.4046, 0.2003, 0.5565, 0.5434],
[0.6508, 0.4446, 0.8944, 0.4353, 0.3638, 0.5242, 0.6494, 0.5329]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6229, 0.4066, 0.7613, 0.2967, 0.4250, 0.2167, 0.5925, 0.5350],
[0.6186, 0.4080, 0.8625, 0.3483, 0.3787, 0.2650, 0.5320, 0.5272],
[0.6279, 0.4008, 0.8600, 0.4883, 0.4325, 0.5283, 0.7010, 0.5378],
[0.6218, 0.4098, 0.7237, 0.1850, 0.4238, 0.2517, 0.6288, 0.5350],
[0.6201, 0.4050, 0.7757, 0.2234, 0.4459, 0.1798, 0.5975, 0.5426],
[0.6135, 0.3994, 0.7912, 0.3050, 0.3625, 0.3050, 0.5838, 0.5050],
[0.6159, 0.4085, 0.6900, 0.2283, 0.4087, 0.1950, 0.5123, 0.5397],
[0.6214, 0.4040, 0.8838, 0.3500, 0.3600, 0.5183, 0.6363, 0.5200]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0021, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0021, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.832502335193567
step: 65
running loss: 0.012807728233747184
Train Steps: 65/90 Loss: 0.0128 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6286, 0.4060, 0.9188, 0.4333, 0.3675, 0.4167, 0.7034, 0.5528],
[0.6261, 0.4045, 0.8865, 0.5369, 0.3895, 0.4859, 0.6683, 0.5249],
[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334],
[0.6226, 0.4125, 0.8800, 0.4900, 0.4512, 0.5600, 0.6275, 0.5517],
[0.6346, 0.4086, 0.7938, 0.5500, 0.3962, 0.4867, 0.7343, 0.5702],
[ nan, nan, 0.7612, 0.3250, 0.4037, 0.2533, 0.5438, 0.5767],
[0.6186, 0.3967, 0.7337, 0.1992, 0.4120, 0.2508, 0.6105, 0.5395],
[0.6189, 0.4033, 0.8650, 0.5267, 0.4487, 0.5150, 0.5925, 0.5050]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6186, 0.4025, 0.9083, 0.4060, 0.3845, 0.3154, 0.6452, 0.5331],
[0.7243, 0.4844, 0.8551, 0.5121, 0.3872, 0.4598, 0.6464, 0.5225],
[0.6315, 0.4299, 0.7698, 0.2274, 0.3831, 0.2722, 0.6215, 0.5394],
[0.6787, 0.4502, 0.8737, 0.4614, 0.4429, 0.4977, 0.6371, 0.5566],
[0.6768, 0.4684, 0.8210, 0.4514, 0.4072, 0.4349, 0.6284, 0.5537],
[0.5218, 0.3466, 0.7645, 0.2660, 0.4297, 0.2230, 0.5633, 0.5546],
[0.5632, 0.3770, 0.7442, 0.2615, 0.4154, 0.1907, 0.6021, 0.5459],
[0.6338, 0.4305, 0.8497, 0.4663, 0.4445, 0.4249, 0.6135, 0.5289]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6286, 0.4060, 0.9187, 0.4333, 0.3675, 0.4167, 0.7034, 0.5528],
[0.6261, 0.4045, 0.8865, 0.5369, 0.3895, 0.4859, 0.6683, 0.5249],
[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334],
[0.6226, 0.4125, 0.8800, 0.4900, 0.4512, 0.5600, 0.6275, 0.5517],
[0.6346, 0.4086, 0.7937, 0.5500, 0.3963, 0.4867, 0.7343, 0.5702],
[0.0000, 0.0000, 0.7613, 0.3250, 0.4038, 0.2533, 0.5437, 0.5767],
[0.6186, 0.3967, 0.7337, 0.1992, 0.4120, 0.2508, 0.6105, 0.5395],
[0.6189, 0.4033, 0.8650, 0.5267, 0.4487, 0.5150, 0.5925, 0.5050]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0078, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0078, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.8403434584615752
step: 66
running loss: 0.0127324766433572
Train Steps: 66/90 Loss: 0.0127 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6144, 0.4032, 0.8563, 0.3283, 0.3525, 0.4200, 0.5775, 0.5583],
[0.6085, 0.4005, 0.8400, 0.4317, 0.3763, 0.4750, 0.5476, 0.5058],
[0.6201, 0.4082, 0.8827, 0.3715, 0.3825, 0.2712, 0.5845, 0.5412],
[0.6109, 0.3943, 0.8525, 0.4950, 0.4338, 0.4800, 0.5449, 0.5383],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4012, 0.4633, 0.5338, 0.5767],
[0.6248, 0.4032, 0.7738, 0.1900, 0.4813, 0.1400, 0.5941, 0.4904],
[0.6202, 0.4053, 0.8638, 0.5283, 0.4546, 0.5108, 0.5900, 0.5133],
[0.6275, 0.4024, 0.8500, 0.5383, 0.3912, 0.4883, 0.6288, 0.5100]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6932, 0.4450, 0.8531, 0.3368, 0.3961, 0.3903, 0.6321, 0.5604],
[0.7086, 0.4471, 0.8215, 0.3704, 0.4030, 0.4471, 0.6338, 0.5231],
[0.6424, 0.4138, 0.8391, 0.3307, 0.4225, 0.2711, 0.6367, 0.5248],
[0.6202, 0.4266, 0.8456, 0.4140, 0.4342, 0.4385, 0.6412, 0.5650],
[0.6707, 0.4512, 0.8489, 0.4675, 0.4233, 0.4563, 0.6271, 0.5644],
[0.5194, 0.3450, 0.6983, 0.1942, 0.4850, 0.1519, 0.6323, 0.5231],
[0.6732, 0.4427, 0.8219, 0.4614, 0.4517, 0.4596, 0.6375, 0.5391],
[0.7076, 0.4632, 0.8452, 0.4561, 0.4193, 0.4764, 0.6555, 0.5310]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6144, 0.4032, 0.8562, 0.3283, 0.3525, 0.4200, 0.5775, 0.5583],
[0.6084, 0.4005, 0.8400, 0.4317, 0.3762, 0.4750, 0.5476, 0.5058],
[0.6201, 0.4082, 0.8827, 0.3715, 0.3825, 0.2712, 0.5845, 0.5412],
[0.6109, 0.3943, 0.8525, 0.4950, 0.4338, 0.4800, 0.5449, 0.5383],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4013, 0.4633, 0.5337, 0.5767],
[0.6248, 0.4032, 0.7738, 0.1900, 0.4812, 0.1400, 0.5941, 0.4904],
[0.6202, 0.4053, 0.8637, 0.5283, 0.4546, 0.5108, 0.5900, 0.5133],
[0.6275, 0.4024, 0.8500, 0.5383, 0.3913, 0.4883, 0.6288, 0.5100]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0022, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0022, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.84257042047102
step: 67
running loss: 0.012575677917477912
Train Steps: 67/90 Loss: 0.0126 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6279, 0.4008, 0.8600, 0.4883, 0.4325, 0.5283, 0.7010, 0.5378],
[0.6339, 0.4112, 0.8838, 0.5067, 0.4000, 0.5433, 0.7549, 0.5378],
[0.6275, 0.4111, 0.8463, 0.2617, 0.4487, 0.1983, 0.6211, 0.4904],
[0.6202, 0.4053, 0.8638, 0.5283, 0.4546, 0.5108, 0.5900, 0.5133],
[0.6263, 0.4065, 0.9038, 0.4317, 0.3588, 0.4550, 0.6325, 0.5250],
[0.6205, 0.4004, 0.8938, 0.4883, 0.3663, 0.5000, 0.6357, 0.4947],
[0.6102, 0.4001, 0.7738, 0.3583, 0.3463, 0.3800, 0.5524, 0.5689],
[0.6229, 0.4066, 0.7612, 0.2967, 0.4250, 0.2167, 0.5925, 0.5350]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6659, 0.4144, 0.8573, 0.4683, 0.4495, 0.4916, 0.6621, 0.5355],
[0.6986, 0.4502, 0.8708, 0.4760, 0.4388, 0.5419, 0.6633, 0.5493],
[0.6271, 0.3910, 0.8422, 0.2759, 0.4727, 0.2775, 0.6521, 0.5047],
[0.6675, 0.4245, 0.8207, 0.4953, 0.4582, 0.4860, 0.6060, 0.5264],
[0.6498, 0.4277, 0.8808, 0.4407, 0.4198, 0.4427, 0.6638, 0.5178],
[0.6913, 0.4296, 0.8735, 0.4553, 0.4264, 0.4849, 0.6353, 0.5129],
[0.6791, 0.4282, 0.7736, 0.3109, 0.3759, 0.3660, 0.6060, 0.5501],
[0.6112, 0.3996, 0.7485, 0.2576, 0.4500, 0.2823, 0.6342, 0.5452]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6279, 0.4008, 0.8600, 0.4883, 0.4325, 0.5283, 0.7010, 0.5378],
[0.6339, 0.4112, 0.8838, 0.5067, 0.4000, 0.5433, 0.7549, 0.5378],
[0.6275, 0.4111, 0.8462, 0.2617, 0.4487, 0.1983, 0.6211, 0.4904],
[0.6202, 0.4053, 0.8637, 0.5283, 0.4546, 0.5108, 0.5900, 0.5133],
[0.6263, 0.4065, 0.9038, 0.4317, 0.3587, 0.4550, 0.6325, 0.5250],
[0.6205, 0.4004, 0.8938, 0.4883, 0.3663, 0.5000, 0.6357, 0.4947],
[0.6102, 0.4001, 0.7738, 0.3583, 0.3462, 0.3800, 0.5524, 0.5689],
[0.6229, 0.4066, 0.7613, 0.2967, 0.4250, 0.2167, 0.5925, 0.5350]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.8437589161330834
step: 68
running loss: 0.012408219354898286
Train Steps: 68/90 Loss: 0.0124 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6230, 0.4152, 0.7588, 0.2283, 0.4012, 0.2883, 0.6200, 0.5767],
[0.6243, 0.4128, 0.7762, 0.2717, 0.3825, 0.3133, 0.6212, 0.5417],
[0.6143, 0.4040, 0.8237, 0.3333, 0.4075, 0.2117, 0.5137, 0.4973],
[0.6139, 0.4019, 0.7137, 0.2150, 0.4375, 0.1533, 0.5293, 0.5006],
[0.6201, 0.3970, 0.8413, 0.4950, 0.4413, 0.5183, 0.6088, 0.5400],
[ nan, nan, 0.7097, 0.2346, 0.4250, 0.1850, 0.5175, 0.5583],
[0.6226, 0.4125, 0.8800, 0.4900, 0.4512, 0.5600, 0.6275, 0.5517],
[0.6271, 0.4040, 0.9000, 0.3250, 0.4938, 0.2300, 0.7192, 0.5413]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6574, 0.4143, 0.8031, 0.3755, 0.4134, 0.3475, 0.6050, 0.5221],
[0.6055, 0.3822, 0.7905, 0.3181, 0.4092, 0.3100, 0.6078, 0.5171],
[0.6002, 0.3704, 0.7617, 0.3438, 0.4273, 0.2910, 0.5583, 0.5095],
[0.5412, 0.3202, 0.6806, 0.2306, 0.4217, 0.2505, 0.5640, 0.5077],
[0.6804, 0.4248, 0.9077, 0.5563, 0.4179, 0.5659, 0.5997, 0.5211],
[0.4818, 0.3003, 0.6873, 0.2609, 0.4478, 0.2683, 0.5393, 0.5116],
[0.7298, 0.4601, 0.8969, 0.5499, 0.4313, 0.6434, 0.6491, 0.5297],
[0.6359, 0.4006, 0.8891, 0.3423, 0.4818, 0.3901, 0.6773, 0.4832]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6230, 0.4152, 0.7588, 0.2283, 0.4013, 0.2883, 0.6200, 0.5767],
[0.6243, 0.4128, 0.7763, 0.2717, 0.3825, 0.3133, 0.6212, 0.5417],
[0.6143, 0.4040, 0.8238, 0.3333, 0.4075, 0.2117, 0.5137, 0.4973],
[0.6139, 0.4019, 0.7138, 0.2150, 0.4375, 0.1533, 0.5293, 0.5006],
[0.6201, 0.3970, 0.8413, 0.4950, 0.4412, 0.5183, 0.6087, 0.5400],
[0.0000, 0.0000, 0.7097, 0.2346, 0.4250, 0.1850, 0.5175, 0.5583],
[0.6226, 0.4125, 0.8800, 0.4900, 0.4512, 0.5600, 0.6275, 0.5517],
[0.6271, 0.4040, 0.9000, 0.3250, 0.4938, 0.2300, 0.7192, 0.5413]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0075, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0075, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.8512897320324555
step: 69
running loss: 0.012337532348296456
Train Steps: 69/90 Loss: 0.0123 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6175, 0.4093, 0.8800, 0.4433, 0.4075, 0.4367, 0.5128, 0.4901],
[0.6073, 0.3932, 0.8363, 0.5817, 0.4425, 0.5117, 0.5204, 0.4817],
[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466],
[0.6109, 0.4003, 0.8650, 0.4883, 0.4775, 0.4867, 0.5175, 0.5683],
[0.6111, 0.3995, 0.8788, 0.4567, 0.3813, 0.4833, 0.5450, 0.5700],
[0.6043, 0.4022, 0.6887, 0.1983, 0.3775, 0.2483, 0.5480, 0.5136],
[0.6346, 0.4165, 0.9138, 0.3983, 0.3875, 0.4317, 0.7469, 0.5471],
[0.6262, 0.4163, 0.8850, 0.5183, 0.3763, 0.4150, 0.6025, 0.5500]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6429, 0.3846, 0.9090, 0.4461, 0.4379, 0.4578, 0.5886, 0.5220],
[0.6341, 0.3974, 0.8621, 0.5092, 0.4944, 0.4995, 0.6058, 0.5295],
[0.6139, 0.4076, 0.7800, 0.3218, 0.3755, 0.4063, 0.5946, 0.5400],
[0.6022, 0.3759, 0.8596, 0.4588, 0.5010, 0.5012, 0.6091, 0.5032],
[0.6845, 0.4206, 0.8694, 0.4623, 0.3940, 0.5087, 0.6284, 0.5446],
[0.5806, 0.3420, 0.6818, 0.2290, 0.4298, 0.2716, 0.5601, 0.5289],
[0.6133, 0.3850, 0.9095, 0.4131, 0.4331, 0.4100, 0.6622, 0.5053],
[0.6524, 0.3739, 0.8804, 0.4687, 0.3983, 0.4143, 0.6038, 0.5301]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6175, 0.4093, 0.8800, 0.4433, 0.4075, 0.4367, 0.5128, 0.4901],
[0.6073, 0.3932, 0.8363, 0.5817, 0.4425, 0.5117, 0.5204, 0.4817],
[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466],
[0.6109, 0.4003, 0.8650, 0.4883, 0.4775, 0.4867, 0.5175, 0.5683],
[0.6111, 0.3995, 0.8788, 0.4567, 0.3812, 0.4833, 0.5450, 0.5700],
[0.6043, 0.4022, 0.6888, 0.1983, 0.3775, 0.2483, 0.5480, 0.5136],
[0.6346, 0.4165, 0.9137, 0.3983, 0.3875, 0.4317, 0.7469, 0.5471],
[0.6262, 0.4163, 0.8850, 0.5183, 0.3762, 0.4150, 0.6025, 0.5500]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.8528305467916653
step: 70
running loss: 0.012183293525595218
Train Steps: 70/90 Loss: 0.0122 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6026, 0.3979, 0.8550, 0.4233, 0.3613, 0.5233, 0.5582, 0.4967],
[0.6286, 0.4078, 0.8063, 0.2267, 0.4788, 0.1533, 0.5953, 0.4913],
[0.6102, 0.4001, 0.7738, 0.3583, 0.3463, 0.3800, 0.5524, 0.5689],
[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837],
[0.6037, 0.4020, 0.8300, 0.4033, 0.3575, 0.4883, 0.5647, 0.5631],
[0.6095, 0.4002, 0.8533, 0.5168, 0.5031, 0.5094, 0.5125, 0.5433],
[0.6286, 0.4055, 0.9000, 0.4717, 0.3763, 0.4683, 0.7018, 0.5494],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5413, 0.5683]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6255, 0.3748, 0.8938, 0.4418, 0.3911, 0.5406, 0.5918, 0.5268],
[0.5163, 0.3047, 0.7975, 0.2625, 0.4969, 0.1968, 0.5712, 0.5116],
[0.6273, 0.3768, 0.8290, 0.3421, 0.3700, 0.3842, 0.5794, 0.5481],
[0.5764, 0.3479, 0.7528, 0.3221, 0.3897, 0.3325, 0.5494, 0.5493],
[0.5990, 0.3626, 0.8662, 0.4235, 0.3871, 0.5108, 0.6057, 0.5491],
[0.6179, 0.3711, 0.8998, 0.5116, 0.4923, 0.4869, 0.5835, 0.5161],
[0.6275, 0.3973, 0.9284, 0.4910, 0.4084, 0.5210, 0.6650, 0.5278],
[0.6413, 0.3900, 0.8882, 0.5357, 0.3857, 0.4287, 0.5707, 0.5402]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6026, 0.3979, 0.8550, 0.4233, 0.3613, 0.5233, 0.5582, 0.4967],
[0.6286, 0.4078, 0.8062, 0.2267, 0.4787, 0.1533, 0.5953, 0.4913],
[0.6102, 0.4001, 0.7738, 0.3583, 0.3462, 0.3800, 0.5524, 0.5689],
[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837],
[0.6037, 0.4020, 0.8300, 0.4033, 0.3575, 0.4883, 0.5647, 0.5631],
[0.6095, 0.4002, 0.8533, 0.5168, 0.5031, 0.5094, 0.5125, 0.5433],
[0.6286, 0.4055, 0.9000, 0.4717, 0.3762, 0.4683, 0.7018, 0.5494],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5412, 0.5683]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.8542323596775532
step: 71
running loss: 0.01203144168559934
Train Steps: 71/90 Loss: 0.0120 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6339, 0.4102, 0.8588, 0.3133, 0.4425, 0.2117, 0.6417, 0.5089],
[0.6193, 0.4165, 0.8838, 0.4700, 0.4150, 0.4867, 0.5427, 0.5261],
[0.6118, 0.4052, 0.8463, 0.3917, 0.3538, 0.3450, 0.5053, 0.5593],
[0.6268, 0.4052, 0.8175, 0.2250, 0.4688, 0.1917, 0.6375, 0.5267],
[0.6157, 0.4102, 0.8513, 0.3817, 0.3613, 0.3667, 0.5096, 0.5890],
[0.6107, 0.4013, 0.8700, 0.4650, 0.5049, 0.5176, 0.5850, 0.5550],
[0.6276, 0.4095, 0.8237, 0.2250, 0.4662, 0.1783, 0.6171, 0.4869],
[0.6260, 0.4161, 0.9000, 0.3833, 0.4450, 0.2133, 0.6237, 0.4986]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5770, 0.3702, 0.8246, 0.3224, 0.4389, 0.3208, 0.6044, 0.5446],
[0.5811, 0.3755, 0.8506, 0.5164, 0.3648, 0.5003, 0.5496, 0.5302],
[0.5792, 0.3675, 0.8441, 0.4449, 0.3259, 0.4114, 0.5041, 0.5739],
[0.5408, 0.3342, 0.7698, 0.2914, 0.4380, 0.2589, 0.5881, 0.5285],
[0.5530, 0.3469, 0.8460, 0.4321, 0.3400, 0.4086, 0.5180, 0.5602],
[0.5483, 0.3793, 0.8731, 0.4913, 0.4134, 0.4735, 0.5696, 0.5521],
[0.5468, 0.3407, 0.8052, 0.2672, 0.4373, 0.2658, 0.5853, 0.5293],
[0.5349, 0.3487, 0.8739, 0.4018, 0.4091, 0.3381, 0.5687, 0.5299]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6339, 0.4102, 0.8587, 0.3133, 0.4425, 0.2117, 0.6417, 0.5089],
[0.6193, 0.4165, 0.8838, 0.4700, 0.4150, 0.4867, 0.5427, 0.5261],
[0.6118, 0.4052, 0.8462, 0.3917, 0.3537, 0.3450, 0.5053, 0.5593],
[0.6268, 0.4052, 0.8175, 0.2250, 0.4688, 0.1917, 0.6375, 0.5267],
[0.6157, 0.4102, 0.8512, 0.3817, 0.3613, 0.3667, 0.5096, 0.5890],
[0.6107, 0.4013, 0.8700, 0.4650, 0.5049, 0.5176, 0.5850, 0.5550],
[0.6276, 0.4095, 0.8238, 0.2250, 0.4663, 0.1783, 0.6171, 0.4869],
[0.6260, 0.4161, 0.9000, 0.3833, 0.4450, 0.2133, 0.6237, 0.4986]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0024, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0024, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.856674063950777
step: 72
running loss: 0.011898250888205238
Train Steps: 72/90 Loss: 0.0119 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6198, 0.4115, 0.7762, 0.2717, 0.3713, 0.3200, 0.5837, 0.5683],
[0.6202, 0.4079, 0.8025, 0.2500, 0.3763, 0.3217, 0.6125, 0.5533],
[0.6201, 0.4098, 0.8575, 0.3617, 0.3700, 0.3550, 0.5988, 0.5667],
[0.6198, 0.4164, 0.8700, 0.5067, 0.4625, 0.5650, 0.5464, 0.5197],
[0.6135, 0.3994, 0.7913, 0.3050, 0.3625, 0.3050, 0.5837, 0.5050],
[0.6200, 0.4039, 0.8880, 0.4799, 0.3625, 0.4285, 0.5866, 0.5148],
[0.6201, 0.3970, 0.8413, 0.4950, 0.4413, 0.5183, 0.6088, 0.5400],
[0.6161, 0.4055, 0.8675, 0.3867, 0.3713, 0.4033, 0.5195, 0.5162]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5721, 0.3648, 0.8202, 0.3269, 0.3815, 0.3023, 0.5253, 0.5557],
[0.6015, 0.3963, 0.8259, 0.3027, 0.3946, 0.2854, 0.5421, 0.5332],
[0.6075, 0.4009, 0.8630, 0.3853, 0.3760, 0.3307, 0.5422, 0.5464],
[0.5815, 0.3768, 0.8523, 0.5206, 0.4387, 0.4850, 0.5653, 0.5391],
[0.5945, 0.3826, 0.7995, 0.3192, 0.3579, 0.3361, 0.5497, 0.5543],
[0.5935, 0.3802, 0.8935, 0.5007, 0.3762, 0.4188, 0.5464, 0.5353],
[0.5296, 0.3543, 0.8798, 0.5008, 0.4285, 0.4748, 0.5198, 0.5715],
[0.5407, 0.3619, 0.8395, 0.4189, 0.3694, 0.3604, 0.4980, 0.5526]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6198, 0.4115, 0.7763, 0.2717, 0.3713, 0.3200, 0.5838, 0.5683],
[0.6202, 0.4079, 0.8025, 0.2500, 0.3762, 0.3217, 0.6125, 0.5533],
[0.6201, 0.4098, 0.8575, 0.3617, 0.3700, 0.3550, 0.5987, 0.5667],
[0.6198, 0.4164, 0.8700, 0.5067, 0.4625, 0.5650, 0.5464, 0.5197],
[0.6135, 0.3994, 0.7912, 0.3050, 0.3625, 0.3050, 0.5838, 0.5050],
[0.6201, 0.4039, 0.8880, 0.4799, 0.3625, 0.4285, 0.5866, 0.5148],
[0.6201, 0.3970, 0.8413, 0.4950, 0.4412, 0.5183, 0.6087, 0.5400],
[0.6161, 0.4055, 0.8675, 0.3867, 0.3713, 0.4033, 0.5195, 0.5162]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.8580122668063268
step: 73
running loss: 0.01175359269597708
Train Steps: 73/90 Loss: 0.0118 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6277, 0.4083, 0.8350, 0.2717, 0.4562, 0.1800, 0.5918, 0.4878],
[0.6199, 0.4065, 0.7598, 0.2385, 0.4317, 0.1981, 0.5933, 0.5221],
[0.6339, 0.4159, 0.8400, 0.5617, 0.3825, 0.4150, 0.7343, 0.5748],
[0.6329, 0.4175, 0.8550, 0.2333, 0.5425, 0.2250, 0.7398, 0.5609],
[0.6204, 0.4049, 0.7975, 0.2700, 0.3937, 0.2567, 0.5700, 0.5183],
[0.6111, 0.3995, 0.8788, 0.4567, 0.3813, 0.4833, 0.5450, 0.5700],
[0.6132, 0.4066, 0.7259, 0.2402, 0.3588, 0.3300, 0.6000, 0.5600],
[0.6124, 0.4083, 0.6954, 0.3069, 0.3650, 0.2750, 0.5163, 0.5485]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5556, 0.3674, 0.8377, 0.2737, 0.4335, 0.2239, 0.5279, 0.5071],
[0.5495, 0.3718, 0.7725, 0.2917, 0.4186, 0.2792, 0.5280, 0.5383],
[0.5975, 0.4284, 0.8890, 0.5499, 0.3918, 0.4092, 0.5249, 0.5415],
[0.5203, 0.3569, 0.8910, 0.2834, 0.4844, 0.2743, 0.6489, 0.5207],
[0.5784, 0.4225, 0.8261, 0.3489, 0.3764, 0.2834, 0.5185, 0.5526],
[0.6175, 0.4279, 0.9348, 0.5584, 0.3562, 0.5445, 0.5273, 0.5581],
[0.6138, 0.4256, 0.7771, 0.3004, 0.3516, 0.3386, 0.5488, 0.5665],
[0.6027, 0.4076, 0.7594, 0.3404, 0.3540, 0.3074, 0.4966, 0.5514]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6277, 0.4083, 0.8350, 0.2717, 0.4563, 0.1800, 0.5918, 0.4878],
[0.6199, 0.4065, 0.7598, 0.2385, 0.4317, 0.1981, 0.5933, 0.5221],
[0.6339, 0.4159, 0.8400, 0.5617, 0.3825, 0.4150, 0.7343, 0.5748],
[0.6329, 0.4175, 0.8550, 0.2333, 0.5425, 0.2250, 0.7398, 0.5609],
[0.6204, 0.4049, 0.7975, 0.2700, 0.3938, 0.2567, 0.5700, 0.5183],
[0.6111, 0.3995, 0.8788, 0.4567, 0.3812, 0.4833, 0.5450, 0.5700],
[0.6132, 0.4066, 0.7259, 0.2402, 0.3587, 0.3300, 0.6000, 0.5600],
[0.6123, 0.4083, 0.6954, 0.3069, 0.3650, 0.2750, 0.5163, 0.5485]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0026, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0026, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.8606450074585155
step: 74
running loss: 0.011630337938628587
Train Steps: 74/90 Loss: 0.0116 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6357, 0.4097, 0.9038, 0.3883, 0.4213, 0.2950, 0.6686, 0.5390],
[0.6124, 0.4030, 0.8650, 0.4867, 0.4999, 0.5106, 0.5137, 0.5773],
[0.6129, 0.3925, 0.8720, 0.5246, 0.4534, 0.5515, 0.6026, 0.5114],
[0.6189, 0.3911, 0.8800, 0.4917, 0.3713, 0.4800, 0.6038, 0.4833],
[0.6163, 0.4114, 0.7650, 0.2017, 0.3763, 0.2867, 0.5631, 0.5071],
[0.6129, 0.3930, 0.8769, 0.5105, 0.4146, 0.5642, 0.6000, 0.5082],
[0.6176, 0.3911, 0.8738, 0.4217, 0.3488, 0.4033, 0.6025, 0.4817],
[0.6332, 0.4128, 0.9200, 0.3517, 0.4400, 0.3833, 0.7461, 0.5494]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6290, 0.4395, 0.8563, 0.3367, 0.4081, 0.2847, 0.6071, 0.5613],
[0.6373, 0.4309, 0.8770, 0.4503, 0.4436, 0.4187, 0.5412, 0.5536],
[0.6073, 0.4401, 0.8787, 0.4466, 0.4488, 0.4279, 0.5620, 0.5581],
[0.6246, 0.4447, 0.8888, 0.4558, 0.3932, 0.4469, 0.5294, 0.5504],
[0.6540, 0.4370, 0.7701, 0.2456, 0.3673, 0.2334, 0.5448, 0.5332],
[0.6194, 0.4169, 0.8621, 0.4388, 0.4443, 0.5149, 0.5497, 0.5537],
[0.6443, 0.4170, 0.8732, 0.3948, 0.3623, 0.3728, 0.5195, 0.5393],
[0.6201, 0.4285, 0.8864, 0.3037, 0.4047, 0.3044, 0.6332, 0.5474]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6357, 0.4097, 0.9038, 0.3883, 0.4212, 0.2950, 0.6686, 0.5390],
[0.6124, 0.4030, 0.8650, 0.4867, 0.4999, 0.5106, 0.5137, 0.5773],
[0.6129, 0.3925, 0.8720, 0.5246, 0.4534, 0.5515, 0.6026, 0.5114],
[0.6189, 0.3911, 0.8800, 0.4917, 0.3713, 0.4800, 0.6037, 0.4833],
[0.6163, 0.4114, 0.7650, 0.2017, 0.3762, 0.2867, 0.5631, 0.5071],
[0.6129, 0.3930, 0.8769, 0.5105, 0.4146, 0.5642, 0.6000, 0.5082],
[0.6176, 0.3911, 0.8737, 0.4217, 0.3487, 0.4033, 0.6025, 0.4817],
[0.6332, 0.4128, 0.9200, 0.3517, 0.4400, 0.3833, 0.7461, 0.5494]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0020, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0020, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.8626611140789464
step: 75
running loss: 0.011502148187719285
Train Steps: 75/90 Loss: 0.0115 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6209, 0.3920, 0.8650, 0.5367, 0.4400, 0.5067, 0.6025, 0.4950],
[0.6222, 0.4169, 0.8638, 0.5650, 0.4313, 0.4783, 0.5637, 0.5633],
[0.6268, 0.4061, 0.8350, 0.2433, 0.4575, 0.2283, 0.6350, 0.5300],
[0.6275, 0.4003, 0.9100, 0.3783, 0.4388, 0.3133, 0.7058, 0.5343],
[0.6257, 0.4024, 0.8612, 0.5352, 0.4361, 0.5253, 0.6680, 0.5166],
[0.6296, 0.4045, 0.9138, 0.4100, 0.4232, 0.4242, 0.7422, 0.5297],
[0.6205, 0.4004, 0.8938, 0.4883, 0.3663, 0.5000, 0.6357, 0.4947],
[0.6125, 0.3983, 0.8750, 0.4867, 0.4275, 0.4783, 0.5413, 0.5717]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6245, 0.4360, 0.8635, 0.4273, 0.4271, 0.4352, 0.5655, 0.5258],
[0.6267, 0.4584, 0.8634, 0.4847, 0.3942, 0.4329, 0.5814, 0.5642],
[0.6581, 0.4601, 0.8488, 0.2100, 0.4235, 0.1943, 0.6559, 0.5183],
[0.6071, 0.4238, 0.8191, 0.2969, 0.3818, 0.2718, 0.6269, 0.5375],
[0.6349, 0.4543, 0.8456, 0.4415, 0.4136, 0.4470, 0.6092, 0.5495],
[0.6615, 0.4462, 0.8442, 0.3378, 0.3510, 0.3641, 0.6180, 0.5369],
[0.6187, 0.4142, 0.8872, 0.4145, 0.3976, 0.4471, 0.5936, 0.5266],
[0.6192, 0.4561, 0.8630, 0.4248, 0.4287, 0.4223, 0.5841, 0.5305]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6209, 0.3920, 0.8650, 0.5367, 0.4400, 0.5067, 0.6025, 0.4950],
[0.6222, 0.4169, 0.8637, 0.5650, 0.4313, 0.4783, 0.5638, 0.5633],
[0.6268, 0.4060, 0.8350, 0.2433, 0.4575, 0.2283, 0.6350, 0.5300],
[0.6275, 0.4003, 0.9100, 0.3783, 0.4387, 0.3133, 0.7058, 0.5343],
[0.6257, 0.4024, 0.8612, 0.5352, 0.4361, 0.5253, 0.6680, 0.5166],
[0.6296, 0.4045, 0.9137, 0.4100, 0.4232, 0.4242, 0.7422, 0.5297],
[0.6205, 0.4004, 0.8938, 0.4883, 0.3663, 0.5000, 0.6357, 0.4947],
[0.6125, 0.3983, 0.8750, 0.4867, 0.4275, 0.4783, 0.5412, 0.5717]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0024, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0024, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.86508232972119
step: 76
running loss: 0.011382662233173553
Train Steps: 76/90 Loss: 0.0114 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6296, 0.4060, 0.9100, 0.3267, 0.4726, 0.3367, 0.7446, 0.5355],
[0.6130, 0.4072, 0.8550, 0.4567, 0.3638, 0.3667, 0.5290, 0.5892],
[0.6204, 0.4055, 0.8438, 0.5733, 0.4574, 0.4801, 0.5487, 0.5617],
[0.6201, 0.4116, 0.8725, 0.4733, 0.3700, 0.3217, 0.5386, 0.5767],
[0.6250, 0.4131, 0.8688, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367],
[0.6286, 0.4034, 0.8191, 0.2414, 0.4262, 0.2393, 0.6365, 0.5356],
[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.6307, 0.4060, 0.8950, 0.5183, 0.3750, 0.3850, 0.6338, 0.4938]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5771, 0.3978, 0.8029, 0.2722, 0.4141, 0.3073, 0.6815, 0.5198],
[0.6085, 0.4261, 0.8393, 0.4270, 0.3635, 0.4012, 0.5760, 0.5183],
[0.5968, 0.4245, 0.8060, 0.4617, 0.4207, 0.4515, 0.6187, 0.5316],
[0.6251, 0.4489, 0.8296, 0.3746, 0.3768, 0.3473, 0.5871, 0.5281],
[0.6556, 0.4485, 0.8583, 0.2192, 0.4339, 0.2290, 0.6672, 0.5177],
[0.6243, 0.4550, 0.7873, 0.1887, 0.4288, 0.1917, 0.6569, 0.5013],
[0.5891, 0.4459, 0.8296, 0.4930, 0.4048, 0.5645, 0.6507, 0.5437],
[0.6506, 0.4640, 0.8796, 0.4551, 0.3506, 0.4018, 0.6355, 0.4990]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6296, 0.4060, 0.9100, 0.3267, 0.4726, 0.3367, 0.7446, 0.5355],
[0.6130, 0.4072, 0.8550, 0.4567, 0.3638, 0.3667, 0.5290, 0.5892],
[0.6204, 0.4055, 0.8438, 0.5733, 0.4574, 0.4801, 0.5487, 0.5617],
[0.6201, 0.4116, 0.8725, 0.4733, 0.3700, 0.3217, 0.5386, 0.5767],
[0.6250, 0.4131, 0.8687, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367],
[0.6286, 0.4034, 0.8191, 0.2414, 0.4262, 0.2393, 0.6365, 0.5356],
[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.6307, 0.4060, 0.8950, 0.5183, 0.3750, 0.3850, 0.6338, 0.4938]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.8669920227257535
step: 77
running loss: 0.01125963665877602
Train Steps: 77/90 Loss: 0.0113 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6109, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117],
[0.6205, 0.4062, 0.8337, 0.2683, 0.3675, 0.4283, 0.6338, 0.5250],
[0.6260, 0.4133, 0.8800, 0.5117, 0.3713, 0.3283, 0.6223, 0.4967],
[0.6211, 0.3993, 0.7650, 0.1933, 0.4575, 0.1550, 0.5965, 0.4895],
[0.6223, 0.3990, 0.8037, 0.2800, 0.4000, 0.2283, 0.5864, 0.5208],
[0.6125, 0.4035, 0.7825, 0.3100, 0.3463, 0.4900, 0.5832, 0.5637],
[0.6107, 0.4013, 0.8700, 0.4650, 0.5049, 0.5176, 0.5850, 0.5550],
[0.6357, 0.4159, 0.8788, 0.5583, 0.3638, 0.4433, 0.6488, 0.5297]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6650, 0.4347, 0.8744, 0.4900, 0.3861, 0.4386, 0.6273, 0.5055],
[0.6044, 0.4057, 0.8026, 0.2726, 0.3897, 0.3852, 0.6577, 0.5237],
[0.7325, 0.5001, 0.8779, 0.5122, 0.4095, 0.3320, 0.6974, 0.5019],
[0.6298, 0.4239, 0.7692, 0.2225, 0.4536, 0.1487, 0.6777, 0.4890],
[0.6142, 0.3649, 0.8179, 0.2979, 0.4253, 0.2464, 0.6475, 0.5156],
[0.5920, 0.3943, 0.7995, 0.3386, 0.3788, 0.4432, 0.6688, 0.5305],
[0.6075, 0.4290, 0.8975, 0.4775, 0.4835, 0.4502, 0.6819, 0.5282],
[0.6853, 0.4624, 0.8745, 0.5447, 0.3783, 0.4823, 0.6775, 0.5141]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6108, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117],
[0.6205, 0.4062, 0.8338, 0.2683, 0.3675, 0.4283, 0.6338, 0.5250],
[0.6260, 0.4133, 0.8800, 0.5117, 0.3713, 0.3283, 0.6223, 0.4967],
[0.6211, 0.3993, 0.7650, 0.1933, 0.4575, 0.1550, 0.5965, 0.4895],
[0.6223, 0.3990, 0.8037, 0.2800, 0.4000, 0.2283, 0.5864, 0.5208],
[0.6125, 0.4035, 0.7825, 0.3100, 0.3462, 0.4900, 0.5832, 0.5637],
[0.6107, 0.4013, 0.8700, 0.4650, 0.5049, 0.5176, 0.5850, 0.5550],
[0.6357, 0.4159, 0.8788, 0.5583, 0.3638, 0.4433, 0.6488, 0.5297]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.8684362914646044
step: 78
running loss: 0.01113379860852057
Train Steps: 78/90 Loss: 0.0111 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6216, 0.4099, 0.7225, 0.2033, 0.4188, 0.2217, 0.5975, 0.5283],
[0.6252, 0.4158, 0.8988, 0.4083, 0.3788, 0.4783, 0.6225, 0.5633],
[0.6115, 0.3998, 0.7063, 0.2383, 0.4037, 0.1950, 0.5320, 0.4993],
[0.6275, 0.4157, 0.8337, 0.5800, 0.3763, 0.4200, 0.5547, 0.6125],
[0.6113, 0.4088, 0.6859, 0.2208, 0.4363, 0.1700, 0.5188, 0.5533],
[0.6236, 0.3977, 0.8985, 0.4806, 0.3835, 0.5216, 0.6613, 0.5166],
[0.6218, 0.4185, 0.7338, 0.2650, 0.4625, 0.1950, 0.5687, 0.5800],
[0.6222, 0.3937, 0.8350, 0.5617, 0.4138, 0.4600, 0.5800, 0.5233]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6333, 0.4204, 0.7791, 0.2819, 0.4128, 0.2189, 0.6612, 0.5254],
[0.7018, 0.4661, 0.9411, 0.4837, 0.3963, 0.5429, 0.7287, 0.5176],
[0.6514, 0.4204, 0.7638, 0.2597, 0.4110, 0.1882, 0.6433, 0.4838],
[0.7044, 0.4533, 0.8991, 0.6170, 0.3925, 0.5476, 0.6761, 0.5157],
[0.5008, 0.2885, 0.7548, 0.2519, 0.4445, 0.1971, 0.6265, 0.5172],
[0.6706, 0.4102, 0.9236, 0.5346, 0.4214, 0.6095, 0.6859, 0.4901],
[0.6292, 0.3884, 0.8051, 0.2587, 0.4408, 0.2057, 0.6468, 0.5499],
[0.6336, 0.3999, 0.9124, 0.6172, 0.4317, 0.5350, 0.6373, 0.5216]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6216, 0.4099, 0.7225, 0.2033, 0.4187, 0.2217, 0.5975, 0.5283],
[0.6252, 0.4158, 0.8988, 0.4083, 0.3787, 0.4783, 0.6225, 0.5633],
[0.6115, 0.3998, 0.7063, 0.2383, 0.4038, 0.1950, 0.5320, 0.4993],
[0.6275, 0.4157, 0.8338, 0.5800, 0.3762, 0.4200, 0.5547, 0.6125],
[0.6113, 0.4088, 0.6859, 0.2208, 0.4363, 0.1700, 0.5188, 0.5533],
[0.6236, 0.3977, 0.8985, 0.4806, 0.3835, 0.5216, 0.6613, 0.5166],
[0.6218, 0.4185, 0.7337, 0.2650, 0.4625, 0.1950, 0.5688, 0.5800],
[0.6222, 0.3937, 0.8350, 0.5617, 0.4137, 0.4600, 0.5800, 0.5233]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0033, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0033, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.8717839835444465
step: 79
running loss: 0.011035240298030968
Train Steps: 79/90 Loss: 0.0110 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6102, 0.4005, 0.8688, 0.5100, 0.4813, 0.5400, 0.5404, 0.5064],
[0.6353, 0.4128, 0.8488, 0.2600, 0.5525, 0.1616, 0.6694, 0.5540],
[0.6129, 0.3925, 0.8720, 0.5246, 0.4534, 0.5515, 0.6026, 0.5114],
[0.6124, 0.4069, 0.8314, 0.5001, 0.3738, 0.4650, 0.5167, 0.5402],
[0.6357, 0.4159, 0.8788, 0.5583, 0.3638, 0.4433, 0.6488, 0.5297],
[0.6040, 0.4002, 0.7338, 0.2267, 0.3975, 0.2100, 0.5231, 0.4778],
[0.6223, 0.3990, 0.8037, 0.2800, 0.4000, 0.2283, 0.5864, 0.5208],
[0.6307, 0.4029, 0.8988, 0.4817, 0.3937, 0.3500, 0.7311, 0.5378]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6030, 0.3594, 0.8412, 0.5356, 0.4528, 0.4940, 0.6149, 0.5121],
[0.5933, 0.3381, 0.8520, 0.2899, 0.5123, 0.2131, 0.6733, 0.5340],
[0.6143, 0.3798, 0.8628, 0.5381, 0.4447, 0.5084, 0.6310, 0.5308],
[0.6493, 0.3699, 0.8399, 0.5038, 0.3668, 0.4863, 0.6120, 0.5405],
[0.6789, 0.4246, 0.8697, 0.5666, 0.3557, 0.4841, 0.6516, 0.5291],
[0.6382, 0.3728, 0.7099, 0.2474, 0.4178, 0.1808, 0.5965, 0.5131],
[0.6297, 0.3438, 0.8159, 0.3174, 0.4052, 0.2538, 0.6249, 0.5244],
[0.7083, 0.4381, 0.9010, 0.4947, 0.4144, 0.3560, 0.7052, 0.5052]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6102, 0.4005, 0.8687, 0.5100, 0.4812, 0.5400, 0.5404, 0.5064],
[0.6353, 0.4128, 0.8487, 0.2600, 0.5525, 0.1616, 0.6694, 0.5540],
[0.6129, 0.3925, 0.8720, 0.5246, 0.4534, 0.5515, 0.6026, 0.5114],
[0.6123, 0.4069, 0.8314, 0.5001, 0.3738, 0.4650, 0.5167, 0.5402],
[0.6357, 0.4159, 0.8788, 0.5583, 0.3638, 0.4433, 0.6488, 0.5297],
[0.6040, 0.4002, 0.7337, 0.2267, 0.3975, 0.2100, 0.5231, 0.4778],
[0.6223, 0.3990, 0.8037, 0.2800, 0.4000, 0.2283, 0.5864, 0.5208],
[0.6307, 0.4029, 0.8988, 0.4817, 0.3938, 0.3500, 0.7311, 0.5378]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.8729040948674083
step: 80
running loss: 0.010911301185842603
Train Steps: 80/90 Loss: 0.0109 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.7515, 0.2708, 0.3987, 0.2267, 0.5162, 0.5567],
[0.6134, 0.4090, 0.6926, 0.2819, 0.3538, 0.3233, 0.5563, 0.5667],
[0.6200, 0.4049, 0.8638, 0.5617, 0.4125, 0.5100, 0.6013, 0.5317],
[0.6234, 0.4023, 0.8888, 0.4633, 0.3975, 0.5767, 0.6400, 0.5183],
[0.6246, 0.4028, 0.8738, 0.4867, 0.4088, 0.5667, 0.6362, 0.5200],
[0.6198, 0.4076, 0.7945, 0.2453, 0.4475, 0.1871, 0.5897, 0.5350],
[0.6277, 0.4103, 0.8087, 0.5717, 0.4188, 0.4750, 0.5663, 0.6083],
[0.6275, 0.4024, 0.8600, 0.2283, 0.5350, 0.1800, 0.7074, 0.5413]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5762, 0.3329, 0.7517, 0.2781, 0.4145, 0.1953, 0.5292, 0.5349],
[0.6681, 0.4076, 0.7123, 0.3287, 0.3506, 0.2726, 0.5663, 0.5310],
[0.6413, 0.3766, 0.8545, 0.6113, 0.4202, 0.5100, 0.5876, 0.5184],
[0.5882, 0.3514, 0.9092, 0.5452, 0.4597, 0.5661, 0.6020, 0.5366],
[0.6590, 0.3704, 0.8900, 0.5376, 0.4571, 0.5833, 0.6199, 0.5511],
[0.6882, 0.4035, 0.7938, 0.2930, 0.4340, 0.1886, 0.6237, 0.5297],
[0.6247, 0.3833, 0.8365, 0.5761, 0.4203, 0.4921, 0.5985, 0.5927],
[0.6403, 0.3778, 0.8570, 0.3007, 0.5033, 0.2290, 0.6974, 0.5138]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.7515, 0.2708, 0.3988, 0.2267, 0.5163, 0.5567],
[0.6134, 0.4090, 0.6926, 0.2819, 0.3537, 0.3233, 0.5562, 0.5667],
[0.6199, 0.4049, 0.8637, 0.5617, 0.4125, 0.5100, 0.6012, 0.5317],
[0.6234, 0.4023, 0.8888, 0.4633, 0.3975, 0.5767, 0.6400, 0.5183],
[0.6246, 0.4028, 0.8737, 0.4867, 0.4087, 0.5667, 0.6363, 0.5200],
[0.6198, 0.4076, 0.7945, 0.2453, 0.4475, 0.1871, 0.5897, 0.5350],
[0.6277, 0.4103, 0.8087, 0.5717, 0.4187, 0.4750, 0.5663, 0.6083],
[0.6275, 0.4024, 0.8600, 0.2283, 0.5350, 0.1800, 0.7074, 0.5413]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0079, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0079, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.880808724090457
step: 81
running loss: 0.01087418177889453
Train Steps: 81/90 Loss: 0.0109 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6261, 0.4045, 0.8865, 0.5369, 0.3895, 0.4859, 0.6683, 0.5249],
[0.6182, 0.3987, 0.7878, 0.2889, 0.3699, 0.3260, 0.6086, 0.5367],
[0.6250, 0.4008, 0.8950, 0.4183, 0.3550, 0.4383, 0.6361, 0.4927],
[0.6090, 0.4010, 0.7838, 0.3483, 0.3538, 0.3783, 0.5462, 0.5077],
[0.6170, 0.4102, 0.7468, 0.3695, 0.3463, 0.3767, 0.5238, 0.5823],
[0.6137, 0.4035, 0.8850, 0.4417, 0.3900, 0.4283, 0.5449, 0.5617],
[0.6133, 0.4066, 0.6787, 0.2617, 0.3800, 0.2433, 0.5147, 0.5358],
[0.6329, 0.4055, 0.9050, 0.4783, 0.3613, 0.3917, 0.6464, 0.5019]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6216, 0.3691, 0.8633, 0.5882, 0.4457, 0.5147, 0.6355, 0.5467],
[0.6850, 0.3830, 0.8209, 0.3345, 0.4442, 0.2901, 0.6099, 0.5626],
[0.6290, 0.3722, 0.8811, 0.4910, 0.4291, 0.4807, 0.6123, 0.5476],
[0.6498, 0.3795, 0.8206, 0.3536, 0.3999, 0.3637, 0.5786, 0.5534],
[0.6327, 0.3948, 0.7703, 0.3668, 0.4033, 0.3676, 0.5708, 0.5905],
[0.6211, 0.3289, 0.8803, 0.5134, 0.4360, 0.4698, 0.5691, 0.5627],
[0.5953, 0.3649, 0.7168, 0.2784, 0.4429, 0.1925, 0.5494, 0.5407],
[0.6489, 0.3648, 0.8822, 0.5375, 0.4523, 0.4195, 0.5986, 0.5419]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6261, 0.4045, 0.8865, 0.5369, 0.3895, 0.4859, 0.6683, 0.5249],
[0.6182, 0.3987, 0.7878, 0.2889, 0.3699, 0.3260, 0.6086, 0.5367],
[0.6250, 0.4008, 0.8950, 0.4183, 0.3550, 0.4383, 0.6361, 0.4927],
[0.6090, 0.4010, 0.7837, 0.3483, 0.3537, 0.3783, 0.5462, 0.5077],
[0.6170, 0.4102, 0.7468, 0.3695, 0.3462, 0.3767, 0.5238, 0.5823],
[0.6137, 0.4035, 0.8850, 0.4417, 0.3900, 0.4283, 0.5449, 0.5617],
[0.6133, 0.4065, 0.6787, 0.2617, 0.3800, 0.2433, 0.5147, 0.5358],
[0.6329, 0.4055, 0.9050, 0.4783, 0.3613, 0.3917, 0.6464, 0.5019]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.882431311882101
step: 82
running loss: 0.010761357461976841
Train Steps: 82/90 Loss: 0.0108 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6147, 0.4026, 0.6600, 0.2467, 0.4088, 0.2150, 0.5489, 0.5773],
[0.6264, 0.4035, 0.8888, 0.4883, 0.4050, 0.5217, 0.6361, 0.4791],
[0.6195, 0.4101, 0.8650, 0.3917, 0.3575, 0.4033, 0.5800, 0.5650],
[0.6095, 0.4002, 0.8533, 0.5168, 0.5031, 0.5094, 0.5125, 0.5433],
[0.6339, 0.4118, 0.7988, 0.5800, 0.3912, 0.4583, 0.7343, 0.5760],
[ nan, nan, 0.8037, 0.2483, 0.3975, 0.2517, 0.5575, 0.5600],
[0.6090, 0.4045, 0.7250, 0.2100, 0.4075, 0.2300, 0.5476, 0.5663],
[ nan, nan, 0.8363, 0.3317, 0.3563, 0.3367, 0.5329, 0.5142]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6214, 0.3727, 0.7104, 0.2819, 0.4215, 0.2213, 0.5095, 0.5704],
[0.6013, 0.3810, 0.8906, 0.5344, 0.4157, 0.5617, 0.6100, 0.5443],
[0.6315, 0.3857, 0.8651, 0.4446, 0.3643, 0.4125, 0.5376, 0.5502],
[0.6312, 0.3986, 0.8583, 0.5682, 0.5022, 0.4889, 0.5536, 0.5491],
[0.5955, 0.4035, 0.8144, 0.5087, 0.3951, 0.4339, 0.5913, 0.5845],
[0.5218, 0.3318, 0.7971, 0.2683, 0.4273, 0.2634, 0.5459, 0.5848],
[0.5299, 0.3395, 0.7230, 0.2444, 0.4156, 0.1974, 0.5371, 0.5694],
[0.5515, 0.3686, 0.8005, 0.3105, 0.3675, 0.3014, 0.5491, 0.5271]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6147, 0.4026, 0.6600, 0.2467, 0.4087, 0.2150, 0.5489, 0.5773],
[0.6264, 0.4035, 0.8888, 0.4883, 0.4050, 0.5217, 0.6361, 0.4791],
[0.6195, 0.4101, 0.8650, 0.3917, 0.3575, 0.4033, 0.5800, 0.5650],
[0.6095, 0.4002, 0.8533, 0.5168, 0.5031, 0.5094, 0.5125, 0.5433],
[0.6339, 0.4118, 0.7987, 0.5800, 0.3913, 0.4583, 0.7343, 0.5760],
[0.0000, 0.0000, 0.8037, 0.2483, 0.3975, 0.2517, 0.5575, 0.5600],
[0.6090, 0.4045, 0.7250, 0.2100, 0.4075, 0.2300, 0.5476, 0.5663],
[0.0000, 0.0000, 0.8363, 0.3317, 0.3562, 0.3367, 0.5329, 0.5142]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0140, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0140, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.8964379815151915
step: 83
running loss: 0.010800457608616766
Train Steps: 83/90 Loss: 0.0108 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6140, 0.4070, 0.8700, 0.5000, 0.4612, 0.4900, 0.5260, 0.5852],
[0.6257, 0.4060, 0.8300, 0.2333, 0.4688, 0.2583, 0.7050, 0.5633],
[0.6198, 0.4114, 0.8263, 0.3283, 0.3550, 0.3583, 0.5813, 0.5667],
[0.6180, 0.4064, 0.7200, 0.2467, 0.4275, 0.2367, 0.5963, 0.6217],
[0.6293, 0.3982, 0.8700, 0.5300, 0.3763, 0.4717, 0.7050, 0.5297],
[0.6257, 0.4024, 0.8672, 0.5422, 0.4196, 0.5198, 0.6694, 0.5204],
[0.6135, 0.3994, 0.7913, 0.3050, 0.3625, 0.3050, 0.5837, 0.5050],
[0.6168, 0.4081, 0.8438, 0.3367, 0.3500, 0.4667, 0.6212, 0.5400]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5326, 0.3346, 0.8373, 0.5127, 0.4292, 0.4920, 0.5383, 0.5489],
[0.5526, 0.3637, 0.8333, 0.2463, 0.4774, 0.2220, 0.6235, 0.5523],
[0.5676, 0.3812, 0.8502, 0.3600, 0.3812, 0.3840, 0.5246, 0.5630],
[0.5029, 0.3379, 0.7094, 0.2572, 0.4360, 0.2681, 0.5220, 0.5629],
[0.5869, 0.3627, 0.8255, 0.5369, 0.3665, 0.4870, 0.5639, 0.5548],
[0.5658, 0.3800, 0.8173, 0.5128, 0.4016, 0.4779, 0.5786, 0.5503],
[0.5854, 0.3794, 0.7980, 0.2851, 0.3610, 0.3052, 0.5562, 0.5387],
[0.5243, 0.3401, 0.8351, 0.3306, 0.3540, 0.4555, 0.5691, 0.5675]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6140, 0.4070, 0.8700, 0.5000, 0.4613, 0.4900, 0.5260, 0.5852],
[0.6257, 0.4060, 0.8300, 0.2333, 0.4688, 0.2583, 0.7050, 0.5633],
[0.6198, 0.4114, 0.8263, 0.3283, 0.3550, 0.3583, 0.5813, 0.5667],
[0.6180, 0.4064, 0.7200, 0.2467, 0.4275, 0.2367, 0.5962, 0.6217],
[0.6293, 0.3982, 0.8700, 0.5300, 0.3762, 0.4717, 0.7050, 0.5297],
[0.6257, 0.4024, 0.8672, 0.5422, 0.4196, 0.5198, 0.6694, 0.5204],
[0.6135, 0.3994, 0.7912, 0.3050, 0.3625, 0.3050, 0.5838, 0.5050],
[0.6168, 0.4081, 0.8438, 0.3367, 0.3500, 0.4667, 0.6212, 0.5400]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0021, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0021, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.8985337674384937
step: 84
running loss: 0.010696830564743973
Train Steps: 84/90 Loss: 0.0107 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6085, 0.4005, 0.8400, 0.4317, 0.3763, 0.4750, 0.5476, 0.5058],
[0.6180, 0.4064, 0.7200, 0.2467, 0.4275, 0.2367, 0.5963, 0.6217],
[0.6333, 0.4037, 0.8638, 0.5733, 0.4012, 0.4717, 0.6369, 0.4938],
[0.6160, 0.4086, 0.8775, 0.3983, 0.3750, 0.3783, 0.5128, 0.4882],
[0.6214, 0.4112, 0.7838, 0.2117, 0.3650, 0.3133, 0.5675, 0.5083],
[0.6070, 0.3979, 0.8575, 0.5083, 0.4350, 0.5400, 0.5180, 0.5466],
[0.6293, 0.3982, 0.8700, 0.5300, 0.3763, 0.4717, 0.7050, 0.5297],
[0.6277, 0.4103, 0.8087, 0.5717, 0.4188, 0.4750, 0.5663, 0.6083]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5225, 0.3469, 0.8365, 0.3800, 0.3507, 0.4460, 0.5555, 0.5378],
[0.4763, 0.3448, 0.7153, 0.2141, 0.4209, 0.2689, 0.5513, 0.5684],
[0.5475, 0.3803, 0.8438, 0.5036, 0.3565, 0.4401, 0.5760, 0.5350],
[0.4865, 0.3568, 0.8518, 0.3545, 0.3320, 0.3578, 0.5361, 0.5598],
[0.5865, 0.3979, 0.8120, 0.2146, 0.3638, 0.2559, 0.5730, 0.5537],
[0.4913, 0.3482, 0.8402, 0.4484, 0.4285, 0.4935, 0.5410, 0.5497],
[0.5621, 0.3714, 0.8258, 0.4831, 0.3521, 0.4723, 0.6025, 0.5578],
[0.5258, 0.3645, 0.8049, 0.4832, 0.3943, 0.4806, 0.5652, 0.6209]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6084, 0.4005, 0.8400, 0.4317, 0.3762, 0.4750, 0.5476, 0.5058],
[0.6180, 0.4064, 0.7200, 0.2467, 0.4275, 0.2367, 0.5962, 0.6217],
[0.6334, 0.4037, 0.8637, 0.5733, 0.4013, 0.4717, 0.6369, 0.4938],
[0.6160, 0.4086, 0.8775, 0.3983, 0.3750, 0.3783, 0.5128, 0.4882],
[0.6214, 0.4112, 0.7837, 0.2117, 0.3650, 0.3133, 0.5675, 0.5083],
[0.6070, 0.3979, 0.8575, 0.5083, 0.4350, 0.5400, 0.5180, 0.5466],
[0.6293, 0.3982, 0.8700, 0.5300, 0.3762, 0.4717, 0.7050, 0.5297],
[0.6277, 0.4103, 0.8087, 0.5717, 0.4187, 0.4750, 0.5663, 0.6083]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0027, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0027, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.901197498315014
step: 85
running loss: 0.0106023235095884
Train Steps: 85/90 Loss: 0.0106 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6170, 0.4102, 0.7468, 0.3695, 0.3463, 0.3767, 0.5238, 0.5823],
[0.6260, 0.4161, 0.9000, 0.3833, 0.4450, 0.2133, 0.6237, 0.4986],
[0.6236, 0.4081, 0.8575, 0.3000, 0.3713, 0.3033, 0.5550, 0.5633],
[ nan, nan, 0.8363, 0.3317, 0.3563, 0.3367, 0.5329, 0.5142],
[0.6133, 0.4066, 0.6787, 0.2617, 0.3800, 0.2433, 0.5147, 0.5358],
[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383],
[0.6274, 0.4117, 0.8100, 0.5801, 0.4000, 0.4583, 0.5582, 0.6118],
[0.6280, 0.4101, 0.9050, 0.4533, 0.3775, 0.3217, 0.6338, 0.4915]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5604, 0.4111, 0.7505, 0.3297, 0.3333, 0.3955, 0.5836, 0.5738],
[0.4741, 0.3754, 0.8639, 0.3444, 0.4385, 0.3285, 0.6015, 0.5387],
[0.4714, 0.3799, 0.8131, 0.3051, 0.3737, 0.3540, 0.5557, 0.5612],
[0.3484, 0.2857, 0.7763, 0.2619, 0.3515, 0.3478, 0.5347, 0.5393],
[0.4544, 0.3571, 0.6789, 0.2221, 0.3817, 0.2357, 0.5271, 0.5358],
[0.5848, 0.3920, 0.8319, 0.3195, 0.3314, 0.4011, 0.6398, 0.5342],
[0.5762, 0.3898, 0.8072, 0.5178, 0.3728, 0.5168, 0.5860, 0.5971],
[0.5460, 0.3911, 0.8495, 0.4813, 0.3454, 0.3946, 0.5857, 0.5254]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6170, 0.4102, 0.7468, 0.3695, 0.3462, 0.3767, 0.5238, 0.5823],
[0.6260, 0.4161, 0.9000, 0.3833, 0.4450, 0.2133, 0.6237, 0.4986],
[0.6236, 0.4081, 0.8575, 0.3000, 0.3713, 0.3033, 0.5550, 0.5633],
[0.0000, 0.0000, 0.8363, 0.3317, 0.3562, 0.3367, 0.5329, 0.5142],
[0.6133, 0.4065, 0.6787, 0.2617, 0.3800, 0.2433, 0.5147, 0.5358],
[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383],
[0.6274, 0.4117, 0.8100, 0.5801, 0.4000, 0.4583, 0.5582, 0.6118],
[0.6280, 0.4101, 0.9050, 0.4533, 0.3775, 0.3217, 0.6338, 0.4915]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0056, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0056, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.9067885667318478
step: 86
running loss: 0.010544053101533115
Train Steps: 86/90 Loss: 0.0105 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6282, 0.4092, 0.8000, 0.2183, 0.4500, 0.2383, 0.6787, 0.5364],
[0.6058, 0.3978, 0.8287, 0.3600, 0.3400, 0.4050, 0.5529, 0.5461],
[0.6059, 0.4002, 0.7562, 0.2767, 0.3538, 0.3033, 0.5529, 0.5455],
[0.6262, 0.4085, 0.8438, 0.3150, 0.4025, 0.2633, 0.6339, 0.4810],
[0.6203, 0.4021, 0.8780, 0.5031, 0.3667, 0.3882, 0.5842, 0.5405],
[ nan, nan, 0.8675, 0.2833, 0.5350, 0.1983, 0.6678, 0.5621],
[0.6129, 0.4063, 0.8738, 0.5250, 0.4313, 0.4733, 0.5230, 0.5874],
[0.6263, 0.4065, 0.9038, 0.4317, 0.3588, 0.4550, 0.6325, 0.5250]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4804, 0.3765, 0.7629, 0.2209, 0.4160, 0.2672, 0.5957, 0.5630],
[0.5317, 0.4018, 0.8057, 0.3704, 0.3130, 0.4027, 0.5884, 0.5213],
[0.5202, 0.4078, 0.7146, 0.2645, 0.3400, 0.3162, 0.5732, 0.5277],
[0.5567, 0.4072, 0.7966, 0.2697, 0.3687, 0.3272, 0.5992, 0.5057],
[0.5670, 0.3871, 0.8749, 0.5211, 0.3079, 0.4514, 0.5793, 0.5269],
[0.3928, 0.3086, 0.8130, 0.2346, 0.4734, 0.2574, 0.5827, 0.5535],
[0.5530, 0.3793, 0.8436, 0.5372, 0.3630, 0.5155, 0.5582, 0.5575],
[0.5016, 0.3815, 0.8580, 0.4418, 0.3176, 0.5024, 0.6462, 0.5298]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6282, 0.4092, 0.8000, 0.2183, 0.4500, 0.2383, 0.6787, 0.5364],
[0.6058, 0.3978, 0.8288, 0.3600, 0.3400, 0.4050, 0.5529, 0.5461],
[0.6059, 0.4002, 0.7563, 0.2767, 0.3537, 0.3033, 0.5529, 0.5455],
[0.6262, 0.4085, 0.8438, 0.3150, 0.4025, 0.2633, 0.6339, 0.4810],
[0.6203, 0.4020, 0.8780, 0.5031, 0.3667, 0.3882, 0.5842, 0.5405],
[0.0000, 0.0000, 0.8675, 0.2833, 0.5350, 0.1983, 0.6678, 0.5621],
[0.6130, 0.4063, 0.8737, 0.5250, 0.4313, 0.4733, 0.5230, 0.5874],
[0.6263, 0.4065, 0.9038, 0.4317, 0.3587, 0.4550, 0.6325, 0.5250]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0060, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0060, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.9128216054523364
step: 87
running loss: 0.010492202361521107
Train Steps: 87/90 Loss: 0.0105 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6274, 0.4087, 0.8375, 0.5700, 0.4025, 0.4800, 0.5700, 0.6117],
[0.6136, 0.3955, 0.8400, 0.3267, 0.3500, 0.4200, 0.5863, 0.5467],
[0.6264, 0.4069, 0.7900, 0.1650, 0.4275, 0.2267, 0.6290, 0.4947],
[0.6225, 0.4191, 0.8500, 0.4167, 0.3688, 0.3233, 0.5650, 0.5650],
[0.6210, 0.4164, 0.7202, 0.2930, 0.4025, 0.2483, 0.5687, 0.5567],
[0.6196, 0.4094, 0.7562, 0.2817, 0.3937, 0.3183, 0.6013, 0.6183],
[ nan, nan, 0.7725, 0.2611, 0.3675, 0.2733, 0.5413, 0.5167],
[0.6227, 0.4049, 0.8750, 0.5367, 0.3775, 0.3667, 0.5725, 0.5317]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6309, 0.4411, 0.8566, 0.5458, 0.3440, 0.4899, 0.6248, 0.5228],
[0.6560, 0.4673, 0.8795, 0.3399, 0.3029, 0.3756, 0.6669, 0.4935],
[0.5384, 0.3722, 0.7807, 0.1819, 0.4088, 0.2115, 0.6427, 0.5097],
[0.4743, 0.3617, 0.8475, 0.3988, 0.3414, 0.3437, 0.5752, 0.5261],
[0.4291, 0.3059, 0.7685, 0.2349, 0.4137, 0.2631, 0.5626, 0.5433],
[0.5035, 0.3525, 0.8084, 0.2813, 0.3893, 0.3058, 0.5725, 0.5391],
[0.3030, 0.2367, 0.7332, 0.2236, 0.3690, 0.2707, 0.5061, 0.5414],
[0.5988, 0.4033, 0.8804, 0.5317, 0.3392, 0.4191, 0.6056, 0.5135]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6274, 0.4087, 0.8375, 0.5700, 0.4025, 0.4800, 0.5700, 0.6117],
[0.6136, 0.3955, 0.8400, 0.3267, 0.3500, 0.4200, 0.5863, 0.5467],
[0.6264, 0.4069, 0.7900, 0.1650, 0.4275, 0.2267, 0.6290, 0.4947],
[0.6225, 0.4191, 0.8500, 0.4167, 0.3688, 0.3233, 0.5650, 0.5650],
[0.6210, 0.4164, 0.7202, 0.2930, 0.4025, 0.2483, 0.5688, 0.5567],
[0.6196, 0.4094, 0.7563, 0.2817, 0.3938, 0.3183, 0.6012, 0.6183],
[0.0000, 0.0000, 0.7725, 0.2611, 0.3675, 0.2733, 0.5412, 0.5167],
[0.6227, 0.4049, 0.8750, 0.5367, 0.3775, 0.3667, 0.5725, 0.5317]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0050, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0050, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.9177949238801375
step: 88
running loss: 0.010429487771365199
Train Steps: 88/90 Loss: 0.0104 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6026, 0.3979, 0.8550, 0.4233, 0.3613, 0.5233, 0.5582, 0.4967],
[0.6202, 0.4066, 0.8746, 0.3376, 0.3717, 0.3090, 0.5842, 0.5165],
[0.6216, 0.4099, 0.7225, 0.2033, 0.4188, 0.2217, 0.5975, 0.5283],
[0.6064, 0.4019, 0.8650, 0.4517, 0.4037, 0.5367, 0.5703, 0.5609],
[0.6200, 0.4059, 0.8700, 0.4900, 0.4163, 0.5000, 0.6162, 0.5467],
[0.6142, 0.3982, 0.8650, 0.4883, 0.3912, 0.4317, 0.5315, 0.5350],
[0.6263, 0.4065, 0.9038, 0.4317, 0.3588, 0.4550, 0.6325, 0.5250],
[0.6203, 0.4078, 0.8800, 0.5083, 0.3900, 0.5000, 0.6100, 0.5583]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5929, 0.3731, 0.8705, 0.4031, 0.3528, 0.4151, 0.6100, 0.5097],
[0.4927, 0.3507, 0.8621, 0.2883, 0.3869, 0.2458, 0.5743, 0.5135],
[0.5013, 0.3601, 0.7256, 0.2112, 0.4145, 0.1674, 0.5532, 0.5421],
[0.5520, 0.3886, 0.8470, 0.3874, 0.4040, 0.4425, 0.6123, 0.5298],
[0.6129, 0.4044, 0.8738, 0.4380, 0.4148, 0.4499, 0.6192, 0.5410],
[0.5775, 0.3733, 0.8324, 0.4880, 0.3656, 0.3719, 0.5710, 0.5103],
[0.5449, 0.3729, 0.8941, 0.4075, 0.3529, 0.3875, 0.6507, 0.5150],
[0.5946, 0.3648, 0.8880, 0.5087, 0.3705, 0.4399, 0.5809, 0.5327]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6026, 0.3979, 0.8550, 0.4233, 0.3613, 0.5233, 0.5582, 0.4967],
[0.6202, 0.4066, 0.8746, 0.3376, 0.3717, 0.3090, 0.5842, 0.5165],
[0.6216, 0.4099, 0.7225, 0.2033, 0.4187, 0.2217, 0.5975, 0.5283],
[0.6064, 0.4019, 0.8650, 0.4517, 0.4038, 0.5367, 0.5703, 0.5609],
[0.6199, 0.4059, 0.8700, 0.4900, 0.4162, 0.5000, 0.6162, 0.5467],
[0.6143, 0.3982, 0.8650, 0.4883, 0.3913, 0.4317, 0.5315, 0.5350],
[0.6263, 0.4065, 0.9038, 0.4317, 0.3587, 0.4550, 0.6325, 0.5250],
[0.6203, 0.4078, 0.8800, 0.5083, 0.3900, 0.5000, 0.6100, 0.5583]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.9196687457151711
step: 89
running loss: 0.010333356693428889
Train Steps: 89/90 Loss: 0.0103 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6213, 0.4131, 0.8438, 0.3550, 0.3513, 0.4400, 0.5716, 0.5123],
[0.6128, 0.4115, 0.7934, 0.3778, 0.3450, 0.4033, 0.5337, 0.5456],
[0.6212, 0.4171, 0.7875, 0.3633, 0.3813, 0.2933, 0.5675, 0.5700],
[0.6246, 0.4090, 0.6964, 0.2027, 0.3925, 0.2683, 0.6088, 0.5583],
[ nan, nan, 0.8938, 0.2850, 0.4662, 0.3117, 0.7406, 0.5528],
[0.6211, 0.3993, 0.7650, 0.1933, 0.4575, 0.1550, 0.5965, 0.4895],
[0.6277, 0.4057, 0.8300, 0.2650, 0.4363, 0.1850, 0.6140, 0.4823],
[0.6176, 0.4017, 0.8788, 0.5100, 0.4075, 0.5250, 0.5913, 0.5033]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5435, 0.3552, 0.8985, 0.4497, 0.3395, 0.4142, 0.5730, 0.5355],
[0.5902, 0.3901, 0.8323, 0.3892, 0.3376, 0.3772, 0.5743, 0.5076],
[0.6234, 0.4027, 0.7875, 0.3771, 0.3801, 0.3209, 0.5971, 0.5437],
[0.5622, 0.3665, 0.7203, 0.2761, 0.3826, 0.2560, 0.5562, 0.5354],
[0.5153, 0.3298, 0.9352, 0.3171, 0.4653, 0.2956, 0.6762, 0.5267],
[0.5273, 0.3673, 0.7741, 0.2380, 0.4547, 0.1751, 0.5787, 0.5063],
[0.6221, 0.4118, 0.8282, 0.2833, 0.4419, 0.2312, 0.6158, 0.5239],
[0.6492, 0.3897, 0.8705, 0.5609, 0.4380, 0.5152, 0.5819, 0.5223]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6213, 0.4131, 0.8438, 0.3550, 0.3512, 0.4400, 0.5716, 0.5123],
[0.6128, 0.4115, 0.7934, 0.3778, 0.3450, 0.4033, 0.5337, 0.5456],
[0.6212, 0.4171, 0.7875, 0.3633, 0.3812, 0.2933, 0.5675, 0.5700],
[0.6246, 0.4090, 0.6964, 0.2027, 0.3925, 0.2683, 0.6087, 0.5583],
[0.0000, 0.0000, 0.8938, 0.2850, 0.4663, 0.3117, 0.7406, 0.5528],
[0.6211, 0.3993, 0.7650, 0.1933, 0.4575, 0.1550, 0.5965, 0.4895],
[0.6277, 0.4056, 0.8300, 0.2650, 0.4363, 0.1850, 0.6140, 0.4823],
[0.6176, 0.4017, 0.8788, 0.5100, 0.4075, 0.5250, 0.5913, 0.5033]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0071, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0071, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.9267268031835556
step: 90
running loss: 0.010296964479817285
Valid Steps: 10/10 Loss: nan 9.9663
--------------------------------------------------
Epoch: 1 Train Loss: 0.0103 Valid Loss: nan
--------------------------------------------------
size of train loader is: 90
torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6263, 0.4057, 0.8800, 0.3833, 0.3650, 0.3717, 0.6375, 0.4804],
[0.6090, 0.4010, 0.7838, 0.3483, 0.3538, 0.3783, 0.5462, 0.5077],
[0.6201, 0.4027, 0.8029, 0.2728, 0.4042, 0.2310, 0.5980, 0.5391],
[0.6299, 0.4303, 0.7963, 0.3933, 0.4850, 0.2283, 0.5480, 0.6222],
[0.6151, 0.4058, 0.7068, 0.2680, 0.3400, 0.4083, 0.5775, 0.5733],
[0.6198, 0.4105, 0.7950, 0.3267, 0.3675, 0.3767, 0.6038, 0.6167],
[0.6350, 0.4043, 0.8738, 0.5650, 0.3850, 0.4750, 0.6401, 0.4950],
[0.6182, 0.3982, 0.7541, 0.2379, 0.3959, 0.2792, 0.6079, 0.5389]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6872, 0.4337, 0.8972, 0.4201, 0.3770, 0.3324, 0.6289, 0.5134],
[0.6172, 0.3803, 0.8485, 0.3648, 0.3583, 0.3490, 0.5906, 0.5130],
[0.6515, 0.3853, 0.8185, 0.2864, 0.4441, 0.2439, 0.6147, 0.5116],
[0.4792, 0.2720, 0.8376, 0.3685, 0.4626, 0.3081, 0.5410, 0.5550],
[0.5997, 0.3969, 0.7568, 0.2729, 0.3546, 0.3386, 0.5979, 0.5413],
[0.5900, 0.3652, 0.8555, 0.3659, 0.4145, 0.3966, 0.5892, 0.5485],
[0.6974, 0.4176, 0.8878, 0.5917, 0.4094, 0.4353, 0.6341, 0.5390],
[0.4887, 0.3089, 0.8156, 0.2632, 0.4195, 0.2369, 0.5856, 0.5529]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6263, 0.4057, 0.8800, 0.3833, 0.3650, 0.3717, 0.6375, 0.4804],
[0.6090, 0.4010, 0.7837, 0.3483, 0.3537, 0.3783, 0.5462, 0.5077],
[0.6201, 0.4027, 0.8029, 0.2728, 0.4042, 0.2310, 0.5980, 0.5391],
[0.6299, 0.4303, 0.7962, 0.3933, 0.4850, 0.2283, 0.5480, 0.6222],
[0.6151, 0.4058, 0.7068, 0.2680, 0.3400, 0.4083, 0.5775, 0.5733],
[0.6198, 0.4105, 0.7950, 0.3267, 0.3675, 0.3767, 0.6037, 0.6167],
[0.6350, 0.4043, 0.8737, 0.5650, 0.3850, 0.4750, 0.6401, 0.4950],
[0.6182, 0.3982, 0.7541, 0.2379, 0.3959, 0.2792, 0.6079, 0.5389]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0023, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0023, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.002330109942704439
step: 1
running loss: 0.002330109942704439
Train Steps: 1/90 Loss: 0.0023 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6109, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117],
[0.6091, 0.3997, 0.8314, 0.4334, 0.3788, 0.4550, 0.5213, 0.5656],
[0.6150, 0.3935, 0.8696, 0.5158, 0.4647, 0.5329, 0.6041, 0.5153],
[0.6200, 0.4071, 0.7338, 0.1917, 0.4200, 0.2450, 0.6150, 0.5517],
[0.6339, 0.4123, 0.8638, 0.5367, 0.4075, 0.5467, 0.7517, 0.5436],
[0.6245, 0.4115, 0.8700, 0.4883, 0.4625, 0.5517, 0.6100, 0.5217],
[0.6204, 0.4049, 0.7975, 0.2700, 0.3937, 0.2567, 0.5700, 0.5183],
[0.6148, 0.3996, 0.8488, 0.3867, 0.3488, 0.4067, 0.5863, 0.5000]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6145, 0.3738, 0.8607, 0.4208, 0.3780, 0.3628, 0.5549, 0.5305],
[0.6738, 0.3928, 0.8229, 0.4044, 0.3819, 0.3683, 0.5741, 0.5606],
[0.6270, 0.3677, 0.8551, 0.4638, 0.4560, 0.4233, 0.5913, 0.5175],
[0.5668, 0.3573, 0.7547, 0.2084, 0.4347, 0.1876, 0.6145, 0.5623],
[0.7260, 0.4346, 0.8786, 0.5015, 0.4410, 0.4891, 0.6635, 0.5420],
[0.6284, 0.3754, 0.8509, 0.4435, 0.4574, 0.4805, 0.6267, 0.5466],
[0.5074, 0.3131, 0.7886, 0.2444, 0.4170, 0.2448, 0.5512, 0.5679],
[0.6932, 0.4020, 0.8751, 0.3573, 0.3753, 0.3645, 0.6225, 0.5110]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6108, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117],
[0.6091, 0.3997, 0.8314, 0.4334, 0.3787, 0.4550, 0.5213, 0.5656],
[0.6150, 0.3935, 0.8696, 0.5158, 0.4647, 0.5329, 0.6041, 0.5153],
[0.6200, 0.4071, 0.7337, 0.1917, 0.4200, 0.2450, 0.6150, 0.5517],
[0.6339, 0.4123, 0.8637, 0.5367, 0.4075, 0.5467, 0.7517, 0.5436],
[0.6245, 0.4115, 0.8700, 0.4883, 0.4625, 0.5517, 0.6100, 0.5217],
[0.6204, 0.4049, 0.7975, 0.2700, 0.3938, 0.2567, 0.5700, 0.5183],
[0.6148, 0.3996, 0.8487, 0.3867, 0.3487, 0.4067, 0.5863, 0.5000]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0018, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0018, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.004169229883700609
step: 2
running loss: 0.0020846149418503046
Train Steps: 2/90 Loss: 0.0021 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6072, 0.4029, 0.7037, 0.2150, 0.3912, 0.2267, 0.5516, 0.5507],
[0.6264, 0.4248, 0.8938, 0.4183, 0.3875, 0.4100, 0.5400, 0.5350],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5413, 0.5683],
[0.6236, 0.3977, 0.8985, 0.4806, 0.3835, 0.5216, 0.6613, 0.5166],
[0.6129, 0.4069, 0.8750, 0.5067, 0.3875, 0.4233, 0.5235, 0.5881],
[0.6064, 0.4019, 0.8650, 0.4517, 0.4037, 0.5367, 0.5703, 0.5609],
[0.6271, 0.4081, 0.9081, 0.4894, 0.3700, 0.4283, 0.6661, 0.5274],
[0.6204, 0.4110, 0.7913, 0.2667, 0.4062, 0.2500, 0.6225, 0.5367]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6210, 0.3733, 0.7070, 0.1875, 0.4298, 0.2392, 0.6003, 0.5556],
[0.5637, 0.3689, 0.8830, 0.3828, 0.3889, 0.4043, 0.5980, 0.5772],
[0.6553, 0.3891, 0.8563, 0.4888, 0.3935, 0.3760, 0.5745, 0.5657],
[0.7391, 0.4401, 0.8648, 0.4355, 0.4207, 0.4890, 0.6368, 0.5273],
[0.7080, 0.4109, 0.8534, 0.5227, 0.4033, 0.4343, 0.5789, 0.5379],
[0.6257, 0.4029, 0.8454, 0.4019, 0.4475, 0.5099, 0.6265, 0.5559],
[0.5795, 0.3841, 0.8735, 0.4313, 0.3932, 0.4179, 0.6239, 0.5749],
[0.7210, 0.4312, 0.7837, 0.2215, 0.4313, 0.2648, 0.6441, 0.5431]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6072, 0.4029, 0.7038, 0.2150, 0.3913, 0.2267, 0.5516, 0.5507],
[0.6264, 0.4248, 0.8938, 0.4183, 0.3875, 0.4100, 0.5400, 0.5350],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5412, 0.5683],
[0.6236, 0.3977, 0.8985, 0.4806, 0.3835, 0.5216, 0.6613, 0.5166],
[0.6129, 0.4069, 0.8750, 0.5067, 0.3875, 0.4233, 0.5235, 0.5881],
[0.6064, 0.4019, 0.8650, 0.4517, 0.4038, 0.5367, 0.5703, 0.5609],
[0.6271, 0.4081, 0.9081, 0.4894, 0.3700, 0.4283, 0.6661, 0.5274],
[0.6204, 0.4110, 0.7912, 0.2667, 0.4062, 0.2500, 0.6225, 0.5367]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.005690339137800038
step: 3
running loss: 0.0018967797126000125
Train Steps: 3/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6196, 0.4094, 0.7562, 0.2817, 0.3937, 0.3183, 0.6013, 0.6183],
[0.6264, 0.3972, 0.8853, 0.4771, 0.3853, 0.4511, 0.6293, 0.5334],
[0.6095, 0.3970, 0.8688, 0.4767, 0.4860, 0.4879, 0.5191, 0.4940],
[0.6339, 0.4118, 0.7988, 0.5800, 0.3912, 0.4583, 0.7343, 0.5760],
[0.6106, 0.4022, 0.7125, 0.2650, 0.3713, 0.2700, 0.5431, 0.5123],
[0.6346, 0.4092, 0.7712, 0.5917, 0.4037, 0.4767, 0.7343, 0.5725],
[ nan, nan, 0.7268, 0.2333, 0.4125, 0.1933, 0.5112, 0.5383],
[0.6201, 0.4036, 0.8596, 0.3850, 0.3492, 0.3785, 0.5978, 0.5131]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6077, 0.3637, 0.8153, 0.3016, 0.4283, 0.3415, 0.6094, 0.5728],
[0.7280, 0.4462, 0.8907, 0.4716, 0.3838, 0.4796, 0.6378, 0.5437],
[0.6187, 0.3866, 0.8951, 0.4905, 0.4692, 0.4792, 0.5636, 0.5441],
[0.6859, 0.4542, 0.8208, 0.4771, 0.3889, 0.4240, 0.6505, 0.5725],
[0.6441, 0.4278, 0.7551, 0.2768, 0.4004, 0.3053, 0.5613, 0.5257],
[0.6740, 0.4174, 0.8163, 0.4472, 0.3975, 0.4796, 0.6239, 0.5814],
[0.4253, 0.2775, 0.7268, 0.2199, 0.4191, 0.2303, 0.5546, 0.5585],
[0.7390, 0.4758, 0.8779, 0.4258, 0.3620, 0.4260, 0.6183, 0.5347]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6196, 0.4094, 0.7563, 0.2817, 0.3938, 0.3183, 0.6012, 0.6183],
[0.6264, 0.3972, 0.8853, 0.4771, 0.3853, 0.4511, 0.6293, 0.5334],
[0.6095, 0.3970, 0.8687, 0.4767, 0.4860, 0.4879, 0.5191, 0.4940],
[0.6339, 0.4118, 0.7987, 0.5800, 0.3913, 0.4583, 0.7343, 0.5760],
[0.6106, 0.4022, 0.7125, 0.2650, 0.3713, 0.2700, 0.5431, 0.5123],
[0.6346, 0.4092, 0.7713, 0.5917, 0.4038, 0.4767, 0.7343, 0.5725],
[0.0000, 0.0000, 0.7268, 0.2333, 0.4125, 0.1933, 0.5113, 0.5383],
[0.6201, 0.4036, 0.8596, 0.3850, 0.3492, 0.3785, 0.5978, 0.5131]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0060, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0060, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.011675780289806426
step: 4
running loss: 0.0029189450724516064
Train Steps: 4/90 Loss: 0.0029 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6202, 0.4054, 0.8892, 0.4428, 0.3642, 0.3249, 0.5840, 0.5426],
[0.6172, 0.4055, 0.8175, 0.2650, 0.3550, 0.3683, 0.5787, 0.5550],
[0.6216, 0.4100, 0.7350, 0.2067, 0.4325, 0.2050, 0.5950, 0.5333],
[0.6086, 0.3998, 0.8788, 0.4450, 0.4025, 0.4650, 0.5306, 0.5103],
[0.6136, 0.4060, 0.8025, 0.3217, 0.3650, 0.3000, 0.5060, 0.5646],
[0.6073, 0.3932, 0.8363, 0.5817, 0.4425, 0.5117, 0.5204, 0.4817],
[0.6339, 0.4118, 0.7988, 0.5800, 0.3912, 0.4583, 0.7343, 0.5760],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6264, 0.3890, 0.8849, 0.4577, 0.3787, 0.3752, 0.6042, 0.5390],
[0.6357, 0.4101, 0.8017, 0.3282, 0.3719, 0.4082, 0.6085, 0.5483],
[0.5796, 0.3818, 0.7151, 0.2136, 0.4244, 0.2336, 0.6140, 0.5432],
[0.5836, 0.3846, 0.8652, 0.4589, 0.3859, 0.4856, 0.5789, 0.5566],
[0.4955, 0.3177, 0.7559, 0.3055, 0.3664, 0.3517, 0.5298, 0.5826],
[0.6555, 0.4345, 0.8346, 0.5506, 0.4640, 0.4997, 0.5712, 0.5504],
[0.6729, 0.4611, 0.7886, 0.4845, 0.3807, 0.4276, 0.6603, 0.5793],
[0.6554, 0.4426, 0.8285, 0.4267, 0.4289, 0.4932, 0.5877, 0.5431]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6202, 0.4054, 0.8892, 0.4428, 0.3642, 0.3249, 0.5840, 0.5426],
[0.6172, 0.4055, 0.8175, 0.2650, 0.3550, 0.3683, 0.5788, 0.5550],
[0.6216, 0.4100, 0.7350, 0.2067, 0.4325, 0.2050, 0.5950, 0.5333],
[0.6086, 0.3998, 0.8788, 0.4450, 0.4025, 0.4650, 0.5306, 0.5103],
[0.6136, 0.4060, 0.8025, 0.3217, 0.3650, 0.3000, 0.5060, 0.5646],
[0.6073, 0.3932, 0.8363, 0.5817, 0.4425, 0.5117, 0.5204, 0.4817],
[0.6339, 0.4118, 0.7987, 0.5800, 0.3913, 0.4583, 0.7343, 0.5760],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.013066976680420339
step: 5
running loss: 0.002613395336084068
Train Steps: 5/90 Loss: 0.0026 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466],
[0.6299, 0.4008, 0.8450, 0.5350, 0.4213, 0.5000, 0.6350, 0.5100],
[ nan, nan, 0.7553, 0.2722, 0.3875, 0.2550, 0.5125, 0.5633],
[0.6034, 0.4011, 0.7350, 0.2533, 0.3438, 0.3367, 0.5516, 0.5084],
[0.6136, 0.4085, 0.6688, 0.2317, 0.3862, 0.2367, 0.5517, 0.5783],
[0.6201, 0.4116, 0.8725, 0.4733, 0.3700, 0.3217, 0.5386, 0.5767],
[0.6205, 0.4062, 0.8337, 0.2683, 0.3675, 0.4283, 0.6338, 0.5250],
[0.6206, 0.4123, 0.7175, 0.2400, 0.3887, 0.2933, 0.6225, 0.5750]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5977, 0.4350, 0.8050, 0.4319, 0.3415, 0.4584, 0.5779, 0.5418],
[0.6764, 0.4721, 0.8811, 0.6016, 0.4422, 0.5708, 0.6735, 0.5176],
[0.3770, 0.2507, 0.8024, 0.3486, 0.4141, 0.3534, 0.5272, 0.5591],
[0.6396, 0.4189, 0.7438, 0.3510, 0.3652, 0.4136, 0.6224, 0.5179],
[0.5993, 0.3926, 0.7307, 0.3044, 0.3918, 0.3173, 0.5537, 0.5438],
[0.5945, 0.3974, 0.8848, 0.5304, 0.3780, 0.4062, 0.5683, 0.5607],
[0.6597, 0.4484, 0.8276, 0.3433, 0.3842, 0.4623, 0.6476, 0.5271],
[0.6816, 0.4689, 0.7731, 0.3694, 0.3935, 0.3450, 0.6229, 0.5515]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466],
[0.6299, 0.4008, 0.8450, 0.5350, 0.4212, 0.5000, 0.6350, 0.5100],
[0.0000, 0.0000, 0.7553, 0.2722, 0.3875, 0.2550, 0.5125, 0.5633],
[0.6033, 0.4011, 0.7350, 0.2533, 0.3438, 0.3367, 0.5516, 0.5084],
[0.6136, 0.4085, 0.6687, 0.2317, 0.3862, 0.2367, 0.5517, 0.5783],
[0.6201, 0.4116, 0.8725, 0.4733, 0.3700, 0.3217, 0.5386, 0.5767],
[0.6205, 0.4062, 0.8338, 0.2683, 0.3675, 0.4283, 0.6338, 0.5250],
[0.6206, 0.4123, 0.7175, 0.2400, 0.3887, 0.2933, 0.6225, 0.5750]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0054, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0054, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.018506109598092735
step: 6
running loss: 0.0030843515996821225
Train Steps: 6/90 Loss: 0.0031 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6128, 0.4115, 0.7934, 0.3778, 0.3450, 0.4033, 0.5337, 0.5456],
[0.6246, 0.4126, 0.8850, 0.4833, 0.4200, 0.5350, 0.6112, 0.5250],
[0.6200, 0.4055, 0.8011, 0.2988, 0.3842, 0.2798, 0.5949, 0.5183],
[0.6177, 0.4086, 0.8738, 0.3950, 0.3775, 0.5600, 0.6225, 0.5700],
[0.6040, 0.4002, 0.7338, 0.2267, 0.3975, 0.2100, 0.5231, 0.4778],
[0.6350, 0.4118, 0.8363, 0.2717, 0.4850, 0.1700, 0.6441, 0.5170],
[0.6073, 0.3932, 0.8363, 0.5817, 0.4425, 0.5117, 0.5204, 0.4817],
[0.6161, 0.4024, 0.8838, 0.4583, 0.3688, 0.3733, 0.5311, 0.5344]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5708, 0.3968, 0.7693, 0.4015, 0.3199, 0.4287, 0.5562, 0.5247],
[0.5546, 0.3773, 0.8702, 0.5485, 0.3906, 0.5924, 0.6215, 0.5399],
[0.6222, 0.4316, 0.7642, 0.3521, 0.3556, 0.3273, 0.5974, 0.5201],
[0.6468, 0.4305, 0.8375, 0.4463, 0.3929, 0.5610, 0.6378, 0.5235],
[0.5255, 0.3410, 0.6833, 0.2793, 0.3942, 0.2555, 0.5385, 0.5084],
[0.5840, 0.3774, 0.7915, 0.2801, 0.4503, 0.2402, 0.6608, 0.5368],
[0.5709, 0.4004, 0.8241, 0.6080, 0.4465, 0.5133, 0.5526, 0.5187],
[0.5726, 0.3613, 0.8635, 0.5536, 0.3483, 0.4468, 0.5813, 0.5152]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6128, 0.4115, 0.7934, 0.3778, 0.3450, 0.4033, 0.5337, 0.5456],
[0.6246, 0.4126, 0.8850, 0.4833, 0.4200, 0.5350, 0.6112, 0.5250],
[0.6201, 0.4055, 0.8011, 0.2988, 0.3842, 0.2798, 0.5949, 0.5183],
[0.6177, 0.4085, 0.8737, 0.3950, 0.3775, 0.5600, 0.6225, 0.5700],
[0.6040, 0.4002, 0.7337, 0.2267, 0.3975, 0.2100, 0.5231, 0.4778],
[0.6350, 0.4118, 0.8363, 0.2717, 0.4850, 0.1700, 0.6441, 0.5170],
[0.6073, 0.3932, 0.8363, 0.5817, 0.4425, 0.5117, 0.5204, 0.4817],
[0.6161, 0.4024, 0.8838, 0.4583, 0.3688, 0.3733, 0.5311, 0.5344]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.01996891770977527
step: 7
running loss: 0.0028527025299678955
Train Steps: 7/90 Loss: 0.0029 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6205, 0.4016, 0.8350, 0.2717, 0.3987, 0.2550, 0.5787, 0.5133],
[0.6055, 0.4015, 0.7425, 0.2033, 0.4113, 0.1883, 0.5217, 0.4823],
[0.6205, 0.4004, 0.8938, 0.4883, 0.3663, 0.5000, 0.6357, 0.4947],
[0.6273, 0.4110, 0.8900, 0.3817, 0.4188, 0.2167, 0.5858, 0.4835],
[0.6222, 0.4108, 0.8938, 0.4233, 0.3600, 0.3817, 0.5825, 0.5283],
[0.6200, 0.3913, 0.8788, 0.5217, 0.4075, 0.5100, 0.6060, 0.4913],
[0.6273, 0.4105, 0.8988, 0.4517, 0.3912, 0.2550, 0.5894, 0.4811],
[0.6325, 0.4066, 0.8438, 0.5350, 0.3925, 0.5267, 0.7113, 0.5795]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5045, 0.3187, 0.7871, 0.2918, 0.3870, 0.3102, 0.5536, 0.5498],
[0.4373, 0.3065, 0.6487, 0.2241, 0.3569, 0.2030, 0.5153, 0.5458],
[0.6749, 0.4379, 0.8354, 0.4962, 0.3637, 0.5110, 0.5942, 0.4977],
[0.5190, 0.3392, 0.8178, 0.3587, 0.4088, 0.2443, 0.5731, 0.5093],
[0.5491, 0.3799, 0.8266, 0.4311, 0.3344, 0.3934, 0.5794, 0.5571],
[0.6324, 0.3970, 0.8339, 0.5412, 0.4179, 0.5375, 0.5340, 0.5230],
[0.5478, 0.3553, 0.8102, 0.4492, 0.3866, 0.3094, 0.5413, 0.5078],
[0.6430, 0.4296, 0.8219, 0.5368, 0.3574, 0.5627, 0.6212, 0.5529]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6205, 0.4015, 0.8350, 0.2717, 0.3988, 0.2550, 0.5788, 0.5133],
[0.6055, 0.4015, 0.7425, 0.2033, 0.4112, 0.1883, 0.5217, 0.4823],
[0.6205, 0.4004, 0.8938, 0.4883, 0.3663, 0.5000, 0.6357, 0.4947],
[0.6273, 0.4110, 0.8900, 0.3817, 0.4187, 0.2167, 0.5858, 0.4835],
[0.6222, 0.4108, 0.8938, 0.4233, 0.3600, 0.3817, 0.5825, 0.5283],
[0.6199, 0.3913, 0.8788, 0.5217, 0.4075, 0.5100, 0.6060, 0.4913],
[0.6273, 0.4105, 0.8988, 0.4517, 0.3913, 0.2550, 0.5894, 0.4811],
[0.6325, 0.4066, 0.8438, 0.5350, 0.3925, 0.5267, 0.7113, 0.5795]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0027, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0027, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.022683476679958403
step: 8
running loss: 0.0028354345849948004
Train Steps: 8/90 Loss: 0.0028 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6148, 0.4076, 0.8666, 0.4820, 0.4138, 0.5067, 0.5250, 0.5767],
[0.6142, 0.4127, 0.7575, 0.3067, 0.3438, 0.4383, 0.5778, 0.5207],
[0.6161, 0.4024, 0.8662, 0.4683, 0.4935, 0.5364, 0.6063, 0.5567],
[0.6197, 0.4050, 0.7527, 0.2000, 0.4042, 0.2249, 0.5895, 0.4995],
[0.6202, 0.4066, 0.8746, 0.3376, 0.3717, 0.3090, 0.5842, 0.5165],
[0.6227, 0.4049, 0.8750, 0.5367, 0.3775, 0.3667, 0.5725, 0.5317],
[0.6179, 0.3961, 0.8347, 0.6020, 0.3887, 0.4624, 0.5714, 0.5373],
[0.6300, 0.4102, 0.9088, 0.4433, 0.4088, 0.3067, 0.6820, 0.5540]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6031, 0.4043, 0.8679, 0.4927, 0.4254, 0.4905, 0.5511, 0.5095],
[0.5522, 0.3762, 0.7357, 0.2780, 0.3510, 0.3617, 0.5283, 0.5241],
[0.5653, 0.3769, 0.8385, 0.4342, 0.4193, 0.4412, 0.5588, 0.5099],
[0.5708, 0.3708, 0.7378, 0.2137, 0.3824, 0.2108, 0.5804, 0.4831],
[0.5330, 0.3495, 0.8532, 0.3130, 0.3553, 0.2720, 0.5710, 0.4873],
[0.6152, 0.3664, 0.8556, 0.5128, 0.3753, 0.3823, 0.5417, 0.4911],
[0.6507, 0.4053, 0.8211, 0.5239, 0.3740, 0.4510, 0.5287, 0.5169],
[0.5049, 0.3249, 0.8977, 0.4204, 0.3946, 0.3056, 0.6048, 0.5078]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6148, 0.4076, 0.8666, 0.4820, 0.4137, 0.5067, 0.5250, 0.5767],
[0.6142, 0.4127, 0.7575, 0.3067, 0.3438, 0.4383, 0.5778, 0.5207],
[0.6161, 0.4024, 0.8662, 0.4683, 0.4935, 0.5364, 0.6062, 0.5567],
[0.6197, 0.4050, 0.7527, 0.2000, 0.4042, 0.2249, 0.5895, 0.4995],
[0.6202, 0.4066, 0.8746, 0.3376, 0.3717, 0.3090, 0.5842, 0.5165],
[0.6227, 0.4049, 0.8750, 0.5367, 0.3775, 0.3667, 0.5725, 0.5317],
[0.6179, 0.3961, 0.8347, 0.6020, 0.3887, 0.4624, 0.5714, 0.5373],
[0.6300, 0.4102, 0.9087, 0.4433, 0.4087, 0.3067, 0.6820, 0.5540]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.02442885807249695
step: 9
running loss: 0.002714317563610772
Train Steps: 9/90 Loss: 0.0027 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6095, 0.4002, 0.8533, 0.5168, 0.5031, 0.5094, 0.5125, 0.5433],
[ nan, nan, 0.7525, 0.2291, 0.3838, 0.3017, 0.6050, 0.5667],
[0.6271, 0.4005, 0.8450, 0.6067, 0.3850, 0.4983, 0.6069, 0.4649],
[0.6229, 0.4086, 0.7538, 0.2600, 0.4775, 0.1617, 0.5900, 0.5383],
[0.6198, 0.4076, 0.7945, 0.2453, 0.4475, 0.1871, 0.5897, 0.5350],
[0.6161, 0.4076, 0.8900, 0.4667, 0.4125, 0.5917, 0.6262, 0.5367],
[0.6226, 0.4001, 0.8438, 0.5733, 0.3862, 0.4250, 0.5750, 0.5283],
[0.6117, 0.4018, 0.6562, 0.1967, 0.3738, 0.2550, 0.5280, 0.5103]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6161, 0.3976, 0.8913, 0.5049, 0.4627, 0.4538, 0.5329, 0.5048],
[0.4613, 0.3151, 0.7858, 0.2366, 0.3750, 0.2504, 0.5672, 0.5301],
[0.6097, 0.4158, 0.8656, 0.5438, 0.3685, 0.4619, 0.5735, 0.4866],
[0.5733, 0.3802, 0.7500, 0.2107, 0.4054, 0.1448, 0.5669, 0.5125],
[0.5220, 0.3303, 0.7986, 0.2464, 0.3953, 0.2086, 0.5738, 0.5130],
[0.5901, 0.4047, 0.9199, 0.4660, 0.4396, 0.5506, 0.5753, 0.4923],
[0.6348, 0.4031, 0.9029, 0.5513, 0.3419, 0.3958, 0.5533, 0.5214],
[0.5432, 0.3565, 0.7056, 0.2154, 0.3556, 0.2192, 0.5092, 0.5026]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6095, 0.4002, 0.8533, 0.5168, 0.5031, 0.5094, 0.5125, 0.5433],
[0.0000, 0.0000, 0.7525, 0.2291, 0.3837, 0.3017, 0.6050, 0.5667],
[0.6271, 0.4005, 0.8450, 0.6067, 0.3850, 0.4983, 0.6069, 0.4649],
[0.6229, 0.4086, 0.7538, 0.2600, 0.4775, 0.1617, 0.5900, 0.5383],
[0.6198, 0.4076, 0.7945, 0.2453, 0.4475, 0.1871, 0.5897, 0.5350],
[0.6161, 0.4076, 0.8900, 0.4667, 0.4125, 0.5917, 0.6263, 0.5367],
[0.6226, 0.4001, 0.8438, 0.5733, 0.3862, 0.4250, 0.5750, 0.5283],
[0.6116, 0.4018, 0.6562, 0.1967, 0.3738, 0.2550, 0.5280, 0.5103]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0062, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0062, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.030593233765102923
step: 10
running loss: 0.003059323376510292
Train Steps: 10/90 Loss: 0.0031 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6267, 0.4065, 0.8313, 0.2467, 0.4788, 0.1733, 0.6312, 0.5133],
[0.6248, 0.4032, 0.7738, 0.1900, 0.4813, 0.1400, 0.5941, 0.4904],
[0.6219, 0.4114, 0.8175, 0.2817, 0.3925, 0.2783, 0.5900, 0.5350],
[0.6311, 0.3998, 0.7975, 0.5767, 0.3838, 0.4850, 0.7327, 0.5343],
[0.6101, 0.4042, 0.7775, 0.2617, 0.3713, 0.2817, 0.5440, 0.5650],
[0.6189, 0.4049, 0.8888, 0.4417, 0.4213, 0.5200, 0.5988, 0.5633],
[0.6236, 0.4084, 0.7738, 0.2133, 0.3663, 0.3233, 0.5813, 0.5567],
[0.6124, 0.4083, 0.6954, 0.3069, 0.3650, 0.2750, 0.5163, 0.5485]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6524, 0.4194, 0.8302, 0.2453, 0.4642, 0.2088, 0.6127, 0.5133],
[0.5333, 0.3385, 0.7581, 0.2202, 0.4625, 0.1170, 0.5673, 0.4804],
[0.4795, 0.3257, 0.8051, 0.2669, 0.3902, 0.2321, 0.5726, 0.5239],
[0.5878, 0.4107, 0.8545, 0.5105, 0.3563, 0.4354, 0.5768, 0.5078],
[0.4419, 0.3261, 0.7948, 0.2944, 0.3893, 0.2562, 0.5276, 0.5387],
[0.6046, 0.4057, 0.9291, 0.5008, 0.4122, 0.5362, 0.5740, 0.5424],
[0.5551, 0.3804, 0.8104, 0.3170, 0.3766, 0.2811, 0.5634, 0.5270],
[0.6001, 0.3880, 0.7420, 0.3093, 0.3546, 0.2835, 0.4877, 0.5316]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6266, 0.4065, 0.8313, 0.2467, 0.4787, 0.1733, 0.6313, 0.5133],
[0.6248, 0.4032, 0.7738, 0.1900, 0.4812, 0.1400, 0.5941, 0.4904],
[0.6219, 0.4114, 0.8175, 0.2817, 0.3925, 0.2783, 0.5900, 0.5350],
[0.6311, 0.3998, 0.7975, 0.5767, 0.3837, 0.4850, 0.7327, 0.5343],
[0.6101, 0.4042, 0.7775, 0.2617, 0.3713, 0.2817, 0.5440, 0.5650],
[0.6189, 0.4049, 0.8888, 0.4417, 0.4212, 0.5200, 0.5987, 0.5633],
[0.6236, 0.4084, 0.7738, 0.2133, 0.3663, 0.3233, 0.5813, 0.5567],
[0.6123, 0.4083, 0.6954, 0.3069, 0.3650, 0.2750, 0.5163, 0.5485]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0024, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0024, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.033024250413291156
step: 11
running loss: 0.0030022045830264688
Train Steps: 11/90 Loss: 0.0030 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6336, 0.4154, 0.8900, 0.2767, 0.4988, 0.2867, 0.7422, 0.5540],
[0.6343, 0.4097, 0.9287, 0.4367, 0.4313, 0.3600, 0.7248, 0.5841],
[0.6296, 0.4076, 0.8400, 0.5583, 0.3700, 0.4367, 0.6876, 0.5494],
[0.6266, 0.4070, 0.8712, 0.5600, 0.3713, 0.4783, 0.5775, 0.6100],
[0.6325, 0.4165, 0.9000, 0.4617, 0.3813, 0.4900, 0.7485, 0.5447],
[0.6198, 0.4130, 0.8762, 0.4117, 0.3650, 0.4900, 0.5707, 0.5103],
[0.6250, 0.4236, 0.8638, 0.3767, 0.4050, 0.3150, 0.5649, 0.5799],
[0.6222, 0.4172, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5612, 0.3811, 0.8602, 0.2296, 0.4916, 0.2306, 0.6434, 0.5336],
[0.6425, 0.4218, 0.8356, 0.3556, 0.4207, 0.3121, 0.6238, 0.5244],
[0.6146, 0.4007, 0.8371, 0.4343, 0.4082, 0.3477, 0.6174, 0.5276],
[0.6623, 0.4279, 0.8380, 0.4641, 0.4136, 0.4596, 0.5665, 0.5384],
[0.5593, 0.3786, 0.9084, 0.4347, 0.4017, 0.4581, 0.6508, 0.5335],
[0.6136, 0.4184, 0.9224, 0.3770, 0.3960, 0.4299, 0.5676, 0.5565],
[0.5552, 0.3466, 0.8568, 0.3470, 0.4307, 0.2913, 0.5624, 0.5741],
[0.6698, 0.4377, 0.8489, 0.4851, 0.4061, 0.4395, 0.5585, 0.5461]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6336, 0.4154, 0.8900, 0.2767, 0.4988, 0.2867, 0.7422, 0.5540],
[0.6343, 0.4097, 0.9287, 0.4367, 0.4313, 0.3600, 0.7248, 0.5841],
[0.6296, 0.4076, 0.8400, 0.5583, 0.3700, 0.4367, 0.6876, 0.5494],
[0.6266, 0.4070, 0.8712, 0.5600, 0.3713, 0.4783, 0.5775, 0.6100],
[0.6325, 0.4165, 0.9000, 0.4617, 0.3812, 0.4900, 0.7485, 0.5447],
[0.6198, 0.4130, 0.8763, 0.4117, 0.3650, 0.4900, 0.5707, 0.5103],
[0.6250, 0.4236, 0.8637, 0.3767, 0.4050, 0.3150, 0.5649, 0.5799],
[0.6222, 0.4171, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0024, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0024, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03542143327649683
step: 12
running loss: 0.0029517861063747355
Train Steps: 12/90 Loss: 0.0030 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6102, 0.4020, 0.8638, 0.3717, 0.3625, 0.5017, 0.6038, 0.5500],
[0.6207, 0.4081, 0.7662, 0.2067, 0.3962, 0.3200, 0.6312, 0.5300],
[0.6195, 0.4101, 0.8650, 0.3917, 0.3575, 0.4033, 0.5800, 0.5650],
[0.6286, 0.4097, 0.8107, 0.2414, 0.4425, 0.2483, 0.6745, 0.5385],
[0.6226, 0.4185, 0.8850, 0.5500, 0.3800, 0.4250, 0.5625, 0.5617],
[ nan, nan, 0.8037, 0.2483, 0.3975, 0.2517, 0.5575, 0.5600],
[0.6203, 0.4073, 0.8189, 0.2398, 0.4400, 0.2054, 0.5929, 0.5501],
[0.6204, 0.4049, 0.7975, 0.2700, 0.3937, 0.2567, 0.5700, 0.5183]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5890, 0.4046, 0.8961, 0.4043, 0.4132, 0.5221, 0.6450, 0.5752],
[0.6591, 0.4443, 0.7609, 0.2467, 0.4018, 0.2730, 0.6092, 0.5504],
[0.6208, 0.4260, 0.8892, 0.4191, 0.3758, 0.3963, 0.5760, 0.5460],
[0.6432, 0.4296, 0.8513, 0.2810, 0.4636, 0.2191, 0.6936, 0.5478],
[0.6852, 0.4710, 0.8878, 0.5743, 0.4098, 0.4560, 0.5968, 0.5572],
[0.3552, 0.2292, 0.8169, 0.2640, 0.4351, 0.2463, 0.5953, 0.5789],
[0.6208, 0.4168, 0.8051, 0.2661, 0.4353, 0.2119, 0.6514, 0.5384],
[0.5933, 0.4019, 0.8066, 0.2821, 0.4158, 0.2314, 0.5887, 0.5460]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6102, 0.4020, 0.8637, 0.3717, 0.3625, 0.5017, 0.6037, 0.5500],
[0.6207, 0.4081, 0.7663, 0.2067, 0.3963, 0.3200, 0.6313, 0.5300],
[0.6195, 0.4101, 0.8650, 0.3917, 0.3575, 0.4033, 0.5800, 0.5650],
[0.6286, 0.4097, 0.8107, 0.2414, 0.4425, 0.2483, 0.6745, 0.5385],
[0.6226, 0.4185, 0.8850, 0.5500, 0.3800, 0.4250, 0.5625, 0.5617],
[0.0000, 0.0000, 0.8037, 0.2483, 0.3975, 0.2517, 0.5575, 0.5600],
[0.6203, 0.4073, 0.8189, 0.2398, 0.4400, 0.2054, 0.5929, 0.5501],
[0.6204, 0.4049, 0.7975, 0.2700, 0.3938, 0.2567, 0.5700, 0.5183]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0035, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0035, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.038919162820093334
step: 13
running loss: 0.0029937817553917947
Train Steps: 13/90 Loss: 0.0030 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6199, 0.4015, 0.8716, 0.5228, 0.3833, 0.4772, 0.5883, 0.5148],
[0.6257, 0.4060, 0.8300, 0.2333, 0.4688, 0.2583, 0.7050, 0.5633],
[0.6189, 0.4029, 0.8375, 0.5767, 0.4745, 0.4829, 0.5551, 0.5598],
[0.6189, 0.3911, 0.8800, 0.4917, 0.3713, 0.4800, 0.6038, 0.4833],
[0.6129, 0.3930, 0.8769, 0.5105, 0.4146, 0.5642, 0.6000, 0.5082],
[0.6204, 0.4091, 0.8950, 0.4783, 0.3613, 0.4617, 0.6063, 0.5617],
[0.6216, 0.4167, 0.8588, 0.5583, 0.3975, 0.5167, 0.5775, 0.5667],
[0.6250, 0.4054, 0.8770, 0.4723, 0.4662, 0.5367, 0.6162, 0.5433]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6692, 0.4524, 0.8693, 0.4409, 0.3938, 0.4273, 0.6492, 0.5632],
[0.5813, 0.3906, 0.8782, 0.1791, 0.4501, 0.1834, 0.7445, 0.5954],
[0.6371, 0.4335, 0.8636, 0.4553, 0.4532, 0.3713, 0.6627, 0.5859],
[0.6131, 0.4125, 0.8602, 0.4216, 0.3713, 0.4308, 0.6201, 0.5651],
[0.5784, 0.3985, 0.8561, 0.4410, 0.4433, 0.4864, 0.6356, 0.5596],
[0.6493, 0.4302, 0.8929, 0.4087, 0.3751, 0.4351, 0.6520, 0.5835],
[0.6617, 0.4436, 0.8709, 0.4943, 0.4211, 0.4950, 0.6436, 0.5883],
[0.5980, 0.4068, 0.8920, 0.3774, 0.4322, 0.4469, 0.6501, 0.5687]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6199, 0.4015, 0.8716, 0.5228, 0.3833, 0.4772, 0.5883, 0.5148],
[0.6257, 0.4060, 0.8300, 0.2333, 0.4688, 0.2583, 0.7050, 0.5633],
[0.6189, 0.4029, 0.8375, 0.5767, 0.4745, 0.4829, 0.5551, 0.5598],
[0.6189, 0.3911, 0.8800, 0.4917, 0.3713, 0.4800, 0.6037, 0.4833],
[0.6129, 0.3930, 0.8769, 0.5105, 0.4146, 0.5642, 0.6000, 0.5082],
[0.6204, 0.4091, 0.8950, 0.4783, 0.3613, 0.4617, 0.6062, 0.5617],
[0.6216, 0.4167, 0.8587, 0.5583, 0.3975, 0.5167, 0.5775, 0.5667],
[0.6250, 0.4054, 0.8770, 0.4723, 0.4663, 0.5367, 0.6162, 0.5433]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0024, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0024, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04132039553951472
step: 14
running loss: 0.0029514568242510514
Train Steps: 14/90 Loss: 0.0030 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6081, 0.3950, 0.8538, 0.4667, 0.3850, 0.4917, 0.5342, 0.4954],
[0.6200, 0.3993, 0.8639, 0.3687, 0.3658, 0.3139, 0.6002, 0.5374],
[0.6118, 0.4052, 0.8463, 0.3917, 0.3538, 0.3450, 0.5053, 0.5593],
[0.6339, 0.4102, 0.8588, 0.3133, 0.4425, 0.2117, 0.6417, 0.5089],
[0.6198, 0.3997, 0.8582, 0.5361, 0.4117, 0.5016, 0.5942, 0.5134],
[ nan, nan, 0.8900, 0.3217, 0.5038, 0.2233, 0.6694, 0.5609],
[0.6275, 0.4050, 0.9038, 0.3767, 0.3838, 0.3533, 0.7074, 0.5575],
[0.6200, 0.3978, 0.8900, 0.4550, 0.3775, 0.5200, 0.6150, 0.5367]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5942, 0.3891, 0.8576, 0.4474, 0.4046, 0.4978, 0.5956, 0.5803],
[0.6719, 0.4472, 0.8531, 0.3704, 0.3951, 0.3693, 0.6507, 0.5522],
[0.6160, 0.4064, 0.8342, 0.3875, 0.3559, 0.3626, 0.5747, 0.6071],
[0.7079, 0.4728, 0.8355, 0.2891, 0.4455, 0.2665, 0.7089, 0.5726],
[0.6223, 0.4199, 0.8382, 0.5415, 0.4098, 0.5251, 0.6462, 0.5646],
[0.3999, 0.2640, 0.8994, 0.3008, 0.4934, 0.2666, 0.7216, 0.5950],
[0.6839, 0.4563, 0.8921, 0.3541, 0.4058, 0.3401, 0.7596, 0.5681],
[0.6237, 0.4080, 0.8588, 0.4664, 0.3939, 0.5808, 0.6382, 0.6014]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6081, 0.3950, 0.8537, 0.4667, 0.3850, 0.4917, 0.5342, 0.4954],
[0.6200, 0.3993, 0.8639, 0.3687, 0.3658, 0.3139, 0.6002, 0.5374],
[0.6118, 0.4052, 0.8462, 0.3917, 0.3537, 0.3450, 0.5053, 0.5593],
[0.6339, 0.4102, 0.8587, 0.3133, 0.4425, 0.2117, 0.6417, 0.5089],
[0.6198, 0.3997, 0.8582, 0.5361, 0.4117, 0.5016, 0.5942, 0.5134],
[0.0000, 0.0000, 0.8900, 0.3217, 0.5038, 0.2233, 0.6694, 0.5609],
[0.6275, 0.4050, 0.9038, 0.3767, 0.3837, 0.3533, 0.7074, 0.5575],
[0.6199, 0.3978, 0.8900, 0.4550, 0.3775, 0.5200, 0.6150, 0.5367]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0049, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0049, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.046259972150437534
step: 15
running loss: 0.003083998143362502
Train Steps: 15/90 Loss: 0.0031 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6236, 0.4084, 0.7738, 0.2133, 0.3663, 0.3233, 0.5813, 0.5567],
[0.6275, 0.4013, 0.8850, 0.2833, 0.4975, 0.2233, 0.7058, 0.5343],
[0.6205, 0.4012, 0.8675, 0.3283, 0.3713, 0.3050, 0.5813, 0.5117],
[0.6200, 0.3993, 0.8519, 0.4923, 0.3962, 0.4717, 0.6013, 0.5433],
[0.6228, 0.4004, 0.8750, 0.5250, 0.3825, 0.5233, 0.6362, 0.5000],
[ nan, nan, 0.6793, 0.2110, 0.4012, 0.2167, 0.5112, 0.5583],
[0.6271, 0.4020, 0.8375, 0.6083, 0.3925, 0.4867, 0.6037, 0.4626],
[ nan, nan, 0.7725, 0.2611, 0.3675, 0.2733, 0.5413, 0.5167]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6457, 0.4295, 0.8061, 0.3196, 0.3867, 0.3391, 0.6472, 0.5647],
[0.6592, 0.4132, 0.8562, 0.3014, 0.4840, 0.2955, 0.7247, 0.5346],
[0.6431, 0.4059, 0.9184, 0.3719, 0.3832, 0.3503, 0.6498, 0.5410],
[0.6882, 0.4392, 0.8831, 0.5727, 0.3650, 0.5405, 0.6501, 0.5698],
[0.6855, 0.4245, 0.9158, 0.5830, 0.3851, 0.6142, 0.6524, 0.5226],
[0.3411, 0.2191, 0.7176, 0.2231, 0.4243, 0.2191, 0.5480, 0.5725],
[0.6789, 0.4679, 0.8847, 0.6112, 0.3784, 0.5188, 0.6684, 0.5326],
[0.2940, 0.1794, 0.7829, 0.2765, 0.3914, 0.2806, 0.5706, 0.5670]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6236, 0.4084, 0.7738, 0.2133, 0.3663, 0.3233, 0.5813, 0.5567],
[0.6275, 0.4013, 0.8850, 0.2833, 0.4975, 0.2233, 0.7058, 0.5343],
[0.6205, 0.4012, 0.8675, 0.3283, 0.3713, 0.3050, 0.5813, 0.5117],
[0.6200, 0.3993, 0.8519, 0.4923, 0.3963, 0.4717, 0.6012, 0.5433],
[0.6228, 0.4004, 0.8750, 0.5250, 0.3825, 0.5233, 0.6363, 0.5000],
[0.0000, 0.0000, 0.6793, 0.2110, 0.4013, 0.2167, 0.5113, 0.5583],
[0.6271, 0.4020, 0.8375, 0.6083, 0.3925, 0.4867, 0.6037, 0.4626],
[0.0000, 0.0000, 0.7725, 0.2611, 0.3675, 0.2733, 0.5412, 0.5167]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0061, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0061, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05236703611444682
step: 16
running loss: 0.003272939757152926
Train Steps: 16/90 Loss: 0.0033 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6163, 0.4114, 0.7650, 0.2017, 0.3763, 0.2867, 0.5631, 0.5071],
[0.6202, 0.4064, 0.7879, 0.2179, 0.4567, 0.1725, 0.5955, 0.5478],
[0.6296, 0.4060, 0.9100, 0.3267, 0.4726, 0.3367, 0.7446, 0.5355],
[0.6200, 0.4112, 0.8862, 0.4100, 0.3638, 0.4917, 0.6088, 0.6050],
[0.6127, 0.4115, 0.7163, 0.2883, 0.3625, 0.2950, 0.5327, 0.5495],
[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334],
[0.6228, 0.4119, 0.7938, 0.2233, 0.4674, 0.1773, 0.6188, 0.5433],
[0.6055, 0.4015, 0.7425, 0.2033, 0.4113, 0.1883, 0.5217, 0.4823]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5899, 0.3427, 0.7989, 0.3637, 0.3790, 0.3644, 0.6021, 0.5073],
[0.5794, 0.3500, 0.7829, 0.3558, 0.4715, 0.2606, 0.6293, 0.5235],
[0.5524, 0.3206, 0.8937, 0.4374, 0.4395, 0.4080, 0.6941, 0.5116],
[0.5741, 0.3633, 0.9493, 0.5738, 0.3724, 0.6298, 0.6568, 0.5525],
[0.5215, 0.3038, 0.7782, 0.3703, 0.3806, 0.3965, 0.5499, 0.5504],
[0.6112, 0.3637, 0.8144, 0.3356, 0.3792, 0.4078, 0.6076, 0.5224],
[0.5639, 0.3496, 0.8526, 0.3172, 0.4734, 0.2581, 0.6480, 0.5238],
[0.4399, 0.2583, 0.7541, 0.2975, 0.3986, 0.2429, 0.5493, 0.5150]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6163, 0.4114, 0.7650, 0.2017, 0.3762, 0.2867, 0.5631, 0.5071],
[0.6202, 0.4064, 0.7879, 0.2179, 0.4567, 0.1725, 0.5955, 0.5478],
[0.6296, 0.4060, 0.9100, 0.3267, 0.4726, 0.3367, 0.7446, 0.5355],
[0.6200, 0.4112, 0.8863, 0.4100, 0.3638, 0.4917, 0.6087, 0.6050],
[0.6127, 0.4114, 0.7163, 0.2883, 0.3625, 0.2950, 0.5327, 0.5495],
[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334],
[0.6228, 0.4119, 0.7937, 0.2233, 0.4674, 0.1773, 0.6187, 0.5433],
[0.6055, 0.4015, 0.7425, 0.2033, 0.4112, 0.1883, 0.5217, 0.4823]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0050, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0050, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.057400591555051506
step: 17
running loss: 0.003376505385591265
Train Steps: 17/90 Loss: 0.0034 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6209, 0.3920, 0.8650, 0.5367, 0.4400, 0.5067, 0.6025, 0.4950],
[0.6149, 0.4054, 0.6713, 0.2333, 0.4025, 0.2017, 0.5213, 0.5695],
[0.6131, 0.4037, 0.6907, 0.2819, 0.3688, 0.2700, 0.5217, 0.5680],
[ nan, nan, 0.6469, 0.1943, 0.4025, 0.2000, 0.5125, 0.5533],
[0.6109, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117],
[0.6239, 0.4174, 0.8425, 0.5733, 0.4825, 0.4500, 0.5625, 0.5933],
[0.6136, 0.4029, 0.8263, 0.3350, 0.3625, 0.3067, 0.5675, 0.5167],
[0.6279, 0.4050, 0.8025, 0.2200, 0.4313, 0.2733, 0.6820, 0.5320]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5694, 0.3072, 0.9180, 0.5808, 0.4260, 0.5578, 0.5957, 0.4780],
[0.4657, 0.2800, 0.7147, 0.2770, 0.4011, 0.2651, 0.5142, 0.5039],
[0.5343, 0.2985, 0.7305, 0.2937, 0.3831, 0.3645, 0.5357, 0.5165],
[0.3305, 0.1637, 0.7213, 0.2061, 0.4155, 0.2128, 0.5293, 0.5100],
[0.5894, 0.3573, 0.9104, 0.5207, 0.3549, 0.4583, 0.5722, 0.4644],
[0.6676, 0.4207, 0.8576, 0.6183, 0.4383, 0.4724, 0.6427, 0.5154],
[0.5665, 0.3570, 0.8540, 0.3346, 0.3749, 0.3530, 0.5816, 0.4958],
[0.5989, 0.3703, 0.8312, 0.2364, 0.4190, 0.3152, 0.6319, 0.4938]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6209, 0.3920, 0.8650, 0.5367, 0.4400, 0.5067, 0.6025, 0.4950],
[0.6149, 0.4054, 0.6712, 0.2333, 0.4025, 0.2017, 0.5213, 0.5695],
[0.6131, 0.4036, 0.6907, 0.2819, 0.3688, 0.2700, 0.5217, 0.5680],
[0.0000, 0.0000, 0.6469, 0.1943, 0.4025, 0.2000, 0.5125, 0.5533],
[0.6108, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117],
[0.6239, 0.4174, 0.8425, 0.5733, 0.4825, 0.4500, 0.5625, 0.5933],
[0.6136, 0.4029, 0.8263, 0.3350, 0.3625, 0.3067, 0.5675, 0.5167],
[0.6279, 0.4050, 0.8025, 0.2200, 0.4313, 0.2733, 0.6820, 0.5320]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0045, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0045, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06192554801236838
step: 18
running loss: 0.0034403082229093546
Train Steps: 18/90 Loss: 0.0034 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6196, 0.4068, 0.7645, 0.2234, 0.4575, 0.1737, 0.5926, 0.5284],
[0.6076, 0.3953, 0.8125, 0.3917, 0.3525, 0.4083, 0.5346, 0.4954],
[0.6161, 0.4099, 0.8738, 0.4383, 0.3788, 0.5483, 0.5605, 0.5019],
[0.6282, 0.4092, 0.8000, 0.2183, 0.4500, 0.2383, 0.6787, 0.5364],
[0.6185, 0.4129, 0.8900, 0.4567, 0.3937, 0.5417, 0.5734, 0.5110],
[0.6227, 0.4083, 0.8938, 0.4800, 0.3800, 0.2950, 0.5737, 0.5350],
[0.6275, 0.4024, 0.8500, 0.5383, 0.3912, 0.4883, 0.6288, 0.5100],
[0.6201, 0.4027, 0.8029, 0.2728, 0.4042, 0.2310, 0.5980, 0.5391]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5125, 0.2871, 0.7511, 0.2094, 0.4505, 0.1997, 0.5630, 0.4911],
[0.4933, 0.3047, 0.8090, 0.3301, 0.3396, 0.3870, 0.5353, 0.5002],
[0.5513, 0.3362, 0.8229, 0.4283, 0.3745, 0.5247, 0.5657, 0.4955],
[0.5318, 0.3230, 0.7729, 0.2162, 0.4420, 0.2273, 0.6116, 0.5084],
[0.5149, 0.2947, 0.9065, 0.5164, 0.4007, 0.5175, 0.5539, 0.5059],
[0.6284, 0.3912, 0.8496, 0.4788, 0.4001, 0.3236, 0.5528, 0.5050],
[0.5536, 0.3453, 0.8191, 0.5324, 0.3937, 0.4933, 0.5993, 0.4796],
[0.5261, 0.3023, 0.7768, 0.2523, 0.4267, 0.2545, 0.5609, 0.4950]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6196, 0.4068, 0.7645, 0.2234, 0.4575, 0.1737, 0.5926, 0.5284],
[0.6076, 0.3952, 0.8125, 0.3917, 0.3525, 0.4083, 0.5346, 0.4954],
[0.6161, 0.4099, 0.8737, 0.4383, 0.3787, 0.5483, 0.5605, 0.5019],
[0.6282, 0.4092, 0.8000, 0.2183, 0.4500, 0.2383, 0.6787, 0.5364],
[0.6186, 0.4129, 0.8900, 0.4567, 0.3938, 0.5417, 0.5734, 0.5110],
[0.6227, 0.4083, 0.8938, 0.4800, 0.3800, 0.2950, 0.5738, 0.5350],
[0.6275, 0.4024, 0.8500, 0.5383, 0.3913, 0.4883, 0.6288, 0.5100],
[0.6201, 0.4027, 0.8029, 0.2728, 0.4042, 0.2310, 0.5980, 0.5391]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0025, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0025, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0644436435541138
step: 19
running loss: 0.003391770713374411
Train Steps: 19/90 Loss: 0.0034 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6197, 0.4090, 0.7825, 0.2500, 0.4200, 0.2483, 0.5988, 0.5667],
[0.6339, 0.4123, 0.8638, 0.5367, 0.4075, 0.5467, 0.7517, 0.5436],
[0.6200, 0.3993, 0.8519, 0.4923, 0.3962, 0.4717, 0.6013, 0.5433],
[0.6196, 0.4090, 0.8450, 0.3900, 0.3575, 0.3933, 0.5975, 0.5583],
[0.6129, 0.4114, 0.6950, 0.2467, 0.4050, 0.2133, 0.5363, 0.5550],
[0.6300, 0.4102, 0.9088, 0.4433, 0.4088, 0.3067, 0.6820, 0.5540],
[0.6260, 0.4161, 0.9000, 0.3833, 0.4450, 0.2133, 0.6237, 0.4986],
[0.6097, 0.3988, 0.8650, 0.5250, 0.4213, 0.5200, 0.5675, 0.5050]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5718, 0.3611, 0.7569, 0.1923, 0.4113, 0.2334, 0.5492, 0.5280],
[0.5646, 0.3674, 0.8176, 0.4881, 0.4099, 0.5417, 0.6300, 0.5248],
[0.5698, 0.3466, 0.8024, 0.4662, 0.3711, 0.4423, 0.5449, 0.5125],
[0.6244, 0.3827, 0.8229, 0.3401, 0.3483, 0.3685, 0.5368, 0.5160],
[0.5406, 0.3454, 0.6538, 0.2001, 0.3887, 0.2130, 0.4810, 0.4885],
[0.5050, 0.3236, 0.8718, 0.3897, 0.4116, 0.2701, 0.5983, 0.4890],
[0.4879, 0.3313, 0.8646, 0.3113, 0.4415, 0.2104, 0.6023, 0.4683],
[0.5498, 0.3600, 0.8173, 0.4844, 0.4335, 0.4855, 0.4931, 0.4710]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6197, 0.4090, 0.7825, 0.2500, 0.4200, 0.2483, 0.5987, 0.5667],
[0.6339, 0.4123, 0.8637, 0.5367, 0.4075, 0.5467, 0.7517, 0.5436],
[0.6200, 0.3993, 0.8519, 0.4923, 0.3963, 0.4717, 0.6012, 0.5433],
[0.6196, 0.4090, 0.8450, 0.3900, 0.3575, 0.3933, 0.5975, 0.5583],
[0.6129, 0.4114, 0.6950, 0.2467, 0.4050, 0.2133, 0.5362, 0.5550],
[0.6300, 0.4102, 0.9087, 0.4433, 0.4087, 0.3067, 0.6820, 0.5540],
[0.6260, 0.4161, 0.9000, 0.3833, 0.4450, 0.2133, 0.6237, 0.4986],
[0.6097, 0.3988, 0.8650, 0.5250, 0.4212, 0.5200, 0.5675, 0.5050]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0027, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0027, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06718559598084539
step: 20
running loss: 0.0033592797990422696
Train Steps: 20/90 Loss: 0.0034 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6193, 0.4165, 0.8838, 0.4700, 0.4150, 0.4867, 0.5427, 0.5261],
[0.6179, 0.4118, 0.7278, 0.4237, 0.3588, 0.3400, 0.5675, 0.5917],
[0.6109, 0.3943, 0.8525, 0.4950, 0.4338, 0.4800, 0.5449, 0.5383],
[0.6226, 0.4001, 0.8438, 0.5733, 0.3862, 0.4250, 0.5750, 0.5283],
[0.6168, 0.4081, 0.8438, 0.3367, 0.3500, 0.4667, 0.6212, 0.5400],
[ nan, nan, 0.7648, 0.2722, 0.3962, 0.2183, 0.5060, 0.5422],
[0.6268, 0.4029, 0.8500, 0.2683, 0.3937, 0.3500, 0.6860, 0.5297],
[0.6101, 0.3977, 0.8550, 0.5667, 0.3862, 0.4417, 0.5128, 0.4869]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5591, 0.3825, 0.8259, 0.4147, 0.4141, 0.3745, 0.5544, 0.5147],
[0.5839, 0.4089, 0.7758, 0.2976, 0.3758, 0.2668, 0.5041, 0.5495],
[0.5310, 0.3788, 0.8315, 0.4217, 0.4207, 0.3984, 0.5459, 0.5369],
[0.6807, 0.4494, 0.8215, 0.5131, 0.3843, 0.3442, 0.5462, 0.5332],
[0.5852, 0.4040, 0.8322, 0.2623, 0.3493, 0.4323, 0.6110, 0.5552],
[0.3095, 0.2227, 0.7204, 0.1732, 0.4180, 0.1595, 0.4772, 0.5234],
[0.6958, 0.4777, 0.7973, 0.2119, 0.3881, 0.2798, 0.6438, 0.5153],
[0.5824, 0.4102, 0.8456, 0.4937, 0.4169, 0.3476, 0.5649, 0.5045]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6193, 0.4165, 0.8838, 0.4700, 0.4150, 0.4867, 0.5427, 0.5261],
[0.6179, 0.4118, 0.7278, 0.4237, 0.3587, 0.3400, 0.5675, 0.5917],
[0.6109, 0.3943, 0.8525, 0.4950, 0.4338, 0.4800, 0.5449, 0.5383],
[0.6226, 0.4001, 0.8438, 0.5733, 0.3862, 0.4250, 0.5750, 0.5283],
[0.6168, 0.4081, 0.8438, 0.3367, 0.3500, 0.4667, 0.6212, 0.5400],
[0.0000, 0.0000, 0.7648, 0.2722, 0.3963, 0.2183, 0.5060, 0.5422],
[0.6268, 0.4029, 0.8500, 0.2683, 0.3938, 0.3500, 0.6860, 0.5297],
[0.6101, 0.3977, 0.8550, 0.5667, 0.3862, 0.4417, 0.5128, 0.4869]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0048, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0048, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07193988130893558
step: 21
running loss: 0.0034257086337588375
Train Steps: 21/90 Loss: 0.0034 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6148, 0.4076, 0.8666, 0.4820, 0.4138, 0.5067, 0.5250, 0.5767],
[0.6265, 0.4071, 0.8875, 0.3367, 0.3975, 0.3350, 0.6312, 0.5250],
[0.6059, 0.4002, 0.7562, 0.2767, 0.3538, 0.3033, 0.5529, 0.5455],
[0.6280, 0.4101, 0.9050, 0.4533, 0.3775, 0.3217, 0.6338, 0.4915],
[0.6138, 0.4054, 0.8750, 0.4750, 0.4363, 0.5017, 0.5086, 0.5822],
[0.6329, 0.4175, 0.8550, 0.2333, 0.5425, 0.2250, 0.7398, 0.5609],
[ nan, nan, 0.7512, 0.2117, 0.4288, 0.2000, 0.5600, 0.5617],
[0.6098, 0.3991, 0.8638, 0.4717, 0.4263, 0.4967, 0.5212, 0.5650]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6355, 0.4614, 0.8250, 0.4840, 0.3991, 0.4634, 0.5587, 0.5688],
[0.5501, 0.3784, 0.8598, 0.2704, 0.3954, 0.2741, 0.6230, 0.5681],
[0.6268, 0.4654, 0.7134, 0.2568, 0.3502, 0.2695, 0.5437, 0.5430],
[0.6804, 0.4713, 0.8506, 0.4430, 0.3397, 0.2755, 0.5728, 0.5126],
[0.5909, 0.4225, 0.8107, 0.4818, 0.3905, 0.4480, 0.5322, 0.5546],
[0.5062, 0.3929, 0.8450, 0.2082, 0.5034, 0.1870, 0.6914, 0.5587],
[0.3170, 0.2427, 0.7268, 0.1864, 0.4102, 0.1592, 0.4986, 0.5714],
[0.5695, 0.4248, 0.7992, 0.4864, 0.3944, 0.4476, 0.5511, 0.5406]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6148, 0.4076, 0.8666, 0.4820, 0.4137, 0.5067, 0.5250, 0.5767],
[0.6265, 0.4071, 0.8875, 0.3367, 0.3975, 0.3350, 0.6313, 0.5250],
[0.6059, 0.4002, 0.7563, 0.2767, 0.3537, 0.3033, 0.5529, 0.5455],
[0.6280, 0.4101, 0.9050, 0.4533, 0.3775, 0.3217, 0.6338, 0.4915],
[0.6138, 0.4054, 0.8750, 0.4750, 0.4363, 0.5017, 0.5086, 0.5822],
[0.6329, 0.4175, 0.8550, 0.2333, 0.5425, 0.2250, 0.7398, 0.5609],
[0.0000, 0.0000, 0.7513, 0.2117, 0.4288, 0.2000, 0.5600, 0.5617],
[0.6098, 0.3991, 0.8637, 0.4717, 0.4263, 0.4967, 0.5213, 0.5650]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0041, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0041, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07605478435289115
step: 22
running loss: 0.003457035652404143
Train Steps: 22/90 Loss: 0.0035 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6300, 0.4133, 0.8538, 0.2167, 0.5587, 0.2250, 0.7390, 0.5413],
[0.6122, 0.4048, 0.7506, 0.3014, 0.3475, 0.3333, 0.5487, 0.5749],
[0.6346, 0.4086, 0.7938, 0.5500, 0.3962, 0.4867, 0.7343, 0.5702],
[0.6292, 0.4010, 0.8988, 0.4800, 0.3638, 0.3817, 0.6357, 0.5051],
[0.6265, 0.4251, 0.7113, 0.3550, 0.4375, 0.2117, 0.5587, 0.6118],
[0.6206, 0.4001, 0.8900, 0.3933, 0.3588, 0.3567, 0.5837, 0.5083],
[0.6197, 0.4091, 0.8800, 0.4783, 0.3538, 0.4767, 0.5950, 0.5550],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4578, 0.3519, 0.8790, 0.2221, 0.5106, 0.2299, 0.6964, 0.5784],
[0.5498, 0.3720, 0.7646, 0.2784, 0.3612, 0.3090, 0.5244, 0.5695],
[0.6279, 0.4609, 0.8070, 0.5108, 0.3879, 0.4680, 0.6271, 0.5730],
[0.6880, 0.4932, 0.8739, 0.4629, 0.3677, 0.3500, 0.5938, 0.5400],
[0.5222, 0.4169, 0.7394, 0.2919, 0.3977, 0.2462, 0.5193, 0.6034],
[0.6170, 0.4211, 0.8745, 0.3801, 0.3498, 0.3347, 0.5682, 0.5492],
[0.6112, 0.4401, 0.8528, 0.4759, 0.3710, 0.4550, 0.5889, 0.5859],
[0.5333, 0.4033, 0.8534, 0.3997, 0.4135, 0.4587, 0.5547, 0.5614]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6300, 0.4133, 0.8537, 0.2167, 0.5587, 0.2250, 0.7390, 0.5413],
[0.6122, 0.4048, 0.7506, 0.3014, 0.3475, 0.3333, 0.5487, 0.5749],
[0.6346, 0.4086, 0.7937, 0.5500, 0.3963, 0.4867, 0.7343, 0.5702],
[0.6292, 0.4010, 0.8988, 0.4800, 0.3638, 0.3817, 0.6357, 0.5051],
[0.6265, 0.4251, 0.7113, 0.3550, 0.4375, 0.2117, 0.5587, 0.6118],
[0.6206, 0.4001, 0.8900, 0.3933, 0.3587, 0.3567, 0.5838, 0.5083],
[0.6197, 0.4091, 0.8800, 0.4783, 0.3537, 0.4767, 0.5950, 0.5550],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07791255612391979
step: 23
running loss: 0.0033875024401704254
Train Steps: 23/90 Loss: 0.0034 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6125, 0.4035, 0.7825, 0.3100, 0.3463, 0.4900, 0.5832, 0.5637],
[0.6137, 0.4038, 0.8563, 0.4050, 0.3813, 0.2550, 0.5106, 0.4954],
[0.6261, 0.4066, 0.8325, 0.2150, 0.4763, 0.2667, 0.7002, 0.5633],
[0.6272, 0.4120, 0.9038, 0.4117, 0.3725, 0.3200, 0.6175, 0.5250],
[0.6267, 0.4080, 0.8438, 0.2633, 0.4763, 0.1800, 0.6259, 0.5240],
[ nan, nan, 0.8850, 0.2817, 0.5112, 0.2183, 0.7184, 0.5436],
[0.6307, 0.4029, 0.8988, 0.4817, 0.3937, 0.3500, 0.7311, 0.5378],
[0.6069, 0.3975, 0.8625, 0.5083, 0.4388, 0.5483, 0.5650, 0.4967]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5630, 0.4143, 0.7481, 0.3400, 0.3264, 0.4892, 0.5747, 0.5941],
[0.5112, 0.3690, 0.7888, 0.3976, 0.3908, 0.2515, 0.4968, 0.5846],
[0.5933, 0.4247, 0.7916, 0.2289, 0.4429, 0.2337, 0.6436, 0.6058],
[0.6395, 0.4488, 0.8615, 0.4161, 0.3459, 0.3268, 0.5817, 0.5449],
[0.5625, 0.4243, 0.8189, 0.2745, 0.4324, 0.2153, 0.5916, 0.5724],
[0.4407, 0.3259, 0.8781, 0.2678, 0.4856, 0.2394, 0.6811, 0.5764],
[0.6495, 0.4705, 0.8612, 0.4888, 0.3962, 0.3317, 0.6322, 0.5577],
[0.6276, 0.4688, 0.8113, 0.5343, 0.4078, 0.5237, 0.5561, 0.6000]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6125, 0.4035, 0.7825, 0.3100, 0.3462, 0.4900, 0.5832, 0.5637],
[0.6137, 0.4038, 0.8562, 0.4050, 0.3812, 0.2550, 0.5106, 0.4954],
[0.6261, 0.4066, 0.8325, 0.2150, 0.4762, 0.2667, 0.7002, 0.5633],
[0.6272, 0.4120, 0.9038, 0.4117, 0.3725, 0.3200, 0.6175, 0.5250],
[0.6267, 0.4080, 0.8438, 0.2633, 0.4762, 0.1800, 0.6259, 0.5240],
[0.0000, 0.0000, 0.8850, 0.2817, 0.5113, 0.2183, 0.7184, 0.5436],
[0.6307, 0.4029, 0.8988, 0.4817, 0.3938, 0.3500, 0.7311, 0.5378],
[0.6069, 0.3975, 0.8625, 0.5083, 0.4387, 0.5483, 0.5650, 0.4967]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0063, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0063, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.08417737309355289
step: 24
running loss: 0.0035073905455647036
Train Steps: 24/90 Loss: 0.0035 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.8213, 0.2700, 0.3775, 0.2817, 0.5425, 0.5533],
[0.6272, 0.4120, 0.9038, 0.4117, 0.3725, 0.3200, 0.6175, 0.5250],
[0.6346, 0.4092, 0.7712, 0.5917, 0.4037, 0.4767, 0.7343, 0.5725],
[0.6175, 0.3997, 0.6737, 0.2500, 0.4313, 0.1933, 0.5513, 0.5750],
[0.6271, 0.4081, 0.9081, 0.4894, 0.3700, 0.4283, 0.6661, 0.5274],
[0.6133, 0.4094, 0.8495, 0.4028, 0.3588, 0.3200, 0.5003, 0.5407],
[0.6075, 0.4007, 0.8275, 0.4917, 0.4050, 0.5100, 0.5167, 0.5280],
[0.6223, 0.4171, 0.8750, 0.5500, 0.4050, 0.4817, 0.5675, 0.5600]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.3853, 0.2412, 0.7946, 0.2664, 0.3667, 0.2621, 0.5691, 0.5883],
[0.6728, 0.4472, 0.9294, 0.3902, 0.3840, 0.3261, 0.6674, 0.5337],
[0.6466, 0.4458, 0.8176, 0.4990, 0.4050, 0.4815, 0.6699, 0.6091],
[0.2990, 0.2104, 0.7380, 0.1906, 0.4629, 0.1769, 0.5771, 0.6129],
[0.6577, 0.4726, 0.9106, 0.4686, 0.3657, 0.4160, 0.6843, 0.5803],
[0.5791, 0.3975, 0.8685, 0.3931, 0.3932, 0.3091, 0.5628, 0.5776],
[0.6461, 0.4384, 0.8341, 0.4709, 0.4037, 0.5106, 0.6007, 0.5653],
[0.7838, 0.5244, 0.8995, 0.5693, 0.4290, 0.5269, 0.6741, 0.5730]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.8213, 0.2700, 0.3775, 0.2817, 0.5425, 0.5533],
[0.6272, 0.4120, 0.9038, 0.4117, 0.3725, 0.3200, 0.6175, 0.5250],
[0.6346, 0.4092, 0.7713, 0.5917, 0.4038, 0.4767, 0.7343, 0.5725],
[0.6175, 0.3997, 0.6737, 0.2500, 0.4313, 0.1933, 0.5512, 0.5750],
[0.6271, 0.4081, 0.9081, 0.4894, 0.3700, 0.4283, 0.6661, 0.5274],
[0.6133, 0.4094, 0.8495, 0.4028, 0.3587, 0.3200, 0.5003, 0.5407],
[0.6075, 0.4006, 0.8275, 0.4917, 0.4050, 0.5100, 0.5167, 0.5280],
[0.6223, 0.4171, 0.8750, 0.5500, 0.4050, 0.4817, 0.5675, 0.5600]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0073, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0073, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.09143890452105552
step: 25
running loss: 0.0036575561808422207
Train Steps: 25/90 Loss: 0.0037 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6145, 0.4007, 0.8775, 0.4533, 0.4562, 0.5533, 0.6088, 0.5533],
[0.6339, 0.4123, 0.8638, 0.5367, 0.4075, 0.5467, 0.7517, 0.5436],
[0.6254, 0.3993, 0.8988, 0.4767, 0.3987, 0.5517, 0.6955, 0.5285],
[0.6186, 0.4154, 0.6825, 0.2633, 0.4150, 0.2300, 0.5713, 0.5517],
[0.6339, 0.4102, 0.8588, 0.3133, 0.4425, 0.2117, 0.6417, 0.5089],
[0.6154, 0.4112, 0.7037, 0.2317, 0.4238, 0.1833, 0.5350, 0.5600],
[0.6265, 0.4088, 0.8025, 0.1850, 0.4163, 0.2500, 0.6290, 0.4947],
[0.6118, 0.4052, 0.8463, 0.3917, 0.3538, 0.3450, 0.5053, 0.5593]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6105, 0.3962, 0.8903, 0.5136, 0.4423, 0.5345, 0.6518, 0.5574],
[0.7116, 0.4549, 0.8984, 0.5937, 0.4033, 0.5888, 0.7316, 0.5672],
[0.7130, 0.4386, 0.9326, 0.5597, 0.3984, 0.5887, 0.6999, 0.5537],
[0.4522, 0.2795, 0.7579, 0.2800, 0.4087, 0.2454, 0.5992, 0.5730],
[0.6696, 0.4300, 0.9044, 0.3524, 0.4478, 0.2530, 0.6978, 0.5384],
[0.4153, 0.2761, 0.7562, 0.2718, 0.4272, 0.2038, 0.5829, 0.5567],
[0.4782, 0.3126, 0.8689, 0.2631, 0.4484, 0.2345, 0.6533, 0.5612],
[0.6062, 0.3808, 0.8682, 0.4297, 0.3464, 0.3637, 0.5453, 0.5646]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6145, 0.4007, 0.8775, 0.4533, 0.4563, 0.5533, 0.6087, 0.5533],
[0.6339, 0.4123, 0.8637, 0.5367, 0.4075, 0.5467, 0.7517, 0.5436],
[0.6254, 0.3993, 0.8988, 0.4767, 0.3988, 0.5517, 0.6955, 0.5285],
[0.6186, 0.4154, 0.6825, 0.2633, 0.4150, 0.2300, 0.5713, 0.5517],
[0.6339, 0.4102, 0.8587, 0.3133, 0.4425, 0.2117, 0.6417, 0.5089],
[0.6154, 0.4112, 0.7038, 0.2317, 0.4238, 0.1833, 0.5350, 0.5600],
[0.6265, 0.4088, 0.8025, 0.1850, 0.4162, 0.2500, 0.6290, 0.4947],
[0.6118, 0.4052, 0.8462, 0.3917, 0.3537, 0.3450, 0.5053, 0.5593]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0035, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0035, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.09492857556324452
step: 26
running loss: 0.0036510990601247894
Train Steps: 26/90 Loss: 0.0037 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6339, 0.4149, 0.8800, 0.5000, 0.3900, 0.5283, 0.7541, 0.5424],
[ nan, nan, 0.7335, 0.2569, 0.3788, 0.2667, 0.5066, 0.5578],
[0.6252, 0.4158, 0.8988, 0.4083, 0.3788, 0.4783, 0.6225, 0.5633],
[0.6268, 0.4094, 0.9038, 0.4300, 0.3700, 0.3483, 0.6262, 0.5167],
[0.6250, 0.4116, 0.8700, 0.4850, 0.4650, 0.5567, 0.6088, 0.5183],
[0.6138, 0.4020, 0.8800, 0.4717, 0.4375, 0.4717, 0.5502, 0.5611],
[0.6159, 0.4085, 0.6900, 0.2283, 0.4088, 0.1950, 0.5123, 0.5397],
[0.6141, 0.4038, 0.8650, 0.4833, 0.4839, 0.5176, 0.5787, 0.5600]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7710, 0.4596, 0.9157, 0.5361, 0.3850, 0.5504, 0.7209, 0.5340],
[0.1755, 0.0911, 0.7831, 0.2816, 0.4241, 0.2348, 0.5595, 0.5750],
[0.6858, 0.4413, 0.8724, 0.4188, 0.3791, 0.4858, 0.6770, 0.5232],
[0.6731, 0.4134, 0.9235, 0.4454, 0.3964, 0.3642, 0.6883, 0.5083],
[0.6874, 0.3868, 0.9253, 0.4927, 0.4442, 0.5354, 0.6994, 0.5263],
[0.6664, 0.3893, 0.8907, 0.4971, 0.4151, 0.4613, 0.6301, 0.5303],
[0.4252, 0.2396, 0.7291, 0.2757, 0.4188, 0.1851, 0.5661, 0.5395],
[0.6321, 0.3918, 0.8892, 0.5291, 0.4634, 0.4708, 0.6284, 0.5273]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6339, 0.4149, 0.8800, 0.5000, 0.3900, 0.5283, 0.7541, 0.5424],
[0.0000, 0.0000, 0.7335, 0.2569, 0.3787, 0.2667, 0.5066, 0.5578],
[0.6252, 0.4158, 0.8988, 0.4083, 0.3787, 0.4783, 0.6225, 0.5633],
[0.6268, 0.4094, 0.9038, 0.4300, 0.3700, 0.3483, 0.6263, 0.5167],
[0.6251, 0.4116, 0.8700, 0.4850, 0.4650, 0.5567, 0.6087, 0.5183],
[0.6138, 0.4020, 0.8800, 0.4717, 0.4375, 0.4717, 0.5502, 0.5611],
[0.6159, 0.4085, 0.6900, 0.2283, 0.4087, 0.1950, 0.5123, 0.5397],
[0.6141, 0.4038, 0.8650, 0.4833, 0.4839, 0.5176, 0.5788, 0.5600]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0031, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0031, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.09805791999679059
step: 27
running loss: 0.003631774814695948
Train Steps: 27/90 Loss: 0.0036 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6168, 0.4081, 0.8438, 0.3367, 0.3500, 0.4667, 0.6212, 0.5400],
[0.6182, 0.3967, 0.8263, 0.3065, 0.3526, 0.4161, 0.6192, 0.5290],
[0.6175, 0.4013, 0.7734, 0.2783, 0.4475, 0.1786, 0.5790, 0.5351],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5413, 0.5683],
[0.6311, 0.3998, 0.7975, 0.5767, 0.3838, 0.4850, 0.7327, 0.5343],
[0.6229, 0.4066, 0.7612, 0.2967, 0.4250, 0.2167, 0.5925, 0.5350],
[0.6305, 0.3983, 0.8950, 0.4833, 0.3688, 0.4683, 0.6375, 0.5117],
[0.6127, 0.4119, 0.8650, 0.5300, 0.4512, 0.5250, 0.5260, 0.5461]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5901, 0.3425, 0.8881, 0.3529, 0.3891, 0.5200, 0.6666, 0.5400],
[0.6469, 0.3587, 0.8641, 0.3298, 0.3718, 0.4317, 0.6578, 0.5125],
[0.4706, 0.2787, 0.8005, 0.2850, 0.4421, 0.2119, 0.6169, 0.5088],
[0.7143, 0.4069, 0.8990, 0.5666, 0.3859, 0.4117, 0.5918, 0.5235],
[0.5770, 0.3445, 0.8539, 0.5257, 0.4015, 0.4867, 0.6826, 0.5029],
[0.6092, 0.3633, 0.8144, 0.3106, 0.4484, 0.2981, 0.6340, 0.5114],
[0.6334, 0.3657, 0.9173, 0.5061, 0.3971, 0.5020, 0.6485, 0.4940],
[0.6372, 0.3549, 0.8855, 0.5803, 0.4888, 0.5151, 0.5938, 0.5249]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6168, 0.4081, 0.8438, 0.3367, 0.3500, 0.4667, 0.6212, 0.5400],
[0.6182, 0.3967, 0.8263, 0.3065, 0.3526, 0.4161, 0.6192, 0.5290],
[0.6175, 0.4013, 0.7734, 0.2783, 0.4475, 0.1786, 0.5790, 0.5351],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5412, 0.5683],
[0.6311, 0.3998, 0.7975, 0.5767, 0.3837, 0.4850, 0.7327, 0.5343],
[0.6229, 0.4066, 0.7613, 0.2967, 0.4250, 0.2167, 0.5925, 0.5350],
[0.6305, 0.3983, 0.8950, 0.4833, 0.3688, 0.4683, 0.6375, 0.5117],
[0.6127, 0.4119, 0.8650, 0.5300, 0.4512, 0.5250, 0.5260, 0.5461]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0020, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0020, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.1000079937512055
step: 28
running loss: 0.0035717140625430538
Train Steps: 28/90 Loss: 0.0036 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6239, 0.4206, 0.8750, 0.5400, 0.3688, 0.4850, 0.5737, 0.5700],
[0.6080, 0.4010, 0.8750, 0.4500, 0.4825, 0.5617, 0.5837, 0.5583],
[ nan, nan, 0.9088, 0.3783, 0.4562, 0.2617, 0.6741, 0.5575],
[0.6277, 0.4118, 0.8988, 0.3833, 0.3950, 0.2650, 0.6290, 0.4938],
[0.6226, 0.4098, 0.8912, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367],
[0.6272, 0.4071, 0.8738, 0.5600, 0.3675, 0.3783, 0.5926, 0.4742],
[0.6102, 0.3999, 0.8750, 0.5133, 0.3825, 0.4750, 0.5637, 0.5083],
[0.6022, 0.3994, 0.8025, 0.3350, 0.3350, 0.4400, 0.5565, 0.5025]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7127, 0.4073, 0.8357, 0.5393, 0.4057, 0.5256, 0.6161, 0.5145],
[0.5640, 0.3250, 0.8582, 0.3967, 0.4815, 0.4831, 0.5866, 0.5296],
[0.4414, 0.2499, 0.8859, 0.3510, 0.4725, 0.3156, 0.6743, 0.5210],
[0.5667, 0.3196, 0.8532, 0.3744, 0.4023, 0.2934, 0.6232, 0.5004],
[0.5504, 0.3089, 0.8489, 0.3942, 0.4237, 0.3078, 0.5773, 0.4963],
[0.7316, 0.4151, 0.8370, 0.5199, 0.3864, 0.4018, 0.6152, 0.4532],
[0.6351, 0.3639, 0.8403, 0.4770, 0.4038, 0.4873, 0.5663, 0.4826],
[0.5848, 0.3555, 0.7833, 0.3287, 0.3813, 0.4267, 0.5954, 0.5164]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6239, 0.4206, 0.8750, 0.5400, 0.3688, 0.4850, 0.5738, 0.5700],
[0.6080, 0.4010, 0.8750, 0.4500, 0.4825, 0.5617, 0.5838, 0.5583],
[0.0000, 0.0000, 0.9087, 0.3783, 0.4563, 0.2617, 0.6741, 0.5575],
[0.6277, 0.4117, 0.8988, 0.3833, 0.3950, 0.2650, 0.6290, 0.4938],
[0.6226, 0.4098, 0.8913, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367],
[0.6272, 0.4071, 0.8737, 0.5600, 0.3675, 0.3783, 0.5926, 0.4742],
[0.6102, 0.3999, 0.8750, 0.5133, 0.3825, 0.4750, 0.5638, 0.5083],
[0.6022, 0.3994, 0.8025, 0.3350, 0.3350, 0.4400, 0.5565, 0.5025]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0057, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0057, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.10573010763619095
step: 29
running loss: 0.003645865780558309
Train Steps: 29/90 Loss: 0.0036 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6134, 0.4090, 0.6926, 0.2819, 0.3538, 0.3233, 0.5563, 0.5667],
[0.6161, 0.4099, 0.8738, 0.4383, 0.3788, 0.5483, 0.5605, 0.5019],
[0.6109, 0.3943, 0.8525, 0.4950, 0.4338, 0.4800, 0.5449, 0.5383],
[0.6129, 0.4069, 0.8750, 0.5067, 0.3875, 0.4233, 0.5235, 0.5881],
[0.6127, 0.4115, 0.7163, 0.2883, 0.3625, 0.2950, 0.5327, 0.5495],
[0.6085, 0.4008, 0.8588, 0.5200, 0.4959, 0.4977, 0.5175, 0.5283],
[ nan, nan, 0.9088, 0.3783, 0.4562, 0.2617, 0.6741, 0.5575],
[0.6201, 0.4036, 0.8596, 0.3850, 0.3492, 0.3785, 0.5978, 0.5131]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5710, 0.3733, 0.7081, 0.3260, 0.3558, 0.3593, 0.5647, 0.5183],
[0.6567, 0.4062, 0.8642, 0.4450, 0.4036, 0.5435, 0.6240, 0.4872],
[0.5467, 0.3397, 0.8757, 0.5004, 0.4346, 0.4875, 0.5935, 0.5118],
[0.6675, 0.4063, 0.8734, 0.5478, 0.3892, 0.4632, 0.5665, 0.5052],
[0.5614, 0.3626, 0.7455, 0.3123, 0.3859, 0.3185, 0.5494, 0.5276],
[0.6181, 0.3625, 0.8679, 0.5189, 0.4946, 0.4535, 0.6002, 0.4781],
[0.4248, 0.2752, 0.9296, 0.4028, 0.4848, 0.3101, 0.6864, 0.5216],
[0.6556, 0.4074, 0.8741, 0.4087, 0.3746, 0.4201, 0.6057, 0.4803]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6134, 0.4090, 0.6926, 0.2819, 0.3537, 0.3233, 0.5562, 0.5667],
[0.6161, 0.4099, 0.8737, 0.4383, 0.3787, 0.5483, 0.5605, 0.5019],
[0.6109, 0.3943, 0.8525, 0.4950, 0.4338, 0.4800, 0.5449, 0.5383],
[0.6129, 0.4069, 0.8750, 0.5067, 0.3875, 0.4233, 0.5235, 0.5881],
[0.6127, 0.4114, 0.7163, 0.2883, 0.3625, 0.2950, 0.5327, 0.5495],
[0.6084, 0.4008, 0.8587, 0.5200, 0.4959, 0.4977, 0.5175, 0.5283],
[0.0000, 0.0000, 0.9087, 0.3783, 0.4563, 0.2617, 0.6741, 0.5575],
[0.6201, 0.4036, 0.8596, 0.3850, 0.3492, 0.3785, 0.5978, 0.5131]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0052, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0052, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.11088850733358413
step: 30
running loss: 0.003696283577786138
Train Steps: 30/90 Loss: 0.0037 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6082, 0.4024, 0.8738, 0.4017, 0.3688, 0.3950, 0.5306, 0.5136],
[ nan, nan, 0.7268, 0.2333, 0.4125, 0.1933, 0.5112, 0.5383],
[ nan, nan, 0.6469, 0.1943, 0.4025, 0.2000, 0.5125, 0.5533],
[0.6110, 0.3984, 0.8750, 0.4933, 0.4625, 0.4950, 0.5578, 0.5676],
[0.6102, 0.3999, 0.8750, 0.5133, 0.3825, 0.4750, 0.5637, 0.5083],
[0.6175, 0.3997, 0.6737, 0.2500, 0.4313, 0.1933, 0.5513, 0.5750],
[ nan, nan, 0.6859, 0.2194, 0.4150, 0.1867, 0.5153, 0.5729],
[0.6332, 0.4165, 0.9100, 0.3350, 0.4188, 0.3683, 0.7438, 0.5528]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5922, 0.4017, 0.8713, 0.4405, 0.3612, 0.4238, 0.5184, 0.5151],
[0.3582, 0.2298, 0.7556, 0.3063, 0.4014, 0.2411, 0.5185, 0.5444],
[0.2946, 0.1886, 0.7170, 0.2601, 0.4136, 0.2340, 0.5188, 0.5606],
[0.7030, 0.4408, 0.9341, 0.5412, 0.4614, 0.5772, 0.5865, 0.5240],
[0.7953, 0.5029, 0.9016, 0.5643, 0.3886, 0.5612, 0.5478, 0.4993],
[0.5802, 0.3809, 0.7125, 0.2922, 0.4219, 0.2625, 0.5282, 0.5478],
[0.3664, 0.2401, 0.7380, 0.2883, 0.4304, 0.2344, 0.5059, 0.5507],
[0.6292, 0.4025, 0.9526, 0.4345, 0.4087, 0.4079, 0.6802, 0.5200]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6082, 0.4024, 0.8737, 0.4017, 0.3688, 0.3950, 0.5306, 0.5136],
[0.0000, 0.0000, 0.7268, 0.2333, 0.4125, 0.1933, 0.5113, 0.5383],
[0.0000, 0.0000, 0.6469, 0.1943, 0.4025, 0.2000, 0.5125, 0.5533],
[0.6110, 0.3984, 0.8750, 0.4933, 0.4625, 0.4950, 0.5578, 0.5676],
[0.6102, 0.3999, 0.8750, 0.5133, 0.3825, 0.4750, 0.5638, 0.5083],
[0.6175, 0.3997, 0.6737, 0.2500, 0.4313, 0.1933, 0.5512, 0.5750],
[0.0000, 0.0000, 0.6859, 0.2194, 0.4150, 0.1867, 0.5153, 0.5729],
[0.6332, 0.4165, 0.9100, 0.3350, 0.4187, 0.3683, 0.7438, 0.5528]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0100, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0100, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.12087913427967578
step: 31
running loss: 0.003899326912247606
Train Steps: 31/90 Loss: 0.0039 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758],
[0.6126, 0.4073, 0.8750, 0.5133, 0.3800, 0.4333, 0.4986, 0.5378],
[0.6230, 0.4152, 0.7588, 0.2283, 0.4012, 0.2883, 0.6200, 0.5767],
[0.6198, 0.4076, 0.7945, 0.2453, 0.4475, 0.1871, 0.5897, 0.5350],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3788, 0.4900, 0.7121, 0.5864],
[0.6214, 0.4175, 0.7300, 0.2883, 0.4338, 0.2167, 0.5698, 0.5773],
[0.6234, 0.4023, 0.8888, 0.4633, 0.3975, 0.5767, 0.6400, 0.5183],
[0.6183, 0.4076, 0.8838, 0.4517, 0.3813, 0.4483, 0.5775, 0.5633]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4806, 0.2998, 0.8918, 0.4452, 0.4107, 0.5104, 0.5396, 0.5420],
[0.4820, 0.3437, 0.8743, 0.5086, 0.3730, 0.4249, 0.5120, 0.5413],
[0.4814, 0.3564, 0.7628, 0.3216, 0.4086, 0.2817, 0.5722, 0.5560],
[0.5544, 0.3869, 0.7628, 0.2905, 0.4290, 0.2236, 0.5466, 0.5370],
[0.4566, 0.3315, 0.8674, 0.4907, 0.3861, 0.4601, 0.6026, 0.5633],
[0.5705, 0.4234, 0.7099, 0.3097, 0.3921, 0.2522, 0.5098, 0.5591],
[0.5269, 0.3574, 0.8905, 0.4368, 0.4251, 0.5545, 0.5447, 0.5600],
[0.4295, 0.2856, 0.8784, 0.4406, 0.3848, 0.4491, 0.5455, 0.5579]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758],
[0.6126, 0.4073, 0.8750, 0.5133, 0.3800, 0.4333, 0.4986, 0.5378],
[0.6230, 0.4152, 0.7588, 0.2283, 0.4013, 0.2883, 0.6200, 0.5767],
[0.6198, 0.4076, 0.7945, 0.2453, 0.4475, 0.1871, 0.5897, 0.5350],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3787, 0.4900, 0.7121, 0.5864],
[0.6214, 0.4175, 0.7300, 0.2883, 0.4338, 0.2167, 0.5698, 0.5773],
[0.6234, 0.4023, 0.8888, 0.4633, 0.3975, 0.5767, 0.6400, 0.5183],
[0.6183, 0.4076, 0.8838, 0.4517, 0.3812, 0.4483, 0.5775, 0.5633]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0040, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0040, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.12484196957666427
step: 32
running loss: 0.0039013115492707584
Train Steps: 32/90 Loss: 0.0039 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6140, 0.4070, 0.8700, 0.5000, 0.4612, 0.4900, 0.5260, 0.5852],
[0.6147, 0.4026, 0.6600, 0.2467, 0.4088, 0.2150, 0.5489, 0.5773],
[0.6186, 0.4013, 0.8191, 0.3188, 0.4279, 0.2060, 0.5767, 0.5411],
[0.6224, 0.4097, 0.7438, 0.2267, 0.3850, 0.2850, 0.5988, 0.5250],
[0.6265, 0.4071, 0.8875, 0.3367, 0.3975, 0.3350, 0.6312, 0.5250],
[0.6353, 0.4128, 0.8488, 0.2600, 0.5525, 0.1616, 0.6694, 0.5540],
[0.6058, 0.3978, 0.8287, 0.3600, 0.3400, 0.4050, 0.5529, 0.5461],
[ nan, nan, 0.8675, 0.2833, 0.5350, 0.1983, 0.6678, 0.5621]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5385, 0.3726, 0.8863, 0.5260, 0.4290, 0.5047, 0.5160, 0.5818],
[0.6499, 0.4474, 0.6659, 0.2844, 0.3601, 0.2414, 0.4926, 0.5716],
[0.4714, 0.3264, 0.7618, 0.3114, 0.3952, 0.2498, 0.5081, 0.5671],
[0.6327, 0.4728, 0.7146, 0.2756, 0.3698, 0.3003, 0.5684, 0.5530],
[0.5012, 0.3294, 0.8662, 0.3438, 0.3913, 0.3386, 0.5953, 0.5621],
[0.1845, 0.1296, 0.8389, 0.2707, 0.5110, 0.2170, 0.5929, 0.5841],
[0.6692, 0.4743, 0.8151, 0.3947, 0.3312, 0.4365, 0.5337, 0.5487],
[0.0382, 0.0638, 0.8499, 0.2784, 0.4862, 0.1974, 0.5803, 0.5828]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6140, 0.4070, 0.8700, 0.5000, 0.4613, 0.4900, 0.5260, 0.5852],
[0.6147, 0.4026, 0.6600, 0.2467, 0.4087, 0.2150, 0.5489, 0.5773],
[0.6186, 0.4013, 0.8191, 0.3188, 0.4279, 0.2060, 0.5767, 0.5411],
[0.6224, 0.4097, 0.7437, 0.2267, 0.3850, 0.2850, 0.5987, 0.5250],
[0.6265, 0.4071, 0.8875, 0.3367, 0.3975, 0.3350, 0.6313, 0.5250],
[0.6353, 0.4128, 0.8487, 0.2600, 0.5525, 0.1616, 0.6694, 0.5540],
[0.6058, 0.3978, 0.8288, 0.3600, 0.3400, 0.4050, 0.5529, 0.5461],
[0.0000, 0.0000, 0.8675, 0.2833, 0.5350, 0.1983, 0.6678, 0.5621]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0065, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0065, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.1313714758725837
step: 33
running loss: 0.003980953814320717
Train Steps: 33/90 Loss: 0.0040 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.8888, 0.3100, 0.5262, 0.2817, 0.7145, 0.6003],
[0.6170, 0.4102, 0.7468, 0.3695, 0.3463, 0.3767, 0.5238, 0.5823],
[0.6104, 0.4029, 0.8738, 0.4900, 0.4088, 0.4533, 0.5070, 0.5510],
[0.6136, 0.4085, 0.6688, 0.2317, 0.3862, 0.2367, 0.5517, 0.5783],
[0.6090, 0.4045, 0.7250, 0.2100, 0.4075, 0.2300, 0.5476, 0.5663],
[0.6300, 0.4102, 0.9088, 0.4433, 0.4088, 0.3067, 0.6820, 0.5540],
[0.6286, 0.4274, 0.8500, 0.4500, 0.4525, 0.2583, 0.5440, 0.6209],
[0.6361, 0.4076, 0.8862, 0.5350, 0.3713, 0.4650, 0.6654, 0.5297]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.2869, 0.1952, 0.8825, 0.2657, 0.4910, 0.2325, 0.6424, 0.5585],
[0.5847, 0.4135, 0.7391, 0.3092, 0.3318, 0.3839, 0.5174, 0.6051],
[0.5349, 0.3649, 0.8738, 0.4602, 0.4067, 0.4506, 0.5075, 0.5688],
[0.5407, 0.3837, 0.6720, 0.2071, 0.3599, 0.2307, 0.5037, 0.5578],
[0.3352, 0.2542, 0.6870, 0.2115, 0.3747, 0.2059, 0.5195, 0.5942],
[0.4570, 0.3381, 0.8863, 0.4052, 0.4083, 0.2791, 0.6182, 0.5715],
[0.4635, 0.3456, 0.8060, 0.3912, 0.4406, 0.2866, 0.5146, 0.6138],
[0.6070, 0.4359, 0.8601, 0.5168, 0.3663, 0.4816, 0.6266, 0.5784]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.8888, 0.3100, 0.5263, 0.2817, 0.7145, 0.6003],
[0.6170, 0.4102, 0.7468, 0.3695, 0.3462, 0.3767, 0.5238, 0.5823],
[0.6104, 0.4029, 0.8737, 0.4900, 0.4087, 0.4533, 0.5070, 0.5510],
[0.6136, 0.4085, 0.6687, 0.2317, 0.3862, 0.2367, 0.5517, 0.5783],
[0.6090, 0.4045, 0.7250, 0.2100, 0.4075, 0.2300, 0.5476, 0.5663],
[0.6300, 0.4102, 0.9087, 0.4433, 0.4087, 0.3067, 0.6820, 0.5540],
[0.6286, 0.4274, 0.8500, 0.4500, 0.4525, 0.2583, 0.5440, 0.6209],
[0.6361, 0.4076, 0.8863, 0.5350, 0.3713, 0.4650, 0.6654, 0.5297]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0055, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0055, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.1368311574915424
step: 34
running loss: 0.004024445808574776
Train Steps: 34/90 Loss: 0.0040 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6142, 0.4127, 0.7575, 0.3067, 0.3438, 0.4383, 0.5778, 0.5207],
[0.6219, 0.3934, 0.8688, 0.5267, 0.4313, 0.4967, 0.5988, 0.4983],
[0.6310, 0.4017, 0.8563, 0.5800, 0.3688, 0.4750, 0.6326, 0.5006],
[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758],
[0.6124, 0.4083, 0.6954, 0.3069, 0.3650, 0.2750, 0.5163, 0.5485],
[0.6053, 0.4035, 0.6897, 0.1916, 0.4000, 0.2117, 0.5440, 0.5168],
[0.6197, 0.4050, 0.7527, 0.2000, 0.4042, 0.2249, 0.5895, 0.4995],
[0.6131, 0.4064, 0.8638, 0.5200, 0.4788, 0.4783, 0.5258, 0.5867]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4963, 0.3862, 0.7514, 0.2513, 0.3589, 0.3394, 0.5619, 0.5993],
[0.4562, 0.3419, 0.8819, 0.4533, 0.4124, 0.4145, 0.5854, 0.5761],
[0.6197, 0.4237, 0.8685, 0.5307, 0.3926, 0.4467, 0.5880, 0.6016],
[0.5460, 0.3521, 0.9146, 0.4189, 0.4082, 0.4825, 0.5842, 0.5735],
[0.5055, 0.3693, 0.7325, 0.2684, 0.3590, 0.2630, 0.5277, 0.6086],
[0.3609, 0.2583, 0.6952, 0.1869, 0.4173, 0.1355, 0.5613, 0.5715],
[0.5359, 0.4054, 0.7737, 0.1995, 0.4128, 0.1637, 0.6384, 0.5586],
[0.5642, 0.3956, 0.8697, 0.4497, 0.4499, 0.4201, 0.6075, 0.5898]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6142, 0.4127, 0.7575, 0.3067, 0.3438, 0.4383, 0.5778, 0.5207],
[0.6219, 0.3934, 0.8687, 0.5267, 0.4313, 0.4967, 0.5987, 0.4983],
[0.6310, 0.4017, 0.8562, 0.5800, 0.3688, 0.4750, 0.6326, 0.5006],
[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758],
[0.6123, 0.4083, 0.6954, 0.3069, 0.3650, 0.2750, 0.5163, 0.5485],
[0.6054, 0.4035, 0.6897, 0.1916, 0.4000, 0.2117, 0.5440, 0.5168],
[0.6197, 0.4050, 0.7527, 0.2000, 0.4042, 0.2249, 0.5895, 0.4995],
[0.6132, 0.4063, 0.8637, 0.5200, 0.4787, 0.4783, 0.5258, 0.5867]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0043, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0043, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.14112150168512017
step: 35
running loss: 0.004032042905289148
Train Steps: 35/90 Loss: 0.0040 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6169, 0.4108, 0.6821, 0.2722, 0.3825, 0.2550, 0.5550, 0.5717],
[0.6329, 0.4175, 0.8550, 0.2333, 0.5425, 0.2250, 0.7398, 0.5609],
[0.6038, 0.3946, 0.8413, 0.4883, 0.3563, 0.4550, 0.5266, 0.4693],
[0.6257, 0.4034, 0.8287, 0.2333, 0.3925, 0.2717, 0.6330, 0.4901],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3513, 0.4050, 0.6112, 0.5500],
[0.6142, 0.4127, 0.7575, 0.3067, 0.3438, 0.4383, 0.5778, 0.5207],
[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459],
[ nan, nan, 0.7192, 0.2346, 0.4037, 0.2050, 0.5138, 0.5650]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4819, 0.3458, 0.6869, 0.2910, 0.3688, 0.2382, 0.5282, 0.5730],
[0.5417, 0.3932, 0.8482, 0.2817, 0.5320, 0.2175, 0.7606, 0.5362],
[0.6417, 0.4459, 0.8624, 0.4964, 0.3670, 0.4702, 0.5220, 0.5442],
[0.6376, 0.4358, 0.8091, 0.2879, 0.3997, 0.2430, 0.6488, 0.5202],
[0.6563, 0.4553, 0.7634, 0.2758, 0.3470, 0.3813, 0.6249, 0.5541],
[0.5801, 0.4157, 0.7382, 0.2946, 0.3624, 0.3834, 0.5646, 0.5530],
[0.5191, 0.3747, 0.8364, 0.2815, 0.5005, 0.2101, 0.6680, 0.5510],
[0.2037, 0.1414, 0.7333, 0.2334, 0.4252, 0.2144, 0.5101, 0.5678]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6169, 0.4108, 0.6821, 0.2722, 0.3825, 0.2550, 0.5550, 0.5717],
[0.6329, 0.4175, 0.8550, 0.2333, 0.5425, 0.2250, 0.7398, 0.5609],
[0.6038, 0.3946, 0.8413, 0.4883, 0.3562, 0.4550, 0.5266, 0.4693],
[0.6257, 0.4034, 0.8288, 0.2333, 0.3925, 0.2717, 0.6330, 0.4901],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3512, 0.4050, 0.6112, 0.5500],
[0.6142, 0.4127, 0.7575, 0.3067, 0.3438, 0.4383, 0.5778, 0.5207],
[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459],
[0.0000, 0.0000, 0.7192, 0.2346, 0.4038, 0.2050, 0.5138, 0.5650]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0022, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0022, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.14336391224060208
step: 36
running loss: 0.00398233089557228
Train Steps: 36/90 Loss: 0.0040 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6157, 0.3956, 0.8323, 0.4138, 0.3479, 0.4431, 0.5914, 0.5131],
[0.6274, 0.4117, 0.8100, 0.5801, 0.4000, 0.4583, 0.5582, 0.6118],
[0.6073, 0.3932, 0.8363, 0.5817, 0.4425, 0.5117, 0.5204, 0.4817],
[0.6304, 0.4029, 0.8413, 0.5217, 0.4125, 0.5617, 0.7089, 0.5679],
[0.6081, 0.3950, 0.8538, 0.4667, 0.3850, 0.4917, 0.5342, 0.4954],
[0.6329, 0.4196, 0.9238, 0.4583, 0.4263, 0.2933, 0.7343, 0.5748],
[0.6240, 0.4217, 0.8150, 0.3133, 0.4425, 0.2650, 0.5650, 0.5817],
[0.6177, 0.4086, 0.8738, 0.3950, 0.3775, 0.5600, 0.6225, 0.5700]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7228, 0.4681, 0.7525, 0.3056, 0.3635, 0.3611, 0.5924, 0.4883],
[0.6475, 0.4415, 0.7789, 0.4468, 0.3754, 0.3749, 0.5925, 0.5845],
[0.5587, 0.3827, 0.8006, 0.4904, 0.4415, 0.3936, 0.5719, 0.4867],
[0.4817, 0.3434, 0.8249, 0.4164, 0.4155, 0.4739, 0.6631, 0.5691],
[0.5975, 0.3980, 0.8270, 0.3494, 0.3865, 0.3966, 0.5595, 0.4871],
[0.5687, 0.3749, 0.8677, 0.3652, 0.4322, 0.1858, 0.6998, 0.4778],
[0.4849, 0.3461, 0.7653, 0.2249, 0.4421, 0.1733, 0.6068, 0.5384],
[0.5811, 0.3800, 0.8053, 0.2997, 0.3964, 0.4467, 0.6727, 0.5288]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6157, 0.3956, 0.8323, 0.4138, 0.3479, 0.4431, 0.5914, 0.5131],
[0.6274, 0.4117, 0.8100, 0.5801, 0.4000, 0.4583, 0.5582, 0.6118],
[0.6073, 0.3932, 0.8363, 0.5817, 0.4425, 0.5117, 0.5204, 0.4817],
[0.6304, 0.4029, 0.8413, 0.5217, 0.4125, 0.5617, 0.7089, 0.5679],
[0.6081, 0.3950, 0.8537, 0.4667, 0.3850, 0.4917, 0.5342, 0.4954],
[0.6329, 0.4196, 0.9237, 0.4583, 0.4263, 0.2933, 0.7343, 0.5748],
[0.6240, 0.4217, 0.8150, 0.3133, 0.4425, 0.2650, 0.5650, 0.5817],
[0.6177, 0.4085, 0.8737, 0.3950, 0.3775, 0.5600, 0.6225, 0.5700]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0046, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0046, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.14793575985822827
step: 37
running loss: 0.003998263779952115
Train Steps: 37/90 Loss: 0.0040 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6138, 0.4020, 0.8800, 0.4717, 0.4375, 0.4717, 0.5502, 0.5611],
[0.6250, 0.4131, 0.8688, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367],
[0.6263, 0.4039, 0.9000, 0.4400, 0.3625, 0.4667, 0.6424, 0.4804],
[0.6170, 0.4102, 0.7468, 0.3695, 0.3463, 0.3767, 0.5238, 0.5823],
[0.6201, 0.4017, 0.8871, 0.4621, 0.3517, 0.4675, 0.5999, 0.5106],
[0.6273, 0.4110, 0.8900, 0.3817, 0.4188, 0.2167, 0.5858, 0.4835],
[0.6143, 0.4034, 0.8800, 0.4833, 0.4512, 0.5367, 0.5289, 0.5097],
[0.6205, 0.4062, 0.8337, 0.2683, 0.3675, 0.4283, 0.6338, 0.5250]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5927, 0.3793, 0.8371, 0.4345, 0.4220, 0.4288, 0.6075, 0.5332],
[0.6252, 0.3783, 0.8342, 0.2596, 0.4505, 0.2143, 0.6791, 0.5136],
[0.6643, 0.4283, 0.8630, 0.4127, 0.3536, 0.4288, 0.6292, 0.4873],
[0.6172, 0.4089, 0.7182, 0.3220, 0.3551, 0.3615, 0.5789, 0.5728],
[0.6835, 0.4250, 0.7887, 0.4249, 0.3495, 0.4700, 0.5967, 0.5164],
[0.6390, 0.4108, 0.8453, 0.3511, 0.4372, 0.1673, 0.6323, 0.4891],
[0.5556, 0.3422, 0.8279, 0.4370, 0.4475, 0.4216, 0.5880, 0.5037],
[0.6281, 0.4205, 0.7479, 0.2551, 0.3832, 0.3778, 0.6559, 0.5277]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6138, 0.4020, 0.8800, 0.4717, 0.4375, 0.4717, 0.5502, 0.5611],
[0.6250, 0.4131, 0.8687, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367],
[0.6263, 0.4038, 0.9000, 0.4400, 0.3625, 0.4667, 0.6424, 0.4804],
[0.6170, 0.4102, 0.7468, 0.3695, 0.3462, 0.3767, 0.5238, 0.5823],
[0.6201, 0.4017, 0.8871, 0.4621, 0.3517, 0.4675, 0.5999, 0.5106],
[0.6273, 0.4110, 0.8900, 0.3817, 0.4187, 0.2167, 0.5858, 0.4835],
[0.6143, 0.4034, 0.8800, 0.4833, 0.4512, 0.5367, 0.5289, 0.5097],
[0.6205, 0.4062, 0.8338, 0.2683, 0.3675, 0.4283, 0.6338, 0.5250]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.1494324274826795
step: 38
running loss: 0.003932432302175776
Train Steps: 38/90 Loss: 0.0039 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6058, 0.3986, 0.8324, 0.4626, 0.3838, 0.4983, 0.5147, 0.5466],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3788, 0.4900, 0.7121, 0.5864],
[0.6129, 0.3925, 0.8720, 0.5246, 0.4534, 0.5515, 0.6026, 0.5114],
[0.6182, 0.4058, 0.8738, 0.4350, 0.3563, 0.3400, 0.5290, 0.5822],
[0.6034, 0.4011, 0.7350, 0.2533, 0.3438, 0.3367, 0.5516, 0.5084],
[0.6286, 0.4034, 0.8191, 0.2414, 0.4262, 0.2393, 0.6365, 0.5356],
[0.6098, 0.3991, 0.8638, 0.4717, 0.4263, 0.4967, 0.5212, 0.5650],
[0.6197, 0.3930, 0.8793, 0.4736, 0.4152, 0.5464, 0.6308, 0.5235]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6082, 0.3901, 0.8104, 0.4446, 0.3821, 0.4699, 0.5674, 0.5060],
[0.6610, 0.4154, 0.8537, 0.5049, 0.3697, 0.4719, 0.6829, 0.5151],
[0.6313, 0.4098, 0.8679, 0.4890, 0.4500, 0.4796, 0.6458, 0.4985],
[0.6464, 0.4064, 0.8509, 0.4027, 0.3388, 0.3724, 0.5377, 0.5235],
[0.7227, 0.4560, 0.6997, 0.2580, 0.3332, 0.3190, 0.5898, 0.4940],
[0.6985, 0.4387, 0.7837, 0.2486, 0.4359, 0.2209, 0.6642, 0.5135],
[0.6163, 0.3792, 0.8439, 0.4967, 0.4222, 0.4776, 0.5871, 0.5058],
[0.6270, 0.3982, 0.8587, 0.4695, 0.4115, 0.5075, 0.6632, 0.5138]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6058, 0.3986, 0.8324, 0.4626, 0.3837, 0.4983, 0.5147, 0.5466],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3787, 0.4900, 0.7121, 0.5864],
[0.6129, 0.3925, 0.8720, 0.5246, 0.4534, 0.5515, 0.6026, 0.5114],
[0.6182, 0.4058, 0.8737, 0.4350, 0.3562, 0.3400, 0.5290, 0.5822],
[0.6033, 0.4011, 0.7350, 0.2533, 0.3438, 0.3367, 0.5516, 0.5084],
[0.6286, 0.4034, 0.8191, 0.2414, 0.4262, 0.2393, 0.6365, 0.5356],
[0.6098, 0.3991, 0.8637, 0.4717, 0.4263, 0.4967, 0.5213, 0.5650],
[0.6197, 0.3930, 0.8793, 0.4736, 0.4152, 0.5464, 0.6308, 0.5235]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.1505707015749067
step: 39
running loss: 0.0038607872198694027
Train Steps: 39/90 Loss: 0.0039 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6219, 0.4097, 0.8738, 0.3400, 0.3563, 0.4117, 0.5975, 0.5683],
[0.6166, 0.4008, 0.8563, 0.5667, 0.4388, 0.4933, 0.5575, 0.5567],
[0.6198, 0.4115, 0.7762, 0.2717, 0.3713, 0.3200, 0.5837, 0.5683],
[0.6257, 0.4034, 0.8287, 0.2333, 0.3925, 0.2717, 0.6330, 0.4901],
[0.6195, 0.4101, 0.8650, 0.3917, 0.3575, 0.4033, 0.5800, 0.5650],
[0.6257, 0.4167, 0.8775, 0.3433, 0.3563, 0.4133, 0.6200, 0.5667],
[0.6307, 0.4029, 0.8988, 0.4817, 0.3937, 0.3500, 0.7311, 0.5378],
[0.6280, 0.4101, 0.9050, 0.4533, 0.3775, 0.3217, 0.6338, 0.4915]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6763, 0.4203, 0.8212, 0.3882, 0.3392, 0.4437, 0.5854, 0.5210],
[0.5837, 0.3779, 0.8425, 0.5387, 0.4452, 0.5220, 0.5871, 0.5394],
[0.6857, 0.4187, 0.7855, 0.3141, 0.3728, 0.3482, 0.5546, 0.5442],
[0.6829, 0.4323, 0.7807, 0.3014, 0.3951, 0.3038, 0.6372, 0.4918],
[0.6924, 0.4353, 0.8441, 0.4242, 0.3433, 0.4517, 0.5365, 0.5052],
[0.6510, 0.3992, 0.8452, 0.3819, 0.3662, 0.4419, 0.6248, 0.5265],
[0.6469, 0.4096, 0.8938, 0.4680, 0.4248, 0.3783, 0.6646, 0.4929],
[0.7247, 0.4555, 0.8720, 0.4785, 0.3858, 0.3604, 0.6007, 0.4724]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6219, 0.4097, 0.8737, 0.3400, 0.3562, 0.4117, 0.5975, 0.5683],
[0.6166, 0.4008, 0.8562, 0.5667, 0.4387, 0.4933, 0.5575, 0.5567],
[0.6198, 0.4115, 0.7763, 0.2717, 0.3713, 0.3200, 0.5838, 0.5683],
[0.6257, 0.4034, 0.8288, 0.2333, 0.3925, 0.2717, 0.6330, 0.4901],
[0.6195, 0.4101, 0.8650, 0.3917, 0.3575, 0.4033, 0.5800, 0.5650],
[0.6257, 0.4167, 0.8775, 0.3433, 0.3562, 0.4133, 0.6200, 0.5667],
[0.6307, 0.4029, 0.8988, 0.4817, 0.3938, 0.3500, 0.7311, 0.5378],
[0.6280, 0.4101, 0.9050, 0.4533, 0.3775, 0.3217, 0.6338, 0.4915]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.15187458659056574
step: 40
running loss: 0.0037968646647641435
Train Steps: 40/90 Loss: 0.0038 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6201, 0.4055, 0.7717, 0.1919, 0.4250, 0.2079, 0.5871, 0.5044],
[0.6108, 0.4011, 0.8037, 0.3400, 0.3700, 0.2933, 0.5658, 0.5617],
[0.6148, 0.3996, 0.8488, 0.3867, 0.3488, 0.4067, 0.5863, 0.5000],
[0.6179, 0.4082, 0.6688, 0.2667, 0.3588, 0.3317, 0.5750, 0.5783],
[0.6261, 0.3987, 0.8688, 0.4917, 0.4300, 0.5333, 0.7010, 0.5309],
[0.6317, 0.4038, 0.8287, 0.5900, 0.3800, 0.4717, 0.6295, 0.4986],
[ nan, nan, 0.9050, 0.3500, 0.5138, 0.2300, 0.7359, 0.5702],
[0.6055, 0.4015, 0.7425, 0.2033, 0.4113, 0.1883, 0.5217, 0.4823]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7187, 0.4657, 0.8306, 0.2767, 0.4167, 0.2786, 0.6047, 0.5362],
[0.6980, 0.4498, 0.8665, 0.3995, 0.3762, 0.4197, 0.5474, 0.5448],
[0.6695, 0.4380, 0.9158, 0.4737, 0.3652, 0.5028, 0.6096, 0.5110],
[0.7887, 0.4816, 0.7583, 0.3533, 0.3352, 0.4078, 0.5599, 0.5510],
[0.6274, 0.4131, 0.9500, 0.5838, 0.4386, 0.6303, 0.6465, 0.5380],
[0.7863, 0.5082, 0.9138, 0.6277, 0.3542, 0.5731, 0.5936, 0.5166],
[0.5299, 0.3224, 0.9347, 0.3950, 0.4768, 0.3456, 0.6791, 0.5457],
[0.6023, 0.3797, 0.7298, 0.2535, 0.3751, 0.2667, 0.5376, 0.5283]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6202, 0.4055, 0.7717, 0.1919, 0.4250, 0.2079, 0.5871, 0.5044],
[0.6108, 0.4011, 0.8037, 0.3400, 0.3700, 0.2933, 0.5658, 0.5617],
[0.6148, 0.3996, 0.8487, 0.3867, 0.3487, 0.4067, 0.5863, 0.5000],
[0.6179, 0.4082, 0.6687, 0.2667, 0.3587, 0.3317, 0.5750, 0.5783],
[0.6261, 0.3987, 0.8687, 0.4917, 0.4300, 0.5333, 0.7010, 0.5309],
[0.6317, 0.4038, 0.8288, 0.5900, 0.3800, 0.4717, 0.6295, 0.4986],
[0.0000, 0.0000, 0.9050, 0.3500, 0.5138, 0.2300, 0.7359, 0.5702],
[0.6055, 0.4015, 0.7425, 0.2033, 0.4112, 0.1883, 0.5217, 0.4823]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0102, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0102, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.16205621568951756
step: 41
running loss: 0.003952590626573599
Train Steps: 41/90 Loss: 0.0040 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6092, 0.4001, 0.8638, 0.4867, 0.4288, 0.5367, 0.5484, 0.5064],
[0.6263, 0.4065, 0.9038, 0.4317, 0.3588, 0.4550, 0.6325, 0.5250],
[0.6261, 0.4131, 0.8938, 0.3550, 0.4000, 0.2683, 0.6188, 0.5283],
[0.6147, 0.4107, 0.8137, 0.3333, 0.3750, 0.2683, 0.5006, 0.5412],
[0.6350, 0.4118, 0.8363, 0.2717, 0.4850, 0.1700, 0.6441, 0.5170],
[0.6109, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117],
[0.6143, 0.4040, 0.8237, 0.3333, 0.4075, 0.2117, 0.5137, 0.4973],
[0.6196, 0.4068, 0.7645, 0.2234, 0.4575, 0.1737, 0.5926, 0.5284]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6168, 0.3942, 0.8755, 0.5418, 0.4090, 0.6057, 0.5533, 0.5243],
[0.6289, 0.3965, 0.9262, 0.4993, 0.3608, 0.5306, 0.6536, 0.5308],
[0.7041, 0.4402, 0.9332, 0.4216, 0.4070, 0.3354, 0.6179, 0.5408],
[0.5029, 0.3301, 0.8102, 0.3966, 0.3733, 0.3770, 0.5184, 0.5792],
[0.6606, 0.4101, 0.8494, 0.2925, 0.4726, 0.2737, 0.6511, 0.5564],
[0.7221, 0.4742, 0.8928, 0.5254, 0.3563, 0.5033, 0.5423, 0.5139],
[0.5314, 0.3336, 0.8073, 0.3495, 0.4271, 0.3116, 0.5455, 0.5472],
[0.6883, 0.4347, 0.7809, 0.2945, 0.4331, 0.2745, 0.5999, 0.5528]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6092, 0.4001, 0.8637, 0.4867, 0.4288, 0.5367, 0.5484, 0.5064],
[0.6263, 0.4065, 0.9038, 0.4317, 0.3587, 0.4550, 0.6325, 0.5250],
[0.6261, 0.4131, 0.8938, 0.3550, 0.4000, 0.2683, 0.6187, 0.5283],
[0.6147, 0.4107, 0.8138, 0.3333, 0.3750, 0.2683, 0.5006, 0.5412],
[0.6350, 0.4118, 0.8363, 0.2717, 0.4850, 0.1700, 0.6441, 0.5170],
[0.6108, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117],
[0.6143, 0.4040, 0.8238, 0.3333, 0.4075, 0.2117, 0.5137, 0.4973],
[0.6196, 0.4068, 0.7645, 0.2234, 0.4575, 0.1737, 0.5926, 0.5284]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0026, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0026, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.16464617906603962
step: 42
running loss: 0.003920147120619991
Train Steps: 42/90 Loss: 0.0039 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6161, 0.4024, 0.8662, 0.4683, 0.4935, 0.5364, 0.6063, 0.5567],
[0.6260, 0.4120, 0.8013, 0.2350, 0.4888, 0.1533, 0.6281, 0.4895],
[0.6307, 0.4029, 0.8988, 0.4817, 0.3937, 0.3500, 0.7311, 0.5378],
[ nan, nan, 0.7225, 0.2167, 0.3987, 0.2283, 0.5427, 0.5181],
[0.6125, 0.3983, 0.8750, 0.4867, 0.4275, 0.4783, 0.5413, 0.5717],
[0.6321, 0.4048, 0.8738, 0.5617, 0.3875, 0.4417, 0.6361, 0.4927],
[0.6277, 0.4057, 0.8300, 0.2650, 0.4363, 0.1850, 0.6140, 0.4823],
[0.6113, 0.4104, 0.8650, 0.4250, 0.3925, 0.5967, 0.5787, 0.5116]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5914, 0.3750, 0.9267, 0.4842, 0.4291, 0.5331, 0.5822, 0.5713],
[0.6727, 0.4229, 0.8425, 0.2422, 0.4783, 0.1994, 0.6245, 0.5530],
[0.6520, 0.4122, 0.9716, 0.4921, 0.4072, 0.3805, 0.6626, 0.5454],
[0.4037, 0.2400, 0.7607, 0.2332, 0.4031, 0.2527, 0.5299, 0.5721],
[0.6678, 0.4063, 0.9150, 0.5728, 0.4048, 0.5287, 0.5675, 0.5446],
[0.7441, 0.4790, 0.9230, 0.5637, 0.3632, 0.5035, 0.5689, 0.5169],
[0.6529, 0.4008, 0.8589, 0.2868, 0.4395, 0.2580, 0.6256, 0.5510],
[0.5707, 0.3659, 0.9312, 0.4682, 0.4123, 0.6192, 0.5800, 0.5642]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6161, 0.4024, 0.8662, 0.4683, 0.4935, 0.5364, 0.6062, 0.5567],
[0.6259, 0.4120, 0.8012, 0.2350, 0.4888, 0.1533, 0.6281, 0.4895],
[0.6307, 0.4029, 0.8988, 0.4817, 0.3938, 0.3500, 0.7311, 0.5378],
[0.0000, 0.0000, 0.7225, 0.2167, 0.3988, 0.2283, 0.5427, 0.5181],
[0.6125, 0.3983, 0.8750, 0.4867, 0.4275, 0.4783, 0.5412, 0.5717],
[0.6321, 0.4048, 0.8737, 0.5617, 0.3875, 0.4417, 0.6361, 0.4927],
[0.6277, 0.4056, 0.8300, 0.2650, 0.4363, 0.1850, 0.6140, 0.4823],
[0.6113, 0.4104, 0.8650, 0.4250, 0.3925, 0.5967, 0.5787, 0.5116]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0052, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0052, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.16981427988503128
step: 43
running loss: 0.00394916929965189
Train Steps: 43/90 Loss: 0.0039 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6267, 0.4094, 0.8712, 0.3083, 0.4400, 0.2267, 0.6250, 0.5200],
[0.6161, 0.4099, 0.8738, 0.4383, 0.3788, 0.5483, 0.5605, 0.5019],
[ nan, nan, 0.7412, 0.2200, 0.4450, 0.1517, 0.5312, 0.4983],
[0.6198, 0.4130, 0.8762, 0.4117, 0.3650, 0.4900, 0.5707, 0.5103],
[0.6086, 0.3940, 0.8712, 0.4783, 0.4025, 0.4900, 0.5498, 0.5390],
[0.6274, 0.4099, 0.8625, 0.3233, 0.4400, 0.1983, 0.5876, 0.4869],
[0.6145, 0.3983, 0.8700, 0.5017, 0.4400, 0.4800, 0.5375, 0.5750],
[0.6286, 0.4078, 0.8063, 0.2267, 0.4788, 0.1533, 0.5953, 0.4913]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5744, 0.3610, 0.8981, 0.3053, 0.4541, 0.2640, 0.6367, 0.5374],
[0.6513, 0.4209, 0.9170, 0.4760, 0.3727, 0.5281, 0.6176, 0.5163],
[0.3297, 0.2064, 0.7455, 0.2015, 0.4621, 0.1717, 0.5486, 0.5469],
[0.6995, 0.4713, 0.9346, 0.4540, 0.3628, 0.4868, 0.5914, 0.5479],
[0.5862, 0.3670, 0.9249, 0.5698, 0.4216, 0.4958, 0.5751, 0.5130],
[0.5996, 0.3651, 0.8751, 0.3118, 0.4596, 0.2157, 0.5981, 0.5374],
[0.6333, 0.4009, 0.9072, 0.5587, 0.4147, 0.4863, 0.5798, 0.5360],
[0.5015, 0.3147, 0.8200, 0.2512, 0.4896, 0.1724, 0.5748, 0.5407]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6267, 0.4094, 0.8712, 0.3083, 0.4400, 0.2267, 0.6250, 0.5200],
[0.6161, 0.4099, 0.8737, 0.4383, 0.3787, 0.5483, 0.5605, 0.5019],
[0.0000, 0.0000, 0.7412, 0.2200, 0.4450, 0.1517, 0.5312, 0.4983],
[0.6198, 0.4130, 0.8763, 0.4117, 0.3650, 0.4900, 0.5707, 0.5103],
[0.6086, 0.3940, 0.8712, 0.4783, 0.4025, 0.4900, 0.5498, 0.5390],
[0.6274, 0.4099, 0.8625, 0.3233, 0.4400, 0.1983, 0.5876, 0.4869],
[0.6145, 0.3983, 0.8700, 0.5017, 0.4400, 0.4800, 0.5375, 0.5750],
[0.6286, 0.4078, 0.8062, 0.2267, 0.4787, 0.1533, 0.5953, 0.4913]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0039, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0039, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.1736702184425667
step: 44
running loss: 0.003947050419149243
Train Steps: 44/90 Loss: 0.0039 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6239, 0.4107, 0.8162, 0.2763, 0.3625, 0.3600, 0.5988, 0.5700],
[0.6038, 0.3946, 0.8413, 0.4883, 0.3563, 0.4550, 0.5266, 0.4693],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4012, 0.4633, 0.5338, 0.5767],
[0.6249, 0.4142, 0.8350, 0.3283, 0.3613, 0.3700, 0.6188, 0.5400],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3513, 0.4050, 0.6112, 0.5500],
[0.6201, 0.4029, 0.8776, 0.4602, 0.3683, 0.4203, 0.5938, 0.5450],
[0.6286, 0.4060, 0.9188, 0.4333, 0.3675, 0.4167, 0.7034, 0.5528],
[0.6161, 0.4076, 0.8900, 0.4667, 0.4125, 0.5917, 0.6262, 0.5367]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4946, 0.3198, 0.8330, 0.2777, 0.4325, 0.2888, 0.5966, 0.5509],
[0.5412, 0.3576, 0.8926, 0.4817, 0.4078, 0.4237, 0.5483, 0.4943],
[0.5436, 0.3551, 0.8983, 0.5374, 0.4359, 0.4431, 0.5623, 0.5453],
[0.6110, 0.3883, 0.8518, 0.3097, 0.4324, 0.2751, 0.5913, 0.5272],
[0.5764, 0.3854, 0.8313, 0.2675, 0.3994, 0.3353, 0.5966, 0.5245],
[0.6086, 0.3816, 0.9137, 0.5039, 0.4031, 0.3933, 0.5720, 0.5005],
[0.5202, 0.3427, 0.9587, 0.4177, 0.4165, 0.3402, 0.6581, 0.5295],
[0.5557, 0.3643, 0.9287, 0.4716, 0.4642, 0.5385, 0.6326, 0.5063]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6239, 0.4107, 0.8162, 0.2763, 0.3625, 0.3600, 0.5987, 0.5700],
[0.6038, 0.3946, 0.8413, 0.4883, 0.3562, 0.4550, 0.5266, 0.4693],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4013, 0.4633, 0.5337, 0.5767],
[0.6249, 0.4142, 0.8350, 0.3283, 0.3613, 0.3700, 0.6187, 0.5400],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3512, 0.4050, 0.6112, 0.5500],
[0.6201, 0.4029, 0.8776, 0.4602, 0.3683, 0.4203, 0.5938, 0.5450],
[0.6286, 0.4060, 0.9187, 0.4333, 0.3675, 0.4167, 0.7034, 0.5528],
[0.6161, 0.4076, 0.8900, 0.4667, 0.4125, 0.5917, 0.6263, 0.5367]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0022, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0022, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.17585839342791587
step: 45
running loss: 0.003907964298398131
Train Steps: 45/90 Loss: 0.0039 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6224, 0.4061, 0.8988, 0.4300, 0.3838, 0.4750, 0.6112, 0.5483],
[0.6339, 0.4102, 0.8588, 0.3133, 0.4425, 0.2117, 0.6417, 0.5089],
[0.6138, 0.4020, 0.8800, 0.4717, 0.4375, 0.4717, 0.5502, 0.5611],
[0.6107, 0.4013, 0.8700, 0.4650, 0.5049, 0.5176, 0.5850, 0.5550],
[0.6152, 0.4131, 0.6863, 0.2567, 0.3625, 0.3300, 0.5765, 0.5305],
[0.6162, 0.4134, 0.6700, 0.2467, 0.3962, 0.2533, 0.5737, 0.5467],
[0.6273, 0.4143, 0.8750, 0.5700, 0.3987, 0.4717, 0.6013, 0.5467],
[0.6159, 0.4085, 0.6900, 0.2283, 0.4088, 0.1950, 0.5123, 0.5397]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5982, 0.3846, 0.9121, 0.4259, 0.3752, 0.5248, 0.6178, 0.4911],
[0.5487, 0.3555, 0.8807, 0.2899, 0.4626, 0.1906, 0.6620, 0.4942],
[0.5193, 0.3321, 0.8960, 0.4542, 0.4383, 0.4488, 0.5616, 0.5277],
[0.4869, 0.3403, 0.9145, 0.4456, 0.4816, 0.4387, 0.6093, 0.5287],
[0.5725, 0.3812, 0.7642, 0.2518, 0.3758, 0.2768, 0.5590, 0.5411],
[0.5903, 0.3854, 0.7478, 0.2506, 0.3907, 0.2212, 0.5636, 0.5075],
[0.5732, 0.3680, 0.8950, 0.5185, 0.4251, 0.4477, 0.5844, 0.5426],
[0.3919, 0.2581, 0.7479, 0.2186, 0.4290, 0.1590, 0.5343, 0.5263]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6224, 0.4061, 0.8988, 0.4300, 0.3837, 0.4750, 0.6112, 0.5483],
[0.6339, 0.4102, 0.8587, 0.3133, 0.4425, 0.2117, 0.6417, 0.5089],
[0.6138, 0.4020, 0.8800, 0.4717, 0.4375, 0.4717, 0.5502, 0.5611],
[0.6107, 0.4013, 0.8700, 0.4650, 0.5049, 0.5176, 0.5850, 0.5550],
[0.6152, 0.4131, 0.6862, 0.2567, 0.3625, 0.3300, 0.5765, 0.5305],
[0.6162, 0.4134, 0.6700, 0.2467, 0.3963, 0.2533, 0.5738, 0.5467],
[0.6273, 0.4143, 0.8750, 0.5700, 0.3988, 0.4717, 0.6012, 0.5467],
[0.6159, 0.4085, 0.6900, 0.2283, 0.4087, 0.1950, 0.5123, 0.5397]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0028, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0028, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.1786146817030385
step: 46
running loss: 0.003882927863109533
Train Steps: 46/90 Loss: 0.0039 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6260, 0.4133, 0.8800, 0.5117, 0.3713, 0.3283, 0.6223, 0.4967],
[0.6364, 0.4165, 0.9088, 0.4367, 0.4075, 0.3150, 0.6448, 0.5297],
[0.6275, 0.4024, 0.8600, 0.2283, 0.5350, 0.1800, 0.7074, 0.5413],
[0.6179, 0.3961, 0.8347, 0.6020, 0.3887, 0.4624, 0.5714, 0.5373],
[ nan, nan, 0.8938, 0.2850, 0.4662, 0.3117, 0.7406, 0.5528],
[0.6292, 0.4010, 0.8988, 0.4800, 0.3638, 0.3817, 0.6357, 0.5051],
[0.6223, 0.4028, 0.8988, 0.4200, 0.3763, 0.5733, 0.6375, 0.5167],
[0.6183, 0.4076, 0.8838, 0.4517, 0.3813, 0.4483, 0.5775, 0.5633]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5902, 0.4247, 0.8342, 0.4375, 0.4049, 0.2877, 0.5761, 0.4922],
[0.5506, 0.3890, 0.8556, 0.3736, 0.4278, 0.2765, 0.5867, 0.5182],
[0.4517, 0.3155, 0.8016, 0.1960, 0.5234, 0.2164, 0.6464, 0.5249],
[0.5782, 0.3937, 0.7643, 0.4926, 0.3738, 0.4246, 0.5473, 0.5271],
[0.3472, 0.2472, 0.8567, 0.2544, 0.4739, 0.2547, 0.6857, 0.5190],
[0.5657, 0.3600, 0.8437, 0.4191, 0.3642, 0.3413, 0.5603, 0.4914],
[0.5481, 0.3568, 0.8340, 0.3782, 0.3921, 0.5499, 0.6102, 0.4830],
[0.5766, 0.3872, 0.8331, 0.4085, 0.3848, 0.4229, 0.5482, 0.5033]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6260, 0.4133, 0.8800, 0.5117, 0.3713, 0.3283, 0.6223, 0.4967],
[0.6364, 0.4165, 0.9087, 0.4367, 0.4075, 0.3150, 0.6448, 0.5297],
[0.6275, 0.4024, 0.8600, 0.2283, 0.5350, 0.1800, 0.7074, 0.5413],
[0.6179, 0.3961, 0.8347, 0.6020, 0.3887, 0.4624, 0.5714, 0.5373],
[0.0000, 0.0000, 0.8938, 0.2850, 0.4663, 0.3117, 0.7406, 0.5528],
[0.6292, 0.4010, 0.8988, 0.4800, 0.3638, 0.3817, 0.6357, 0.5051],
[0.6223, 0.4028, 0.8988, 0.4200, 0.3762, 0.5733, 0.6375, 0.5167],
[0.6183, 0.4076, 0.8838, 0.4517, 0.3812, 0.4483, 0.5775, 0.5633]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0054, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0054, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.18397039466071874
step: 47
running loss: 0.003914263716185505
Train Steps: 47/90 Loss: 0.0039 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6128, 0.4022, 0.8738, 0.5067, 0.4983, 0.5231, 0.5364, 0.5064],
[0.6357, 0.4097, 0.9038, 0.3883, 0.4213, 0.2950, 0.6686, 0.5390],
[0.6248, 0.4032, 0.7738, 0.1900, 0.4813, 0.1400, 0.5941, 0.4904],
[0.6132, 0.4118, 0.8200, 0.3633, 0.3563, 0.5400, 0.5787, 0.5136],
[0.6231, 0.3973, 0.8650, 0.3950, 0.3625, 0.3183, 0.5837, 0.5167],
[0.6343, 0.4097, 0.9287, 0.4367, 0.4313, 0.3600, 0.7248, 0.5841],
[0.6269, 0.4073, 0.8900, 0.4933, 0.3625, 0.4183, 0.6288, 0.5150],
[0.6364, 0.4144, 0.8625, 0.3083, 0.4913, 0.2000, 0.6448, 0.5274]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5356, 0.3720, 0.8169, 0.4604, 0.4491, 0.4540, 0.5478, 0.5239],
[0.5339, 0.3525, 0.8122, 0.3496, 0.3886, 0.2890, 0.6373, 0.5348],
[0.4764, 0.3318, 0.7208, 0.1869, 0.4643, 0.1142, 0.5922, 0.5236],
[0.5076, 0.3286, 0.7992, 0.3146, 0.3590, 0.5195, 0.6077, 0.5179],
[0.5510, 0.3645, 0.8016, 0.3514, 0.3689, 0.3138, 0.5630, 0.5140],
[0.5081, 0.3545, 0.8147, 0.3891, 0.3914, 0.3503, 0.6489, 0.5292],
[0.6319, 0.4548, 0.8447, 0.4583, 0.3428, 0.4245, 0.6191, 0.5207],
[0.5233, 0.3743, 0.8006, 0.2742, 0.4410, 0.2303, 0.6163, 0.5454]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6128, 0.4022, 0.8737, 0.5067, 0.4983, 0.5231, 0.5364, 0.5064],
[0.6357, 0.4097, 0.9038, 0.3883, 0.4212, 0.2950, 0.6686, 0.5390],
[0.6248, 0.4032, 0.7738, 0.1900, 0.4812, 0.1400, 0.5941, 0.4904],
[0.6132, 0.4118, 0.8200, 0.3633, 0.3562, 0.5400, 0.5787, 0.5136],
[0.6231, 0.3973, 0.8650, 0.3950, 0.3625, 0.3183, 0.5838, 0.5167],
[0.6343, 0.4097, 0.9287, 0.4367, 0.4313, 0.3600, 0.7248, 0.5841],
[0.6269, 0.4073, 0.8900, 0.4933, 0.3625, 0.4183, 0.6288, 0.5150],
[0.6364, 0.4144, 0.8625, 0.3083, 0.4913, 0.2000, 0.6448, 0.5274]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0029, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0029, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.18689397221896797
step: 48
running loss: 0.0038936244212284996
Train Steps: 48/90 Loss: 0.0039 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6175, 0.4093, 0.8800, 0.4433, 0.4075, 0.4367, 0.5128, 0.4901],
[0.6275, 0.4024, 0.7722, 0.2080, 0.4392, 0.2234, 0.6435, 0.5290],
[0.6250, 0.4008, 0.8950, 0.4183, 0.3550, 0.4383, 0.6361, 0.4927],
[0.6070, 0.3979, 0.8575, 0.5083, 0.4350, 0.5400, 0.5180, 0.5466],
[0.6226, 0.4185, 0.8850, 0.5500, 0.3800, 0.4250, 0.5625, 0.5617],
[0.6250, 0.4116, 0.8700, 0.4850, 0.4650, 0.5567, 0.6088, 0.5183],
[0.6229, 0.4198, 0.7662, 0.2700, 0.4700, 0.2133, 0.5675, 0.5783],
[0.6131, 0.4037, 0.6907, 0.2819, 0.3688, 0.2700, 0.5217, 0.5680]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5783, 0.3915, 0.8595, 0.4291, 0.3632, 0.4066, 0.5616, 0.5293],
[0.5297, 0.3724, 0.7324, 0.2156, 0.4202, 0.1592, 0.6418, 0.5288],
[0.6896, 0.4471, 0.8466, 0.3719, 0.3241, 0.4163, 0.6480, 0.5045],
[0.5473, 0.3957, 0.8311, 0.4912, 0.4214, 0.5023, 0.5809, 0.5467],
[0.6278, 0.4192, 0.8578, 0.5170, 0.3710, 0.4178, 0.6087, 0.5449],
[0.5861, 0.3984, 0.8378, 0.4504, 0.4305, 0.5174, 0.6835, 0.5589],
[0.4583, 0.3411, 0.7667, 0.2237, 0.4115, 0.2177, 0.6164, 0.5766],
[0.5240, 0.3749, 0.6977, 0.2363, 0.3559, 0.2672, 0.5716, 0.5624]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6175, 0.4093, 0.8800, 0.4433, 0.4075, 0.4367, 0.5128, 0.4901],
[0.6275, 0.4024, 0.7722, 0.2080, 0.4392, 0.2234, 0.6435, 0.5290],
[0.6250, 0.4008, 0.8950, 0.4183, 0.3550, 0.4383, 0.6361, 0.4927],
[0.6070, 0.3979, 0.8575, 0.5083, 0.4350, 0.5400, 0.5180, 0.5466],
[0.6226, 0.4185, 0.8850, 0.5500, 0.3800, 0.4250, 0.5625, 0.5617],
[0.6251, 0.4116, 0.8700, 0.4850, 0.4650, 0.5567, 0.6087, 0.5183],
[0.6229, 0.4198, 0.7663, 0.2700, 0.4700, 0.2133, 0.5675, 0.5783],
[0.6131, 0.4036, 0.6907, 0.2819, 0.3688, 0.2700, 0.5217, 0.5680]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.1887947202194482
step: 49
running loss: 0.00385295347386629
Train Steps: 49/90 Loss: 0.0039 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6193, 0.4165, 0.8838, 0.4700, 0.4150, 0.4867, 0.5427, 0.5261],
[0.6143, 0.4055, 0.8150, 0.2767, 0.3825, 0.2567, 0.5173, 0.4901],
[0.6304, 0.4024, 0.8925, 0.4800, 0.3937, 0.4817, 0.7485, 0.5297],
[0.6161, 0.4040, 0.7525, 0.2133, 0.4125, 0.2067, 0.5787, 0.5117],
[0.6250, 0.4008, 0.8950, 0.4183, 0.3550, 0.4383, 0.6361, 0.4927],
[0.6227, 0.4083, 0.8938, 0.4800, 0.3800, 0.2950, 0.5737, 0.5350],
[0.6200, 0.3978, 0.8900, 0.4550, 0.3775, 0.5200, 0.6150, 0.5367],
[0.6226, 0.4103, 0.8575, 0.3450, 0.4388, 0.2067, 0.5787, 0.5383]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5907, 0.4206, 0.8311, 0.4863, 0.3859, 0.4446, 0.6255, 0.5465],
[0.4468, 0.3266, 0.7506, 0.2761, 0.3689, 0.2431, 0.5742, 0.5514],
[0.5799, 0.3804, 0.8372, 0.4546, 0.3878, 0.4680, 0.6465, 0.5339],
[0.6617, 0.4215, 0.7334, 0.2241, 0.4029, 0.1739, 0.6141, 0.5315],
[0.6885, 0.4408, 0.8412, 0.3858, 0.3437, 0.4316, 0.6301, 0.5134],
[0.6789, 0.4871, 0.8510, 0.4682, 0.3937, 0.3102, 0.6101, 0.5566],
[0.5780, 0.3749, 0.8523, 0.4565, 0.3673, 0.5337, 0.6059, 0.5508],
[0.5551, 0.4059, 0.8128, 0.3384, 0.4452, 0.2528, 0.6119, 0.5846]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6193, 0.4165, 0.8838, 0.4700, 0.4150, 0.4867, 0.5427, 0.5261],
[0.6143, 0.4055, 0.8150, 0.2767, 0.3825, 0.2567, 0.5173, 0.4901],
[0.6304, 0.4024, 0.8925, 0.4800, 0.3938, 0.4817, 0.7485, 0.5297],
[0.6161, 0.4040, 0.7525, 0.2133, 0.4125, 0.2067, 0.5788, 0.5117],
[0.6250, 0.4008, 0.8950, 0.4183, 0.3550, 0.4383, 0.6361, 0.4927],
[0.6227, 0.4083, 0.8938, 0.4800, 0.3800, 0.2950, 0.5738, 0.5350],
[0.6199, 0.3978, 0.8900, 0.4550, 0.3775, 0.5200, 0.6150, 0.5367],
[0.6226, 0.4103, 0.8575, 0.3450, 0.4387, 0.2067, 0.5788, 0.5383]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.19071150361560285
step: 50
running loss: 0.003814230072312057
Train Steps: 50/90 Loss: 0.0038 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6268, 0.4052, 0.8175, 0.2250, 0.4688, 0.1917, 0.6375, 0.5267],
[0.6188, 0.4099, 0.7400, 0.2433, 0.3962, 0.2750, 0.6162, 0.5467],
[0.6192, 0.3980, 0.7078, 0.2750, 0.4250, 0.2100, 0.5450, 0.5783],
[0.6184, 0.4079, 0.8350, 0.3700, 0.3675, 0.2883, 0.5312, 0.5783],
[0.6053, 0.4035, 0.6897, 0.1916, 0.4000, 0.2117, 0.5440, 0.5168],
[0.6257, 0.4034, 0.8287, 0.2333, 0.3925, 0.2717, 0.6330, 0.4901],
[0.6169, 0.4052, 0.8742, 0.4779, 0.4288, 0.4917, 0.5763, 0.5617],
[0.6168, 0.4055, 0.7575, 0.2950, 0.4050, 0.2717, 0.5938, 0.6167]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6429, 0.4160, 0.8269, 0.2762, 0.4544, 0.2121, 0.6649, 0.5159],
[0.6870, 0.4637, 0.7694, 0.2872, 0.3812, 0.3079, 0.6157, 0.5234],
[0.3769, 0.2598, 0.7436, 0.2793, 0.4277, 0.2608, 0.5515, 0.5496],
[0.7011, 0.4604, 0.8506, 0.3975, 0.3754, 0.3619, 0.5322, 0.5614],
[0.5484, 0.3436, 0.7126, 0.2348, 0.4148, 0.2125, 0.5711, 0.4997],
[0.6928, 0.4471, 0.8586, 0.2866, 0.3946, 0.2889, 0.6364, 0.4866],
[0.7239, 0.4933, 0.8775, 0.5449, 0.4109, 0.5543, 0.5762, 0.5451],
[0.6751, 0.4653, 0.7992, 0.3384, 0.3962, 0.3202, 0.6100, 0.5912]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6268, 0.4052, 0.8175, 0.2250, 0.4688, 0.1917, 0.6375, 0.5267],
[0.6188, 0.4099, 0.7400, 0.2433, 0.3963, 0.2750, 0.6162, 0.5467],
[0.6192, 0.3980, 0.7078, 0.2750, 0.4250, 0.2100, 0.5450, 0.5783],
[0.6184, 0.4079, 0.8350, 0.3700, 0.3675, 0.2883, 0.5312, 0.5783],
[0.6054, 0.4035, 0.6897, 0.1916, 0.4000, 0.2117, 0.5440, 0.5168],
[0.6257, 0.4034, 0.8288, 0.2333, 0.3925, 0.2717, 0.6330, 0.4901],
[0.6169, 0.4052, 0.8742, 0.4779, 0.4288, 0.4917, 0.5763, 0.5617],
[0.6168, 0.4055, 0.7575, 0.2950, 0.4050, 0.2717, 0.5938, 0.6167]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0028, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0028, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.1935047539882362
step: 51
running loss: 0.003794210862514435
Train Steps: 51/90 Loss: 0.0038 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6101, 0.3977, 0.8550, 0.5667, 0.3862, 0.4417, 0.5128, 0.4869],
[0.6258, 0.4038, 0.8750, 0.4883, 0.3900, 0.5500, 0.6375, 0.5217],
[0.6225, 0.4191, 0.8500, 0.4167, 0.3688, 0.3233, 0.5650, 0.5650],
[ nan, nan, 0.7097, 0.2346, 0.4250, 0.1850, 0.5175, 0.5583],
[0.6274, 0.4087, 0.8375, 0.5700, 0.4025, 0.4800, 0.5700, 0.6117],
[0.6153, 0.4117, 0.8688, 0.5167, 0.4895, 0.5647, 0.5524, 0.5136],
[0.6212, 0.4033, 0.8938, 0.4167, 0.3813, 0.4267, 0.5613, 0.5583],
[0.6182, 0.4099, 0.7812, 0.3000, 0.3937, 0.2367, 0.5325, 0.5750]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7185, 0.4708, 0.8618, 0.5070, 0.4093, 0.3858, 0.6009, 0.5121],
[0.8135, 0.4977, 0.8833, 0.4586, 0.3953, 0.5580, 0.6702, 0.5256],
[0.7068, 0.4859, 0.8293, 0.3565, 0.3601, 0.2996, 0.6099, 0.5512],
[0.3108, 0.2245, 0.7162, 0.2091, 0.4363, 0.1829, 0.5488, 0.5426],
[0.7652, 0.4867, 0.8227, 0.5169, 0.3867, 0.4359, 0.5665, 0.5834],
[0.6891, 0.4566, 0.8543, 0.4532, 0.4490, 0.4629, 0.5988, 0.5428],
[0.6487, 0.4061, 0.9048, 0.4152, 0.3674, 0.4081, 0.5812, 0.5541],
[0.6153, 0.4052, 0.7894, 0.2775, 0.4123, 0.2320, 0.5595, 0.5471]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6101, 0.3977, 0.8550, 0.5667, 0.3862, 0.4417, 0.5128, 0.4869],
[0.6258, 0.4038, 0.8750, 0.4883, 0.3900, 0.5500, 0.6375, 0.5217],
[0.6225, 0.4191, 0.8500, 0.4167, 0.3688, 0.3233, 0.5650, 0.5650],
[0.0000, 0.0000, 0.7097, 0.2346, 0.4250, 0.1850, 0.5175, 0.5583],
[0.6274, 0.4087, 0.8375, 0.5700, 0.4025, 0.4800, 0.5700, 0.6117],
[0.6154, 0.4117, 0.8687, 0.5167, 0.4895, 0.5647, 0.5524, 0.5136],
[0.6212, 0.4033, 0.8938, 0.4167, 0.3812, 0.4267, 0.5612, 0.5583],
[0.6182, 0.4099, 0.7812, 0.3000, 0.3938, 0.2367, 0.5325, 0.5750]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0048, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0048, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.19832616718485951
step: 52
running loss: 0.0038139647535549905
Train Steps: 52/90 Loss: 0.0038 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6053, 0.4035, 0.6897, 0.1916, 0.4000, 0.2117, 0.5440, 0.5168],
[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758],
[0.6225, 0.4196, 0.8788, 0.3467, 0.3750, 0.3400, 0.5413, 0.5433],
[ nan, nan, 0.7612, 0.3250, 0.4037, 0.2533, 0.5438, 0.5767],
[0.6250, 0.4236, 0.8638, 0.3767, 0.4050, 0.3150, 0.5649, 0.5799],
[0.6160, 0.4093, 0.8314, 0.4417, 0.3675, 0.4583, 0.5250, 0.5808],
[0.6131, 0.4037, 0.6907, 0.2819, 0.3688, 0.2700, 0.5217, 0.5680],
[0.6137, 0.4084, 0.8076, 0.3889, 0.3650, 0.3150, 0.5356, 0.5896]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6246, 0.3846, 0.7061, 0.2208, 0.4330, 0.1798, 0.5548, 0.5012],
[0.7532, 0.4474, 0.9285, 0.5140, 0.4293, 0.5499, 0.6269, 0.5106],
[0.6529, 0.4466, 0.8533, 0.3775, 0.3637, 0.3183, 0.5681, 0.5332],
[0.4785, 0.2866, 0.8067, 0.3179, 0.4354, 0.2605, 0.5388, 0.5638],
[0.7072, 0.4532, 0.8808, 0.4216, 0.4210, 0.3280, 0.5693, 0.5640],
[0.6810, 0.4414, 0.8535, 0.4714, 0.3980, 0.4581, 0.5754, 0.5703],
[0.6754, 0.4343, 0.7393, 0.2802, 0.3996, 0.2901, 0.5359, 0.5503],
[0.6758, 0.4444, 0.8548, 0.4092, 0.3865, 0.3137, 0.5375, 0.5456]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6054, 0.4035, 0.6897, 0.1916, 0.4000, 0.2117, 0.5440, 0.5168],
[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758],
[0.6225, 0.4196, 0.8788, 0.3467, 0.3750, 0.3400, 0.5412, 0.5433],
[0.0000, 0.0000, 0.7613, 0.3250, 0.4038, 0.2533, 0.5437, 0.5767],
[0.6250, 0.4236, 0.8637, 0.3767, 0.4050, 0.3150, 0.5649, 0.5799],
[0.6160, 0.4092, 0.8314, 0.4417, 0.3675, 0.4583, 0.5250, 0.5808],
[0.6131, 0.4036, 0.6907, 0.2819, 0.3688, 0.2700, 0.5217, 0.5680],
[0.6137, 0.4084, 0.8076, 0.3889, 0.3650, 0.3150, 0.5356, 0.5896]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0060, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0060, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.2043646709062159
step: 53
running loss: 0.003855937186909734
Train Steps: 53/90 Loss: 0.0039 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6201, 0.4116, 0.8725, 0.4733, 0.3700, 0.3217, 0.5386, 0.5767],
[0.6127, 0.4118, 0.8650, 0.5083, 0.4088, 0.5367, 0.5300, 0.5456],
[0.6223, 0.3990, 0.8037, 0.2800, 0.4000, 0.2283, 0.5864, 0.5208],
[0.6125, 0.3974, 0.7725, 0.2517, 0.3538, 0.3317, 0.5887, 0.5500],
[0.6128, 0.4116, 0.8450, 0.4583, 0.3675, 0.4867, 0.5337, 0.5446],
[0.6350, 0.4118, 0.8363, 0.2717, 0.4850, 0.1700, 0.6441, 0.5170],
[0.6222, 0.3957, 0.8838, 0.5017, 0.3937, 0.4600, 0.5900, 0.5017],
[0.6164, 0.4119, 0.7913, 0.2650, 0.3538, 0.3500, 0.5614, 0.5038]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6823, 0.4182, 0.8925, 0.5127, 0.3848, 0.3467, 0.5078, 0.5746],
[0.6324, 0.3610, 0.8778, 0.5452, 0.4411, 0.5536, 0.5033, 0.5969],
[0.6364, 0.3702, 0.8149, 0.3233, 0.4203, 0.2426, 0.5644, 0.5335],
[0.6659, 0.3918, 0.7969, 0.2866, 0.3929, 0.3467, 0.5385, 0.5664],
[0.6106, 0.3540, 0.8478, 0.4741, 0.3870, 0.4879, 0.5421, 0.5649],
[0.6444, 0.3753, 0.8584, 0.2748, 0.4906, 0.1783, 0.6106, 0.5320],
[0.6796, 0.4049, 0.9135, 0.5595, 0.4094, 0.4721, 0.5515, 0.5398],
[0.7185, 0.4458, 0.8179, 0.2925, 0.3749, 0.3738, 0.5725, 0.5191]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6201, 0.4116, 0.8725, 0.4733, 0.3700, 0.3217, 0.5386, 0.5767],
[0.6127, 0.4118, 0.8650, 0.5083, 0.4087, 0.5367, 0.5300, 0.5456],
[0.6223, 0.3990, 0.8037, 0.2800, 0.4000, 0.2283, 0.5864, 0.5208],
[0.6125, 0.3974, 0.7725, 0.2517, 0.3537, 0.3317, 0.5888, 0.5500],
[0.6128, 0.4116, 0.8450, 0.4583, 0.3675, 0.4867, 0.5337, 0.5446],
[0.6350, 0.4118, 0.8363, 0.2717, 0.4850, 0.1700, 0.6441, 0.5170],
[0.6222, 0.3957, 0.8838, 0.5017, 0.3938, 0.4600, 0.5900, 0.5017],
[0.6164, 0.4119, 0.7912, 0.2650, 0.3537, 0.3500, 0.5614, 0.5038]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.20535756752360612
step: 54
running loss: 0.003802917917103817
Train Steps: 54/90 Loss: 0.0038 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6241, 0.4143, 0.8938, 0.4650, 0.4075, 0.5350, 0.6250, 0.5550],
[0.6226, 0.4098, 0.8912, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367],
[0.6038, 0.3946, 0.8413, 0.4883, 0.3563, 0.4550, 0.5266, 0.4693],
[ nan, nan, 0.6469, 0.1943, 0.4025, 0.2000, 0.5125, 0.5533],
[0.6097, 0.3988, 0.8650, 0.5250, 0.4213, 0.5200, 0.5675, 0.5050],
[0.6286, 0.4274, 0.8500, 0.4500, 0.4525, 0.2583, 0.5440, 0.6209],
[0.6149, 0.4054, 0.6713, 0.2333, 0.4025, 0.2017, 0.5213, 0.5695],
[0.6274, 0.4270, 0.8938, 0.4967, 0.3550, 0.4283, 0.5700, 0.5733]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5917, 0.3723, 0.8891, 0.4751, 0.4165, 0.5489, 0.6182, 0.5760],
[0.7117, 0.4290, 0.8914, 0.4276, 0.4067, 0.2642, 0.5423, 0.5531],
[0.5924, 0.3717, 0.8861, 0.4923, 0.3642, 0.4655, 0.5262, 0.5317],
[0.2581, 0.1246, 0.7177, 0.2037, 0.4130, 0.1838, 0.5022, 0.5447],
[0.6910, 0.4236, 0.8848, 0.5404, 0.4288, 0.5179, 0.5153, 0.5370],
[0.7144, 0.4450, 0.8453, 0.4453, 0.4477, 0.3143, 0.5251, 0.5701],
[0.5903, 0.3559, 0.7124, 0.2420, 0.3795, 0.2064, 0.4764, 0.5346],
[0.6276, 0.3709, 0.8845, 0.5027, 0.3586, 0.4799, 0.5622, 0.5465]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6241, 0.4142, 0.8938, 0.4650, 0.4075, 0.5350, 0.6250, 0.5550],
[0.6226, 0.4098, 0.8913, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367],
[0.6038, 0.3946, 0.8413, 0.4883, 0.3562, 0.4550, 0.5266, 0.4693],
[0.0000, 0.0000, 0.6469, 0.1943, 0.4025, 0.2000, 0.5125, 0.5533],
[0.6097, 0.3988, 0.8650, 0.5250, 0.4212, 0.5200, 0.5675, 0.5050],
[0.6286, 0.4274, 0.8500, 0.4500, 0.4525, 0.2583, 0.5440, 0.6209],
[0.6149, 0.4054, 0.6712, 0.2333, 0.4025, 0.2017, 0.5213, 0.5695],
[0.6274, 0.4270, 0.8938, 0.4967, 0.3550, 0.4283, 0.5700, 0.5733]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0023, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0023, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.20769805239979178
step: 55
running loss: 0.0037763282254507594
Train Steps: 55/90 Loss: 0.0038 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6200, 0.3993, 0.8519, 0.4923, 0.3962, 0.4717, 0.6013, 0.5433],
[0.6200, 0.4098, 0.8237, 0.2917, 0.4012, 0.2967, 0.6000, 0.5683],
[0.6166, 0.4008, 0.8563, 0.5667, 0.4388, 0.4933, 0.5575, 0.5567],
[0.6264, 0.4069, 0.7900, 0.1650, 0.4275, 0.2267, 0.6290, 0.4947],
[0.6136, 0.4117, 0.8700, 0.5167, 0.4188, 0.5083, 0.5147, 0.5495],
[0.6198, 0.3997, 0.8582, 0.5361, 0.4117, 0.5016, 0.5942, 0.5134],
[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758],
[0.6147, 0.4112, 0.7988, 0.3200, 0.3775, 0.2767, 0.5150, 0.5550]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5744, 0.3695, 0.8922, 0.5000, 0.3746, 0.4588, 0.5700, 0.5711],
[0.6601, 0.4320, 0.8350, 0.3069, 0.3937, 0.2802, 0.5901, 0.5480],
[0.5936, 0.3623, 0.8516, 0.5368, 0.4231, 0.4702, 0.5124, 0.5805],
[0.5631, 0.3485, 0.7975, 0.2137, 0.4321, 0.2081, 0.6074, 0.5147],
[0.6031, 0.3717, 0.8932, 0.5464, 0.4023, 0.4963, 0.5162, 0.5645],
[0.5450, 0.3490, 0.8726, 0.5144, 0.4051, 0.4960, 0.5226, 0.5375],
[0.6051, 0.3576, 0.8927, 0.4888, 0.4008, 0.5298, 0.5622, 0.5188],
[0.4384, 0.3046, 0.7921, 0.3440, 0.3716, 0.2838, 0.4716, 0.5635]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6200, 0.3993, 0.8519, 0.4923, 0.3963, 0.4717, 0.6012, 0.5433],
[0.6200, 0.4098, 0.8238, 0.2917, 0.4013, 0.2967, 0.6000, 0.5683],
[0.6166, 0.4008, 0.8562, 0.5667, 0.4387, 0.4933, 0.5575, 0.5567],
[0.6264, 0.4069, 0.7900, 0.1650, 0.4275, 0.2267, 0.6290, 0.4947],
[0.6136, 0.4117, 0.8700, 0.5167, 0.4187, 0.5083, 0.5147, 0.5495],
[0.6198, 0.3997, 0.8582, 0.5361, 0.4117, 0.5016, 0.5942, 0.5134],
[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758],
[0.6147, 0.4112, 0.7987, 0.3200, 0.3775, 0.2767, 0.5150, 0.5550]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.20929075684398413
step: 56
running loss: 0.0037373349436425735
Train Steps: 56/90 Loss: 0.0037 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6273, 0.4143, 0.8750, 0.5700, 0.3987, 0.4717, 0.6013, 0.5467],
[0.6125, 0.3983, 0.8750, 0.4867, 0.4275, 0.4783, 0.5413, 0.5717],
[0.6311, 0.4008, 0.7935, 0.5746, 0.3900, 0.5033, 0.6955, 0.5366],
[0.6179, 0.3998, 0.8396, 0.3505, 0.3552, 0.3768, 0.6064, 0.5329],
[0.6109, 0.3943, 0.8525, 0.4950, 0.4338, 0.4800, 0.5449, 0.5383],
[0.6200, 0.3993, 0.8639, 0.3687, 0.3658, 0.3139, 0.6002, 0.5374],
[0.6143, 0.4040, 0.8237, 0.3333, 0.4075, 0.2117, 0.5137, 0.4973],
[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5484, 0.3537, 0.8765, 0.5648, 0.4005, 0.4816, 0.5476, 0.5668],
[0.5897, 0.3917, 0.8650, 0.5099, 0.4313, 0.4779, 0.5345, 0.5749],
[0.5643, 0.3977, 0.8293, 0.5187, 0.4009, 0.4767, 0.5955, 0.5563],
[0.6404, 0.4238, 0.8493, 0.3751, 0.3361, 0.3527, 0.5680, 0.5031],
[0.5447, 0.3584, 0.8739, 0.5105, 0.4286, 0.4851, 0.5295, 0.5788],
[0.5144, 0.3560, 0.8684, 0.3694, 0.3730, 0.3466, 0.5790, 0.5290],
[0.4598, 0.3012, 0.8132, 0.3359, 0.4055, 0.2180, 0.5332, 0.5154],
[0.4954, 0.3271, 0.8524, 0.3360, 0.3561, 0.3671, 0.6126, 0.5512]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6273, 0.4143, 0.8750, 0.5700, 0.3988, 0.4717, 0.6012, 0.5467],
[0.6125, 0.3983, 0.8750, 0.4867, 0.4275, 0.4783, 0.5412, 0.5717],
[0.6311, 0.4008, 0.7935, 0.5746, 0.3900, 0.5033, 0.6955, 0.5366],
[0.6179, 0.3998, 0.8396, 0.3505, 0.3552, 0.3768, 0.6064, 0.5329],
[0.6109, 0.3943, 0.8525, 0.4950, 0.4338, 0.4800, 0.5449, 0.5383],
[0.6200, 0.3993, 0.8639, 0.3687, 0.3658, 0.3139, 0.6002, 0.5374],
[0.6143, 0.4040, 0.8238, 0.3333, 0.4075, 0.2117, 0.5137, 0.4973],
[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.2111712924670428
step: 57
running loss: 0.003704759516965663
Train Steps: 57/90 Loss: 0.0037 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6229, 0.4107, 0.8137, 0.2883, 0.4750, 0.1717, 0.5813, 0.5400],
[0.6151, 0.4125, 0.8738, 0.4417, 0.3575, 0.3783, 0.5138, 0.5483],
[0.6090, 0.4010, 0.7838, 0.3483, 0.3538, 0.3783, 0.5462, 0.5077],
[0.6260, 0.4120, 0.8013, 0.2350, 0.4888, 0.1533, 0.6281, 0.4895],
[0.6275, 0.4008, 0.8047, 0.2484, 0.4037, 0.2777, 0.6506, 0.5212],
[ nan, nan, 0.6412, 0.1900, 0.4238, 0.1883, 0.5487, 0.5700],
[0.6357, 0.4097, 0.9038, 0.3883, 0.4213, 0.2950, 0.6686, 0.5390],
[0.6325, 0.4066, 0.8438, 0.5350, 0.3925, 0.5267, 0.7113, 0.5795]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5698, 0.3906, 0.7905, 0.3307, 0.4393, 0.2544, 0.5648, 0.5202],
[0.5052, 0.3361, 0.8728, 0.5273, 0.3377, 0.4399, 0.5142, 0.5462],
[0.5575, 0.3894, 0.8096, 0.3553, 0.3398, 0.4197, 0.5326, 0.4992],
[0.5576, 0.3766, 0.8028, 0.2573, 0.4620, 0.2038, 0.6238, 0.4937],
[0.5404, 0.3751, 0.8065, 0.2962, 0.4041, 0.3262, 0.5811, 0.5038],
[0.4746, 0.3273, 0.7100, 0.2725, 0.4144, 0.2445, 0.4917, 0.5355],
[0.5059, 0.3507, 0.8818, 0.4093, 0.3965, 0.3580, 0.6559, 0.5396],
[0.5314, 0.3847, 0.8582, 0.5777, 0.3785, 0.6152, 0.6551, 0.5945]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6229, 0.4107, 0.8138, 0.2883, 0.4750, 0.1717, 0.5813, 0.5400],
[0.6151, 0.4125, 0.8737, 0.4417, 0.3575, 0.3783, 0.5138, 0.5483],
[0.6090, 0.4010, 0.7837, 0.3483, 0.3537, 0.3783, 0.5462, 0.5077],
[0.6259, 0.4120, 0.8012, 0.2350, 0.4888, 0.1533, 0.6281, 0.4895],
[0.6275, 0.4008, 0.8047, 0.2484, 0.4037, 0.2777, 0.6506, 0.5212],
[0.0000, 0.0000, 0.6413, 0.1900, 0.4238, 0.1883, 0.5487, 0.5700],
[0.6357, 0.4097, 0.9038, 0.3883, 0.4212, 0.2950, 0.6686, 0.5390],
[0.6325, 0.4066, 0.8438, 0.5350, 0.3925, 0.5267, 0.7113, 0.5795]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0075, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0075, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.21865464956499636
step: 58
running loss: 0.003769907751120627
Train Steps: 58/90 Loss: 0.0038 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6218, 0.4098, 0.7238, 0.1850, 0.4238, 0.2517, 0.6288, 0.5350],
[0.6079, 0.3964, 0.7420, 0.2958, 0.3563, 0.2917, 0.5351, 0.4980],
[0.6264, 0.4049, 0.8988, 0.4633, 0.3813, 0.4983, 0.6326, 0.4843],
[0.6125, 0.4010, 0.8650, 0.4567, 0.3663, 0.3900, 0.5600, 0.5567],
[0.6222, 0.3937, 0.8350, 0.5617, 0.4138, 0.4600, 0.5800, 0.5233],
[0.6124, 0.4083, 0.6954, 0.3069, 0.3650, 0.2750, 0.5163, 0.5485],
[0.6131, 0.4064, 0.8638, 0.5200, 0.4788, 0.4783, 0.5258, 0.5867],
[0.6082, 0.4042, 0.6975, 0.1917, 0.4100, 0.1983, 0.5502, 0.5578]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5859, 0.4131, 0.7635, 0.2248, 0.4391, 0.2565, 0.6437, 0.5214],
[0.5467, 0.3847, 0.7767, 0.2812, 0.3527, 0.3002, 0.5714, 0.4764],
[0.5477, 0.3962, 0.9153, 0.4810, 0.3778, 0.5369, 0.6626, 0.4993],
[0.5260, 0.3667, 0.8673, 0.4650, 0.3777, 0.4376, 0.5970, 0.5427],
[0.4763, 0.3250, 0.8709, 0.5843, 0.4274, 0.4781, 0.5866, 0.5502],
[0.5177, 0.3731, 0.7484, 0.2848, 0.3712, 0.3071, 0.5603, 0.5259],
[0.6167, 0.4277, 0.8827, 0.5338, 0.4489, 0.4727, 0.6133, 0.5438],
[0.4654, 0.3342, 0.7150, 0.2396, 0.3987, 0.2010, 0.5648, 0.5176]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6218, 0.4098, 0.7237, 0.1850, 0.4238, 0.2517, 0.6288, 0.5350],
[0.6079, 0.3964, 0.7420, 0.2958, 0.3562, 0.2917, 0.5351, 0.4980],
[0.6264, 0.4049, 0.8988, 0.4633, 0.3812, 0.4983, 0.6326, 0.4843],
[0.6125, 0.4010, 0.8650, 0.4567, 0.3663, 0.3900, 0.5600, 0.5567],
[0.6222, 0.3937, 0.8350, 0.5617, 0.4137, 0.4600, 0.5800, 0.5233],
[0.6123, 0.4083, 0.6954, 0.3069, 0.3650, 0.2750, 0.5163, 0.5485],
[0.6132, 0.4063, 0.8637, 0.5200, 0.4787, 0.4783, 0.5258, 0.5867],
[0.6082, 0.4042, 0.6975, 0.1917, 0.4100, 0.1983, 0.5502, 0.5578]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.2205590239027515
step: 59
running loss: 0.0037382885407246016
Train Steps: 59/90 Loss: 0.0037 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6129, 0.3930, 0.8769, 0.5105, 0.4146, 0.5642, 0.6000, 0.5082],
[0.6273, 0.4143, 0.8750, 0.5700, 0.3987, 0.4717, 0.6013, 0.5467],
[0.6193, 0.4079, 0.7288, 0.2500, 0.4250, 0.2550, 0.5989, 0.6266],
[0.6175, 0.4091, 0.7863, 0.2800, 0.3638, 0.3583, 0.6188, 0.5433],
[0.6125, 0.3974, 0.7725, 0.2517, 0.3538, 0.3317, 0.5887, 0.5500],
[0.6271, 0.4024, 0.9000, 0.3517, 0.3700, 0.4517, 0.6931, 0.5285],
[0.6080, 0.4010, 0.8750, 0.4500, 0.4825, 0.5617, 0.5837, 0.5583],
[0.6131, 0.4064, 0.8638, 0.5200, 0.4788, 0.4783, 0.5258, 0.5867]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5923, 0.3933, 0.8322, 0.5039, 0.4399, 0.5371, 0.6048, 0.4884],
[0.5682, 0.3870, 0.8590, 0.5505, 0.3958, 0.4336, 0.6032, 0.5265],
[0.6281, 0.4465, 0.7253, 0.2506, 0.4124, 0.2161, 0.6342, 0.5426],
[0.5458, 0.3981, 0.7589, 0.2239, 0.3483, 0.3101, 0.6219, 0.4943],
[0.5405, 0.3728, 0.7586, 0.2376, 0.3597, 0.2994, 0.5904, 0.5146],
[0.5155, 0.3839, 0.8459, 0.3394, 0.3507, 0.4217, 0.7081, 0.4893],
[0.5667, 0.4076, 0.8640, 0.4323, 0.4619, 0.4661, 0.6003, 0.5212],
[0.6148, 0.4273, 0.8491, 0.5168, 0.4372, 0.4141, 0.5909, 0.5302]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6129, 0.3930, 0.8769, 0.5105, 0.4146, 0.5642, 0.6000, 0.5082],
[0.6273, 0.4143, 0.8750, 0.5700, 0.3988, 0.4717, 0.6012, 0.5467],
[0.6193, 0.4078, 0.7287, 0.2500, 0.4250, 0.2550, 0.5989, 0.6266],
[0.6175, 0.4091, 0.7862, 0.2800, 0.3638, 0.3583, 0.6187, 0.5433],
[0.6125, 0.3974, 0.7725, 0.2517, 0.3537, 0.3317, 0.5888, 0.5500],
[0.6271, 0.4024, 0.9000, 0.3517, 0.3700, 0.4517, 0.6931, 0.5285],
[0.6080, 0.4010, 0.8750, 0.4500, 0.4825, 0.5617, 0.5838, 0.5583],
[0.6132, 0.4063, 0.8637, 0.5200, 0.4787, 0.4783, 0.5258, 0.5867]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.22198802302591503
step: 60
running loss: 0.0036998003837652505
Train Steps: 60/90 Loss: 0.0037 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.7725, 0.2611, 0.3675, 0.2733, 0.5413, 0.5167],
[0.6350, 0.4118, 0.8363, 0.2717, 0.4850, 0.1700, 0.6441, 0.5170],
[0.6171, 0.4127, 0.8900, 0.4800, 0.4325, 0.5783, 0.5769, 0.5090],
[0.6222, 0.3937, 0.8350, 0.5617, 0.4138, 0.4600, 0.5800, 0.5233],
[0.6250, 0.3993, 0.9138, 0.4333, 0.3763, 0.5217, 0.6995, 0.5320],
[0.6229, 0.4066, 0.8513, 0.5717, 0.4500, 0.5050, 0.6025, 0.5350],
[0.6200, 0.4059, 0.8700, 0.4900, 0.4163, 0.5000, 0.6162, 0.5467],
[0.6161, 0.4040, 0.7525, 0.2133, 0.4125, 0.2067, 0.5787, 0.5117]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.1789, 0.1370, 0.7120, 0.2195, 0.3751, 0.2633, 0.5566, 0.5312],
[0.5631, 0.3876, 0.8010, 0.1853, 0.4524, 0.1427, 0.6686, 0.5063],
[0.6861, 0.4646, 0.8735, 0.4319, 0.4315, 0.5165, 0.5684, 0.5173],
[0.5888, 0.4002, 0.8069, 0.5105, 0.4057, 0.4213, 0.5696, 0.5447],
[0.7186, 0.4990, 0.8426, 0.4124, 0.3694, 0.4953, 0.7160, 0.5340],
[0.6200, 0.4549, 0.8096, 0.5021, 0.4174, 0.4357, 0.6127, 0.5518],
[0.6523, 0.4633, 0.8407, 0.4444, 0.4231, 0.4848, 0.6290, 0.5298],
[0.6444, 0.4142, 0.7149, 0.1780, 0.3949, 0.1900, 0.5875, 0.5107]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.7725, 0.2611, 0.3675, 0.2733, 0.5412, 0.5167],
[0.6350, 0.4118, 0.8363, 0.2717, 0.4850, 0.1700, 0.6441, 0.5170],
[0.6171, 0.4127, 0.8900, 0.4800, 0.4325, 0.5783, 0.5769, 0.5090],
[0.6222, 0.3937, 0.8350, 0.5617, 0.4137, 0.4600, 0.5800, 0.5233],
[0.6250, 0.3993, 0.9137, 0.4333, 0.3762, 0.5217, 0.6995, 0.5320],
[0.6229, 0.4066, 0.8512, 0.5717, 0.4500, 0.5050, 0.6025, 0.5350],
[0.6199, 0.4059, 0.8700, 0.4900, 0.4162, 0.5000, 0.6162, 0.5467],
[0.6161, 0.4040, 0.7525, 0.2133, 0.4125, 0.2067, 0.5788, 0.5117]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0023, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0023, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.22428614646196365
step: 61
running loss: 0.0036768220731469453
Train Steps: 61/90 Loss: 0.0037 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6260, 0.4106, 0.8025, 0.2583, 0.4550, 0.1867, 0.6281, 0.4869],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4012, 0.4633, 0.5338, 0.5767],
[0.6293, 0.4097, 0.8800, 0.2517, 0.5262, 0.2600, 0.7430, 0.5378],
[0.6279, 0.4008, 0.8600, 0.4883, 0.4325, 0.5283, 0.7010, 0.5378],
[0.6284, 0.4127, 0.8538, 0.5867, 0.4363, 0.5083, 0.6038, 0.5433],
[ nan, nan, 0.7425, 0.2117, 0.3937, 0.2433, 0.5438, 0.5567],
[0.6179, 0.4118, 0.7278, 0.4237, 0.3588, 0.3400, 0.5675, 0.5917],
[0.6222, 0.3957, 0.8838, 0.5017, 0.3937, 0.4600, 0.5900, 0.5017]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5691, 0.3808, 0.7564, 0.1777, 0.4299, 0.1889, 0.6466, 0.5016],
[0.6328, 0.4316, 0.8196, 0.4589, 0.4082, 0.4745, 0.5711, 0.5704],
[0.5339, 0.3510, 0.8157, 0.1961, 0.4921, 0.2346, 0.7271, 0.5324],
[0.7159, 0.4650, 0.8122, 0.4496, 0.4231, 0.5123, 0.6721, 0.5393],
[0.6640, 0.4476, 0.8020, 0.5129, 0.4045, 0.4800, 0.5805, 0.5495],
[0.2912, 0.1803, 0.7068, 0.2265, 0.4071, 0.2261, 0.5405, 0.5527],
[0.6205, 0.4289, 0.7558, 0.3432, 0.3518, 0.3197, 0.5453, 0.5625],
[0.6474, 0.4268, 0.8590, 0.4616, 0.3832, 0.4418, 0.6134, 0.5029]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6260, 0.4106, 0.8025, 0.2583, 0.4550, 0.1867, 0.6281, 0.4869],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4013, 0.4633, 0.5337, 0.5767],
[0.6293, 0.4097, 0.8800, 0.2517, 0.5263, 0.2600, 0.7430, 0.5378],
[0.6279, 0.4008, 0.8600, 0.4883, 0.4325, 0.5283, 0.7010, 0.5378],
[0.6284, 0.4127, 0.8537, 0.5867, 0.4363, 0.5083, 0.6037, 0.5433],
[0.0000, 0.0000, 0.7425, 0.2117, 0.3938, 0.2433, 0.5437, 0.5567],
[0.6179, 0.4118, 0.7278, 0.4237, 0.3587, 0.3400, 0.5675, 0.5917],
[0.6222, 0.3957, 0.8838, 0.5017, 0.3938, 0.4600, 0.5900, 0.5017]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0032, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0032, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.22752876160666347
step: 62
running loss: 0.003669818735591346
Train Steps: 62/90 Loss: 0.0037 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6182, 0.4058, 0.8738, 0.4350, 0.3563, 0.3400, 0.5290, 0.5822],
[0.6225, 0.4116, 0.8662, 0.3517, 0.3663, 0.3233, 0.5837, 0.5317],
[0.6267, 0.4094, 0.8712, 0.3083, 0.4400, 0.2267, 0.6250, 0.5200],
[0.6129, 0.4114, 0.6950, 0.2467, 0.4050, 0.2133, 0.5363, 0.5550],
[0.6143, 0.4040, 0.8237, 0.3333, 0.4075, 0.2117, 0.5137, 0.4973],
[0.6197, 0.4090, 0.7825, 0.2500, 0.4200, 0.2483, 0.5988, 0.5667],
[0.6339, 0.4123, 0.8638, 0.5367, 0.4075, 0.5467, 0.7517, 0.5436],
[0.6109, 0.4036, 0.7188, 0.1750, 0.3850, 0.2550, 0.5863, 0.5567]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6034, 0.3830, 0.8470, 0.4437, 0.3738, 0.3747, 0.5338, 0.5797],
[0.5444, 0.3546, 0.8087, 0.3473, 0.3960, 0.3135, 0.6162, 0.5542],
[0.5521, 0.3261, 0.8409, 0.3032, 0.4649, 0.2440, 0.6543, 0.5259],
[0.5926, 0.3772, 0.6626, 0.2557, 0.4032, 0.2445, 0.5561, 0.5455],
[0.5108, 0.3200, 0.7701, 0.3098, 0.4265, 0.2208, 0.5590, 0.5159],
[0.6456, 0.4156, 0.7671, 0.2335, 0.4370, 0.2696, 0.6316, 0.5587],
[0.6134, 0.4167, 0.8674, 0.5409, 0.4430, 0.5818, 0.7387, 0.5563],
[0.6006, 0.3781, 0.6835, 0.2165, 0.4343, 0.2681, 0.5758, 0.5471]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6182, 0.4058, 0.8737, 0.4350, 0.3562, 0.3400, 0.5290, 0.5822],
[0.6225, 0.4116, 0.8662, 0.3517, 0.3663, 0.3233, 0.5838, 0.5317],
[0.6267, 0.4094, 0.8712, 0.3083, 0.4400, 0.2267, 0.6250, 0.5200],
[0.6129, 0.4114, 0.6950, 0.2467, 0.4050, 0.2133, 0.5362, 0.5550],
[0.6143, 0.4040, 0.8238, 0.3333, 0.4075, 0.2117, 0.5137, 0.4973],
[0.6197, 0.4090, 0.7825, 0.2500, 0.4200, 0.2483, 0.5987, 0.5667],
[0.6339, 0.4123, 0.8637, 0.5367, 0.4075, 0.5467, 0.7517, 0.5436],
[0.6108, 0.4036, 0.7188, 0.1750, 0.3850, 0.2550, 0.5863, 0.5567]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.22869582765270025
step: 63
running loss: 0.0036300925024238136
Train Steps: 63/90 Loss: 0.0036 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6275, 0.4111, 0.8463, 0.2617, 0.4487, 0.1983, 0.6211, 0.4904],
[0.6037, 0.4020, 0.8300, 0.4033, 0.3575, 0.4883, 0.5647, 0.5631],
[0.6339, 0.4081, 0.8425, 0.5417, 0.3850, 0.4833, 0.7335, 0.5760],
[ nan, nan, 0.7981, 0.3194, 0.3625, 0.3167, 0.5040, 0.5563],
[ nan, nan, 0.8675, 0.2833, 0.5350, 0.1983, 0.6678, 0.5621],
[0.6136, 0.3955, 0.8400, 0.3267, 0.3500, 0.4200, 0.5863, 0.5467],
[0.6145, 0.3983, 0.8700, 0.5017, 0.4400, 0.4800, 0.5375, 0.5750],
[0.6329, 0.4055, 0.9050, 0.4783, 0.3613, 0.3917, 0.6464, 0.5019]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6140, 0.3829, 0.8532, 0.2711, 0.4873, 0.2148, 0.6442, 0.5450],
[0.6847, 0.4150, 0.8289, 0.3931, 0.3653, 0.4806, 0.6040, 0.5475],
[0.7392, 0.4679, 0.8294, 0.5288, 0.4050, 0.5031, 0.6651, 0.5992],
[0.4096, 0.2648, 0.7645, 0.3139, 0.3828, 0.2889, 0.5430, 0.5730],
[0.1937, 0.0940, 0.8403, 0.2669, 0.5400, 0.2014, 0.6737, 0.5628],
[0.7099, 0.4543, 0.8390, 0.3263, 0.3754, 0.4002, 0.5924, 0.5534],
[0.7283, 0.4502, 0.8550, 0.4972, 0.4617, 0.4719, 0.5788, 0.5715],
[0.7993, 0.4937, 0.9025, 0.4761, 0.4007, 0.3892, 0.6428, 0.5437]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6275, 0.4111, 0.8462, 0.2617, 0.4487, 0.1983, 0.6211, 0.4904],
[0.6037, 0.4020, 0.8300, 0.4033, 0.3575, 0.4883, 0.5647, 0.5631],
[0.6339, 0.4081, 0.8425, 0.5417, 0.3850, 0.4833, 0.7335, 0.5760],
[0.0000, 0.0000, 0.7981, 0.3194, 0.3625, 0.3167, 0.5040, 0.5563],
[0.0000, 0.0000, 0.8675, 0.2833, 0.5350, 0.1983, 0.6678, 0.5621],
[0.6136, 0.3955, 0.8400, 0.3267, 0.3500, 0.4200, 0.5863, 0.5467],
[0.6145, 0.3983, 0.8700, 0.5017, 0.4400, 0.4800, 0.5375, 0.5750],
[0.6329, 0.4055, 0.9050, 0.4783, 0.3613, 0.3917, 0.6464, 0.5019]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0062, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0062, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.23489011928904802
step: 64
running loss: 0.0036701581138913753
Train Steps: 64/90 Loss: 0.0037 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.9088, 0.3783, 0.4562, 0.2617, 0.6741, 0.5575],
[0.6263, 0.4030, 0.9000, 0.4767, 0.3800, 0.5167, 0.6415, 0.4771],
[0.6137, 0.4084, 0.8076, 0.3889, 0.3650, 0.3150, 0.5356, 0.5896],
[0.6117, 0.4018, 0.6562, 0.1967, 0.3738, 0.2550, 0.5280, 0.5103],
[0.6127, 0.4119, 0.8650, 0.5300, 0.4512, 0.5250, 0.5260, 0.5461],
[0.6161, 0.4040, 0.7525, 0.2133, 0.4125, 0.2067, 0.5787, 0.5117],
[0.6102, 0.4005, 0.8688, 0.5100, 0.4813, 0.5400, 0.5404, 0.5064],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.2212, 0.1345, 0.9286, 0.3959, 0.4843, 0.2741, 0.6916, 0.6015],
[0.6566, 0.4074, 0.9196, 0.4697, 0.3683, 0.5070, 0.6453, 0.4970],
[0.5537, 0.3543, 0.8277, 0.3884, 0.3790, 0.2970, 0.5461, 0.5881],
[0.5645, 0.3503, 0.6897, 0.2247, 0.3856, 0.2232, 0.5269, 0.5686],
[0.6891, 0.4353, 0.8483, 0.5375, 0.4398, 0.4830, 0.5719, 0.5832],
[0.6096, 0.3528, 0.7507, 0.2245, 0.4239, 0.2051, 0.5894, 0.5566],
[0.6337, 0.3920, 0.8727, 0.5009, 0.4832, 0.4534, 0.5873, 0.5605],
[0.6439, 0.4225, 0.8797, 0.4280, 0.4242, 0.4819, 0.6083, 0.5413]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.9087, 0.3783, 0.4563, 0.2617, 0.6741, 0.5575],
[0.6263, 0.4029, 0.9000, 0.4767, 0.3800, 0.5167, 0.6415, 0.4771],
[0.6137, 0.4084, 0.8076, 0.3889, 0.3650, 0.3150, 0.5356, 0.5896],
[0.6116, 0.4018, 0.6562, 0.1967, 0.3738, 0.2550, 0.5280, 0.5103],
[0.6127, 0.4119, 0.8650, 0.5300, 0.4512, 0.5250, 0.5260, 0.5461],
[0.6161, 0.4040, 0.7525, 0.2133, 0.4125, 0.2067, 0.5788, 0.5117],
[0.6102, 0.4005, 0.8687, 0.5100, 0.4812, 0.5400, 0.5404, 0.5064],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0020, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0020, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.23684400937054306
step: 65
running loss: 0.003643753990316047
Train Steps: 65/90 Loss: 0.0036 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6332, 0.4118, 0.9238, 0.4267, 0.4012, 0.4733, 0.7525, 0.5436],
[0.6147, 0.4026, 0.6600, 0.2467, 0.4088, 0.2150, 0.5489, 0.5773],
[0.6222, 0.4172, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633],
[ nan, nan, 0.7225, 0.2167, 0.3987, 0.2283, 0.5427, 0.5181],
[0.6226, 0.4103, 0.8575, 0.3450, 0.4388, 0.2067, 0.5787, 0.5383],
[0.6234, 0.4023, 0.8888, 0.4633, 0.3975, 0.5767, 0.6400, 0.5183],
[0.6202, 0.4053, 0.8638, 0.5283, 0.4546, 0.5108, 0.5900, 0.5133],
[0.6254, 0.4076, 0.8700, 0.3267, 0.4150, 0.3083, 0.7050, 0.5609]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7355, 0.4587, 0.9337, 0.4735, 0.4093, 0.4814, 0.7177, 0.5522],
[0.5557, 0.3274, 0.7331, 0.2659, 0.4116, 0.2238, 0.4978, 0.5754],
[0.7013, 0.4191, 0.9234, 0.5755, 0.3711, 0.4749, 0.5756, 0.5564],
[0.0530, 0.0123, 0.7388, 0.2372, 0.4230, 0.2440, 0.5240, 0.5477],
[0.5336, 0.3270, 0.8849, 0.3829, 0.4673, 0.2350, 0.5589, 0.5687],
[0.6730, 0.3989, 0.9308, 0.5037, 0.4046, 0.6039, 0.6622, 0.5154],
[0.6858, 0.4156, 0.8866, 0.5624, 0.4506, 0.5007, 0.5818, 0.5358],
[0.5166, 0.3204, 0.9286, 0.3357, 0.4373, 0.2783, 0.6617, 0.5548]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6332, 0.4118, 0.9237, 0.4267, 0.4013, 0.4733, 0.7525, 0.5436],
[0.6147, 0.4026, 0.6600, 0.2467, 0.4087, 0.2150, 0.5489, 0.5773],
[0.6222, 0.4171, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633],
[0.0000, 0.0000, 0.7225, 0.2167, 0.3988, 0.2283, 0.5427, 0.5181],
[0.6226, 0.4103, 0.8575, 0.3450, 0.4387, 0.2067, 0.5788, 0.5383],
[0.6234, 0.4023, 0.8888, 0.4633, 0.3975, 0.5767, 0.6400, 0.5183],
[0.6202, 0.4053, 0.8637, 0.5283, 0.4546, 0.5108, 0.5900, 0.5133],
[0.6254, 0.4076, 0.8700, 0.3267, 0.4150, 0.3083, 0.7050, 0.5609]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.2385742465266958
step: 66
running loss: 0.003614761311010542
Train Steps: 66/90 Loss: 0.0036 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6364, 0.4165, 0.9088, 0.4367, 0.4075, 0.3150, 0.6448, 0.5297],
[ nan, nan, 0.7553, 0.2722, 0.3875, 0.2550, 0.5125, 0.5633],
[0.6034, 0.4011, 0.7350, 0.2533, 0.3438, 0.3367, 0.5516, 0.5084],
[ nan, nan, 0.6488, 0.1817, 0.4325, 0.1867, 0.5475, 0.5733],
[0.6186, 0.4154, 0.6825, 0.2633, 0.4150, 0.2300, 0.5713, 0.5517],
[0.6143, 0.4055, 0.8150, 0.2767, 0.3825, 0.2567, 0.5173, 0.4901],
[0.6186, 0.4060, 0.8750, 0.5050, 0.3538, 0.4367, 0.5813, 0.6083],
[0.6097, 0.4024, 0.8488, 0.3717, 0.3875, 0.5517, 0.5836, 0.5591]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6671, 0.4208, 0.9785, 0.5062, 0.4243, 0.3026, 0.6318, 0.5373],
[0.1790, 0.0846, 0.8194, 0.3341, 0.4027, 0.3083, 0.5173, 0.5482],
[0.6645, 0.4287, 0.7940, 0.3145, 0.3603, 0.3541, 0.5978, 0.5310],
[0.2190, 0.1470, 0.7626, 0.2580, 0.4547, 0.2251, 0.5737, 0.5546],
[0.5184, 0.3228, 0.7564, 0.3006, 0.4239, 0.2514, 0.5888, 0.5536],
[0.5250, 0.3274, 0.8387, 0.3473, 0.3684, 0.2694, 0.5364, 0.5339],
[0.6058, 0.3866, 0.9575, 0.5627, 0.4092, 0.5112, 0.6149, 0.5469],
[0.6870, 0.4104, 0.9199, 0.4403, 0.4319, 0.5612, 0.6627, 0.5029]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6364, 0.4165, 0.9087, 0.4367, 0.4075, 0.3150, 0.6448, 0.5297],
[0.0000, 0.0000, 0.7553, 0.2722, 0.3875, 0.2550, 0.5125, 0.5633],
[0.6033, 0.4011, 0.7350, 0.2533, 0.3438, 0.3367, 0.5516, 0.5084],
[0.0000, 0.0000, 0.6488, 0.1817, 0.4325, 0.1867, 0.5475, 0.5733],
[0.6186, 0.4154, 0.6825, 0.2633, 0.4150, 0.2300, 0.5713, 0.5517],
[0.6143, 0.4055, 0.8150, 0.2767, 0.3825, 0.2567, 0.5173, 0.4901],
[0.6186, 0.4060, 0.8750, 0.5050, 0.3537, 0.4367, 0.5813, 0.6083],
[0.6097, 0.4024, 0.8487, 0.3717, 0.3875, 0.5517, 0.5836, 0.5591]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0042, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0042, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.24276340811047703
step: 67
running loss: 0.003623334449410105
Train Steps: 67/90 Loss: 0.0036 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6246, 0.4126, 0.8850, 0.4833, 0.4200, 0.5350, 0.6112, 0.5250],
[0.6132, 0.4066, 0.7259, 0.2402, 0.3588, 0.3300, 0.6000, 0.5600],
[0.6250, 0.4146, 0.8838, 0.3933, 0.3588, 0.4283, 0.6162, 0.5367],
[0.6193, 0.4108, 0.7438, 0.2700, 0.3650, 0.3683, 0.6238, 0.5717],
[ nan, nan, 0.6512, 0.1717, 0.4100, 0.1983, 0.5253, 0.5240],
[0.6286, 0.4055, 0.9000, 0.4717, 0.3763, 0.4683, 0.7018, 0.5494],
[0.6182, 0.3930, 0.8841, 0.3892, 0.3556, 0.4967, 0.6222, 0.5279],
[0.6197, 0.4090, 0.7825, 0.2500, 0.4200, 0.2483, 0.5988, 0.5667]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5577, 0.3404, 0.9322, 0.5424, 0.4028, 0.5637, 0.5783, 0.5157],
[0.5639, 0.3888, 0.7683, 0.2950, 0.3763, 0.3433, 0.5770, 0.5662],
[0.5509, 0.3533, 0.9084, 0.4569, 0.3602, 0.3963, 0.5602, 0.4995],
[0.6154, 0.3938, 0.8092, 0.3178, 0.3638, 0.3636, 0.5955, 0.5416],
[0.0305, 0.0186, 0.7465, 0.2533, 0.4329, 0.2216, 0.5314, 0.5542],
[0.5792, 0.3591, 0.9353, 0.5333, 0.3668, 0.4853, 0.6384, 0.5251],
[0.5785, 0.3509, 0.9181, 0.4518, 0.3553, 0.4828, 0.6251, 0.5212],
[0.5584, 0.3610, 0.8354, 0.2901, 0.4220, 0.2634, 0.5679, 0.5586]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6246, 0.4126, 0.8850, 0.4833, 0.4200, 0.5350, 0.6112, 0.5250],
[0.6132, 0.4066, 0.7259, 0.2402, 0.3587, 0.3300, 0.6000, 0.5600],
[0.6250, 0.4146, 0.8838, 0.3933, 0.3587, 0.4283, 0.6162, 0.5367],
[0.6193, 0.4108, 0.7437, 0.2700, 0.3650, 0.3683, 0.6237, 0.5717],
[0.0000, 0.0000, 0.6513, 0.1717, 0.4100, 0.1983, 0.5253, 0.5240],
[0.6286, 0.4055, 0.9000, 0.4717, 0.3762, 0.4683, 0.7018, 0.5494],
[0.6182, 0.3930, 0.8841, 0.3892, 0.3556, 0.4967, 0.6222, 0.5279],
[0.6197, 0.4090, 0.7825, 0.2500, 0.4200, 0.2483, 0.5987, 0.5667]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.24445695418398827
step: 68
running loss: 0.003594955208588063
Train Steps: 68/90 Loss: 0.0036 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6189, 0.4029, 0.8375, 0.5767, 0.4745, 0.4829, 0.5551, 0.5598],
[ nan, nan, 0.7268, 0.2333, 0.4125, 0.1933, 0.5112, 0.5383],
[0.6259, 0.4156, 0.8812, 0.3183, 0.4775, 0.1867, 0.6219, 0.4960],
[0.6197, 0.3930, 0.8793, 0.4736, 0.4152, 0.5464, 0.6308, 0.5235],
[0.6250, 0.4013, 0.8525, 0.5417, 0.4037, 0.5117, 0.6325, 0.5017],
[0.6236, 0.3967, 0.8675, 0.5400, 0.3862, 0.4517, 0.5825, 0.5200],
[0.6208, 0.4082, 0.8538, 0.3067, 0.3588, 0.3717, 0.6112, 0.5517],
[0.6127, 0.4119, 0.8650, 0.5300, 0.4512, 0.5250, 0.5260, 0.5461]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.5516, 0.3771, 0.8252, 0.4969, 0.4173, 0.4475, 0.5955, 0.5628],
[-0.0498, -0.0271, 0.7035, 0.1818, 0.3952, 0.2227, 0.5223, 0.5519],
[ 0.4824, 0.3117, 0.8709, 0.2582, 0.4267, 0.2320, 0.6016, 0.5198],
[ 0.5551, 0.3592, 0.8599, 0.4213, 0.3784, 0.5226, 0.6311, 0.5210],
[ 0.5545, 0.3603, 0.8491, 0.4894, 0.3806, 0.5112, 0.6097, 0.5152],
[ 0.5212, 0.3685, 0.8626, 0.5007, 0.3574, 0.4597, 0.5946, 0.5317],
[ 0.5741, 0.3873, 0.8403, 0.2797, 0.3233, 0.3746, 0.6037, 0.5376],
[ 0.5667, 0.3745, 0.8423, 0.4916, 0.4029, 0.5023, 0.5392, 0.5470]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6189, 0.4029, 0.8375, 0.5767, 0.4745, 0.4829, 0.5551, 0.5598],
[0.0000, 0.0000, 0.7268, 0.2333, 0.4125, 0.1933, 0.5113, 0.5383],
[0.6259, 0.4156, 0.8813, 0.3183, 0.4775, 0.1867, 0.6219, 0.4960],
[0.6197, 0.3930, 0.8793, 0.4736, 0.4152, 0.5464, 0.6308, 0.5235],
[0.6250, 0.4013, 0.8525, 0.5417, 0.4038, 0.5117, 0.6325, 0.5017],
[0.6236, 0.3967, 0.8675, 0.5400, 0.3862, 0.4517, 0.5825, 0.5200],
[0.6208, 0.4082, 0.8537, 0.3067, 0.3587, 0.3717, 0.6112, 0.5517],
[0.6127, 0.4119, 0.8650, 0.5300, 0.4512, 0.5250, 0.5260, 0.5461]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0018, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0018, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.24625502328854054
step: 69
running loss: 0.003568913380993341
Train Steps: 69/90 Loss: 0.0036 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6193, 0.4050, 0.7313, 0.2433, 0.4075, 0.2117, 0.5649, 0.5656],
[0.6260, 0.4120, 0.8013, 0.2350, 0.4888, 0.1533, 0.6281, 0.4895],
[0.6357, 0.4118, 0.8400, 0.2500, 0.5413, 0.1633, 0.6725, 0.5586],
[0.6282, 0.4034, 0.7830, 0.2080, 0.4532, 0.2080, 0.6404, 0.5323],
[0.6160, 0.4086, 0.8775, 0.3983, 0.3750, 0.3783, 0.5128, 0.4882],
[0.6188, 0.4099, 0.7400, 0.2433, 0.3962, 0.2750, 0.6162, 0.5467],
[0.6228, 0.4004, 0.8750, 0.5250, 0.3825, 0.5233, 0.6362, 0.5000],
[0.6293, 0.3982, 0.8700, 0.5300, 0.3763, 0.4717, 0.7050, 0.5297]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4102, 0.2683, 0.7072, 0.2315, 0.3801, 0.3003, 0.5461, 0.5529],
[0.4654, 0.3223, 0.7671, 0.2061, 0.4613, 0.2163, 0.6026, 0.5000],
[0.3718, 0.2384, 0.8290, 0.2430, 0.4869, 0.2548, 0.6139, 0.5142],
[0.4628, 0.3322, 0.7671, 0.2106, 0.4033, 0.2363, 0.5672, 0.5524],
[0.4736, 0.3394, 0.8669, 0.4077, 0.3232, 0.4130, 0.5212, 0.5193],
[0.5163, 0.3695, 0.7215, 0.2309, 0.3828, 0.3317, 0.5854, 0.5381],
[0.5423, 0.3440, 0.8990, 0.5151, 0.3579, 0.5819, 0.5909, 0.5004],
[0.5993, 0.3707, 0.8675, 0.5264, 0.3271, 0.5180, 0.6483, 0.5365]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6193, 0.4050, 0.7312, 0.2433, 0.4075, 0.2117, 0.5649, 0.5656],
[0.6259, 0.4120, 0.8012, 0.2350, 0.4888, 0.1533, 0.6281, 0.4895],
[0.6357, 0.4118, 0.8400, 0.2500, 0.5412, 0.1633, 0.6725, 0.5586],
[0.6282, 0.4034, 0.7830, 0.2080, 0.4532, 0.2080, 0.6404, 0.5323],
[0.6160, 0.4086, 0.8775, 0.3983, 0.3750, 0.3783, 0.5128, 0.4882],
[0.6188, 0.4099, 0.7400, 0.2433, 0.3963, 0.2750, 0.6162, 0.5467],
[0.6228, 0.4004, 0.8750, 0.5250, 0.3825, 0.5233, 0.6363, 0.5000],
[0.6293, 0.3982, 0.8700, 0.5300, 0.3762, 0.4717, 0.7050, 0.5297]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0054, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0054, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.25164759380277246
step: 70
running loss: 0.003594965625753892
Train Steps: 70/90 Loss: 0.0036 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6118, 0.4052, 0.8463, 0.3917, 0.3538, 0.3450, 0.5053, 0.5593],
[0.6197, 0.4050, 0.7527, 0.2000, 0.4042, 0.2249, 0.5895, 0.4995],
[0.6353, 0.4128, 0.8488, 0.2600, 0.5525, 0.1616, 0.6694, 0.5540],
[0.6193, 0.4050, 0.7313, 0.2433, 0.4075, 0.2117, 0.5649, 0.5656],
[0.6286, 0.3977, 0.9038, 0.4733, 0.3900, 0.4150, 0.7074, 0.5320],
[0.6186, 0.4013, 0.8191, 0.3188, 0.4279, 0.2060, 0.5767, 0.5411],
[0.6189, 0.4049, 0.8888, 0.4417, 0.4213, 0.5200, 0.5988, 0.5633],
[0.6129, 0.4069, 0.8750, 0.5067, 0.3875, 0.4233, 0.5235, 0.5881]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4371, 0.3352, 0.8117, 0.3662, 0.3465, 0.3646, 0.4915, 0.5341],
[0.4829, 0.3549, 0.7093, 0.1705, 0.4160, 0.2348, 0.6135, 0.5019],
[0.3030, 0.1993, 0.7985, 0.2163, 0.5106, 0.2201, 0.6479, 0.5032],
[0.4934, 0.3381, 0.6827, 0.2094, 0.3904, 0.2574, 0.5596, 0.5345],
[0.7015, 0.4689, 0.8686, 0.4039, 0.3264, 0.4478, 0.6475, 0.4829],
[0.4930, 0.3494, 0.7581, 0.2368, 0.4055, 0.2341, 0.5452, 0.5235],
[0.5343, 0.3676, 0.8534, 0.4128, 0.4094, 0.5396, 0.5989, 0.5252],
[0.5998, 0.4077, 0.8622, 0.5105, 0.3764, 0.4379, 0.5306, 0.5128]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6118, 0.4052, 0.8462, 0.3917, 0.3537, 0.3450, 0.5053, 0.5593],
[0.6197, 0.4050, 0.7527, 0.2000, 0.4042, 0.2249, 0.5895, 0.4995],
[0.6353, 0.4128, 0.8487, 0.2600, 0.5525, 0.1616, 0.6694, 0.5540],
[0.6193, 0.4050, 0.7312, 0.2433, 0.4075, 0.2117, 0.5649, 0.5656],
[0.6286, 0.3977, 0.9038, 0.4733, 0.3900, 0.4150, 0.7074, 0.5320],
[0.6186, 0.4013, 0.8191, 0.3188, 0.4279, 0.2060, 0.5767, 0.5411],
[0.6189, 0.4049, 0.8888, 0.4417, 0.4212, 0.5200, 0.5987, 0.5633],
[0.6129, 0.4069, 0.8750, 0.5067, 0.3875, 0.4233, 0.5235, 0.5881]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0053, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0053, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.2569181363796815
step: 71
running loss: 0.003618565301122275
Train Steps: 71/90 Loss: 0.0036 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6277, 0.4036, 0.8688, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742],
[0.6311, 0.4008, 0.7935, 0.5746, 0.3900, 0.5033, 0.6955, 0.5366],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5413, 0.5683],
[0.6147, 0.4112, 0.7988, 0.3200, 0.3775, 0.2767, 0.5150, 0.5550],
[0.6161, 0.4099, 0.8738, 0.4383, 0.3788, 0.5483, 0.5605, 0.5019],
[0.6204, 0.4091, 0.8950, 0.4783, 0.3613, 0.4617, 0.6063, 0.5617],
[0.6250, 0.4008, 0.8950, 0.4183, 0.3550, 0.4383, 0.6361, 0.4927],
[0.6296, 0.4060, 0.9100, 0.3267, 0.4726, 0.3367, 0.7446, 0.5355]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7440, 0.5025, 0.8211, 0.2773, 0.4304, 0.2292, 0.6325, 0.4862],
[0.5843, 0.4262, 0.7705, 0.4431, 0.4198, 0.4516, 0.6558, 0.5235],
[0.5360, 0.3710, 0.8328, 0.4776, 0.3894, 0.3353, 0.5496, 0.5669],
[0.3983, 0.3095, 0.7359, 0.2769, 0.4089, 0.2535, 0.5024, 0.5584],
[0.6206, 0.4284, 0.8121, 0.3538, 0.3933, 0.5180, 0.5663, 0.5119],
[0.6116, 0.4225, 0.8465, 0.4352, 0.3794, 0.4521, 0.5980, 0.5525],
[0.6379, 0.4404, 0.8386, 0.3539, 0.3735, 0.4274, 0.6420, 0.5186],
[0.5376, 0.3719, 0.8287, 0.2723, 0.4434, 0.2788, 0.6565, 0.5224]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6277, 0.4036, 0.8687, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742],
[0.6311, 0.4008, 0.7935, 0.5746, 0.3900, 0.5033, 0.6955, 0.5366],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5412, 0.5683],
[0.6147, 0.4112, 0.7987, 0.3200, 0.3775, 0.2767, 0.5150, 0.5550],
[0.6161, 0.4099, 0.8737, 0.4383, 0.3787, 0.5483, 0.5605, 0.5019],
[0.6204, 0.4091, 0.8950, 0.4783, 0.3613, 0.4617, 0.6062, 0.5617],
[0.6250, 0.4008, 0.8950, 0.4183, 0.3550, 0.4383, 0.6361, 0.4927],
[0.6296, 0.4060, 0.9100, 0.3267, 0.4726, 0.3367, 0.7446, 0.5355]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0032, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0032, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.26006837061140686
step: 72
running loss: 0.0036120607029362065
Train Steps: 72/90 Loss: 0.0036 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6229, 0.4066, 0.8513, 0.5717, 0.4500, 0.5050, 0.6025, 0.5350],
[0.6250, 0.4116, 0.8700, 0.4850, 0.4650, 0.5567, 0.6088, 0.5183],
[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383],
[0.6122, 0.4048, 0.7506, 0.3014, 0.3475, 0.3333, 0.5487, 0.5749],
[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459],
[0.6168, 0.4029, 0.8523, 0.3417, 0.3588, 0.5000, 0.6125, 0.5400],
[0.6314, 0.4050, 0.8227, 0.5431, 0.4150, 0.5517, 0.7121, 0.5690],
[0.6204, 0.4091, 0.8950, 0.4783, 0.3613, 0.4617, 0.6063, 0.5617]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5909, 0.4132, 0.8230, 0.5111, 0.4550, 0.3941, 0.5952, 0.5519],
[0.6030, 0.4113, 0.8529, 0.4071, 0.4819, 0.4526, 0.6298, 0.5334],
[0.6145, 0.4201, 0.8440, 0.3966, 0.4589, 0.4681, 0.6126, 0.5336],
[0.6355, 0.4346, 0.7490, 0.2479, 0.3614, 0.2378, 0.5285, 0.5285],
[0.6995, 0.5085, 0.8196, 0.2540, 0.4860, 0.1383, 0.6536, 0.5236],
[0.6006, 0.4164, 0.8114, 0.3042, 0.3536, 0.4077, 0.6028, 0.5390],
[0.6246, 0.4432, 0.8034, 0.4662, 0.4182, 0.4467, 0.6713, 0.5607],
[0.6711, 0.4687, 0.8610, 0.4468, 0.3593, 0.3986, 0.5906, 0.5496]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6229, 0.4066, 0.8512, 0.5717, 0.4500, 0.5050, 0.6025, 0.5350],
[0.6251, 0.4116, 0.8700, 0.4850, 0.4650, 0.5567, 0.6087, 0.5183],
[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383],
[0.6122, 0.4048, 0.7506, 0.3014, 0.3475, 0.3333, 0.5487, 0.5749],
[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459],
[0.6168, 0.4029, 0.8523, 0.3417, 0.3587, 0.5000, 0.6125, 0.5400],
[0.6314, 0.4050, 0.8227, 0.5431, 0.4150, 0.5517, 0.7121, 0.5690],
[0.6204, 0.4091, 0.8950, 0.4783, 0.3613, 0.4617, 0.6062, 0.5617]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0022, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0022, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.2622584825148806
step: 73
running loss: 0.0035925819522586383
Train Steps: 73/90 Loss: 0.0036 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6161, 0.4076, 0.8900, 0.4667, 0.4125, 0.5917, 0.6262, 0.5367],
[0.6164, 0.3972, 0.7818, 0.3381, 0.3599, 0.3387, 0.5880, 0.5153],
[0.6205, 0.4004, 0.8938, 0.4883, 0.3663, 0.5000, 0.6357, 0.4947],
[0.6095, 0.3970, 0.8688, 0.4767, 0.4860, 0.4879, 0.5191, 0.4940],
[0.6086, 0.3998, 0.8788, 0.4450, 0.4025, 0.4650, 0.5306, 0.5103],
[0.6257, 0.4167, 0.8775, 0.3433, 0.3563, 0.4133, 0.6200, 0.5667],
[0.6289, 0.4024, 0.9088, 0.4567, 0.3937, 0.5633, 0.7058, 0.5609],
[0.6264, 0.4248, 0.8938, 0.4183, 0.3875, 0.4100, 0.5400, 0.5350]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6593, 0.4456, 0.8539, 0.4580, 0.4526, 0.5123, 0.6356, 0.5641],
[0.8243, 0.5577, 0.7724, 0.3118, 0.3512, 0.2677, 0.6180, 0.5296],
[0.6100, 0.3944, 0.8633, 0.4584, 0.3923, 0.4094, 0.6911, 0.5411],
[0.7037, 0.4569, 0.8566, 0.4849, 0.4779, 0.3771, 0.5572, 0.5403],
[0.6089, 0.4352, 0.8558, 0.4276, 0.4084, 0.3731, 0.5672, 0.5224],
[0.7343, 0.5111, 0.8361, 0.3372, 0.3965, 0.3233, 0.6683, 0.5543],
[0.6134, 0.4223, 0.8518, 0.4732, 0.4324, 0.4890, 0.7007, 0.5811],
[0.5786, 0.4307, 0.8439, 0.4056, 0.3870, 0.3162, 0.5765, 0.5565]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6161, 0.4076, 0.8900, 0.4667, 0.4125, 0.5917, 0.6263, 0.5367],
[0.6164, 0.3972, 0.7818, 0.3381, 0.3599, 0.3387, 0.5880, 0.5153],
[0.6205, 0.4004, 0.8938, 0.4883, 0.3663, 0.5000, 0.6357, 0.4947],
[0.6095, 0.3970, 0.8687, 0.4767, 0.4860, 0.4879, 0.5191, 0.4940],
[0.6086, 0.3998, 0.8788, 0.4450, 0.4025, 0.4650, 0.5306, 0.5103],
[0.6257, 0.4167, 0.8775, 0.3433, 0.3562, 0.4133, 0.6200, 0.5667],
[0.6289, 0.4024, 0.9087, 0.4567, 0.3938, 0.5633, 0.7058, 0.5609],
[0.6264, 0.4248, 0.8938, 0.4183, 0.3875, 0.4100, 0.5400, 0.5350]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0032, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0032, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.26550832379143685
step: 74
running loss: 0.0035879503215059034
Train Steps: 74/90 Loss: 0.0036 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6124, 0.4069, 0.8314, 0.5001, 0.3738, 0.4650, 0.5167, 0.5402],
[0.6197, 0.3930, 0.8793, 0.4736, 0.4152, 0.5464, 0.6308, 0.5235],
[0.6275, 0.4071, 0.8075, 0.2100, 0.4700, 0.1533, 0.6148, 0.4834],
[ nan, nan, 0.8750, 0.2467, 0.5138, 0.2617, 0.7382, 0.5552],
[0.6269, 0.4073, 0.8900, 0.4933, 0.3625, 0.4183, 0.6288, 0.5150],
[0.6258, 0.4038, 0.8750, 0.4883, 0.3900, 0.5500, 0.6375, 0.5217],
[0.6226, 0.4098, 0.8912, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367],
[0.6250, 0.4106, 0.8700, 0.3717, 0.3588, 0.4967, 0.6038, 0.5167]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7221, 0.4680, 0.8072, 0.5104, 0.3845, 0.4499, 0.5519, 0.5637],
[0.6449, 0.4268, 0.8583, 0.5027, 0.4076, 0.5221, 0.6426, 0.5507],
[0.7298, 0.5031, 0.7766, 0.2269, 0.4749, 0.1387, 0.6136, 0.5198],
[0.4523, 0.3037, 0.8340, 0.2722, 0.5095, 0.1814, 0.6730, 0.5421],
[0.7061, 0.4926, 0.8780, 0.4993, 0.3746, 0.4107, 0.6573, 0.5228],
[0.7205, 0.4687, 0.8657, 0.5145, 0.4142, 0.5632, 0.6663, 0.5195],
[0.7471, 0.4946, 0.8512, 0.4310, 0.4183, 0.2610, 0.5567, 0.5546],
[0.6749, 0.4517, 0.8457, 0.3970, 0.3774, 0.4914, 0.6339, 0.5649]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6123, 0.4069, 0.8314, 0.5001, 0.3738, 0.4650, 0.5167, 0.5402],
[0.6197, 0.3930, 0.8793, 0.4736, 0.4152, 0.5464, 0.6308, 0.5235],
[0.6275, 0.4071, 0.8075, 0.2100, 0.4700, 0.1533, 0.6148, 0.4834],
[0.0000, 0.0000, 0.8750, 0.2467, 0.5138, 0.2617, 0.7382, 0.5552],
[0.6269, 0.4073, 0.8900, 0.4933, 0.3625, 0.4183, 0.6288, 0.5150],
[0.6258, 0.4038, 0.8750, 0.4883, 0.3900, 0.5500, 0.6375, 0.5217],
[0.6226, 0.4098, 0.8913, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367],
[0.6250, 0.4105, 0.8700, 0.3717, 0.3587, 0.4967, 0.6037, 0.5167]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0066, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0066, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.27209125307854265
step: 75
running loss: 0.003627883374380569
Train Steps: 75/90 Loss: 0.0036 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6097, 0.3988, 0.8650, 0.5250, 0.4213, 0.5200, 0.5675, 0.5050],
[0.6361, 0.4071, 0.9100, 0.4783, 0.3738, 0.3967, 0.6670, 0.5332],
[0.6212, 0.4159, 0.8675, 0.5783, 0.4088, 0.4317, 0.5613, 0.5917],
[0.6296, 0.4060, 0.9100, 0.3267, 0.4726, 0.3367, 0.7446, 0.5355],
[0.6085, 0.4008, 0.8588, 0.5200, 0.4959, 0.4977, 0.5175, 0.5283],
[0.6199, 0.4015, 0.8716, 0.5228, 0.3833, 0.4772, 0.5883, 0.5148],
[0.6280, 0.4055, 0.8600, 0.5317, 0.3800, 0.4700, 0.6275, 0.5133],
[0.6346, 0.4144, 0.9088, 0.4667, 0.3850, 0.4333, 0.7121, 0.5899]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6798, 0.4367, 0.8905, 0.5339, 0.4184, 0.5330, 0.5787, 0.5165],
[0.6814, 0.4195, 0.9055, 0.4748, 0.3659, 0.4066, 0.6685, 0.5359],
[0.6670, 0.4253, 0.8463, 0.5316, 0.3967, 0.4579, 0.5615, 0.5652],
[0.6028, 0.3785, 0.8851, 0.3418, 0.4280, 0.3274, 0.6745, 0.5367],
[0.6783, 0.4034, 0.8593, 0.4999, 0.4756, 0.4750, 0.5447, 0.5214],
[0.6905, 0.4342, 0.9075, 0.4974, 0.3788, 0.4901, 0.6273, 0.5221],
[0.7945, 0.5029, 0.8942, 0.5036, 0.3687, 0.4840, 0.6507, 0.5171],
[0.6484, 0.4060, 0.8931, 0.4606, 0.3984, 0.4084, 0.6942, 0.5413]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6097, 0.3988, 0.8650, 0.5250, 0.4212, 0.5200, 0.5675, 0.5050],
[0.6361, 0.4071, 0.9100, 0.4783, 0.3738, 0.3967, 0.6670, 0.5332],
[0.6212, 0.4159, 0.8675, 0.5783, 0.4087, 0.4317, 0.5612, 0.5917],
[0.6296, 0.4060, 0.9100, 0.3267, 0.4726, 0.3367, 0.7446, 0.5355],
[0.6084, 0.4008, 0.8587, 0.5200, 0.4959, 0.4977, 0.5175, 0.5283],
[0.6199, 0.4015, 0.8716, 0.5228, 0.3833, 0.4772, 0.5883, 0.5148],
[0.6280, 0.4055, 0.8600, 0.5317, 0.3800, 0.4700, 0.6275, 0.5133],
[0.6346, 0.4144, 0.9087, 0.4667, 0.3850, 0.4333, 0.7121, 0.5899]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.27344133728183806
step: 76
running loss: 0.003597912332655764
Train Steps: 76/90 Loss: 0.0036 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6192, 0.3980, 0.7078, 0.2750, 0.4250, 0.2100, 0.5450, 0.5783],
[0.6198, 0.4101, 0.8838, 0.5283, 0.3763, 0.5267, 0.5913, 0.5567],
[0.6229, 0.4107, 0.8137, 0.2883, 0.4750, 0.1717, 0.5813, 0.5400],
[0.6072, 0.4029, 0.7037, 0.2150, 0.3912, 0.2267, 0.5516, 0.5507],
[0.6246, 0.4008, 0.8757, 0.5088, 0.4101, 0.5392, 0.6644, 0.5133],
[0.6250, 0.4103, 0.8950, 0.4400, 0.3912, 0.5650, 0.6050, 0.5133],
[0.6250, 0.3961, 0.8672, 0.4929, 0.4199, 0.4972, 0.6312, 0.5301],
[0.6168, 0.4029, 0.8523, 0.3417, 0.3588, 0.5000, 0.6125, 0.5400]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4302, 0.2588, 0.7816, 0.3117, 0.4392, 0.2675, 0.5540, 0.5430],
[0.6821, 0.4257, 0.9284, 0.6394, 0.3763, 0.5872, 0.6291, 0.5547],
[0.7801, 0.5038, 0.8543, 0.3555, 0.4846, 0.2312, 0.6044, 0.5342],
[0.7169, 0.4645, 0.7590, 0.2761, 0.4219, 0.2503, 0.6018, 0.5394],
[0.6197, 0.3730, 0.9462, 0.5948, 0.3995, 0.5777, 0.6588, 0.5362],
[0.7014, 0.4260, 0.9745, 0.5130, 0.4179, 0.6349, 0.6801, 0.5268],
[0.6904, 0.4121, 0.9245, 0.5656, 0.4052, 0.5342, 0.6547, 0.5416],
[0.6215, 0.3756, 0.9185, 0.4246, 0.3443, 0.5273, 0.6487, 0.5402]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6192, 0.3980, 0.7078, 0.2750, 0.4250, 0.2100, 0.5450, 0.5783],
[0.6198, 0.4101, 0.8838, 0.5283, 0.3762, 0.5267, 0.5913, 0.5567],
[0.6229, 0.4107, 0.8138, 0.2883, 0.4750, 0.1717, 0.5813, 0.5400],
[0.6072, 0.4029, 0.7038, 0.2150, 0.3913, 0.2267, 0.5516, 0.5507],
[0.6246, 0.4008, 0.8757, 0.5088, 0.4101, 0.5392, 0.6644, 0.5133],
[0.6250, 0.4103, 0.8950, 0.4400, 0.3913, 0.5650, 0.6050, 0.5133],
[0.6250, 0.3961, 0.8672, 0.4929, 0.4199, 0.4972, 0.6312, 0.5301],
[0.6168, 0.4029, 0.8523, 0.3417, 0.3587, 0.5000, 0.6125, 0.5400]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0037, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0037, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.27711278037168086
step: 77
running loss: 0.0035988672775542968
Train Steps: 77/90 Loss: 0.0036 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6268, 0.4094, 0.9038, 0.4300, 0.3700, 0.3483, 0.6262, 0.5167],
[ nan, nan, 0.7097, 0.2346, 0.4250, 0.1850, 0.5175, 0.5583],
[0.6350, 0.4118, 0.8363, 0.2717, 0.4850, 0.1700, 0.6441, 0.5170],
[0.6201, 0.4098, 0.8575, 0.3617, 0.3700, 0.3550, 0.5988, 0.5667],
[0.6261, 0.3987, 0.8688, 0.4917, 0.4300, 0.5333, 0.7010, 0.5309],
[0.6227, 0.4049, 0.8750, 0.5367, 0.3775, 0.3667, 0.5725, 0.5317],
[0.6219, 0.3934, 0.8688, 0.5267, 0.4313, 0.4967, 0.5988, 0.4983],
[0.6136, 0.4085, 0.6688, 0.2317, 0.3862, 0.2367, 0.5517, 0.5783]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6488, 0.4085, 0.9239, 0.4528, 0.3710, 0.4379, 0.6246, 0.5328],
[0.1281, 0.0702, 0.7535, 0.2990, 0.4289, 0.2780, 0.5352, 0.5354],
[0.7497, 0.4416, 0.8740, 0.3162, 0.4783, 0.2598, 0.6582, 0.5157],
[0.7471, 0.4585, 0.8960, 0.4175, 0.3671, 0.4120, 0.5890, 0.5436],
[0.6345, 0.3725, 0.9412, 0.5425, 0.4347, 0.6288, 0.6831, 0.5394],
[0.7109, 0.4313, 0.9336, 0.5875, 0.3706, 0.4795, 0.5975, 0.5337],
[0.6542, 0.3831, 0.9247, 0.5839, 0.4145, 0.5602, 0.6040, 0.5012],
[0.6355, 0.3950, 0.7365, 0.2905, 0.3895, 0.3092, 0.5418, 0.5230]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6268, 0.4094, 0.9038, 0.4300, 0.3700, 0.3483, 0.6263, 0.5167],
[0.0000, 0.0000, 0.7097, 0.2346, 0.4250, 0.1850, 0.5175, 0.5583],
[0.6350, 0.4118, 0.8363, 0.2717, 0.4850, 0.1700, 0.6441, 0.5170],
[0.6201, 0.4098, 0.8575, 0.3617, 0.3700, 0.3550, 0.5987, 0.5667],
[0.6261, 0.3987, 0.8687, 0.4917, 0.4300, 0.5333, 0.7010, 0.5309],
[0.6227, 0.4049, 0.8750, 0.5367, 0.3775, 0.3667, 0.5725, 0.5317],
[0.6219, 0.3934, 0.8687, 0.5267, 0.4313, 0.4967, 0.5987, 0.4983],
[0.6136, 0.4085, 0.6687, 0.2317, 0.3862, 0.2367, 0.5517, 0.5783]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0027, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0027, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.27983771497383714
step: 78
running loss: 0.0035876630124850916
Train Steps: 78/90 Loss: 0.0036 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6178, 0.4012, 0.8900, 0.4495, 0.3891, 0.5617, 0.5972, 0.4879],
[0.6106, 0.4022, 0.7125, 0.2650, 0.3713, 0.2700, 0.5431, 0.5123],
[0.6343, 0.4097, 0.9287, 0.4367, 0.4313, 0.3600, 0.7248, 0.5841],
[0.6317, 0.4038, 0.8287, 0.5900, 0.3800, 0.4717, 0.6295, 0.4986],
[0.6122, 0.4006, 0.8850, 0.4217, 0.4088, 0.5517, 0.6063, 0.5517],
[0.6274, 0.4087, 0.8375, 0.5700, 0.4025, 0.4800, 0.5700, 0.6117],
[0.6289, 0.4081, 0.8720, 0.3487, 0.3900, 0.3183, 0.6703, 0.5376],
[0.6209, 0.3920, 0.8650, 0.5367, 0.4400, 0.5067, 0.6025, 0.4950]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6002, 0.3573, 0.9323, 0.4695, 0.4067, 0.5875, 0.6304, 0.5184],
[0.6629, 0.4128, 0.8068, 0.3113, 0.3855, 0.2987, 0.5554, 0.5189],
[0.5464, 0.3306, 0.9350, 0.4519, 0.4138, 0.4141, 0.6858, 0.5519],
[0.6337, 0.3700, 0.9142, 0.5837, 0.3704, 0.5209, 0.6383, 0.5275],
[0.5967, 0.3291, 0.9264, 0.4726, 0.4439, 0.5952, 0.5902, 0.5238],
[0.5697, 0.3110, 0.8690, 0.5939, 0.4222, 0.5291, 0.5780, 0.5865],
[0.6790, 0.4061, 0.9367, 0.3756, 0.4064, 0.3228, 0.6563, 0.5449],
[0.5955, 0.3229, 0.9189, 0.5381, 0.4464, 0.5383, 0.5872, 0.5075]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6178, 0.4012, 0.8900, 0.4495, 0.3891, 0.5617, 0.5972, 0.4879],
[0.6106, 0.4022, 0.7125, 0.2650, 0.3713, 0.2700, 0.5431, 0.5123],
[0.6343, 0.4097, 0.9287, 0.4367, 0.4313, 0.3600, 0.7248, 0.5841],
[0.6317, 0.4038, 0.8288, 0.5900, 0.3800, 0.4717, 0.6295, 0.4986],
[0.6122, 0.4006, 0.8850, 0.4217, 0.4087, 0.5517, 0.6062, 0.5517],
[0.6274, 0.4087, 0.8375, 0.5700, 0.4025, 0.4800, 0.5700, 0.6117],
[0.6289, 0.4081, 0.8720, 0.3487, 0.3900, 0.3183, 0.6703, 0.5376],
[0.6209, 0.3920, 0.8650, 0.5367, 0.4400, 0.5067, 0.6025, 0.4950]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.28146227076649666
step: 79
running loss: 0.0035628135540062868
Train Steps: 79/90 Loss: 0.0036 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6346, 0.4165, 0.9138, 0.3983, 0.3875, 0.4317, 0.7469, 0.5471],
[0.6264, 0.4049, 0.8988, 0.4633, 0.3813, 0.4983, 0.6326, 0.4843],
[ nan, nan, 0.7553, 0.2722, 0.3875, 0.2550, 0.5125, 0.5633],
[0.6240, 0.4217, 0.8150, 0.3133, 0.4425, 0.2650, 0.5650, 0.5817],
[0.6271, 0.4005, 0.8450, 0.6067, 0.3850, 0.4983, 0.6069, 0.4649],
[0.6261, 0.4066, 0.8325, 0.2150, 0.4763, 0.2667, 0.7002, 0.5633],
[0.6109, 0.4015, 0.7668, 0.3639, 0.3513, 0.3667, 0.5200, 0.5641],
[0.6271, 0.4040, 0.9138, 0.3750, 0.4625, 0.2617, 0.7232, 0.5413]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5119, 0.3425, 0.9265, 0.4695, 0.3875, 0.4551, 0.6786, 0.5260],
[0.6343, 0.3938, 0.9262, 0.5178, 0.3744, 0.5502, 0.6083, 0.4991],
[0.1974, 0.1064, 0.7876, 0.3150, 0.3990, 0.3172, 0.5073, 0.5274],
[0.6346, 0.4311, 0.8191, 0.3264, 0.4551, 0.3047, 0.5770, 0.5565],
[0.6159, 0.3697, 0.8444, 0.6172, 0.3703, 0.5573, 0.5787, 0.4977],
[0.7068, 0.4193, 0.8361, 0.2817, 0.4721, 0.2977, 0.6492, 0.5381],
[0.6086, 0.3895, 0.8116, 0.4116, 0.3440, 0.3997, 0.5280, 0.5469],
[0.5484, 0.3277, 0.9446, 0.4219, 0.4743, 0.3307, 0.6781, 0.5497]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6346, 0.4165, 0.9137, 0.3983, 0.3875, 0.4317, 0.7469, 0.5471],
[0.6264, 0.4049, 0.8988, 0.4633, 0.3812, 0.4983, 0.6326, 0.4843],
[0.0000, 0.0000, 0.7553, 0.2722, 0.3875, 0.2550, 0.5125, 0.5633],
[0.6240, 0.4217, 0.8150, 0.3133, 0.4425, 0.2650, 0.5650, 0.5817],
[0.6271, 0.4005, 0.8450, 0.6067, 0.3850, 0.4983, 0.6069, 0.4649],
[0.6261, 0.4066, 0.8325, 0.2150, 0.4762, 0.2667, 0.7002, 0.5633],
[0.6109, 0.4015, 0.7668, 0.3639, 0.3512, 0.3667, 0.5200, 0.5641],
[0.6271, 0.4040, 0.9137, 0.3750, 0.4625, 0.2617, 0.7232, 0.5413]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0024, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0024, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.28381356899626553
step: 80
running loss: 0.0035476696124533192
Train Steps: 80/90 Loss: 0.0035 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6357, 0.4097, 0.9038, 0.3883, 0.4213, 0.2950, 0.6686, 0.5390],
[0.6346, 0.4144, 0.9088, 0.4667, 0.3850, 0.4333, 0.7121, 0.5899],
[0.6159, 0.4085, 0.6900, 0.2283, 0.4088, 0.1950, 0.5123, 0.5397],
[0.6112, 0.4029, 0.8638, 0.4800, 0.4875, 0.5083, 0.5763, 0.5567],
[0.6193, 0.4108, 0.7425, 0.2350, 0.3887, 0.2750, 0.5900, 0.5717],
[0.6178, 0.4059, 0.7525, 0.2250, 0.4313, 0.1783, 0.5404, 0.5240],
[ nan, nan, 0.6412, 0.1900, 0.4238, 0.1883, 0.5487, 0.5700],
[ nan, nan, 0.7240, 0.2722, 0.3900, 0.2567, 0.5168, 0.5933]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7318, 0.4761, 0.9288, 0.4338, 0.4220, 0.3790, 0.6864, 0.5237],
[0.7237, 0.4574, 0.9326, 0.5243, 0.3879, 0.5031, 0.6863, 0.5338],
[0.5232, 0.3285, 0.7327, 0.2817, 0.4121, 0.2591, 0.5487, 0.5335],
[0.6395, 0.4100, 0.9086, 0.5295, 0.4753, 0.5576, 0.5786, 0.5316],
[0.6670, 0.4423, 0.7967, 0.3256, 0.3888, 0.3411, 0.5705, 0.5651],
[0.3493, 0.2167, 0.7714, 0.2595, 0.4272, 0.2022, 0.5383, 0.5256],
[0.2071, 0.1384, 0.7526, 0.2718, 0.4370, 0.2432, 0.5629, 0.5550],
[0.3592, 0.2399, 0.7592, 0.3142, 0.3981, 0.2982, 0.5345, 0.5534]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6357, 0.4097, 0.9038, 0.3883, 0.4212, 0.2950, 0.6686, 0.5390],
[0.6346, 0.4144, 0.9087, 0.4667, 0.3850, 0.4333, 0.7121, 0.5899],
[0.6159, 0.4085, 0.6900, 0.2283, 0.4087, 0.1950, 0.5123, 0.5397],
[0.6112, 0.4029, 0.8637, 0.4800, 0.4875, 0.5083, 0.5763, 0.5567],
[0.6193, 0.4108, 0.7425, 0.2350, 0.3887, 0.2750, 0.5900, 0.5717],
[0.6178, 0.4059, 0.7525, 0.2250, 0.4313, 0.1783, 0.5404, 0.5240],
[0.0000, 0.0000, 0.6413, 0.1900, 0.4238, 0.1883, 0.5487, 0.5700],
[0.0000, 0.0000, 0.7240, 0.2722, 0.3900, 0.2567, 0.5168, 0.5933]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0076, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0076, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.29142689728178084
step: 81
running loss: 0.003597862929404702
Train Steps: 81/90 Loss: 0.0036 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6248, 0.4185, 0.8500, 0.5767, 0.4463, 0.4550, 0.5613, 0.5917],
[0.6259, 0.4156, 0.8812, 0.3183, 0.4775, 0.1867, 0.6219, 0.4960],
[0.6156, 0.4125, 0.8850, 0.4833, 0.4550, 0.5817, 0.5765, 0.5084],
[0.6299, 0.4008, 0.8450, 0.5350, 0.4213, 0.5000, 0.6350, 0.5100],
[0.6127, 0.4118, 0.8650, 0.5083, 0.4088, 0.5367, 0.5300, 0.5456],
[0.6222, 0.4072, 0.7164, 0.2166, 0.3738, 0.3167, 0.6100, 0.5533],
[0.6264, 0.4071, 0.9038, 0.3867, 0.3663, 0.3917, 0.6338, 0.5283],
[0.6267, 0.4065, 0.8313, 0.2467, 0.4788, 0.1733, 0.6312, 0.5133]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5037, 0.3305, 0.8141, 0.5500, 0.4043, 0.4282, 0.5797, 0.5804],
[0.6664, 0.4200, 0.8563, 0.2748, 0.4429, 0.2194, 0.6277, 0.5476],
[0.5060, 0.3348, 0.8612, 0.4524, 0.4320, 0.5289, 0.5627, 0.5324],
[0.4562, 0.3147, 0.8126, 0.4894, 0.3906, 0.4595, 0.6114, 0.5158],
[0.4270, 0.2897, 0.8398, 0.4804, 0.4076, 0.5038, 0.5437, 0.5549],
[0.4705, 0.3189, 0.7083, 0.2346, 0.3568, 0.2952, 0.5956, 0.5650],
[0.5339, 0.3557, 0.8859, 0.3443, 0.3659, 0.3642, 0.6454, 0.5390],
[0.5492, 0.3757, 0.8003, 0.2359, 0.4695, 0.1793, 0.6644, 0.5451]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6248, 0.4185, 0.8500, 0.5767, 0.4462, 0.4550, 0.5612, 0.5917],
[0.6259, 0.4156, 0.8813, 0.3183, 0.4775, 0.1867, 0.6219, 0.4960],
[0.6155, 0.4124, 0.8850, 0.4833, 0.4550, 0.5817, 0.5765, 0.5084],
[0.6299, 0.4008, 0.8450, 0.5350, 0.4212, 0.5000, 0.6350, 0.5100],
[0.6127, 0.4118, 0.8650, 0.5083, 0.4087, 0.5367, 0.5300, 0.5456],
[0.6222, 0.4072, 0.7164, 0.2166, 0.3738, 0.3167, 0.6100, 0.5533],
[0.6264, 0.4071, 0.9038, 0.3867, 0.3663, 0.3917, 0.6338, 0.5283],
[0.6266, 0.4065, 0.8313, 0.2467, 0.4787, 0.1733, 0.6313, 0.5133]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0033, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0033, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.29475518641993403
step: 82
running loss: 0.003594575444145537
Train Steps: 82/90 Loss: 0.0036 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6198, 0.4115, 0.7762, 0.2717, 0.3713, 0.3200, 0.5837, 0.5683],
[0.6161, 0.4024, 0.8662, 0.4683, 0.4935, 0.5364, 0.6063, 0.5567],
[0.6206, 0.4123, 0.7175, 0.2400, 0.3887, 0.2933, 0.6225, 0.5750],
[ nan, nan, 0.7515, 0.2708, 0.3987, 0.2267, 0.5162, 0.5567],
[0.6271, 0.4020, 0.8375, 0.6083, 0.3925, 0.4867, 0.6037, 0.4626],
[0.6336, 0.4191, 0.8938, 0.5167, 0.3937, 0.3517, 0.7343, 0.5748],
[0.6060, 0.3924, 0.8450, 0.5717, 0.4200, 0.5217, 0.5253, 0.4752],
[0.6299, 0.4303, 0.7963, 0.3933, 0.4850, 0.2283, 0.5480, 0.6222]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5219, 0.3660, 0.7790, 0.2321, 0.3643, 0.2673, 0.5809, 0.5409],
[0.5195, 0.3591, 0.8312, 0.3807, 0.4510, 0.4457, 0.5938, 0.5612],
[0.5682, 0.3913, 0.6999, 0.2407, 0.3874, 0.2158, 0.6085, 0.5697],
[0.1475, 0.1097, 0.6956, 0.2113, 0.4007, 0.1901, 0.5284, 0.5563],
[0.5345, 0.3710, 0.8218, 0.4980, 0.3978, 0.4215, 0.6464, 0.4959],
[0.5906, 0.4026, 0.8150, 0.4026, 0.3914, 0.3041, 0.6396, 0.5236],
[0.4948, 0.3323, 0.8203, 0.5143, 0.4422, 0.4626, 0.5775, 0.5119],
[0.6208, 0.4077, 0.7593, 0.2987, 0.4598, 0.2385, 0.5518, 0.5721]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6198, 0.4115, 0.7763, 0.2717, 0.3713, 0.3200, 0.5838, 0.5683],
[0.6161, 0.4024, 0.8662, 0.4683, 0.4935, 0.5364, 0.6062, 0.5567],
[0.6206, 0.4123, 0.7175, 0.2400, 0.3887, 0.2933, 0.6225, 0.5750],
[0.0000, 0.0000, 0.7515, 0.2708, 0.3988, 0.2267, 0.5163, 0.5567],
[0.6271, 0.4020, 0.8375, 0.6083, 0.3925, 0.4867, 0.6037, 0.4626],
[0.6336, 0.4191, 0.8938, 0.5167, 0.3938, 0.3517, 0.7343, 0.5748],
[0.6060, 0.3924, 0.8450, 0.5717, 0.4200, 0.5217, 0.5253, 0.4752],
[0.6299, 0.4303, 0.7962, 0.3933, 0.4850, 0.2283, 0.5480, 0.6222]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0032, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0032, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.29796311957761645
step: 83
running loss: 0.0035899171033447765
Train Steps: 83/90 Loss: 0.0036 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6236, 0.3977, 0.8985, 0.4806, 0.3835, 0.5216, 0.6613, 0.5166],
[0.6182, 0.3987, 0.7878, 0.2889, 0.3699, 0.3260, 0.6086, 0.5367],
[0.6110, 0.3984, 0.8750, 0.4933, 0.4625, 0.4950, 0.5578, 0.5676],
[0.6203, 0.4072, 0.8892, 0.3523, 0.3783, 0.3017, 0.5898, 0.5478],
[0.6152, 0.4131, 0.6863, 0.2567, 0.3625, 0.3300, 0.5765, 0.5305],
[0.6179, 0.4040, 0.7412, 0.1850, 0.3825, 0.2783, 0.5837, 0.5600],
[0.6201, 0.4050, 0.7757, 0.2234, 0.4459, 0.1798, 0.5975, 0.5426],
[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5181, 0.3539, 0.8390, 0.4595, 0.4247, 0.4804, 0.6175, 0.5306],
[0.4836, 0.3487, 0.7682, 0.2725, 0.3916, 0.2523, 0.6011, 0.5581],
[0.5561, 0.3936, 0.8207, 0.4423, 0.4917, 0.4533, 0.5457, 0.5479],
[0.5201, 0.3584, 0.8710, 0.3262, 0.3958, 0.2486, 0.6272, 0.5657],
[0.4927, 0.3735, 0.6764, 0.2544, 0.3768, 0.2560, 0.5766, 0.5698],
[0.4877, 0.3685, 0.7300, 0.2531, 0.3999, 0.2156, 0.5919, 0.5682],
[0.4900, 0.3573, 0.7261, 0.2373, 0.4414, 0.1238, 0.5944, 0.5538],
[0.5658, 0.4001, 0.8245, 0.4372, 0.4641, 0.5247, 0.6171, 0.5283]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6236, 0.3977, 0.8985, 0.4806, 0.3835, 0.5216, 0.6613, 0.5166],
[0.6182, 0.3987, 0.7878, 0.2889, 0.3699, 0.3260, 0.6086, 0.5367],
[0.6110, 0.3984, 0.8750, 0.4933, 0.4625, 0.4950, 0.5578, 0.5676],
[0.6203, 0.4072, 0.8892, 0.3523, 0.3783, 0.3017, 0.5898, 0.5478],
[0.6152, 0.4131, 0.6862, 0.2567, 0.3625, 0.3300, 0.5765, 0.5305],
[0.6179, 0.4040, 0.7412, 0.1850, 0.3825, 0.2783, 0.5838, 0.5600],
[0.6201, 0.4050, 0.7757, 0.2234, 0.4459, 0.1798, 0.5975, 0.5426],
[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0027, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0027, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.3006193444598466
step: 84
running loss: 0.0035788017197600787
Train Steps: 84/90 Loss: 0.0036 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6271, 0.4005, 0.8450, 0.6067, 0.3850, 0.4983, 0.6069, 0.4649],
[0.6190, 0.4135, 0.8000, 0.4883, 0.3566, 0.3647, 0.5613, 0.5900],
[0.6219, 0.4089, 0.8938, 0.4800, 0.3825, 0.4450, 0.5850, 0.5200],
[0.6275, 0.4050, 0.9038, 0.3767, 0.3838, 0.3533, 0.7074, 0.5575],
[0.6136, 0.4029, 0.8263, 0.3350, 0.3625, 0.3067, 0.5675, 0.5167],
[0.6179, 0.4118, 0.7278, 0.4237, 0.3588, 0.3400, 0.5675, 0.5917],
[0.6279, 0.4050, 0.8025, 0.2200, 0.4313, 0.2733, 0.6820, 0.5320],
[0.6128, 0.4084, 0.8738, 0.4683, 0.3613, 0.3700, 0.4960, 0.5397]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5401, 0.3604, 0.7687, 0.5018, 0.4050, 0.4576, 0.5831, 0.5146],
[0.6179, 0.4281, 0.7783, 0.3962, 0.3832, 0.3099, 0.5524, 0.5581],
[0.5014, 0.3646, 0.8290, 0.4376, 0.4013, 0.4111, 0.6210, 0.5631],
[0.5474, 0.3766, 0.8633, 0.2975, 0.4234, 0.2974, 0.6899, 0.5606],
[0.5735, 0.4356, 0.7765, 0.2658, 0.3967, 0.2545, 0.5893, 0.5601],
[0.5691, 0.4091, 0.7424, 0.3332, 0.3733, 0.2847, 0.5574, 0.5884],
[0.4941, 0.3615, 0.7728, 0.1914, 0.4640, 0.2244, 0.6177, 0.5739],
[0.5280, 0.3710, 0.8275, 0.4217, 0.3933, 0.3405, 0.5366, 0.5362]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6271, 0.4005, 0.8450, 0.6067, 0.3850, 0.4983, 0.6069, 0.4649],
[0.6190, 0.4135, 0.8000, 0.4883, 0.3566, 0.3647, 0.5612, 0.5900],
[0.6219, 0.4089, 0.8938, 0.4800, 0.3825, 0.4450, 0.5850, 0.5200],
[0.6275, 0.4050, 0.9038, 0.3767, 0.3837, 0.3533, 0.7074, 0.5575],
[0.6136, 0.4029, 0.8263, 0.3350, 0.3625, 0.3067, 0.5675, 0.5167],
[0.6179, 0.4118, 0.7278, 0.4237, 0.3587, 0.3400, 0.5675, 0.5917],
[0.6279, 0.4050, 0.8025, 0.2200, 0.4313, 0.2733, 0.6820, 0.5320],
[0.6127, 0.4084, 0.8737, 0.4683, 0.3613, 0.3700, 0.4960, 0.5397]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0027, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0027, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.3032755733001977
step: 85
running loss: 0.0035679479211787966
Train Steps: 85/90 Loss: 0.0036 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837],
[0.6307, 0.4029, 0.8988, 0.4817, 0.3937, 0.3500, 0.7311, 0.5378],
[0.6138, 0.4101, 0.8800, 0.5083, 0.4637, 0.5950, 0.5587, 0.5077],
[0.6280, 0.4101, 0.9050, 0.4533, 0.3775, 0.3217, 0.6338, 0.4915],
[0.6133, 0.4094, 0.8495, 0.4028, 0.3588, 0.3200, 0.5003, 0.5407],
[0.6115, 0.3998, 0.7063, 0.2383, 0.4037, 0.1950, 0.5320, 0.4993],
[0.6236, 0.3967, 0.8675, 0.5400, 0.3862, 0.4517, 0.5825, 0.5200],
[0.6135, 0.3994, 0.7913, 0.3050, 0.3625, 0.3050, 0.5837, 0.5050]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5689, 0.3898, 0.6745, 0.2629, 0.3627, 0.2696, 0.5545, 0.5796],
[0.5396, 0.3793, 0.8791, 0.4103, 0.4065, 0.3312, 0.6782, 0.5538],
[0.6021, 0.4020, 0.8272, 0.4906, 0.4783, 0.5328, 0.5690, 0.5541],
[0.6105, 0.4080, 0.8580, 0.4126, 0.3853, 0.2962, 0.6221, 0.5206],
[0.6513, 0.4556, 0.8229, 0.3616, 0.3921, 0.2947, 0.5291, 0.5429],
[0.4928, 0.3361, 0.6731, 0.1926, 0.4042, 0.1822, 0.5665, 0.5280],
[0.5830, 0.4160, 0.8283, 0.5111, 0.3814, 0.4505, 0.5676, 0.5232],
[0.5854, 0.4016, 0.7740, 0.2581, 0.3595, 0.2813, 0.6416, 0.5413]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837],
[0.6307, 0.4029, 0.8988, 0.4817, 0.3938, 0.3500, 0.7311, 0.5378],
[0.6138, 0.4101, 0.8800, 0.5083, 0.4638, 0.5950, 0.5587, 0.5077],
[0.6280, 0.4101, 0.9050, 0.4533, 0.3775, 0.3217, 0.6338, 0.4915],
[0.6133, 0.4094, 0.8495, 0.4028, 0.3587, 0.3200, 0.5003, 0.5407],
[0.6115, 0.3998, 0.7063, 0.2383, 0.4038, 0.1950, 0.5320, 0.4993],
[0.6236, 0.3967, 0.8675, 0.5400, 0.3862, 0.4517, 0.5825, 0.5200],
[0.6135, 0.3994, 0.7912, 0.3050, 0.3625, 0.3050, 0.5838, 0.5050]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.3045844287844375
step: 86
running loss: 0.0035416794044702033
Train Steps: 86/90 Loss: 0.0035 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6179, 0.4008, 0.8600, 0.4015, 0.3932, 0.2515, 0.5711, 0.5438],
[0.6267, 0.4080, 0.8438, 0.2633, 0.4763, 0.1800, 0.6259, 0.5240],
[0.6169, 0.4052, 0.8742, 0.4779, 0.4288, 0.4917, 0.5763, 0.5617],
[0.6260, 0.4161, 0.9000, 0.3833, 0.4450, 0.2133, 0.6237, 0.4986],
[0.6173, 0.4114, 0.7325, 0.2500, 0.4213, 0.1917, 0.5338, 0.5700],
[0.6175, 0.3957, 0.8700, 0.4817, 0.4662, 0.5133, 0.5800, 0.5517],
[ nan, nan, 0.6688, 0.2513, 0.4113, 0.2117, 0.5193, 0.5933],
[ nan, nan, 0.8750, 0.2467, 0.5138, 0.2617, 0.7382, 0.5552]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6938, 0.4627, 0.7745, 0.3595, 0.3673, 0.2659, 0.5422, 0.5378],
[0.7675, 0.5108, 0.8090, 0.2835, 0.4165, 0.2215, 0.5889, 0.5316],
[0.7989, 0.5596, 0.8286, 0.5296, 0.3607, 0.5234, 0.5537, 0.5094],
[0.6746, 0.4583, 0.8689, 0.3938, 0.4130, 0.2602, 0.6126, 0.5131],
[0.4435, 0.2818, 0.6643, 0.2294, 0.3795, 0.2038, 0.5428, 0.5347],
[0.7686, 0.5124, 0.8225, 0.4737, 0.4038, 0.5151, 0.5450, 0.4887],
[0.3795, 0.2579, 0.6317, 0.2452, 0.3483, 0.2038, 0.5323, 0.5397],
[0.2499, 0.1584, 0.8249, 0.2532, 0.4639, 0.2239, 0.6906, 0.5346]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6179, 0.4008, 0.8600, 0.4015, 0.3932, 0.2515, 0.5711, 0.5438],
[0.6267, 0.4080, 0.8438, 0.2633, 0.4762, 0.1800, 0.6259, 0.5240],
[0.6169, 0.4052, 0.8742, 0.4779, 0.4288, 0.4917, 0.5763, 0.5617],
[0.6260, 0.4161, 0.9000, 0.3833, 0.4450, 0.2133, 0.6237, 0.4986],
[0.6173, 0.4114, 0.7325, 0.2500, 0.4212, 0.1917, 0.5337, 0.5700],
[0.6175, 0.3957, 0.8700, 0.4817, 0.4663, 0.5133, 0.5800, 0.5517],
[0.0000, 0.0000, 0.6688, 0.2513, 0.4112, 0.2117, 0.5193, 0.5933],
[0.0000, 0.0000, 0.8750, 0.2467, 0.5138, 0.2617, 0.7382, 0.5552]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0087, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0087, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.31329219427425414
step: 87
running loss: 0.0036010597043017716
Train Steps: 87/90 Loss: 0.0036 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758],
[0.6136, 0.4085, 0.6688, 0.2317, 0.3862, 0.2367, 0.5517, 0.5783],
[0.6131, 0.4064, 0.8638, 0.5200, 0.4788, 0.4783, 0.5258, 0.5867],
[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150],
[0.6267, 0.4080, 0.8438, 0.2633, 0.4763, 0.1800, 0.6259, 0.5240],
[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466],
[0.6132, 0.4118, 0.8200, 0.3633, 0.3563, 0.5400, 0.5787, 0.5136],
[0.6126, 0.4073, 0.8750, 0.5133, 0.3800, 0.4333, 0.4986, 0.5378]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7099, 0.4488, 0.8918, 0.5150, 0.3862, 0.4957, 0.6400, 0.4723],
[0.5831, 0.3690, 0.6823, 0.2410, 0.3665, 0.2161, 0.5593, 0.5425],
[0.6480, 0.4269, 0.8681, 0.5214, 0.4285, 0.4433, 0.5788, 0.5561],
[0.7184, 0.4610, 0.8753, 0.4972, 0.4210, 0.5490, 0.6182, 0.5110],
[0.6838, 0.4470, 0.8567, 0.2835, 0.4509, 0.1811, 0.6441, 0.5405],
[0.5792, 0.3969, 0.7905, 0.3778, 0.3279, 0.3846, 0.5698, 0.5413],
[0.6387, 0.4136, 0.8354, 0.3753, 0.3431, 0.4887, 0.6001, 0.5222],
[0.6564, 0.4403, 0.8673, 0.5548, 0.3776, 0.4223, 0.5660, 0.5180]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758],
[0.6136, 0.4085, 0.6687, 0.2317, 0.3862, 0.2367, 0.5517, 0.5783],
[0.6132, 0.4063, 0.8637, 0.5200, 0.4787, 0.4783, 0.5258, 0.5867],
[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150],
[0.6267, 0.4080, 0.8438, 0.2633, 0.4762, 0.1800, 0.6259, 0.5240],
[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466],
[0.6132, 0.4118, 0.8200, 0.3633, 0.3562, 0.5400, 0.5787, 0.5136],
[0.6126, 0.4073, 0.8750, 0.5133, 0.3800, 0.4333, 0.4986, 0.5378]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.3143081188900396
step: 88
running loss: 0.003571683169204996
Train Steps: 88/90 Loss: 0.0036 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6229, 0.4198, 0.7662, 0.2700, 0.4700, 0.2133, 0.5675, 0.5783],
[0.6082, 0.4042, 0.6975, 0.1917, 0.4100, 0.1983, 0.5502, 0.5578],
[0.6086, 0.3940, 0.8712, 0.4783, 0.4025, 0.4900, 0.5498, 0.5390],
[0.6250, 0.3961, 0.8672, 0.4929, 0.4199, 0.4972, 0.6312, 0.5301],
[0.6154, 0.4112, 0.7037, 0.2317, 0.4238, 0.1833, 0.5350, 0.5600],
[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395],
[0.6271, 0.4081, 0.9081, 0.4894, 0.3700, 0.4283, 0.6661, 0.5274],
[0.6140, 0.4070, 0.8700, 0.5000, 0.4612, 0.4900, 0.5260, 0.5852]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5503, 0.3433, 0.8042, 0.2656, 0.4390, 0.2441, 0.5905, 0.5752],
[0.4924, 0.2846, 0.7159, 0.2282, 0.3960, 0.2076, 0.5492, 0.5356],
[0.7602, 0.4789, 0.9267, 0.5469, 0.4050, 0.5384, 0.5807, 0.4911],
[0.7297, 0.4698, 0.8829, 0.5198, 0.3922, 0.5400, 0.6037, 0.5108],
[0.5250, 0.3183, 0.7260, 0.2407, 0.4251, 0.2064, 0.5545, 0.5222],
[0.6908, 0.4439, 0.9060, 0.5334, 0.3466, 0.3828, 0.5711, 0.5140],
[0.6375, 0.4331, 0.9175, 0.4850, 0.3439, 0.4380, 0.6430, 0.5255],
[0.7003, 0.4664, 0.9140, 0.5508, 0.4439, 0.5048, 0.5472, 0.5362]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6229, 0.4198, 0.7663, 0.2700, 0.4700, 0.2133, 0.5675, 0.5783],
[0.6082, 0.4042, 0.6975, 0.1917, 0.4100, 0.1983, 0.5502, 0.5578],
[0.6086, 0.3940, 0.8712, 0.4783, 0.4025, 0.4900, 0.5498, 0.5390],
[0.6250, 0.3961, 0.8672, 0.4929, 0.4199, 0.4972, 0.6312, 0.5301],
[0.6154, 0.4112, 0.7038, 0.2317, 0.4238, 0.1833, 0.5350, 0.5600],
[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395],
[0.6271, 0.4081, 0.9081, 0.4894, 0.3700, 0.4283, 0.6661, 0.5274],
[0.6140, 0.4070, 0.8700, 0.5000, 0.4613, 0.4900, 0.5260, 0.5852]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0025, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0025, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.31682477600406855
step: 89
running loss: 0.0035598289438659387
Train Steps: 89/90 Loss: 0.0036 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6225, 0.4116, 0.8662, 0.3517, 0.3663, 0.3233, 0.5837, 0.5317],
[0.6059, 0.4002, 0.7562, 0.2767, 0.3538, 0.3033, 0.5529, 0.5455],
[0.6272, 0.4071, 0.8738, 0.5600, 0.3675, 0.3783, 0.5926, 0.4742],
[0.6276, 0.4120, 0.8738, 0.3133, 0.4225, 0.2217, 0.6203, 0.4892],
[0.6289, 0.4019, 0.8113, 0.5467, 0.3875, 0.5017, 0.7367, 0.5332],
[0.6196, 0.4088, 0.8888, 0.4583, 0.4500, 0.5683, 0.6138, 0.5883],
[ nan, nan, 0.7268, 0.2333, 0.4125, 0.1933, 0.5112, 0.5383],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5413, 0.5683]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6008, 0.3638, 0.8715, 0.3505, 0.3895, 0.3336, 0.5966, 0.5717],
[0.6301, 0.4162, 0.7736, 0.2896, 0.3732, 0.3400, 0.5808, 0.5527],
[0.7209, 0.4506, 0.9106, 0.5676, 0.3906, 0.4272, 0.5947, 0.5073],
[0.6660, 0.4047, 0.9162, 0.3639, 0.4761, 0.2391, 0.6249, 0.5336],
[0.7238, 0.4595, 0.8319, 0.5199, 0.3889, 0.5274, 0.6024, 0.5363],
[0.7352, 0.4680, 0.9079, 0.4925, 0.4598, 0.5879, 0.5617, 0.5313],
[0.2352, 0.1203, 0.7305, 0.2232, 0.4102, 0.2230, 0.5104, 0.5519],
[0.7288, 0.4646, 0.8875, 0.5587, 0.3863, 0.4118, 0.5313, 0.5509]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6225, 0.4116, 0.8662, 0.3517, 0.3663, 0.3233, 0.5838, 0.5317],
[0.6059, 0.4002, 0.7563, 0.2767, 0.3537, 0.3033, 0.5529, 0.5455],
[0.6272, 0.4071, 0.8737, 0.5600, 0.3675, 0.3783, 0.5926, 0.4742],
[0.6276, 0.4120, 0.8737, 0.3133, 0.4225, 0.2217, 0.6203, 0.4892],
[0.6289, 0.4019, 0.8112, 0.5467, 0.3875, 0.5017, 0.7367, 0.5332],
[0.6196, 0.4088, 0.8888, 0.4583, 0.4500, 0.5683, 0.6137, 0.5883],
[0.0000, 0.0000, 0.7268, 0.2333, 0.4125, 0.1933, 0.5113, 0.5383],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5412, 0.5683]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0028, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0028, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.31965578126255423
step: 90
running loss: 0.003551730902917269
Valid Steps: 10/10 Loss: nan 36
--------------------------------------------------
Epoch: 2 Train Loss: 0.0036 Valid Loss: nan
--------------------------------------------------
size of train loader is: 90
torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6186, 0.4060, 0.8750, 0.5050, 0.3538, 0.4367, 0.5813, 0.6083],
[0.6086, 0.3998, 0.8788, 0.4450, 0.4025, 0.4650, 0.5306, 0.5103],
[0.6122, 0.4048, 0.7506, 0.3014, 0.3475, 0.3333, 0.5487, 0.5749],
[0.6109, 0.3943, 0.8525, 0.4950, 0.4338, 0.4800, 0.5449, 0.5383],
[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150],
[0.6175, 0.3997, 0.6737, 0.2500, 0.4313, 0.1933, 0.5513, 0.5750],
[0.6219, 0.3934, 0.8688, 0.5267, 0.4313, 0.4967, 0.5988, 0.4983],
[0.6200, 0.4049, 0.8638, 0.5617, 0.4125, 0.5100, 0.6013, 0.5317]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6002, 0.3815, 0.8933, 0.5012, 0.4067, 0.4831, 0.5530, 0.5773],
[0.6410, 0.4013, 0.9355, 0.4723, 0.4100, 0.4706, 0.5617, 0.5201],
[0.5869, 0.3487, 0.8109, 0.3059, 0.3688, 0.3311, 0.5628, 0.5760],
[0.6995, 0.4231, 0.9138, 0.5172, 0.4408, 0.4911, 0.5576, 0.5447],
[0.6746, 0.4112, 0.9438, 0.5046, 0.4605, 0.5980, 0.6225, 0.5350],
[0.3981, 0.2286, 0.7361, 0.2425, 0.4561, 0.2127, 0.5571, 0.5786],
[0.7015, 0.4287, 0.9322, 0.5515, 0.4549, 0.4995, 0.5993, 0.5136],
[0.6751, 0.4332, 0.8995, 0.5880, 0.4387, 0.5118, 0.5768, 0.5340]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6186, 0.4060, 0.8750, 0.5050, 0.3537, 0.4367, 0.5813, 0.6083],
[0.6086, 0.3998, 0.8788, 0.4450, 0.4025, 0.4650, 0.5306, 0.5103],
[0.6122, 0.4048, 0.7506, 0.3014, 0.3475, 0.3333, 0.5487, 0.5749],
[0.6109, 0.3943, 0.8525, 0.4950, 0.4338, 0.4800, 0.5449, 0.5383],
[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150],
[0.6175, 0.3997, 0.6737, 0.2500, 0.4313, 0.1933, 0.5512, 0.5750],
[0.6219, 0.3934, 0.8687, 0.5267, 0.4313, 0.4967, 0.5987, 0.4983],
[0.6199, 0.4049, 0.8637, 0.5617, 0.4125, 0.5100, 0.6012, 0.5317]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0023, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0023, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.002288524992763996
step: 1
running loss: 0.002288524992763996
Train Steps: 1/90 Loss: 0.0023 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6145, 0.4008, 0.8750, 0.5383, 0.3975, 0.4650, 0.5563, 0.5533],
[0.6250, 0.4236, 0.8638, 0.3767, 0.4050, 0.3150, 0.5649, 0.5799],
[0.6030, 0.3969, 0.7988, 0.3917, 0.3450, 0.3667, 0.5266, 0.4700],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533],
[0.6090, 0.4045, 0.7250, 0.2100, 0.4075, 0.2300, 0.5476, 0.5663],
[0.6084, 0.3981, 0.8588, 0.5233, 0.4600, 0.5367, 0.5680, 0.5006],
[0.6258, 0.4038, 0.8750, 0.4883, 0.3900, 0.5500, 0.6375, 0.5217],
[0.6224, 0.4179, 0.8700, 0.5683, 0.4037, 0.4683, 0.5650, 0.5600]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5669, 0.3610, 0.8866, 0.5139, 0.4175, 0.4738, 0.5647, 0.5553],
[0.5978, 0.3696, 0.8827, 0.4233, 0.4464, 0.3263, 0.5813, 0.5786],
[0.5948, 0.3882, 0.8695, 0.4031, 0.3815, 0.3790, 0.5696, 0.5258],
[0.5551, 0.3560, 0.9126, 0.4513, 0.4443, 0.5119, 0.5792, 0.5305],
[0.4847, 0.2875, 0.7358, 0.2585, 0.4195, 0.2411, 0.5638, 0.5675],
[0.5462, 0.3488, 0.8821, 0.5407, 0.4778, 0.5131, 0.5600, 0.5296],
[0.6726, 0.4098, 0.9118, 0.5105, 0.4304, 0.5799, 0.6213, 0.5177],
[0.6760, 0.4343, 0.8956, 0.5829, 0.4141, 0.4797, 0.5930, 0.5445]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6145, 0.4008, 0.8750, 0.5383, 0.3975, 0.4650, 0.5562, 0.5533],
[0.6250, 0.4236, 0.8637, 0.3767, 0.4050, 0.3150, 0.5649, 0.5799],
[0.6030, 0.3969, 0.7987, 0.3917, 0.3450, 0.3667, 0.5266, 0.4700],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533],
[0.6090, 0.4045, 0.7250, 0.2100, 0.4075, 0.2300, 0.5476, 0.5663],
[0.6084, 0.3981, 0.8587, 0.5233, 0.4600, 0.5367, 0.5680, 0.5006],
[0.6258, 0.4038, 0.8750, 0.4883, 0.3900, 0.5500, 0.6375, 0.5217],
[0.6224, 0.4179, 0.8700, 0.5683, 0.4038, 0.4683, 0.5650, 0.5600]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0036328728310763836
step: 2
running loss: 0.0018164364155381918
Train Steps: 2/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6229, 0.4066, 0.8513, 0.5717, 0.4500, 0.5050, 0.6025, 0.5350],
[0.6267, 0.4080, 0.8438, 0.2633, 0.4763, 0.1800, 0.6259, 0.5240],
[0.6223, 0.3990, 0.8037, 0.2800, 0.4000, 0.2283, 0.5864, 0.5208],
[ nan, nan, 0.7850, 0.2700, 0.4288, 0.1717, 0.5199, 0.4999],
[0.6168, 0.4055, 0.7575, 0.2950, 0.4050, 0.2717, 0.5938, 0.6167],
[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837],
[0.6264, 0.4248, 0.8938, 0.4183, 0.3875, 0.4100, 0.5400, 0.5350],
[0.6182, 0.3967, 0.8263, 0.3065, 0.3526, 0.4161, 0.6192, 0.5290]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6359, 0.4082, 0.8793, 0.6344, 0.4539, 0.5514, 0.5787, 0.5307],
[0.6908, 0.4302, 0.8753, 0.3369, 0.4884, 0.2461, 0.6141, 0.5311],
[0.5758, 0.3436, 0.8435, 0.3540, 0.4212, 0.2781, 0.5877, 0.5331],
[0.3117, 0.1714, 0.7735, 0.2756, 0.4538, 0.2254, 0.5412, 0.5513],
[0.5630, 0.3703, 0.7986, 0.3373, 0.4174, 0.3504, 0.5790, 0.6113],
[0.6433, 0.3916, 0.7148, 0.3738, 0.3802, 0.3490, 0.5193, 0.5787],
[0.6158, 0.4063, 0.9110, 0.5084, 0.3871, 0.4496, 0.5415, 0.5369],
[0.5936, 0.3585, 0.8877, 0.3856, 0.3611, 0.4360, 0.6028, 0.5406]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6229, 0.4066, 0.8512, 0.5717, 0.4500, 0.5050, 0.6025, 0.5350],
[0.6267, 0.4080, 0.8438, 0.2633, 0.4762, 0.1800, 0.6259, 0.5240],
[0.6223, 0.3990, 0.8037, 0.2800, 0.4000, 0.2283, 0.5864, 0.5208],
[0.0000, 0.0000, 0.7850, 0.2700, 0.4288, 0.1717, 0.5199, 0.4999],
[0.6168, 0.4055, 0.7575, 0.2950, 0.4050, 0.2717, 0.5938, 0.6167],
[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837],
[0.6264, 0.4248, 0.8938, 0.4183, 0.3875, 0.4100, 0.5400, 0.5350],
[0.6182, 0.3967, 0.8263, 0.3065, 0.3526, 0.4161, 0.6192, 0.5290]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0035, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0035, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.00717794056981802
step: 3
running loss: 0.0023926468566060066
Train Steps: 3/90 Loss: 0.0024 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6072, 0.4029, 0.7037, 0.2150, 0.3912, 0.2267, 0.5516, 0.5507],
[0.6206, 0.4001, 0.8900, 0.3933, 0.3588, 0.3567, 0.5837, 0.5083],
[0.6299, 0.4008, 0.8450, 0.5350, 0.4213, 0.5000, 0.6350, 0.5100],
[0.6203, 0.4073, 0.8189, 0.2398, 0.4400, 0.2054, 0.5929, 0.5501],
[0.6275, 0.4024, 0.7722, 0.2080, 0.4392, 0.2234, 0.6435, 0.5290],
[0.6264, 0.4049, 0.8988, 0.4633, 0.3813, 0.4983, 0.6326, 0.4843],
[0.6182, 0.3987, 0.7878, 0.2889, 0.3699, 0.3260, 0.6086, 0.5367],
[0.6225, 0.4196, 0.8788, 0.3467, 0.3750, 0.3400, 0.5413, 0.5433]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6296, 0.4197, 0.6843, 0.2552, 0.4132, 0.2502, 0.5549, 0.5667],
[0.4891, 0.3154, 0.9120, 0.4422, 0.3716, 0.3887, 0.5510, 0.5275],
[0.5897, 0.3899, 0.8455, 0.5802, 0.4190, 0.5284, 0.5896, 0.5246],
[0.6052, 0.3880, 0.7896, 0.2977, 0.4430, 0.2461, 0.5919, 0.5701],
[0.5638, 0.3631, 0.7524, 0.2583, 0.4390, 0.2381, 0.6076, 0.5492],
[0.5158, 0.3366, 0.9171, 0.5129, 0.3831, 0.5358, 0.5797, 0.4969],
[0.5390, 0.3384, 0.7859, 0.3426, 0.3885, 0.3116, 0.5779, 0.5692],
[0.5654, 0.3864, 0.8075, 0.4019, 0.3687, 0.3412, 0.5067, 0.5633]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6072, 0.4029, 0.7038, 0.2150, 0.3913, 0.2267, 0.5516, 0.5507],
[0.6206, 0.4001, 0.8900, 0.3933, 0.3587, 0.3567, 0.5838, 0.5083],
[0.6299, 0.4008, 0.8450, 0.5350, 0.4212, 0.5000, 0.6350, 0.5100],
[0.6203, 0.4073, 0.8189, 0.2398, 0.4400, 0.2054, 0.5929, 0.5501],
[0.6275, 0.4024, 0.7722, 0.2080, 0.4392, 0.2234, 0.6435, 0.5290],
[0.6264, 0.4049, 0.8988, 0.4633, 0.3812, 0.4983, 0.6326, 0.4843],
[0.6182, 0.3987, 0.7878, 0.2889, 0.3699, 0.3260, 0.6086, 0.5367],
[0.6225, 0.4196, 0.8788, 0.3467, 0.3750, 0.3400, 0.5412, 0.5433]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.008925004513002932
step: 4
running loss: 0.002231251128250733
Train Steps: 4/90 Loss: 0.0022 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6275, 0.4050, 0.9038, 0.3767, 0.3838, 0.3533, 0.7074, 0.5575],
[0.6339, 0.4149, 0.8800, 0.5000, 0.3900, 0.5283, 0.7541, 0.5424],
[0.6257, 0.4034, 0.8287, 0.2333, 0.3925, 0.2717, 0.6330, 0.4901],
[0.6178, 0.4012, 0.8900, 0.4495, 0.3891, 0.5617, 0.5972, 0.4879],
[0.6277, 0.4057, 0.8300, 0.2650, 0.4363, 0.1850, 0.6140, 0.4823],
[0.6198, 0.4114, 0.8263, 0.3283, 0.3550, 0.3583, 0.5813, 0.5667],
[0.6214, 0.4040, 0.8838, 0.3500, 0.3600, 0.5183, 0.6362, 0.5200],
[0.6129, 0.4063, 0.8738, 0.5250, 0.4313, 0.4733, 0.5230, 0.5874]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6101, 0.4008, 0.8775, 0.3697, 0.3979, 0.3186, 0.6877, 0.5551],
[0.5939, 0.4007, 0.8892, 0.5176, 0.3852, 0.5240, 0.6640, 0.5635],
[0.6112, 0.4214, 0.7873, 0.2553, 0.3898, 0.2494, 0.6111, 0.5374],
[0.5689, 0.3956, 0.8435, 0.4460, 0.3896, 0.5423, 0.5555, 0.5107],
[0.6235, 0.4064, 0.7775, 0.2624, 0.4293, 0.2045, 0.6141, 0.5317],
[0.5731, 0.3912, 0.8131, 0.3550, 0.3671, 0.3545, 0.5398, 0.5531],
[0.5109, 0.3331, 0.8373, 0.3655, 0.3707, 0.5275, 0.5966, 0.5326],
[0.6127, 0.4086, 0.8259, 0.5347, 0.4222, 0.4452, 0.5156, 0.5748]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6275, 0.4050, 0.9038, 0.3767, 0.3837, 0.3533, 0.7074, 0.5575],
[0.6339, 0.4149, 0.8800, 0.5000, 0.3900, 0.5283, 0.7541, 0.5424],
[0.6257, 0.4034, 0.8288, 0.2333, 0.3925, 0.2717, 0.6330, 0.4901],
[0.6178, 0.4012, 0.8900, 0.4495, 0.3891, 0.5617, 0.5972, 0.4879],
[0.6277, 0.4056, 0.8300, 0.2650, 0.4363, 0.1850, 0.6140, 0.4823],
[0.6198, 0.4114, 0.8263, 0.3283, 0.3550, 0.3583, 0.5813, 0.5667],
[0.6214, 0.4040, 0.8838, 0.3500, 0.3600, 0.5183, 0.6363, 0.5200],
[0.6130, 0.4063, 0.8737, 0.5250, 0.4313, 0.4733, 0.5230, 0.5874]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.009910384309478104
step: 5
running loss: 0.001982076861895621
Train Steps: 5/90 Loss: 0.0020 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6269, 0.4073, 0.8900, 0.4933, 0.3625, 0.4183, 0.6288, 0.5150],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4012, 0.4633, 0.5338, 0.5767],
[0.6193, 0.3930, 0.8949, 0.4437, 0.3852, 0.5435, 0.6263, 0.5263],
[0.6200, 0.3961, 0.8461, 0.5497, 0.4142, 0.4577, 0.5892, 0.5402],
[0.6275, 0.4024, 0.8500, 0.5383, 0.3912, 0.4883, 0.6288, 0.5100],
[0.6136, 0.4060, 0.8025, 0.3217, 0.3650, 0.3000, 0.5060, 0.5646],
[0.6275, 0.4008, 0.8047, 0.2484, 0.4037, 0.2777, 0.6506, 0.5212],
[0.6182, 0.4099, 0.7812, 0.3000, 0.3937, 0.2367, 0.5325, 0.5750]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6028, 0.4081, 0.8787, 0.4410, 0.3613, 0.3906, 0.6559, 0.5075],
[0.5579, 0.3736, 0.8574, 0.4347, 0.3937, 0.4630, 0.5563, 0.5520],
[0.6174, 0.4114, 0.8715, 0.4025, 0.3697, 0.5316, 0.6222, 0.5028],
[0.5251, 0.3515, 0.8400, 0.4720, 0.3916, 0.4560, 0.5975, 0.5433],
[0.6194, 0.4004, 0.8417, 0.4841, 0.3773, 0.4897, 0.6316, 0.4948],
[0.4978, 0.3611, 0.7664, 0.2651, 0.3495, 0.2716, 0.5151, 0.5461],
[0.6735, 0.4743, 0.7903, 0.2001, 0.4035, 0.2606, 0.6323, 0.5188],
[0.5516, 0.3580, 0.7681, 0.2637, 0.4117, 0.2454, 0.5465, 0.5668]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6269, 0.4073, 0.8900, 0.4933, 0.3625, 0.4183, 0.6288, 0.5150],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4013, 0.4633, 0.5337, 0.5767],
[0.6193, 0.3930, 0.8949, 0.4437, 0.3852, 0.5435, 0.6263, 0.5263],
[0.6200, 0.3961, 0.8461, 0.5497, 0.4142, 0.4577, 0.5892, 0.5402],
[0.6275, 0.4024, 0.8500, 0.5383, 0.3913, 0.4883, 0.6288, 0.5100],
[0.6136, 0.4060, 0.8025, 0.3217, 0.3650, 0.3000, 0.5060, 0.5646],
[0.6275, 0.4008, 0.8047, 0.2484, 0.4037, 0.2777, 0.6506, 0.5212],
[0.6182, 0.4099, 0.7812, 0.3000, 0.3938, 0.2367, 0.5325, 0.5750]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.011184405419044197
step: 6
running loss: 0.0018640675698406994
Train Steps: 6/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6152, 0.4131, 0.6863, 0.2567, 0.3625, 0.3300, 0.5765, 0.5305],
[0.6150, 0.4097, 0.7468, 0.3194, 0.3825, 0.2633, 0.5463, 0.5800],
[0.6154, 0.4112, 0.7037, 0.2317, 0.4238, 0.1833, 0.5350, 0.5600],
[0.6275, 0.4008, 0.8047, 0.2484, 0.4037, 0.2777, 0.6506, 0.5212],
[0.6185, 0.4042, 0.7700, 0.2250, 0.4062, 0.2117, 0.5763, 0.5150],
[0.6234, 0.4179, 0.7825, 0.3450, 0.3813, 0.2867, 0.5675, 0.5617],
[0.6086, 0.3940, 0.8712, 0.4783, 0.4025, 0.4900, 0.5498, 0.5390],
[0.6277, 0.4013, 0.8888, 0.4767, 0.3600, 0.3567, 0.6148, 0.4672]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6380, 0.4439, 0.7222, 0.2509, 0.3482, 0.3219, 0.5899, 0.5464],
[0.5228, 0.3732, 0.7454, 0.2522, 0.3416, 0.2843, 0.5357, 0.5352],
[0.6708, 0.4600, 0.7047, 0.2072, 0.4197, 0.1954, 0.5537, 0.5195],
[0.6443, 0.4543, 0.8250, 0.2313, 0.3901, 0.2928, 0.6525, 0.5063],
[0.6395, 0.4302, 0.7451, 0.2097, 0.3914, 0.2084, 0.6203, 0.5268],
[0.5345, 0.3629, 0.7980, 0.3231, 0.3868, 0.2772, 0.6029, 0.5457],
[0.4908, 0.3311, 0.9332, 0.4952, 0.3968, 0.5405, 0.6285, 0.5112],
[0.5857, 0.3792, 0.9133, 0.4411, 0.3189, 0.3980, 0.6537, 0.4978]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6152, 0.4131, 0.6862, 0.2567, 0.3625, 0.3300, 0.5765, 0.5305],
[0.6150, 0.4097, 0.7468, 0.3194, 0.3825, 0.2633, 0.5462, 0.5800],
[0.6154, 0.4112, 0.7038, 0.2317, 0.4238, 0.1833, 0.5350, 0.5600],
[0.6275, 0.4008, 0.8047, 0.2484, 0.4037, 0.2777, 0.6506, 0.5212],
[0.6184, 0.4042, 0.7700, 0.2250, 0.4062, 0.2117, 0.5763, 0.5150],
[0.6234, 0.4179, 0.7825, 0.3450, 0.3812, 0.2867, 0.5675, 0.5617],
[0.6086, 0.3940, 0.8712, 0.4783, 0.4025, 0.4900, 0.5498, 0.5390],
[0.6277, 0.4013, 0.8888, 0.4767, 0.3600, 0.3567, 0.6148, 0.4672]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.012649990734644234
step: 7
running loss: 0.0018071415335206048
Train Steps: 7/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6279, 0.4050, 0.8025, 0.2200, 0.4313, 0.2733, 0.6820, 0.5320],
[0.6203, 0.4076, 0.8611, 0.2878, 0.4050, 0.2554, 0.5907, 0.5496],
[0.6200, 0.3998, 0.8850, 0.3950, 0.3500, 0.4650, 0.6138, 0.5400],
[0.6254, 0.3993, 0.8988, 0.4767, 0.3987, 0.5517, 0.6955, 0.5285],
[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837],
[0.6264, 0.4035, 0.8888, 0.4883, 0.4050, 0.5217, 0.6361, 0.4791],
[0.6176, 0.4017, 0.8788, 0.5100, 0.4075, 0.5250, 0.5913, 0.5033],
[0.6261, 0.3987, 0.8688, 0.4917, 0.4300, 0.5333, 0.7010, 0.5309]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6730, 0.4779, 0.7829, 0.1793, 0.3983, 0.2202, 0.6320, 0.5176],
[0.6574, 0.4479, 0.8553, 0.2471, 0.3966, 0.2033, 0.6424, 0.5357],
[0.5816, 0.3918, 0.8557, 0.3419, 0.3306, 0.4048, 0.6079, 0.5148],
[0.5688, 0.3792, 0.8812, 0.4301, 0.3675, 0.5155, 0.6587, 0.5246],
[0.6893, 0.4635, 0.6720, 0.2585, 0.3296, 0.2493, 0.5315, 0.5631],
[0.5993, 0.3999, 0.8540, 0.4222, 0.3700, 0.4330, 0.6404, 0.4731],
[0.5385, 0.3690, 0.8455, 0.4344, 0.3897, 0.4744, 0.5790, 0.5234],
[0.6363, 0.4504, 0.8473, 0.4180, 0.4055, 0.4664, 0.6760, 0.5129]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6279, 0.4050, 0.8025, 0.2200, 0.4313, 0.2733, 0.6820, 0.5320],
[0.6203, 0.4076, 0.8611, 0.2878, 0.4050, 0.2554, 0.5907, 0.5496],
[0.6200, 0.3998, 0.8850, 0.3950, 0.3500, 0.4650, 0.6137, 0.5400],
[0.6254, 0.3993, 0.8988, 0.4767, 0.3988, 0.5517, 0.6955, 0.5285],
[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837],
[0.6264, 0.4035, 0.8888, 0.4883, 0.4050, 0.5217, 0.6361, 0.4791],
[0.6176, 0.4017, 0.8788, 0.5100, 0.4075, 0.5250, 0.5913, 0.5033],
[0.6261, 0.3987, 0.8687, 0.4917, 0.4300, 0.5333, 0.7010, 0.5309]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.014307374716736376
step: 8
running loss: 0.001788421839592047
Train Steps: 8/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6257, 0.4060, 0.8300, 0.2333, 0.4688, 0.2583, 0.7050, 0.5633],
[0.6270, 0.4267, 0.7150, 0.3317, 0.4900, 0.1817, 0.5560, 0.6183],
[0.6192, 0.4128, 0.8513, 0.5617, 0.4200, 0.5267, 0.5850, 0.5633],
[0.6197, 0.4118, 0.8688, 0.5517, 0.4037, 0.5233, 0.5875, 0.5600],
[0.6336, 0.4191, 0.8938, 0.5167, 0.3937, 0.3517, 0.7343, 0.5748],
[0.6225, 0.4196, 0.8788, 0.3467, 0.3750, 0.3400, 0.5413, 0.5433],
[0.6101, 0.4042, 0.7775, 0.2617, 0.3713, 0.2817, 0.5440, 0.5650],
[0.6126, 0.3954, 0.8538, 0.4983, 0.4250, 0.4700, 0.5355, 0.5350]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6075, 0.4180, 0.8209, 0.1754, 0.4414, 0.2094, 0.7048, 0.5392],
[0.5856, 0.4044, 0.6639, 0.1650, 0.3894, 0.1484, 0.5538, 0.5401],
[0.6596, 0.4292, 0.8553, 0.4984, 0.3863, 0.5089, 0.6441, 0.4961],
[0.6291, 0.4204, 0.8378, 0.4888, 0.3686, 0.5141, 0.6246, 0.5025],
[0.6524, 0.4352, 0.8420, 0.4286, 0.3649, 0.2985, 0.6814, 0.5026],
[0.6159, 0.4232, 0.7951, 0.2934, 0.3295, 0.2710, 0.5499, 0.5150],
[0.6264, 0.4401, 0.7368, 0.1997, 0.3638, 0.2359, 0.5624, 0.5183],
[0.5910, 0.3714, 0.8494, 0.4495, 0.3998, 0.4437, 0.6143, 0.4924]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6257, 0.4060, 0.8300, 0.2333, 0.4688, 0.2583, 0.7050, 0.5633],
[0.6270, 0.4266, 0.7150, 0.3317, 0.4900, 0.1817, 0.5560, 0.6183],
[0.6192, 0.4128, 0.8512, 0.5617, 0.4200, 0.5267, 0.5850, 0.5633],
[0.6197, 0.4118, 0.8687, 0.5517, 0.4038, 0.5233, 0.5875, 0.5600],
[0.6336, 0.4191, 0.8938, 0.5167, 0.3938, 0.3517, 0.7343, 0.5748],
[0.6225, 0.4196, 0.8788, 0.3467, 0.3750, 0.3400, 0.5412, 0.5433],
[0.6101, 0.4042, 0.7775, 0.2617, 0.3713, 0.2817, 0.5440, 0.5650],
[0.6126, 0.3954, 0.8537, 0.4983, 0.4250, 0.4700, 0.5355, 0.5350]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0023, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0023, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.016634083236567676
step: 9
running loss: 0.0018482314707297417
Train Steps: 9/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6185, 0.4080, 0.8625, 0.3483, 0.3788, 0.2650, 0.5320, 0.5272],
[0.6219, 0.3934, 0.8688, 0.5267, 0.4313, 0.4967, 0.5988, 0.4983],
[0.6140, 0.4070, 0.8700, 0.5000, 0.4612, 0.4900, 0.5260, 0.5852],
[0.6100, 0.4016, 0.8600, 0.5067, 0.4612, 0.5233, 0.5086, 0.5519],
[0.6225, 0.4191, 0.8500, 0.4167, 0.3688, 0.3233, 0.5650, 0.5650],
[0.6250, 0.3961, 0.8672, 0.4929, 0.4199, 0.4972, 0.6312, 0.5301],
[0.6200, 0.4112, 0.8862, 0.4100, 0.3638, 0.4917, 0.6088, 0.6050],
[0.6182, 0.4099, 0.7812, 0.3000, 0.3937, 0.2367, 0.5325, 0.5750]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6524, 0.4339, 0.8155, 0.3268, 0.3706, 0.2373, 0.5624, 0.5438],
[0.5945, 0.3936, 0.8238, 0.4429, 0.4082, 0.4306, 0.6347, 0.4983],
[0.5720, 0.4040, 0.8387, 0.4393, 0.4390, 0.4357, 0.5802, 0.5505],
[0.6188, 0.4136, 0.8323, 0.4499, 0.4364, 0.4505, 0.5917, 0.5264],
[0.6634, 0.4575, 0.7849, 0.3285, 0.3516, 0.2794, 0.5788, 0.5534],
[0.5991, 0.3866, 0.8214, 0.4122, 0.3813, 0.4463, 0.6662, 0.5194],
[0.6810, 0.4477, 0.8417, 0.3520, 0.3407, 0.4455, 0.6495, 0.5353],
[0.6106, 0.3994, 0.7506, 0.2554, 0.3855, 0.2089, 0.5507, 0.5628]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6186, 0.4080, 0.8625, 0.3483, 0.3787, 0.2650, 0.5320, 0.5272],
[0.6219, 0.3934, 0.8687, 0.5267, 0.4313, 0.4967, 0.5987, 0.4983],
[0.6140, 0.4070, 0.8700, 0.5000, 0.4613, 0.4900, 0.5260, 0.5852],
[0.6100, 0.4016, 0.8600, 0.5067, 0.4613, 0.5233, 0.5086, 0.5519],
[0.6225, 0.4191, 0.8500, 0.4167, 0.3688, 0.3233, 0.5650, 0.5650],
[0.6250, 0.3961, 0.8672, 0.4929, 0.4199, 0.4972, 0.6312, 0.5301],
[0.6200, 0.4112, 0.8863, 0.4100, 0.3638, 0.4917, 0.6087, 0.6050],
[0.6182, 0.4099, 0.7812, 0.3000, 0.3938, 0.2367, 0.5325, 0.5750]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.018363903160206974
step: 10
running loss: 0.0018363903160206973
Train Steps: 10/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6317, 0.4038, 0.8287, 0.5900, 0.3800, 0.4717, 0.6295, 0.4986],
[0.6179, 0.4118, 0.7278, 0.4237, 0.3588, 0.3400, 0.5675, 0.5917],
[0.6064, 0.4019, 0.8650, 0.4517, 0.4037, 0.5367, 0.5703, 0.5609],
[0.6093, 0.3990, 0.8400, 0.4333, 0.3688, 0.4633, 0.5560, 0.5656],
[0.6286, 0.4086, 0.8408, 0.2801, 0.4163, 0.2800, 0.6725, 0.5393],
[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383],
[0.6127, 0.4084, 0.8700, 0.4467, 0.3987, 0.4317, 0.5013, 0.5471],
[0.6070, 0.3979, 0.8575, 0.5083, 0.4350, 0.5400, 0.5180, 0.5466]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6670, 0.4386, 0.8303, 0.5567, 0.4043, 0.4091, 0.6370, 0.5482],
[0.6776, 0.4518, 0.7636, 0.4052, 0.3734, 0.2846, 0.5586, 0.5967],
[0.6549, 0.4292, 0.8408, 0.4363, 0.4181, 0.5187, 0.6062, 0.5413],
[0.6972, 0.4272, 0.8284, 0.4156, 0.3770, 0.4023, 0.5834, 0.5589],
[0.6584, 0.4397, 0.8381, 0.2707, 0.4301, 0.2266, 0.6898, 0.5920],
[0.6660, 0.4326, 0.8762, 0.4353, 0.4584, 0.5287, 0.6234, 0.5476],
[0.5939, 0.3899, 0.8410, 0.4262, 0.3975, 0.3439, 0.5154, 0.5441],
[0.5964, 0.3956, 0.8295, 0.4933, 0.4590, 0.4670, 0.5879, 0.5507]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6317, 0.4038, 0.8288, 0.5900, 0.3800, 0.4717, 0.6295, 0.4986],
[0.6179, 0.4118, 0.7278, 0.4237, 0.3587, 0.3400, 0.5675, 0.5917],
[0.6064, 0.4019, 0.8650, 0.4517, 0.4038, 0.5367, 0.5703, 0.5609],
[0.6093, 0.3990, 0.8400, 0.4333, 0.3688, 0.4633, 0.5560, 0.5656],
[0.6286, 0.4086, 0.8408, 0.2801, 0.4162, 0.2800, 0.6725, 0.5393],
[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383],
[0.6127, 0.4084, 0.8700, 0.4467, 0.3988, 0.4317, 0.5013, 0.5471],
[0.6070, 0.3979, 0.8575, 0.5083, 0.4350, 0.5400, 0.5180, 0.5466]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.019579105195589364
step: 11
running loss: 0.0017799186541444876
Train Steps: 11/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6200, 0.4098, 0.8237, 0.2917, 0.4012, 0.2967, 0.6000, 0.5683],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3513, 0.4050, 0.6112, 0.5500],
[0.6053, 0.4035, 0.6897, 0.1916, 0.4000, 0.2117, 0.5440, 0.5168],
[0.6214, 0.3982, 0.8938, 0.4517, 0.3663, 0.4083, 0.5863, 0.5050],
[0.6147, 0.4026, 0.6600, 0.2467, 0.4088, 0.2150, 0.5489, 0.5773],
[0.6300, 0.4013, 0.8938, 0.5350, 0.3675, 0.4600, 0.6456, 0.4973],
[0.6137, 0.4038, 0.8563, 0.4050, 0.3813, 0.2550, 0.5106, 0.4954],
[0.6200, 0.3999, 0.8653, 0.5207, 0.4100, 0.5125, 0.5975, 0.5103]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6627, 0.4582, 0.8446, 0.3431, 0.4621, 0.3512, 0.6252, 0.6020],
[0.6581, 0.4269, 0.7875, 0.3111, 0.3887, 0.4321, 0.5941, 0.5865],
[0.6116, 0.3716, 0.7028, 0.2405, 0.4561, 0.2085, 0.5293, 0.5720],
[0.6217, 0.4010, 0.9149, 0.5132, 0.4004, 0.4406, 0.5760, 0.5551],
[0.7454, 0.4856, 0.7083, 0.3050, 0.4564, 0.2597, 0.4888, 0.6232],
[0.6429, 0.3958, 0.9150, 0.5988, 0.4104, 0.5090, 0.6470, 0.5615],
[0.6573, 0.4318, 0.8670, 0.4660, 0.4384, 0.3084, 0.5093, 0.5605],
[0.6276, 0.4006, 0.9061, 0.5831, 0.4815, 0.5650, 0.5835, 0.5617]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6200, 0.4098, 0.8238, 0.2917, 0.4013, 0.2967, 0.6000, 0.5683],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3512, 0.4050, 0.6112, 0.5500],
[0.6054, 0.4035, 0.6897, 0.1916, 0.4000, 0.2117, 0.5440, 0.5168],
[0.6214, 0.3982, 0.8938, 0.4517, 0.3663, 0.4083, 0.5863, 0.5050],
[0.6147, 0.4026, 0.6600, 0.2467, 0.4087, 0.2150, 0.5489, 0.5773],
[0.6300, 0.4013, 0.8938, 0.5350, 0.3675, 0.4600, 0.6456, 0.4973],
[0.6137, 0.4038, 0.8562, 0.4050, 0.3812, 0.2550, 0.5106, 0.4954],
[0.6200, 0.3999, 0.8653, 0.5207, 0.4100, 0.5125, 0.5975, 0.5103]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0020, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0020, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.021589155890978873
step: 12
running loss: 0.0017990963242482394
Train Steps: 12/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6043, 0.4022, 0.6887, 0.1983, 0.3775, 0.2483, 0.5480, 0.5136],
[0.6273, 0.4143, 0.8750, 0.5700, 0.3987, 0.4717, 0.6013, 0.5467],
[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383],
[0.6162, 0.3949, 0.8838, 0.4517, 0.4250, 0.5183, 0.5837, 0.5500],
[0.6145, 0.3983, 0.8700, 0.5017, 0.4400, 0.4800, 0.5375, 0.5750],
[0.6101, 0.3977, 0.8550, 0.5667, 0.3862, 0.4417, 0.5128, 0.4869],
[0.6186, 0.4154, 0.6825, 0.2633, 0.4150, 0.2300, 0.5713, 0.5517],
[0.6118, 0.4052, 0.8463, 0.3917, 0.3538, 0.3450, 0.5053, 0.5593]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6850, 0.4247, 0.7308, 0.2875, 0.4270, 0.2783, 0.5280, 0.5645],
[0.6193, 0.3962, 0.8800, 0.6018, 0.4218, 0.5049, 0.5980, 0.5801],
[0.6418, 0.3852, 0.8744, 0.3716, 0.3916, 0.4108, 0.6206, 0.5730],
[0.6372, 0.4026, 0.9109, 0.5178, 0.4621, 0.5772, 0.5763, 0.5733],
[0.6267, 0.3887, 0.8751, 0.5489, 0.4650, 0.5104, 0.5475, 0.5908],
[0.6339, 0.4063, 0.8848, 0.5980, 0.4351, 0.4774, 0.5554, 0.5471],
[0.6724, 0.4247, 0.7273, 0.3193, 0.4394, 0.2667, 0.5483, 0.5913],
[0.6507, 0.4327, 0.8642, 0.4348, 0.3746, 0.3852, 0.4934, 0.6010]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6043, 0.4022, 0.6888, 0.1983, 0.3775, 0.2483, 0.5480, 0.5136],
[0.6273, 0.4143, 0.8750, 0.5700, 0.3988, 0.4717, 0.6012, 0.5467],
[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383],
[0.6162, 0.3949, 0.8838, 0.4517, 0.4250, 0.5183, 0.5838, 0.5500],
[0.6145, 0.3983, 0.8700, 0.5017, 0.4400, 0.4800, 0.5375, 0.5750],
[0.6101, 0.3977, 0.8550, 0.5667, 0.3862, 0.4417, 0.5128, 0.4869],
[0.6186, 0.4154, 0.6825, 0.2633, 0.4150, 0.2300, 0.5713, 0.5517],
[0.6118, 0.4052, 0.8462, 0.3917, 0.3537, 0.3450, 0.5053, 0.5593]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.022897822898812592
step: 13
running loss: 0.0017613709922163533
Train Steps: 13/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6271, 0.4024, 0.9000, 0.3517, 0.3700, 0.4517, 0.6931, 0.5285],
[ nan, nan, 0.7648, 0.2722, 0.3962, 0.2183, 0.5060, 0.5422],
[ nan, nan, 0.7612, 0.3250, 0.4037, 0.2533, 0.5438, 0.5767],
[0.6271, 0.4081, 0.9081, 0.4894, 0.3700, 0.4283, 0.6661, 0.5274],
[0.6101, 0.3977, 0.8550, 0.5667, 0.3862, 0.4417, 0.5128, 0.4869],
[0.6257, 0.4060, 0.8300, 0.2333, 0.4688, 0.2583, 0.7050, 0.5633],
[0.6262, 0.4052, 0.8888, 0.4700, 0.3675, 0.5117, 0.6350, 0.5233],
[0.6286, 0.4274, 0.8500, 0.4500, 0.4525, 0.2583, 0.5440, 0.6209]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7103, 0.4486, 0.8747, 0.4249, 0.3902, 0.5114, 0.6438, 0.5376],
[0.3599, 0.2209, 0.7311, 0.3070, 0.3967, 0.2738, 0.4546, 0.5411],
[0.4195, 0.2813, 0.7883, 0.3753, 0.4167, 0.2952, 0.4734, 0.5861],
[0.6465, 0.4145, 0.8845, 0.5313, 0.3612, 0.4709, 0.6170, 0.5398],
[0.6977, 0.4486, 0.8552, 0.6218, 0.4135, 0.4887, 0.5198, 0.5217],
[0.6612, 0.4368, 0.8415, 0.3068, 0.4765, 0.3075, 0.6446, 0.5897],
[0.7176, 0.4319, 0.9126, 0.5278, 0.3973, 0.5687, 0.6204, 0.5488],
[0.7001, 0.4696, 0.8438, 0.5102, 0.4606, 0.3406, 0.4802, 0.6126]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6271, 0.4024, 0.9000, 0.3517, 0.3700, 0.4517, 0.6931, 0.5285],
[0.0000, 0.0000, 0.7648, 0.2722, 0.3963, 0.2183, 0.5060, 0.5422],
[0.0000, 0.0000, 0.7613, 0.3250, 0.4038, 0.2533, 0.5437, 0.5767],
[0.6271, 0.4081, 0.9081, 0.4894, 0.3700, 0.4283, 0.6661, 0.5274],
[0.6101, 0.3977, 0.8550, 0.5667, 0.3862, 0.4417, 0.5128, 0.4869],
[0.6257, 0.4060, 0.8300, 0.2333, 0.4688, 0.2583, 0.7050, 0.5633],
[0.6262, 0.4052, 0.8888, 0.4700, 0.3675, 0.5117, 0.6350, 0.5233],
[0.6286, 0.4274, 0.8500, 0.4500, 0.4525, 0.2583, 0.5440, 0.6209]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0086, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0086, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.031523438286967576
step: 14
running loss: 0.002251674163354827
Train Steps: 14/90 Loss: 0.0023 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6164, 0.3972, 0.7818, 0.3381, 0.3599, 0.3387, 0.5880, 0.5153],
[0.6205, 0.4012, 0.8675, 0.3283, 0.3713, 0.3050, 0.5813, 0.5117],
[0.6192, 0.4128, 0.8513, 0.5617, 0.4200, 0.5267, 0.5850, 0.5633],
[0.6200, 0.4098, 0.8237, 0.2917, 0.4012, 0.2967, 0.6000, 0.5683],
[ nan, nan, 0.8625, 0.2550, 0.5487, 0.2200, 0.7335, 0.5737],
[0.6124, 0.4083, 0.6954, 0.3069, 0.3650, 0.2750, 0.5163, 0.5485],
[0.6147, 0.4112, 0.7988, 0.3200, 0.3775, 0.2767, 0.5150, 0.5550],
[0.6190, 0.4135, 0.8000, 0.4883, 0.3566, 0.3647, 0.5613, 0.5900]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6369, 0.3770, 0.8405, 0.3821, 0.3651, 0.3864, 0.5791, 0.5156],
[0.6178, 0.3775, 0.9148, 0.4095, 0.3825, 0.3501, 0.5726, 0.5146],
[0.7046, 0.4203, 0.8782, 0.6498, 0.4341, 0.5928, 0.5846, 0.5494],
[0.6253, 0.4038, 0.8356, 0.3593, 0.4174, 0.3532, 0.6002, 0.5456],
[0.2293, 0.1415, 0.8490, 0.2963, 0.5242, 0.2863, 0.6327, 0.5384],
[0.6541, 0.4069, 0.7483, 0.3571, 0.3859, 0.3337, 0.5057, 0.5481],
[0.5698, 0.3742, 0.8092, 0.4008, 0.3791, 0.3166, 0.4940, 0.5553],
[0.6750, 0.4287, 0.8318, 0.5494, 0.3564, 0.4079, 0.5192, 0.5380]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6164, 0.3972, 0.7818, 0.3381, 0.3599, 0.3387, 0.5880, 0.5153],
[0.6205, 0.4012, 0.8675, 0.3283, 0.3713, 0.3050, 0.5813, 0.5117],
[0.6192, 0.4128, 0.8512, 0.5617, 0.4200, 0.5267, 0.5850, 0.5633],
[0.6200, 0.4098, 0.8238, 0.2917, 0.4013, 0.2967, 0.6000, 0.5683],
[0.0000, 0.0000, 0.8625, 0.2550, 0.5487, 0.2200, 0.7335, 0.5737],
[0.6123, 0.4083, 0.6954, 0.3069, 0.3650, 0.2750, 0.5163, 0.5485],
[0.6147, 0.4112, 0.7987, 0.3200, 0.3775, 0.2767, 0.5150, 0.5550],
[0.6190, 0.4135, 0.8000, 0.4883, 0.3566, 0.3647, 0.5612, 0.5900]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0028, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0028, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03430542966816574
step: 15
running loss: 0.0022870286445443827
Train Steps: 15/90 Loss: 0.0023 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6264, 0.4049, 0.8988, 0.4633, 0.3813, 0.4983, 0.6326, 0.4843],
[0.6079, 0.3964, 0.7420, 0.2958, 0.3563, 0.2917, 0.5351, 0.4980],
[0.6307, 0.4060, 0.8950, 0.5183, 0.3750, 0.3850, 0.6338, 0.4938],
[0.6169, 0.4052, 0.8742, 0.4779, 0.4288, 0.4917, 0.5763, 0.5617],
[0.6140, 0.4070, 0.8700, 0.5000, 0.4612, 0.4900, 0.5260, 0.5852],
[0.6223, 0.4130, 0.8100, 0.2983, 0.3525, 0.3900, 0.5694, 0.5103],
[0.6229, 0.4086, 0.7538, 0.2600, 0.4775, 0.1617, 0.5900, 0.5383],
[0.6275, 0.4024, 0.7722, 0.2080, 0.4392, 0.2234, 0.6435, 0.5290]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5944, 0.3454, 0.9136, 0.5033, 0.3575, 0.5314, 0.6047, 0.5082],
[0.5365, 0.3196, 0.7885, 0.3145, 0.3401, 0.3181, 0.5186, 0.5181],
[0.6247, 0.3771, 0.9237, 0.5689, 0.3381, 0.4124, 0.5901, 0.5049],
[0.5429, 0.3474, 0.8863, 0.5152, 0.4129, 0.5361, 0.5636, 0.5641],
[0.5060, 0.3406, 0.8971, 0.5473, 0.4520, 0.5284, 0.5180, 0.5835],
[0.5774, 0.3656, 0.8471, 0.3874, 0.3530, 0.4066, 0.5703, 0.5504],
[0.5550, 0.3419, 0.7782, 0.2975, 0.4284, 0.1834, 0.5793, 0.5391],
[0.4954, 0.2894, 0.7917, 0.2573, 0.4166, 0.2622, 0.6149, 0.5335]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6264, 0.4049, 0.8988, 0.4633, 0.3812, 0.4983, 0.6326, 0.4843],
[0.6079, 0.3964, 0.7420, 0.2958, 0.3562, 0.2917, 0.5351, 0.4980],
[0.6307, 0.4060, 0.8950, 0.5183, 0.3750, 0.3850, 0.6338, 0.4938],
[0.6169, 0.4052, 0.8742, 0.4779, 0.4288, 0.4917, 0.5763, 0.5617],
[0.6140, 0.4070, 0.8700, 0.5000, 0.4613, 0.4900, 0.5260, 0.5852],
[0.6223, 0.4130, 0.8100, 0.2983, 0.3525, 0.3900, 0.5694, 0.5103],
[0.6229, 0.4086, 0.7538, 0.2600, 0.4775, 0.1617, 0.5900, 0.5383],
[0.6275, 0.4024, 0.7722, 0.2080, 0.4392, 0.2234, 0.6435, 0.5290]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0021, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0021, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03636402601841837
step: 16
running loss: 0.0022727516261511482
Train Steps: 16/90 Loss: 0.0023 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586],
[0.6279, 0.4008, 0.8600, 0.4883, 0.4325, 0.5283, 0.7010, 0.5378],
[0.6199, 0.4093, 0.7913, 0.2533, 0.4288, 0.2467, 0.5975, 0.5700],
[0.6276, 0.4095, 0.8237, 0.2250, 0.4662, 0.1783, 0.6171, 0.4869],
[0.6198, 0.4130, 0.8762, 0.4117, 0.3650, 0.4900, 0.5707, 0.5103],
[0.6260, 0.4133, 0.8800, 0.5117, 0.3713, 0.3283, 0.6223, 0.4967],
[0.6275, 0.4024, 0.8500, 0.5383, 0.3912, 0.4883, 0.6288, 0.5100],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4012, 0.4633, 0.5338, 0.5767]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4330, 0.2798, 0.8786, 0.2619, 0.4194, 0.2778, 0.6735, 0.5339],
[0.5555, 0.3388, 0.8658, 0.5031, 0.3932, 0.5309, 0.6476, 0.5368],
[0.4834, 0.3136, 0.8026, 0.2625, 0.3900, 0.2671, 0.5784, 0.5424],
[0.5196, 0.3330, 0.8274, 0.2463, 0.4491, 0.2297, 0.6057, 0.4950],
[0.5648, 0.3605, 0.8913, 0.4223, 0.3230, 0.4654, 0.5457, 0.5211],
[0.5265, 0.3438, 0.8746, 0.5002, 0.3539, 0.3281, 0.5949, 0.5066],
[0.5507, 0.3276, 0.8567, 0.5455, 0.3664, 0.5009, 0.5833, 0.4898],
[0.5677, 0.3474, 0.8651, 0.5104, 0.3851, 0.4639, 0.5004, 0.5649]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586],
[0.6279, 0.4008, 0.8600, 0.4883, 0.4325, 0.5283, 0.7010, 0.5378],
[0.6198, 0.4093, 0.7912, 0.2533, 0.4288, 0.2467, 0.5975, 0.5700],
[0.6276, 0.4095, 0.8238, 0.2250, 0.4663, 0.1783, 0.6171, 0.4869],
[0.6198, 0.4130, 0.8763, 0.4117, 0.3650, 0.4900, 0.5707, 0.5103],
[0.6260, 0.4133, 0.8800, 0.5117, 0.3713, 0.3283, 0.6223, 0.4967],
[0.6275, 0.4024, 0.8500, 0.5383, 0.3913, 0.4883, 0.6288, 0.5100],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4013, 0.4633, 0.5337, 0.5767]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0027, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0027, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03901701339054853
step: 17
running loss: 0.0022951184347381488
Train Steps: 17/90 Loss: 0.0023 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6311, 0.3998, 0.7975, 0.5767, 0.3838, 0.4850, 0.7327, 0.5343],
[0.6201, 0.4116, 0.8725, 0.4733, 0.3700, 0.3217, 0.5386, 0.5767],
[0.6246, 0.4126, 0.8850, 0.4833, 0.4200, 0.5350, 0.6112, 0.5250],
[0.6205, 0.4012, 0.8675, 0.3283, 0.3713, 0.3050, 0.5813, 0.5117],
[0.6136, 0.4060, 0.8025, 0.3217, 0.3650, 0.3000, 0.5060, 0.5646],
[0.6250, 0.4131, 0.8688, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367],
[0.6246, 0.4028, 0.8738, 0.4867, 0.4088, 0.5667, 0.6362, 0.5200],
[ nan, nan, 0.7525, 0.2291, 0.3838, 0.3017, 0.6050, 0.5667]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5370, 0.3631, 0.8025, 0.4733, 0.3694, 0.4301, 0.6613, 0.5039],
[0.5555, 0.3662, 0.8576, 0.4481, 0.3509, 0.3076, 0.5604, 0.5309],
[0.5755, 0.3779, 0.8860, 0.4477, 0.3929, 0.5262, 0.6205, 0.5168],
[0.5609, 0.3712, 0.8877, 0.3128, 0.3627, 0.2935, 0.6108, 0.4896],
[0.4438, 0.3181, 0.7941, 0.2994, 0.3447, 0.2704, 0.5179, 0.5191],
[0.5578, 0.3616, 0.8624, 0.2708, 0.4258, 0.2182, 0.6350, 0.5023],
[0.6400, 0.3798, 0.8733, 0.4429, 0.4123, 0.5609, 0.6441, 0.5230],
[0.2633, 0.2200, 0.7622, 0.2249, 0.3862, 0.2525, 0.5937, 0.5282]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6311, 0.3998, 0.7975, 0.5767, 0.3837, 0.4850, 0.7327, 0.5343],
[0.6201, 0.4116, 0.8725, 0.4733, 0.3700, 0.3217, 0.5386, 0.5767],
[0.6246, 0.4126, 0.8850, 0.4833, 0.4200, 0.5350, 0.6112, 0.5250],
[0.6205, 0.4012, 0.8675, 0.3283, 0.3713, 0.3050, 0.5813, 0.5117],
[0.6136, 0.4060, 0.8025, 0.3217, 0.3650, 0.3000, 0.5060, 0.5646],
[0.6250, 0.4131, 0.8687, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367],
[0.6246, 0.4028, 0.8737, 0.4867, 0.4087, 0.5667, 0.6363, 0.5200],
[0.0000, 0.0000, 0.7525, 0.2291, 0.3837, 0.3017, 0.6050, 0.5667]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0036, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0036, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04258008219767362
step: 18
running loss: 0.002365560122092979
Train Steps: 18/90 Loss: 0.0024 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6131, 0.4064, 0.8638, 0.5200, 0.4788, 0.4783, 0.5258, 0.5867],
[0.6197, 0.3986, 0.8800, 0.4617, 0.4188, 0.4783, 0.5687, 0.5550],
[ nan, nan, 0.8938, 0.2850, 0.4662, 0.3117, 0.7406, 0.5528],
[0.6201, 0.4151, 0.8588, 0.5467, 0.3700, 0.3950, 0.5637, 0.5933],
[0.6229, 0.4198, 0.7662, 0.2700, 0.4700, 0.2133, 0.5675, 0.5783],
[0.6286, 0.3977, 0.9038, 0.4733, 0.3900, 0.4150, 0.7074, 0.5320],
[0.6296, 0.4045, 0.9138, 0.4100, 0.4232, 0.4242, 0.7422, 0.5297],
[0.6143, 0.4034, 0.8800, 0.4833, 0.4512, 0.5367, 0.5289, 0.5097]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5918, 0.3952, 0.8584, 0.4755, 0.4334, 0.4507, 0.5884, 0.5322],
[0.5844, 0.3977, 0.8591, 0.4129, 0.3728, 0.4645, 0.6018, 0.5118],
[0.2210, 0.1637, 0.9241, 0.2472, 0.4548, 0.2745, 0.7776, 0.5157],
[0.6087, 0.4235, 0.8215, 0.5093, 0.3536, 0.3738, 0.5898, 0.5271],
[0.5043, 0.3472, 0.7739, 0.2174, 0.4279, 0.2316, 0.6006, 0.5307],
[0.5409, 0.3545, 0.8611, 0.3833, 0.3235, 0.4136, 0.6816, 0.4781],
[0.6830, 0.4531, 0.8903, 0.3539, 0.3679, 0.4203, 0.7136, 0.4970],
[0.5697, 0.3720, 0.8571, 0.4214, 0.4092, 0.4769, 0.5778, 0.4975]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6132, 0.4063, 0.8637, 0.5200, 0.4787, 0.4783, 0.5258, 0.5867],
[0.6197, 0.3986, 0.8800, 0.4617, 0.4187, 0.4783, 0.5688, 0.5550],
[0.0000, 0.0000, 0.8938, 0.2850, 0.4663, 0.3117, 0.7406, 0.5528],
[0.6202, 0.4151, 0.8587, 0.5467, 0.3700, 0.3950, 0.5638, 0.5933],
[0.6229, 0.4198, 0.7663, 0.2700, 0.4700, 0.2133, 0.5675, 0.5783],
[0.6286, 0.3977, 0.9038, 0.4733, 0.3900, 0.4150, 0.7074, 0.5320],
[0.6296, 0.4045, 0.9137, 0.4100, 0.4232, 0.4242, 0.7422, 0.5297],
[0.6143, 0.4034, 0.8800, 0.4833, 0.4512, 0.5367, 0.5289, 0.5097]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0031, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0031, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.045656067435629666
step: 19
running loss: 0.0024029509176647194
Train Steps: 19/90 Loss: 0.0024 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.8850, 0.2817, 0.5112, 0.2183, 0.7184, 0.5436],
[0.6277, 0.4083, 0.8350, 0.2717, 0.4562, 0.1800, 0.5918, 0.4878],
[0.6300, 0.4133, 0.8538, 0.2167, 0.5587, 0.2250, 0.7390, 0.5413],
[ nan, nan, 0.7648, 0.2722, 0.3962, 0.2183, 0.5060, 0.5422],
[0.6266, 0.4101, 0.8350, 0.2333, 0.3950, 0.2950, 0.6264, 0.4921],
[0.6136, 0.4117, 0.8700, 0.5167, 0.4188, 0.5083, 0.5147, 0.5495],
[0.6134, 0.4090, 0.6926, 0.2819, 0.3538, 0.3233, 0.5563, 0.5667],
[0.6260, 0.4120, 0.8013, 0.2350, 0.4888, 0.1533, 0.6281, 0.4895]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.3317, 0.2437, 0.8838, 0.2707, 0.5007, 0.2329, 0.7101, 0.5134],
[0.4226, 0.2902, 0.8046, 0.2608, 0.4476, 0.2214, 0.6137, 0.5088],
[0.5430, 0.3784, 0.8516, 0.2332, 0.5131, 0.2774, 0.7556, 0.5394],
[0.1304, 0.1043, 0.7471, 0.2489, 0.3800, 0.2012, 0.5221, 0.5210],
[0.6030, 0.3979, 0.8176, 0.2325, 0.4119, 0.2649, 0.6792, 0.5080],
[0.7374, 0.4957, 0.8782, 0.5724, 0.4039, 0.4957, 0.5789, 0.5219],
[0.6925, 0.4588, 0.7116, 0.2866, 0.3439, 0.3203, 0.5630, 0.5454],
[0.6044, 0.3941, 0.7845, 0.2106, 0.4687, 0.1488, 0.6680, 0.5050]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.8850, 0.2817, 0.5113, 0.2183, 0.7184, 0.5436],
[0.6277, 0.4083, 0.8350, 0.2717, 0.4563, 0.1800, 0.5918, 0.4878],
[0.6300, 0.4133, 0.8537, 0.2167, 0.5587, 0.2250, 0.7390, 0.5413],
[0.0000, 0.0000, 0.7648, 0.2722, 0.3963, 0.2183, 0.5060, 0.5422],
[0.6266, 0.4101, 0.8350, 0.2333, 0.3950, 0.2950, 0.6264, 0.4921],
[0.6136, 0.4117, 0.8700, 0.5167, 0.4187, 0.5083, 0.5147, 0.5495],
[0.6134, 0.4090, 0.6926, 0.2819, 0.3537, 0.3233, 0.5562, 0.5667],
[0.6259, 0.4120, 0.8012, 0.2350, 0.4888, 0.1533, 0.6281, 0.4895]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0051, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0051, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.050726136774756014
step: 20
running loss: 0.002536306838737801
Train Steps: 20/90 Loss: 0.0025 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6249, 0.4138, 0.9038, 0.4517, 0.3862, 0.4917, 0.6138, 0.5333],
[0.6207, 0.4081, 0.7662, 0.2067, 0.3962, 0.3200, 0.6312, 0.5300],
[0.6115, 0.4081, 0.6725, 0.2433, 0.4088, 0.1933, 0.5167, 0.5544],
[0.6128, 0.4084, 0.8738, 0.4683, 0.3613, 0.3700, 0.4960, 0.5397],
[0.6193, 0.4165, 0.8838, 0.4700, 0.4150, 0.4867, 0.5427, 0.5261],
[0.6201, 0.4151, 0.8588, 0.5467, 0.3700, 0.3950, 0.5637, 0.5933],
[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586],
[0.6157, 0.3956, 0.8323, 0.4138, 0.3479, 0.4431, 0.5914, 0.5131]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5901, 0.4298, 0.8875, 0.4076, 0.3987, 0.4621, 0.6725, 0.5381],
[0.5370, 0.3682, 0.7592, 0.1734, 0.4341, 0.2684, 0.6666, 0.5472],
[0.4572, 0.3172, 0.7158, 0.2226, 0.4405, 0.1772, 0.5711, 0.5436],
[0.5756, 0.3987, 0.8808, 0.4527, 0.3977, 0.3508, 0.5557, 0.5388],
[0.5095, 0.3654, 0.8806, 0.4264, 0.4335, 0.4443, 0.6113, 0.5361],
[0.5600, 0.4047, 0.8448, 0.5110, 0.4104, 0.3563, 0.6075, 0.5725],
[0.4382, 0.3084, 0.8828, 0.2070, 0.4856, 0.2378, 0.7775, 0.5535],
[0.6409, 0.4133, 0.8676, 0.3542, 0.4018, 0.4103, 0.6507, 0.5465]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6249, 0.4138, 0.9038, 0.4517, 0.3862, 0.4917, 0.6137, 0.5333],
[0.6207, 0.4081, 0.7663, 0.2067, 0.3963, 0.3200, 0.6313, 0.5300],
[0.6115, 0.4081, 0.6725, 0.2433, 0.4087, 0.1933, 0.5167, 0.5544],
[0.6127, 0.4084, 0.8737, 0.4683, 0.3613, 0.3700, 0.4960, 0.5397],
[0.6193, 0.4165, 0.8838, 0.4700, 0.4150, 0.4867, 0.5427, 0.5261],
[0.6202, 0.4151, 0.8587, 0.5467, 0.3700, 0.3950, 0.5638, 0.5933],
[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586],
[0.6157, 0.3956, 0.8323, 0.4138, 0.3479, 0.4431, 0.5914, 0.5131]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0028, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0028, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.053505434771068394
step: 21
running loss: 0.002547877846241352
Train Steps: 21/90 Loss: 0.0025 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6296, 0.4060, 0.9100, 0.3267, 0.4726, 0.3367, 0.7446, 0.5355],
[0.6268, 0.4061, 0.8350, 0.2433, 0.4575, 0.2283, 0.6350, 0.5300],
[0.6069, 0.3975, 0.8625, 0.5083, 0.4388, 0.5483, 0.5650, 0.4967],
[0.6211, 0.3935, 0.8636, 0.4841, 0.4417, 0.5126, 0.6331, 0.5268],
[0.6204, 0.4013, 0.8075, 0.2400, 0.4313, 0.2050, 0.5800, 0.5150],
[0.6346, 0.4144, 0.9088, 0.4667, 0.3850, 0.4333, 0.7121, 0.5899],
[0.6361, 0.4071, 0.9100, 0.4783, 0.3738, 0.3967, 0.6670, 0.5332],
[0.6257, 0.4024, 0.8672, 0.5422, 0.4196, 0.5198, 0.6694, 0.5204]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5056, 0.3462, 0.8709, 0.2943, 0.4799, 0.2926, 0.6936, 0.5203],
[0.5236, 0.3603, 0.8550, 0.1726, 0.4822, 0.1785, 0.6520, 0.5347],
[0.5216, 0.3837, 0.8388, 0.4630, 0.4735, 0.4920, 0.5264, 0.5561],
[0.5107, 0.3523, 0.8397, 0.4314, 0.4522, 0.4588, 0.5876, 0.5638],
[0.4940, 0.3262, 0.7804, 0.2140, 0.4554, 0.2161, 0.5925, 0.5326],
[0.5580, 0.3879, 0.8799, 0.4109, 0.4304, 0.3769, 0.6884, 0.5656],
[0.6593, 0.4375, 0.8602, 0.4501, 0.4064, 0.3761, 0.6315, 0.5474],
[0.5514, 0.3732, 0.8135, 0.4741, 0.4225, 0.4865, 0.6201, 0.5624]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6296, 0.4060, 0.9100, 0.3267, 0.4726, 0.3367, 0.7446, 0.5355],
[0.6268, 0.4060, 0.8350, 0.2433, 0.4575, 0.2283, 0.6350, 0.5300],
[0.6069, 0.3975, 0.8625, 0.5083, 0.4387, 0.5483, 0.5650, 0.4967],
[0.6211, 0.3935, 0.8636, 0.4841, 0.4417, 0.5126, 0.6331, 0.5268],
[0.6204, 0.4013, 0.8075, 0.2400, 0.4313, 0.2050, 0.5800, 0.5150],
[0.6346, 0.4144, 0.9087, 0.4667, 0.3850, 0.4333, 0.7121, 0.5899],
[0.6361, 0.4071, 0.9100, 0.4783, 0.3738, 0.3967, 0.6670, 0.5332],
[0.6257, 0.4024, 0.8672, 0.5422, 0.4196, 0.5198, 0.6694, 0.5204]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0025, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0025, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05599151493515819
step: 22
running loss: 0.002545068860689009
Train Steps: 22/90 Loss: 0.0025 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6200, 0.4039, 0.8880, 0.4799, 0.3625, 0.4285, 0.5866, 0.5148],
[ nan, nan, 0.6688, 0.2513, 0.4113, 0.2117, 0.5193, 0.5933],
[0.6124, 0.4083, 0.6954, 0.3069, 0.3650, 0.2750, 0.5163, 0.5485],
[0.6125, 0.3983, 0.8750, 0.4867, 0.4275, 0.4783, 0.5413, 0.5717],
[0.6203, 0.4072, 0.8892, 0.3523, 0.3783, 0.3017, 0.5898, 0.5478],
[0.6122, 0.4006, 0.8850, 0.4217, 0.4088, 0.5517, 0.6063, 0.5517],
[0.6196, 0.4088, 0.8888, 0.4583, 0.4500, 0.5683, 0.6138, 0.5883],
[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6189, 0.3997, 0.8820, 0.4238, 0.4160, 0.3840, 0.6119, 0.5490],
[0.0977, 0.0911, 0.6965, 0.2213, 0.4232, 0.1823, 0.5793, 0.5771],
[0.6315, 0.4235, 0.7317, 0.2649, 0.4093, 0.2834, 0.5647, 0.5624],
[0.6621, 0.4304, 0.8660, 0.4649, 0.4866, 0.4302, 0.5786, 0.5840],
[0.6096, 0.3989, 0.8899, 0.3080, 0.4147, 0.2769, 0.6552, 0.5774],
[0.6882, 0.4586, 0.8791, 0.4039, 0.4599, 0.5236, 0.6363, 0.5646],
[0.6097, 0.4281, 0.8857, 0.4110, 0.4833, 0.5131, 0.6350, 0.5820],
[0.6308, 0.4299, 0.8597, 0.4899, 0.3927, 0.3489, 0.5909, 0.5397]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6201, 0.4039, 0.8880, 0.4799, 0.3625, 0.4285, 0.5866, 0.5148],
[0.0000, 0.0000, 0.6688, 0.2513, 0.4112, 0.2117, 0.5193, 0.5933],
[0.6123, 0.4083, 0.6954, 0.3069, 0.3650, 0.2750, 0.5163, 0.5485],
[0.6125, 0.3983, 0.8750, 0.4867, 0.4275, 0.4783, 0.5412, 0.5717],
[0.6203, 0.4072, 0.8892, 0.3523, 0.3783, 0.3017, 0.5898, 0.5478],
[0.6122, 0.4006, 0.8850, 0.4217, 0.4087, 0.5517, 0.6062, 0.5517],
[0.6196, 0.4088, 0.8888, 0.4583, 0.4500, 0.5683, 0.6137, 0.5883],
[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05741637130267918
step: 23
running loss: 0.0024963639696817036
Train Steps: 23/90 Loss: 0.0025 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6212, 0.4033, 0.8938, 0.4167, 0.3813, 0.4267, 0.5613, 0.5583],
[0.6170, 0.4102, 0.7468, 0.3695, 0.3463, 0.3767, 0.5238, 0.5823],
[0.6214, 0.4116, 0.7750, 0.2317, 0.4487, 0.1883, 0.6200, 0.5400],
[ nan, nan, 0.6469, 0.1943, 0.4025, 0.2000, 0.5125, 0.5533],
[0.6282, 0.4034, 0.7830, 0.2080, 0.4532, 0.2080, 0.6404, 0.5323],
[0.6102, 0.4005, 0.8688, 0.5100, 0.4813, 0.5400, 0.5404, 0.5064],
[0.6361, 0.4165, 0.9038, 0.5017, 0.3750, 0.3783, 0.6448, 0.5309],
[0.6299, 0.4008, 0.8450, 0.5350, 0.4213, 0.5000, 0.6350, 0.5100]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6483, 0.4329, 0.8978, 0.4326, 0.3863, 0.4186, 0.5454, 0.5792],
[0.6430, 0.4231, 0.7608, 0.3607, 0.3721, 0.4013, 0.5512, 0.5972],
[0.6352, 0.3953, 0.7954, 0.2319, 0.4659, 0.2090, 0.6230, 0.5244],
[0.0224, 0.0161, 0.6969, 0.2110, 0.4282, 0.1571, 0.5344, 0.5740],
[0.6293, 0.4141, 0.7977, 0.2335, 0.4426, 0.1968, 0.6254, 0.5558],
[0.6616, 0.4534, 0.8593, 0.5196, 0.4908, 0.4956, 0.5336, 0.5511],
[0.6865, 0.4557, 0.8721, 0.4978, 0.3912, 0.3721, 0.6095, 0.5410],
[0.7057, 0.4689, 0.8426, 0.5325, 0.4386, 0.5152, 0.6351, 0.5462]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6212, 0.4033, 0.8938, 0.4167, 0.3812, 0.4267, 0.5612, 0.5583],
[0.6170, 0.4102, 0.7468, 0.3695, 0.3462, 0.3767, 0.5238, 0.5823],
[0.6214, 0.4116, 0.7750, 0.2317, 0.4487, 0.1883, 0.6200, 0.5400],
[0.0000, 0.0000, 0.6469, 0.1943, 0.4025, 0.2000, 0.5125, 0.5533],
[0.6282, 0.4034, 0.7830, 0.2080, 0.4532, 0.2080, 0.6404, 0.5323],
[0.6102, 0.4005, 0.8687, 0.5100, 0.4812, 0.5400, 0.5404, 0.5064],
[0.6361, 0.4165, 0.9038, 0.5017, 0.3750, 0.3783, 0.6448, 0.5309],
[0.6299, 0.4008, 0.8450, 0.5350, 0.4212, 0.5000, 0.6350, 0.5100]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.058127752621658146
step: 24
running loss: 0.0024219896925690896
Train Steps: 24/90 Loss: 0.0024 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6182, 0.4058, 0.8738, 0.4350, 0.3563, 0.3400, 0.5290, 0.5822],
[0.6200, 0.4112, 0.8862, 0.4100, 0.3638, 0.4917, 0.6088, 0.6050],
[ nan, nan, 0.7512, 0.2117, 0.4288, 0.2000, 0.5600, 0.5617],
[0.6364, 0.4154, 0.8938, 0.3717, 0.4500, 0.2583, 0.6448, 0.5285],
[0.6308, 0.3990, 0.8688, 0.5183, 0.3950, 0.4983, 0.6388, 0.5133],
[0.6128, 0.4022, 0.8738, 0.5067, 0.4983, 0.5231, 0.5364, 0.5064],
[0.6296, 0.3989, 0.9000, 0.4150, 0.3613, 0.3867, 0.6400, 0.5100],
[0.6201, 0.4029, 0.8776, 0.4602, 0.3683, 0.4203, 0.5938, 0.5450]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6093, 0.3999, 0.8337, 0.4284, 0.3559, 0.3779, 0.5022, 0.5830],
[0.6382, 0.4220, 0.8517, 0.4154, 0.3702, 0.5035, 0.5867, 0.5758],
[0.2702, 0.1768, 0.7247, 0.2521, 0.4284, 0.2276, 0.5442, 0.5621],
[0.6540, 0.4113, 0.8690, 0.3864, 0.4371, 0.2669, 0.6174, 0.5398],
[0.6239, 0.3889, 0.8392, 0.5560, 0.4058, 0.5212, 0.6302, 0.5345],
[0.6113, 0.4132, 0.8346, 0.5003, 0.4610, 0.4800, 0.5369, 0.5320],
[0.7170, 0.4505, 0.8821, 0.4155, 0.3609, 0.4126, 0.6495, 0.5369],
[0.6013, 0.3870, 0.8461, 0.4729, 0.3706, 0.4457, 0.5826, 0.5565]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6182, 0.4058, 0.8737, 0.4350, 0.3562, 0.3400, 0.5290, 0.5822],
[0.6200, 0.4112, 0.8863, 0.4100, 0.3638, 0.4917, 0.6087, 0.6050],
[0.0000, 0.0000, 0.7513, 0.2117, 0.4288, 0.2000, 0.5600, 0.5617],
[0.6364, 0.4154, 0.8938, 0.3717, 0.4500, 0.2583, 0.6448, 0.5285],
[0.6308, 0.3990, 0.8687, 0.5183, 0.3950, 0.4983, 0.6388, 0.5133],
[0.6128, 0.4022, 0.8737, 0.5067, 0.4983, 0.5231, 0.5364, 0.5064],
[0.6296, 0.3989, 0.9000, 0.4150, 0.3613, 0.3867, 0.6400, 0.5100],
[0.6201, 0.4029, 0.8776, 0.4602, 0.3683, 0.4203, 0.5938, 0.5450]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0022, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0022, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06033143226522952
step: 25
running loss: 0.002413257290609181
Train Steps: 25/90 Loss: 0.0024 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6196, 0.4094, 0.7562, 0.2817, 0.3937, 0.3183, 0.6013, 0.6183],
[0.6193, 0.4108, 0.7425, 0.2350, 0.3887, 0.2750, 0.5900, 0.5717],
[0.6234, 0.4023, 0.8888, 0.4633, 0.3975, 0.5767, 0.6400, 0.5183],
[0.6148, 0.4076, 0.8666, 0.4820, 0.4138, 0.5067, 0.5250, 0.5767],
[0.6211, 0.4069, 0.8750, 0.5117, 0.4150, 0.4900, 0.5875, 0.5167],
[0.6127, 0.4115, 0.7163, 0.2883, 0.3625, 0.2950, 0.5327, 0.5495],
[0.6333, 0.4037, 0.8638, 0.5733, 0.4012, 0.4717, 0.6369, 0.4938],
[0.6159, 0.4085, 0.6900, 0.2283, 0.4088, 0.1950, 0.5123, 0.5397]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6160, 0.3895, 0.7928, 0.3331, 0.3901, 0.3177, 0.5873, 0.5922],
[0.5629, 0.3442, 0.7577, 0.2975, 0.3681, 0.2849, 0.5655, 0.5591],
[0.6375, 0.3715, 0.9214, 0.4802, 0.3835, 0.5911, 0.6241, 0.5429],
[0.6171, 0.3862, 0.8805, 0.5191, 0.4360, 0.5156, 0.5317, 0.5459],
[0.6700, 0.4098, 0.8710, 0.5518, 0.3930, 0.5352, 0.5776, 0.5149],
[0.5614, 0.3484, 0.7337, 0.3151, 0.3581, 0.3145, 0.5202, 0.5507],
[0.7045, 0.4279, 0.8837, 0.5943, 0.3764, 0.4633, 0.6147, 0.5073],
[0.4651, 0.2801, 0.6989, 0.2835, 0.3888, 0.2057, 0.5165, 0.5298]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6196, 0.4094, 0.7563, 0.2817, 0.3938, 0.3183, 0.6012, 0.6183],
[0.6193, 0.4108, 0.7425, 0.2350, 0.3887, 0.2750, 0.5900, 0.5717],
[0.6234, 0.4023, 0.8888, 0.4633, 0.3975, 0.5767, 0.6400, 0.5183],
[0.6148, 0.4076, 0.8666, 0.4820, 0.4137, 0.5067, 0.5250, 0.5767],
[0.6211, 0.4069, 0.8750, 0.5117, 0.4150, 0.4900, 0.5875, 0.5167],
[0.6127, 0.4114, 0.7163, 0.2883, 0.3625, 0.2950, 0.5327, 0.5495],
[0.6334, 0.4037, 0.8637, 0.5733, 0.4013, 0.4717, 0.6369, 0.4938],
[0.6159, 0.4085, 0.6900, 0.2283, 0.4087, 0.1950, 0.5123, 0.5397]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06175887619610876
step: 26
running loss: 0.002375341392158029
Train Steps: 26/90 Loss: 0.0024 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6141, 0.4038, 0.8650, 0.4833, 0.4839, 0.5176, 0.5787, 0.5600],
[0.6037, 0.4020, 0.8300, 0.4033, 0.3575, 0.4883, 0.5647, 0.5631],
[ nan, nan, 0.7981, 0.3194, 0.3625, 0.3167, 0.5040, 0.5563],
[0.6304, 0.4024, 0.8925, 0.4800, 0.3937, 0.4817, 0.7485, 0.5297],
[0.6034, 0.4011, 0.7350, 0.2533, 0.3438, 0.3367, 0.5516, 0.5084],
[0.6185, 0.4080, 0.8625, 0.3483, 0.3788, 0.2650, 0.5320, 0.5272],
[0.6201, 0.4116, 0.8725, 0.4733, 0.3700, 0.3217, 0.5386, 0.5767],
[0.6229, 0.4086, 0.7538, 0.2600, 0.4775, 0.1617, 0.5900, 0.5383]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6436, 0.3993, 0.8663, 0.5342, 0.4515, 0.5277, 0.5575, 0.5408],
[0.6770, 0.3979, 0.8363, 0.4462, 0.3444, 0.5367, 0.5881, 0.5528],
[0.2007, 0.1157, 0.7863, 0.3516, 0.3207, 0.3140, 0.5153, 0.5435],
[0.6610, 0.3867, 0.8835, 0.5234, 0.3765, 0.5157, 0.6412, 0.5174],
[0.6181, 0.3727, 0.7298, 0.2919, 0.3445, 0.3732, 0.5756, 0.5017],
[0.6510, 0.3927, 0.8464, 0.4056, 0.3709, 0.3140, 0.5137, 0.5286],
[0.6249, 0.3743, 0.8593, 0.4903, 0.3432, 0.3430, 0.5064, 0.5652],
[0.6487, 0.4039, 0.7184, 0.2811, 0.4340, 0.1724, 0.5875, 0.5331]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6141, 0.4038, 0.8650, 0.4833, 0.4839, 0.5176, 0.5788, 0.5600],
[0.6037, 0.4020, 0.8300, 0.4033, 0.3575, 0.4883, 0.5647, 0.5631],
[0.0000, 0.0000, 0.7981, 0.3194, 0.3625, 0.3167, 0.5040, 0.5563],
[0.6304, 0.4024, 0.8925, 0.4800, 0.3938, 0.4817, 0.7485, 0.5297],
[0.6033, 0.4011, 0.7350, 0.2533, 0.3438, 0.3367, 0.5516, 0.5084],
[0.6186, 0.4080, 0.8625, 0.3483, 0.3787, 0.2650, 0.5320, 0.5272],
[0.6201, 0.4116, 0.8725, 0.4733, 0.3700, 0.3217, 0.5386, 0.5767],
[0.6229, 0.4086, 0.7538, 0.2600, 0.4775, 0.1617, 0.5900, 0.5383]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06347480788826942
step: 27
running loss: 0.002350918810676645
Train Steps: 27/90 Loss: 0.0024 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6138, 0.4020, 0.8800, 0.4717, 0.4375, 0.4717, 0.5502, 0.5611],
[0.6185, 0.4079, 0.8838, 0.4617, 0.4838, 0.5650, 0.6175, 0.5850],
[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150],
[0.6277, 0.4036, 0.8688, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742],
[0.6223, 0.4130, 0.8100, 0.2983, 0.3525, 0.3900, 0.5694, 0.5103],
[0.6085, 0.4008, 0.8588, 0.5200, 0.4959, 0.4977, 0.5175, 0.5283],
[0.6117, 0.4018, 0.6562, 0.1967, 0.3738, 0.2550, 0.5280, 0.5103],
[0.6201, 0.4151, 0.8588, 0.5467, 0.3700, 0.3950, 0.5637, 0.5933]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6822, 0.4314, 0.8651, 0.4856, 0.3992, 0.4735, 0.5274, 0.5404],
[0.5400, 0.3283, 0.8774, 0.4733, 0.4195, 0.5492, 0.6072, 0.5681],
[0.4843, 0.2985, 0.8924, 0.5053, 0.3795, 0.5752, 0.6132, 0.5527],
[0.6219, 0.3712, 0.8523, 0.3708, 0.3658, 0.2955, 0.6313, 0.5004],
[0.6180, 0.4010, 0.8046, 0.3480, 0.3300, 0.3867, 0.5747, 0.5360],
[0.6175, 0.3946, 0.8366, 0.5188, 0.4460, 0.4738, 0.5096, 0.5268],
[0.5767, 0.3839, 0.6640, 0.2650, 0.3513, 0.2447, 0.5245, 0.5126],
[0.6322, 0.4174, 0.8397, 0.5665, 0.3124, 0.4103, 0.5321, 0.5726]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6138, 0.4020, 0.8800, 0.4717, 0.4375, 0.4717, 0.5502, 0.5611],
[0.6184, 0.4079, 0.8838, 0.4617, 0.4837, 0.5650, 0.6175, 0.5850],
[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150],
[0.6277, 0.4036, 0.8687, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742],
[0.6223, 0.4130, 0.8100, 0.2983, 0.3525, 0.3900, 0.5694, 0.5103],
[0.6084, 0.4008, 0.8587, 0.5200, 0.4959, 0.4977, 0.5175, 0.5283],
[0.6116, 0.4018, 0.6562, 0.1967, 0.3738, 0.2550, 0.5280, 0.5103],
[0.6202, 0.4151, 0.8587, 0.5467, 0.3700, 0.3950, 0.5638, 0.5933]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06485963379964232
step: 28
running loss: 0.0023164154928443687
Train Steps: 28/90 Loss: 0.0023 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6200, 0.3993, 0.8519, 0.4923, 0.3962, 0.4717, 0.6013, 0.5433],
[0.6296, 0.4060, 0.9100, 0.3267, 0.4726, 0.3367, 0.7446, 0.5355],
[0.6125, 0.4010, 0.8650, 0.4567, 0.3663, 0.3900, 0.5600, 0.5567],
[ nan, nan, 0.7240, 0.2722, 0.3900, 0.2567, 0.5168, 0.5933],
[0.6182, 0.3987, 0.7878, 0.2889, 0.3699, 0.3260, 0.6086, 0.5367],
[0.6118, 0.4052, 0.8463, 0.3917, 0.3538, 0.3450, 0.5053, 0.5593],
[0.6214, 0.4175, 0.7300, 0.2883, 0.4338, 0.2167, 0.5698, 0.5773],
[0.6264, 0.4069, 0.7900, 0.1650, 0.4275, 0.2267, 0.6290, 0.4947]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 6.7090e-01, 4.0646e-01, 8.8374e-01, 5.4438e-01, 3.8827e-01,
5.3380e-01, 5.8710e-01, 5.2107e-01],
[ 6.3156e-01, 3.8918e-01, 8.8924e-01, 3.9016e-01, 4.5429e-01,
3.5994e-01, 7.0014e-01, 5.0003e-01],
[ 7.1235e-01, 4.4388e-01, 8.7769e-01, 4.9250e-01, 3.6733e-01,
4.6729e-01, 5.2955e-01, 5.4011e-01],
[-3.6269e-04, -8.9101e-03, 7.3422e-01, 3.1684e-01, 3.8392e-01,
2.9073e-01, 4.9513e-01, 5.4069e-01],
[ 7.0830e-01, 4.4306e-01, 8.0668e-01, 3.2193e-01, 3.6984e-01,
3.3750e-01, 5.6709e-01, 5.1859e-01],
[ 6.9812e-01, 4.5714e-01, 8.6463e-01, 4.2777e-01, 3.4170e-01,
3.8019e-01, 4.5121e-01, 5.2652e-01],
[ 6.6152e-01, 4.4307e-01, 7.3589e-01, 3.0837e-01, 4.2011e-01,
2.6642e-01, 5.2988e-01, 5.5355e-01],
[ 5.7453e-01, 3.4652e-01, 7.8571e-01, 2.3260e-01, 4.2730e-01,
2.6989e-01, 6.5486e-01, 5.0269e-01]], device='cuda:0',
grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6200, 0.3993, 0.8519, 0.4923, 0.3963, 0.4717, 0.6012, 0.5433],
[0.6296, 0.4060, 0.9100, 0.3267, 0.4726, 0.3367, 0.7446, 0.5355],
[0.6125, 0.4010, 0.8650, 0.4567, 0.3663, 0.3900, 0.5600, 0.5567],
[0.0000, 0.0000, 0.7240, 0.2722, 0.3900, 0.2567, 0.5168, 0.5933],
[0.6182, 0.3987, 0.7878, 0.2889, 0.3699, 0.3260, 0.6086, 0.5367],
[0.6118, 0.4052, 0.8462, 0.3917, 0.3537, 0.3450, 0.5053, 0.5593],
[0.6214, 0.4175, 0.7300, 0.2883, 0.4338, 0.2167, 0.5698, 0.5773],
[0.6264, 0.4069, 0.7900, 0.1650, 0.4275, 0.2267, 0.6290, 0.4947]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.066403744276613
step: 29
running loss: 0.002289784285400448
Train Steps: 29/90 Loss: 0.0023 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6260, 0.4253, 0.8938, 0.4400, 0.3675, 0.3650, 0.5675, 0.5767],
[0.6264, 0.4067, 0.9050, 0.4183, 0.3775, 0.4600, 0.6308, 0.4862],
[0.6203, 0.4056, 0.8942, 0.4086, 0.3643, 0.3617, 0.5917, 0.5482],
[0.6317, 0.4038, 0.8287, 0.5900, 0.3800, 0.4717, 0.6295, 0.4986],
[0.6085, 0.4008, 0.8588, 0.5200, 0.4959, 0.4977, 0.5175, 0.5283],
[0.6214, 0.4112, 0.7838, 0.2117, 0.3650, 0.3133, 0.5675, 0.5083],
[ nan, nan, 0.7525, 0.2291, 0.3838, 0.3017, 0.6050, 0.5667],
[0.6163, 0.4114, 0.7650, 0.2017, 0.3763, 0.2867, 0.5631, 0.5071]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6553, 0.4516, 0.8909, 0.4744, 0.3987, 0.3983, 0.5979, 0.5874],
[0.6033, 0.3995, 0.9001, 0.3978, 0.3655, 0.4665, 0.5997, 0.5057],
[0.6109, 0.3870, 0.8913, 0.4282, 0.3730, 0.3778, 0.5874, 0.5565],
[0.6447, 0.4530, 0.8713, 0.6013, 0.3892, 0.4725, 0.6208, 0.5390],
[0.6460, 0.4327, 0.8558, 0.5071, 0.4999, 0.4846, 0.5085, 0.5388],
[0.6930, 0.4552, 0.7825, 0.2199, 0.3805, 0.2937, 0.5852, 0.5319],
[0.1483, 0.1368, 0.7527, 0.2525, 0.4189, 0.2928, 0.5746, 0.5629],
[0.6174, 0.3917, 0.7474, 0.2506, 0.4010, 0.2601, 0.5830, 0.5165]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6260, 0.4253, 0.8938, 0.4400, 0.3675, 0.3650, 0.5675, 0.5767],
[0.6264, 0.4067, 0.9050, 0.4183, 0.3775, 0.4600, 0.6308, 0.4862],
[0.6203, 0.4056, 0.8942, 0.4086, 0.3643, 0.3617, 0.5917, 0.5482],
[0.6317, 0.4038, 0.8288, 0.5900, 0.3800, 0.4717, 0.6295, 0.4986],
[0.6084, 0.4008, 0.8587, 0.5200, 0.4959, 0.4977, 0.5175, 0.5283],
[0.6214, 0.4112, 0.7837, 0.2117, 0.3650, 0.3133, 0.5675, 0.5083],
[0.0000, 0.0000, 0.7525, 0.2291, 0.3837, 0.3017, 0.6050, 0.5667],
[0.6163, 0.4114, 0.7650, 0.2017, 0.3762, 0.2867, 0.5631, 0.5071]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06759074423462152
step: 30
running loss: 0.0022530248078207176
Train Steps: 30/90 Loss: 0.0023 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6293, 0.4097, 0.8800, 0.2517, 0.5262, 0.2600, 0.7430, 0.5378],
[0.6265, 0.4251, 0.7113, 0.3550, 0.4375, 0.2117, 0.5587, 0.6118],
[0.6145, 0.4008, 0.8750, 0.5383, 0.3975, 0.4650, 0.5563, 0.5533],
[0.6275, 0.4157, 0.8337, 0.5800, 0.3763, 0.4200, 0.5547, 0.6125],
[0.6246, 0.4028, 0.8738, 0.4867, 0.4088, 0.5667, 0.6362, 0.5200],
[0.6125, 0.3999, 0.8750, 0.4883, 0.4750, 0.4700, 0.5533, 0.5617],
[0.6142, 0.3982, 0.8650, 0.4883, 0.3912, 0.4317, 0.5315, 0.5350],
[0.6150, 0.3935, 0.8696, 0.5158, 0.4647, 0.5329, 0.6041, 0.5153]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5891, 0.4129, 0.8819, 0.1990, 0.5162, 0.2382, 0.7617, 0.5226],
[0.5691, 0.4271, 0.7440, 0.2872, 0.3934, 0.2544, 0.5267, 0.5962],
[0.5291, 0.3691, 0.8776, 0.4669, 0.3964, 0.4697, 0.5507, 0.5498],
[0.5685, 0.3836, 0.8484, 0.5101, 0.3768, 0.4332, 0.5894, 0.5859],
[0.5461, 0.3610, 0.8937, 0.4030, 0.4117, 0.5739, 0.6300, 0.5297],
[0.6028, 0.4109, 0.8958, 0.4430, 0.4658, 0.4558, 0.5568, 0.5362],
[0.5917, 0.3764, 0.8950, 0.4554, 0.3693, 0.4597, 0.5308, 0.4896],
[0.5577, 0.3902, 0.8747, 0.4571, 0.4388, 0.5051, 0.5908, 0.5223]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6293, 0.4097, 0.8800, 0.2517, 0.5263, 0.2600, 0.7430, 0.5378],
[0.6265, 0.4251, 0.7113, 0.3550, 0.4375, 0.2117, 0.5587, 0.6118],
[0.6145, 0.4008, 0.8750, 0.5383, 0.3975, 0.4650, 0.5562, 0.5533],
[0.6275, 0.4157, 0.8338, 0.5800, 0.3762, 0.4200, 0.5547, 0.6125],
[0.6246, 0.4028, 0.8737, 0.4867, 0.4087, 0.5667, 0.6363, 0.5200],
[0.6125, 0.3999, 0.8750, 0.4883, 0.4750, 0.4700, 0.5533, 0.5617],
[0.6143, 0.3982, 0.8650, 0.4883, 0.3913, 0.4317, 0.5315, 0.5350],
[0.6150, 0.3935, 0.8696, 0.5158, 0.4647, 0.5329, 0.6041, 0.5153]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06881934218108654
step: 31
running loss: 0.0022199787800350496
Train Steps: 31/90 Loss: 0.0022 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6193, 0.4108, 0.7438, 0.2700, 0.3650, 0.3683, 0.6238, 0.5717],
[0.6111, 0.4019, 0.8350, 0.3867, 0.3500, 0.4283, 0.5480, 0.5719],
[0.6189, 0.4049, 0.8888, 0.4417, 0.4213, 0.5200, 0.5988, 0.5633],
[0.6205, 0.4016, 0.8350, 0.2717, 0.3987, 0.2550, 0.5787, 0.5133],
[0.6201, 0.4036, 0.8596, 0.3850, 0.3492, 0.3785, 0.5978, 0.5131],
[ nan, nan, 0.8037, 0.2483, 0.3975, 0.2517, 0.5575, 0.5600],
[0.6196, 0.4094, 0.7562, 0.2817, 0.3937, 0.3183, 0.6013, 0.6183],
[0.6229, 0.4086, 0.7538, 0.2600, 0.4775, 0.1617, 0.5900, 0.5383]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6275, 0.4265, 0.7716, 0.2781, 0.3984, 0.3497, 0.6382, 0.5523],
[0.5203, 0.3401, 0.8799, 0.4272, 0.3907, 0.4228, 0.5961, 0.5414],
[0.5463, 0.3887, 0.9214, 0.4432, 0.4414, 0.5566, 0.6011, 0.5751],
[0.6827, 0.4398, 0.8401, 0.2632, 0.4333, 0.2702, 0.5930, 0.5047],
[0.6210, 0.4231, 0.8930, 0.4080, 0.3893, 0.3765, 0.5890, 0.5142],
[0.1107, 0.0948, 0.7827, 0.2740, 0.4395, 0.2777, 0.5472, 0.5458],
[0.5985, 0.4182, 0.7871, 0.2891, 0.4246, 0.3038, 0.5919, 0.6043],
[0.6370, 0.4413, 0.7423, 0.2375, 0.4879, 0.1454, 0.5941, 0.5261]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6193, 0.4108, 0.7437, 0.2700, 0.3650, 0.3683, 0.6237, 0.5717],
[0.6111, 0.4019, 0.8350, 0.3867, 0.3500, 0.4283, 0.5480, 0.5719],
[0.6189, 0.4049, 0.8888, 0.4417, 0.4212, 0.5200, 0.5987, 0.5633],
[0.6205, 0.4015, 0.8350, 0.2717, 0.3988, 0.2550, 0.5788, 0.5133],
[0.6201, 0.4036, 0.8596, 0.3850, 0.3492, 0.3785, 0.5978, 0.5131],
[0.0000, 0.0000, 0.8037, 0.2483, 0.3975, 0.2517, 0.5575, 0.5600],
[0.6196, 0.4094, 0.7563, 0.2817, 0.3938, 0.3183, 0.6012, 0.6183],
[0.6229, 0.4086, 0.7538, 0.2600, 0.4775, 0.1617, 0.5900, 0.5383]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06997097912244499
step: 32
running loss: 0.002186593097576406
Train Steps: 32/90 Loss: 0.0022 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6239, 0.4123, 0.8313, 0.2550, 0.4500, 0.2050, 0.6175, 0.5400],
[0.6214, 0.3982, 0.8938, 0.4517, 0.3663, 0.4083, 0.5863, 0.5050],
[0.6189, 0.4033, 0.8650, 0.5267, 0.4487, 0.5150, 0.5925, 0.5050],
[0.6277, 0.4036, 0.8688, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742],
[0.6126, 0.3954, 0.8538, 0.4983, 0.4250, 0.4700, 0.5355, 0.5350],
[0.6202, 0.4054, 0.8892, 0.4428, 0.3642, 0.3249, 0.5840, 0.5426],
[0.6170, 0.4102, 0.7468, 0.3695, 0.3463, 0.3767, 0.5238, 0.5823],
[0.6097, 0.3988, 0.8650, 0.5250, 0.4213, 0.5200, 0.5675, 0.5050]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6632, 0.4778, 0.8182, 0.1933, 0.4617, 0.1867, 0.6462, 0.5282],
[0.5586, 0.3796, 0.8881, 0.3963, 0.3744, 0.3900, 0.5972, 0.5318],
[0.5068, 0.3652, 0.8657, 0.4687, 0.4695, 0.4946, 0.6065, 0.5649],
[0.5647, 0.3709, 0.8731, 0.3147, 0.4259, 0.2559, 0.6572, 0.5229],
[0.5499, 0.3703, 0.8740, 0.4694, 0.4646, 0.4603, 0.5615, 0.5666],
[0.5191, 0.3648, 0.8962, 0.3705, 0.3918, 0.3294, 0.5904, 0.5462],
[0.5249, 0.3715, 0.7566, 0.3213, 0.3711, 0.3640, 0.5613, 0.6067],
[0.5703, 0.3967, 0.8596, 0.4826, 0.4569, 0.4958, 0.5331, 0.5503]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6239, 0.4123, 0.8313, 0.2550, 0.4500, 0.2050, 0.6175, 0.5400],
[0.6214, 0.3982, 0.8938, 0.4517, 0.3663, 0.4083, 0.5863, 0.5050],
[0.6189, 0.4033, 0.8650, 0.5267, 0.4487, 0.5150, 0.5925, 0.5050],
[0.6277, 0.4036, 0.8687, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742],
[0.6126, 0.3954, 0.8537, 0.4983, 0.4250, 0.4700, 0.5355, 0.5350],
[0.6202, 0.4054, 0.8892, 0.4428, 0.3642, 0.3249, 0.5840, 0.5426],
[0.6170, 0.4102, 0.7468, 0.3695, 0.3462, 0.3767, 0.5238, 0.5823],
[0.6097, 0.3988, 0.8650, 0.5250, 0.4212, 0.5200, 0.5675, 0.5050]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0716163640609011
step: 33
running loss: 0.0021701928503303366
Train Steps: 33/90 Loss: 0.0022 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6137, 0.4035, 0.8850, 0.4417, 0.3900, 0.4283, 0.5449, 0.5617],
[0.6258, 0.4143, 0.8525, 0.2617, 0.4950, 0.1667, 0.6219, 0.4967],
[0.6200, 0.4049, 0.8638, 0.5617, 0.4125, 0.5100, 0.6013, 0.5317],
[0.6185, 0.4079, 0.8838, 0.4617, 0.4838, 0.5650, 0.6175, 0.5850],
[0.6223, 0.4130, 0.8100, 0.2983, 0.3525, 0.3900, 0.5694, 0.5103],
[0.6197, 0.4118, 0.8688, 0.5517, 0.4037, 0.5233, 0.5875, 0.5600],
[0.6261, 0.3987, 0.9045, 0.4208, 0.3600, 0.4633, 0.6570, 0.5162],
[0.6279, 0.4008, 0.8600, 0.4883, 0.4325, 0.5283, 0.7010, 0.5378]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5498, 0.3801, 0.8887, 0.4040, 0.3866, 0.3922, 0.5649, 0.5455],
[0.5553, 0.3956, 0.8445, 0.2139, 0.4880, 0.1568, 0.6218, 0.5161],
[0.5328, 0.3725, 0.8469, 0.5384, 0.4104, 0.4539, 0.5756, 0.5725],
[0.6221, 0.4063, 0.8781, 0.4012, 0.4715, 0.5037, 0.6208, 0.5813],
[0.5698, 0.3907, 0.8111, 0.2811, 0.3746, 0.3330, 0.5808, 0.5588],
[0.5970, 0.4106, 0.8380, 0.5187, 0.4095, 0.5040, 0.5817, 0.5924],
[0.6124, 0.4144, 0.8904, 0.4044, 0.3616, 0.4242, 0.6757, 0.5401],
[0.5840, 0.3941, 0.8406, 0.4465, 0.4335, 0.4914, 0.6647, 0.5600]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6137, 0.4035, 0.8850, 0.4417, 0.3900, 0.4283, 0.5449, 0.5617],
[0.6258, 0.4143, 0.8525, 0.2617, 0.4950, 0.1667, 0.6219, 0.4967],
[0.6199, 0.4049, 0.8637, 0.5617, 0.4125, 0.5100, 0.6012, 0.5317],
[0.6184, 0.4079, 0.8838, 0.4617, 0.4837, 0.5650, 0.6175, 0.5850],
[0.6223, 0.4130, 0.8100, 0.2983, 0.3525, 0.3900, 0.5694, 0.5103],
[0.6197, 0.4118, 0.8687, 0.5517, 0.4038, 0.5233, 0.5875, 0.5600],
[0.6261, 0.3987, 0.9045, 0.4208, 0.3600, 0.4633, 0.6570, 0.5162],
[0.6279, 0.4008, 0.8600, 0.4883, 0.4325, 0.5283, 0.7010, 0.5378]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07260472874622792
step: 34
running loss: 0.0021354331984184682
Train Steps: 34/90 Loss: 0.0021 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6245, 0.4100, 0.7762, 0.2583, 0.4963, 0.1517, 0.5875, 0.5417],
[ nan, nan, 0.8213, 0.2700, 0.3775, 0.2817, 0.5425, 0.5533],
[0.6263, 0.4039, 0.9000, 0.4400, 0.3625, 0.4667, 0.6424, 0.4804],
[0.6275, 0.4013, 0.8850, 0.2833, 0.4975, 0.2233, 0.7058, 0.5343],
[0.6126, 0.4039, 0.8237, 0.3967, 0.3625, 0.3600, 0.5894, 0.6138],
[0.6212, 0.4171, 0.7875, 0.3633, 0.3813, 0.2933, 0.5675, 0.5700],
[0.6114, 0.4018, 0.7213, 0.1967, 0.3763, 0.2700, 0.5875, 0.5533],
[0.6179, 0.4008, 0.7505, 0.2678, 0.4368, 0.1891, 0.5831, 0.5263]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5184, 0.3429, 0.7628, 0.2571, 0.4802, 0.1860, 0.6074, 0.5515],
[0.0977, 0.0458, 0.8108, 0.3233, 0.3749, 0.3155, 0.5274, 0.5635],
[0.6940, 0.4294, 0.9553, 0.4917, 0.3541, 0.5029, 0.6596, 0.4610],
[0.5996, 0.3737, 0.8759, 0.3087, 0.5299, 0.2640, 0.7339, 0.5147],
[0.6866, 0.4262, 0.8580, 0.4324, 0.3571, 0.4155, 0.6056, 0.5862],
[0.7120, 0.4739, 0.8066, 0.3997, 0.3782, 0.3399, 0.5830, 0.5756],
[0.6466, 0.4199, 0.7163, 0.2580, 0.3951, 0.2921, 0.5666, 0.5387],
[0.7154, 0.4815, 0.7369, 0.2808, 0.4385, 0.2124, 0.5525, 0.5242]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6245, 0.4100, 0.7763, 0.2583, 0.4963, 0.1517, 0.5875, 0.5417],
[0.0000, 0.0000, 0.8213, 0.2700, 0.3775, 0.2817, 0.5425, 0.5533],
[0.6263, 0.4038, 0.9000, 0.4400, 0.3625, 0.4667, 0.6424, 0.4804],
[0.6275, 0.4013, 0.8850, 0.2833, 0.4975, 0.2233, 0.7058, 0.5343],
[0.6126, 0.4038, 0.8238, 0.3967, 0.3625, 0.3600, 0.5894, 0.6138],
[0.6212, 0.4171, 0.7875, 0.3633, 0.3812, 0.2933, 0.5675, 0.5700],
[0.6114, 0.4018, 0.7212, 0.1967, 0.3762, 0.2700, 0.5875, 0.5533],
[0.6179, 0.4008, 0.7505, 0.2678, 0.4368, 0.1891, 0.5831, 0.5263]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07426053285598755
step: 35
running loss: 0.0021217295101710726
Train Steps: 35/90 Loss: 0.0021 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6274, 0.4003, 0.8638, 0.5967, 0.3688, 0.4900, 0.6108, 0.4661],
[0.6219, 0.3934, 0.8688, 0.5267, 0.4313, 0.4967, 0.5988, 0.4983],
[ nan, nan, 0.8675, 0.2833, 0.5350, 0.1983, 0.6678, 0.5621],
[0.6161, 0.4024, 0.8838, 0.4583, 0.3688, 0.3733, 0.5311, 0.5344],
[0.6130, 0.4072, 0.8550, 0.4567, 0.3638, 0.3667, 0.5290, 0.5892],
[0.6087, 0.3951, 0.8387, 0.5833, 0.4188, 0.4933, 0.5146, 0.4830],
[0.6255, 0.4017, 0.8688, 0.3217, 0.3638, 0.3550, 0.6344, 0.4901],
[0.6248, 0.4185, 0.8500, 0.5767, 0.4463, 0.4550, 0.5613, 0.5917]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6699, 0.4275, 0.8024, 0.5265, 0.3900, 0.4471, 0.6596, 0.5230],
[0.6794, 0.4385, 0.8418, 0.4789, 0.4136, 0.4619, 0.6039, 0.4783],
[0.1114, 0.0595, 0.8397, 0.2376, 0.5027, 0.1908, 0.6890, 0.5289],
[0.6909, 0.4345, 0.8839, 0.4388, 0.3304, 0.3869, 0.5642, 0.5191],
[0.6291, 0.3867, 0.8446, 0.4202, 0.3504, 0.3528, 0.5102, 0.5479],
[0.6586, 0.4093, 0.8303, 0.5168, 0.3792, 0.4555, 0.5674, 0.5253],
[0.7494, 0.4655, 0.8382, 0.2952, 0.3746, 0.3281, 0.6696, 0.5156],
[0.7090, 0.4590, 0.8363, 0.5264, 0.4275, 0.4275, 0.5747, 0.5815]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6274, 0.4003, 0.8637, 0.5967, 0.3688, 0.4900, 0.6108, 0.4661],
[0.6219, 0.3934, 0.8687, 0.5267, 0.4313, 0.4967, 0.5987, 0.4983],
[0.0000, 0.0000, 0.8675, 0.2833, 0.5350, 0.1983, 0.6678, 0.5621],
[0.6161, 0.4024, 0.8838, 0.4583, 0.3688, 0.3733, 0.5311, 0.5344],
[0.6130, 0.4072, 0.8550, 0.4567, 0.3638, 0.3667, 0.5290, 0.5892],
[0.6087, 0.3951, 0.8388, 0.5833, 0.4187, 0.4933, 0.5146, 0.4830],
[0.6255, 0.4017, 0.8687, 0.3217, 0.3638, 0.3550, 0.6344, 0.4901],
[0.6248, 0.4185, 0.8500, 0.5767, 0.4462, 0.4550, 0.5612, 0.5917]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0018, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0018, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07608700543642044
step: 36
running loss: 0.002113527928789457
Train Steps: 36/90 Loss: 0.0021 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6122, 0.4048, 0.7506, 0.3014, 0.3475, 0.3333, 0.5487, 0.5749],
[0.6289, 0.4081, 0.8720, 0.3487, 0.3900, 0.3183, 0.6703, 0.5376],
[0.6124, 0.4030, 0.8650, 0.4867, 0.4999, 0.5106, 0.5137, 0.5773],
[0.6162, 0.4014, 0.8800, 0.5333, 0.3750, 0.4817, 0.5988, 0.5283],
[0.6157, 0.4102, 0.8513, 0.3817, 0.3613, 0.3667, 0.5096, 0.5890],
[0.6257, 0.4034, 0.8287, 0.2333, 0.3925, 0.2717, 0.6330, 0.4901],
[0.6261, 0.4045, 0.8865, 0.5369, 0.3895, 0.4859, 0.6683, 0.5249],
[0.6259, 0.4133, 0.8200, 0.2317, 0.5025, 0.1533, 0.6250, 0.4947]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6112, 0.3707, 0.7490, 0.3077, 0.3605, 0.2968, 0.5415, 0.5408],
[0.5955, 0.3761, 0.8708, 0.3528, 0.3607, 0.2691, 0.6453, 0.5391],
[0.5341, 0.3475, 0.8463, 0.5252, 0.4797, 0.4976, 0.5357, 0.5157],
[0.5937, 0.3833, 0.8467, 0.5804, 0.3934, 0.4725, 0.5941, 0.5159],
[0.5596, 0.3415, 0.8215, 0.3929, 0.3491, 0.3478, 0.5140, 0.5521],
[0.5897, 0.3710, 0.8079, 0.2786, 0.3989, 0.2553, 0.6312, 0.4956],
[0.6347, 0.4102, 0.8645, 0.5367, 0.3555, 0.4859, 0.6540, 0.5185],
[0.5740, 0.3737, 0.8167, 0.2516, 0.4687, 0.1609, 0.6137, 0.5002]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6122, 0.4048, 0.7506, 0.3014, 0.3475, 0.3333, 0.5487, 0.5749],
[0.6289, 0.4081, 0.8720, 0.3487, 0.3900, 0.3183, 0.6703, 0.5376],
[0.6124, 0.4030, 0.8650, 0.4867, 0.4999, 0.5106, 0.5137, 0.5773],
[0.6162, 0.4014, 0.8800, 0.5333, 0.3750, 0.4817, 0.5987, 0.5283],
[0.6157, 0.4102, 0.8512, 0.3817, 0.3613, 0.3667, 0.5096, 0.5890],
[0.6257, 0.4034, 0.8288, 0.2333, 0.3925, 0.2717, 0.6330, 0.4901],
[0.6261, 0.4045, 0.8865, 0.5369, 0.3895, 0.4859, 0.6683, 0.5249],
[0.6259, 0.4132, 0.8200, 0.2317, 0.5025, 0.1533, 0.6250, 0.4947]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07694085594266653
step: 37
running loss: 0.0020794825930450416
Train Steps: 37/90 Loss: 0.0021 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6260, 0.4161, 0.9000, 0.3833, 0.4450, 0.2133, 0.6237, 0.4986],
[0.6111, 0.4033, 0.8300, 0.3267, 0.3588, 0.3333, 0.5444, 0.5637],
[0.6261, 0.4131, 0.8938, 0.3550, 0.4000, 0.2683, 0.6188, 0.5283],
[ nan, nan, 0.7412, 0.2200, 0.4450, 0.1517, 0.5312, 0.4983],
[0.6271, 0.4005, 0.8450, 0.6067, 0.3850, 0.4983, 0.6069, 0.4649],
[0.6129, 0.4114, 0.6950, 0.2467, 0.4050, 0.2133, 0.5363, 0.5550],
[0.6262, 0.4085, 0.8438, 0.3150, 0.4025, 0.2633, 0.6339, 0.4810],
[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.5779, 0.3774, 0.8839, 0.4152, 0.4410, 0.2534, 0.5820, 0.5221],
[ 0.6797, 0.4455, 0.8260, 0.3675, 0.3468, 0.3362, 0.5157, 0.5417],
[ 0.6687, 0.4174, 0.8940, 0.4060, 0.3847, 0.2705, 0.5886, 0.5112],
[-0.0912, -0.0921, 0.6975, 0.2365, 0.4422, 0.1867, 0.5306, 0.5320],
[ 0.6604, 0.4093, 0.8252, 0.6504, 0.3691, 0.5073, 0.6017, 0.4858],
[ 0.6601, 0.4308, 0.6697, 0.2957, 0.3913, 0.2468, 0.5048, 0.5545],
[ 0.7503, 0.4870, 0.8212, 0.3324, 0.4210, 0.2805, 0.6182, 0.4864],
[ 0.6137, 0.3834, 0.8276, 0.2994, 0.4318, 0.2749, 0.6676, 0.5525]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6260, 0.4161, 0.9000, 0.3833, 0.4450, 0.2133, 0.6237, 0.4986],
[0.6111, 0.4033, 0.8300, 0.3267, 0.3587, 0.3333, 0.5444, 0.5637],
[0.6261, 0.4131, 0.8938, 0.3550, 0.4000, 0.2683, 0.6187, 0.5283],
[0.0000, 0.0000, 0.7412, 0.2200, 0.4450, 0.1517, 0.5312, 0.4983],
[0.6271, 0.4005, 0.8450, 0.6067, 0.3850, 0.4983, 0.6069, 0.4649],
[0.6129, 0.4114, 0.6950, 0.2467, 0.4050, 0.2133, 0.5362, 0.5550],
[0.6262, 0.4085, 0.8438, 0.3150, 0.4025, 0.2633, 0.6339, 0.4810],
[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07825841219164431
step: 38
running loss: 0.0020594318997801133
Train Steps: 38/90 Loss: 0.0021 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6086, 0.3940, 0.8712, 0.4783, 0.4025, 0.4900, 0.5498, 0.5390],
[0.6136, 0.4060, 0.8025, 0.3217, 0.3650, 0.3000, 0.5060, 0.5646],
[0.6202, 0.3983, 0.8555, 0.5429, 0.3842, 0.4370, 0.5866, 0.5398],
[0.6275, 0.4050, 0.9038, 0.3767, 0.3838, 0.3533, 0.7074, 0.5575],
[0.6289, 0.4019, 0.8113, 0.5467, 0.3875, 0.5017, 0.7367, 0.5332],
[0.6364, 0.4165, 0.9088, 0.4367, 0.4075, 0.3150, 0.6448, 0.5297],
[0.6185, 0.4079, 0.8838, 0.4617, 0.4838, 0.5650, 0.6175, 0.5850],
[0.6140, 0.4070, 0.8700, 0.5000, 0.4612, 0.4900, 0.5260, 0.5852]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5947, 0.3805, 0.8456, 0.4897, 0.4121, 0.4539, 0.5597, 0.4984],
[0.3858, 0.2530, 0.7886, 0.3215, 0.3442, 0.2716, 0.4741, 0.5347],
[0.5989, 0.3812, 0.8558, 0.5530, 0.3637, 0.4137, 0.6011, 0.5037],
[0.6297, 0.4055, 0.8894, 0.3635, 0.3809, 0.3036, 0.6904, 0.5203],
[0.6403, 0.4136, 0.8121, 0.4900, 0.3675, 0.4450, 0.6480, 0.5108],
[0.5778, 0.3763, 0.8999, 0.4514, 0.4168, 0.2672, 0.6207, 0.5142],
[0.6699, 0.4190, 0.8753, 0.4437, 0.4606, 0.5210, 0.6239, 0.5325],
[0.5892, 0.3982, 0.8542, 0.4954, 0.4509, 0.4645, 0.5348, 0.5564]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6086, 0.3940, 0.8712, 0.4783, 0.4025, 0.4900, 0.5498, 0.5390],
[0.6136, 0.4060, 0.8025, 0.3217, 0.3650, 0.3000, 0.5060, 0.5646],
[0.6202, 0.3983, 0.8555, 0.5429, 0.3842, 0.4370, 0.5866, 0.5398],
[0.6275, 0.4050, 0.9038, 0.3767, 0.3837, 0.3533, 0.7074, 0.5575],
[0.6289, 0.4019, 0.8112, 0.5467, 0.3875, 0.5017, 0.7367, 0.5332],
[0.6364, 0.4165, 0.9087, 0.4367, 0.4075, 0.3150, 0.6448, 0.5297],
[0.6184, 0.4079, 0.8838, 0.4617, 0.4837, 0.5650, 0.6175, 0.5850],
[0.6140, 0.4070, 0.8700, 0.5000, 0.4613, 0.4900, 0.5260, 0.5852]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0020, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0020, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.08022535732015967
step: 39
running loss: 0.0020570604441066584
Train Steps: 39/90 Loss: 0.0021 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6277, 0.4118, 0.8988, 0.3833, 0.3950, 0.2650, 0.6290, 0.4938],
[0.6264, 0.4035, 0.8888, 0.4883, 0.4050, 0.5217, 0.6361, 0.4791],
[ nan, nan, 0.7981, 0.3194, 0.3625, 0.3167, 0.5040, 0.5563],
[0.6159, 0.4085, 0.6900, 0.2283, 0.4088, 0.1950, 0.5123, 0.5397],
[0.6086, 0.3981, 0.8700, 0.4750, 0.4512, 0.5283, 0.5324, 0.5038],
[0.6080, 0.4010, 0.8750, 0.4500, 0.4825, 0.5617, 0.5837, 0.5583],
[0.6143, 0.4040, 0.8237, 0.3333, 0.4075, 0.2117, 0.5137, 0.4973],
[0.6143, 0.4034, 0.8800, 0.4833, 0.4512, 0.5367, 0.5289, 0.5097]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6195, 0.4118, 0.9066, 0.4095, 0.3811, 0.2271, 0.6301, 0.5351],
[ 0.6931, 0.4617, 0.8825, 0.5103, 0.3938, 0.5106, 0.6760, 0.4836],
[-0.0069, -0.0022, 0.7917, 0.3328, 0.3496, 0.2844, 0.5340, 0.5845],
[ 0.5912, 0.3992, 0.6751, 0.2480, 0.3963, 0.1762, 0.5067, 0.5832],
[ 0.6294, 0.4174, 0.8644, 0.5082, 0.4266, 0.4852, 0.5873, 0.5055],
[ 0.7166, 0.4977, 0.8992, 0.4628, 0.4537, 0.5101, 0.6015, 0.5534],
[ 0.4912, 0.3237, 0.8256, 0.3268, 0.4155, 0.2062, 0.5291, 0.5372],
[ 0.7153, 0.4560, 0.8673, 0.5064, 0.4377, 0.4808, 0.5551, 0.5160]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6277, 0.4117, 0.8988, 0.3833, 0.3950, 0.2650, 0.6290, 0.4938],
[0.6264, 0.4035, 0.8888, 0.4883, 0.4050, 0.5217, 0.6361, 0.4791],
[0.0000, 0.0000, 0.7981, 0.3194, 0.3625, 0.3167, 0.5040, 0.5563],
[0.6159, 0.4085, 0.6900, 0.2283, 0.4087, 0.1950, 0.5123, 0.5397],
[0.6086, 0.3981, 0.8700, 0.4750, 0.4512, 0.5283, 0.5324, 0.5038],
[0.6080, 0.4010, 0.8750, 0.4500, 0.4825, 0.5617, 0.5838, 0.5583],
[0.6143, 0.4040, 0.8238, 0.3333, 0.4075, 0.2117, 0.5137, 0.4973],
[0.6143, 0.4034, 0.8800, 0.4833, 0.4512, 0.5367, 0.5289, 0.5097]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.08172035915777087
step: 40
running loss: 0.002043008978944272
Train Steps: 40/90 Loss: 0.0020 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6229, 0.4107, 0.8137, 0.2883, 0.4750, 0.1717, 0.5813, 0.5400],
[0.6080, 0.4010, 0.8750, 0.4500, 0.4825, 0.5617, 0.5837, 0.5583],
[0.6200, 0.4098, 0.8237, 0.2917, 0.4012, 0.2967, 0.6000, 0.5683],
[0.6125, 0.4010, 0.8650, 0.4567, 0.3663, 0.3900, 0.5600, 0.5567],
[0.6274, 0.4003, 0.8638, 0.5967, 0.3688, 0.4900, 0.6108, 0.4661],
[0.6125, 0.3974, 0.7725, 0.2517, 0.3538, 0.3317, 0.5887, 0.5500],
[0.6031, 0.3986, 0.7462, 0.2833, 0.3638, 0.2717, 0.5253, 0.4726],
[0.6199, 0.4112, 0.8475, 0.3717, 0.3550, 0.4350, 0.6063, 0.6083]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5758, 0.3786, 0.8423, 0.3171, 0.4899, 0.2170, 0.5905, 0.5425],
[0.5740, 0.3879, 0.9308, 0.4643, 0.4837, 0.5307, 0.5876, 0.5373],
[0.6391, 0.4176, 0.8629, 0.3083, 0.4227, 0.3055, 0.6264, 0.5473],
[0.5625, 0.3663, 0.8680, 0.4720, 0.3909, 0.4157, 0.5760, 0.5533],
[0.5354, 0.3332, 0.8488, 0.6208, 0.4072, 0.4879, 0.6330, 0.5155],
[0.5616, 0.3440, 0.7892, 0.2749, 0.3800, 0.3443, 0.5898, 0.5582],
[0.6584, 0.4165, 0.7801, 0.2906, 0.4001, 0.2840, 0.5664, 0.5037],
[0.5920, 0.4034, 0.8760, 0.4120, 0.3817, 0.4544, 0.5925, 0.5546]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6229, 0.4107, 0.8138, 0.2883, 0.4750, 0.1717, 0.5813, 0.5400],
[0.6080, 0.4010, 0.8750, 0.4500, 0.4825, 0.5617, 0.5838, 0.5583],
[0.6200, 0.4098, 0.8238, 0.2917, 0.4013, 0.2967, 0.6000, 0.5683],
[0.6125, 0.4010, 0.8650, 0.4567, 0.3663, 0.3900, 0.5600, 0.5567],
[0.6274, 0.4003, 0.8637, 0.5967, 0.3688, 0.4900, 0.6108, 0.4661],
[0.6125, 0.3974, 0.7725, 0.2517, 0.3537, 0.3317, 0.5888, 0.5500],
[0.6031, 0.3986, 0.7462, 0.2833, 0.3638, 0.2717, 0.5253, 0.4726],
[0.6199, 0.4112, 0.8475, 0.3717, 0.3550, 0.4350, 0.6062, 0.6083]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.08272404491435736
step: 41
running loss: 0.002017659632057497
Train Steps: 41/90 Loss: 0.0020 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6084, 0.3981, 0.8588, 0.5233, 0.4600, 0.5367, 0.5680, 0.5006],
[0.6200, 0.4039, 0.8880, 0.4799, 0.3625, 0.4285, 0.5866, 0.5148],
[0.6179, 0.4008, 0.8600, 0.4015, 0.3932, 0.2515, 0.5711, 0.5438],
[0.6093, 0.3990, 0.8400, 0.4333, 0.3688, 0.4633, 0.5560, 0.5656],
[0.6239, 0.4174, 0.8425, 0.5733, 0.4825, 0.4500, 0.5625, 0.5933],
[0.6182, 0.3967, 0.8263, 0.3065, 0.3526, 0.4161, 0.6192, 0.5290],
[0.6275, 0.4157, 0.8337, 0.5800, 0.3763, 0.4200, 0.5547, 0.6125],
[0.6180, 0.4064, 0.7200, 0.2467, 0.4275, 0.2367, 0.5963, 0.6217]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5543, 0.3742, 0.8943, 0.5196, 0.4794, 0.5638, 0.5621, 0.4876],
[0.6037, 0.3794, 0.9385, 0.4418, 0.4021, 0.4450, 0.5992, 0.5035],
[0.6467, 0.4319, 0.8756, 0.3346, 0.4146, 0.2846, 0.5714, 0.5388],
[0.5918, 0.3820, 0.8937, 0.4119, 0.3816, 0.4555, 0.5682, 0.5513],
[0.6275, 0.4428, 0.8985, 0.5641, 0.4904, 0.4356, 0.6108, 0.5810],
[0.5539, 0.3666, 0.8488, 0.2932, 0.3606, 0.4177, 0.6532, 0.5217],
[0.6402, 0.4327, 0.8611, 0.5682, 0.3874, 0.4667, 0.5907, 0.5768],
[0.5660, 0.3770, 0.7327, 0.2319, 0.4440, 0.2731, 0.5796, 0.6056]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6084, 0.3981, 0.8587, 0.5233, 0.4600, 0.5367, 0.5680, 0.5006],
[0.6201, 0.4039, 0.8880, 0.4799, 0.3625, 0.4285, 0.5866, 0.5148],
[0.6179, 0.4008, 0.8600, 0.4015, 0.3932, 0.2515, 0.5711, 0.5438],
[0.6093, 0.3990, 0.8400, 0.4333, 0.3688, 0.4633, 0.5560, 0.5656],
[0.6239, 0.4174, 0.8425, 0.5733, 0.4825, 0.4500, 0.5625, 0.5933],
[0.6182, 0.3967, 0.8263, 0.3065, 0.3526, 0.4161, 0.6192, 0.5290],
[0.6275, 0.4157, 0.8338, 0.5800, 0.3762, 0.4200, 0.5547, 0.6125],
[0.6180, 0.4064, 0.7200, 0.2467, 0.4275, 0.2367, 0.5962, 0.6217]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.08353073458420113
step: 42
running loss: 0.0019888270139095505
Train Steps: 42/90 Loss: 0.0020 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6137, 0.4038, 0.8563, 0.4050, 0.3813, 0.2550, 0.5106, 0.4954],
[0.6199, 0.4060, 0.8888, 0.4667, 0.3800, 0.5050, 0.6188, 0.5433],
[0.6102, 0.4001, 0.7738, 0.3583, 0.3463, 0.3800, 0.5524, 0.5689],
[0.6186, 0.3967, 0.7337, 0.1992, 0.4120, 0.2508, 0.6105, 0.5395],
[0.6293, 0.3982, 0.8700, 0.5300, 0.3763, 0.4717, 0.7050, 0.5297],
[0.6204, 0.4110, 0.7913, 0.2667, 0.4062, 0.2500, 0.6225, 0.5367],
[0.6129, 0.3925, 0.8720, 0.5246, 0.4534, 0.5515, 0.6026, 0.5114],
[0.6263, 0.4065, 0.9038, 0.4317, 0.3588, 0.4550, 0.6325, 0.5250]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6746, 0.4319, 0.8910, 0.3957, 0.4231, 0.3041, 0.4968, 0.5360],
[0.6110, 0.4048, 0.9118, 0.4690, 0.4132, 0.5844, 0.6055, 0.5478],
[0.5277, 0.3620, 0.8001, 0.3551, 0.3683, 0.4127, 0.5339, 0.5777],
[0.6432, 0.4046, 0.7831, 0.2371, 0.4205, 0.2584, 0.5683, 0.5560],
[0.5422, 0.3705, 0.8758, 0.5354, 0.3853, 0.5174, 0.6447, 0.5465],
[0.6417, 0.4331, 0.8154, 0.2463, 0.4465, 0.2785, 0.5989, 0.5654],
[0.5830, 0.4069, 0.8817, 0.5367, 0.4828, 0.5881, 0.5900, 0.5317],
[0.6231, 0.4210, 0.9309, 0.4411, 0.3923, 0.4972, 0.6554, 0.5362]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6137, 0.4038, 0.8562, 0.4050, 0.3812, 0.2550, 0.5106, 0.4954],
[0.6199, 0.4060, 0.8888, 0.4667, 0.3800, 0.5050, 0.6187, 0.5433],
[0.6102, 0.4001, 0.7738, 0.3583, 0.3462, 0.3800, 0.5524, 0.5689],
[0.6186, 0.3967, 0.7337, 0.1992, 0.4120, 0.2508, 0.6105, 0.5395],
[0.6293, 0.3982, 0.8700, 0.5300, 0.3762, 0.4717, 0.7050, 0.5297],
[0.6204, 0.4110, 0.7912, 0.2667, 0.4062, 0.2500, 0.6225, 0.5367],
[0.6129, 0.3925, 0.8720, 0.5246, 0.4534, 0.5515, 0.6026, 0.5114],
[0.6263, 0.4065, 0.9038, 0.4317, 0.3587, 0.4550, 0.6325, 0.5250]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.08457283378811553
step: 43
running loss: 0.0019668100880957102
Train Steps: 43/90 Loss: 0.0020 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6132, 0.4118, 0.8200, 0.3633, 0.3563, 0.5400, 0.5787, 0.5136],
[0.6272, 0.4045, 0.8538, 0.5900, 0.3750, 0.4417, 0.5989, 0.4649],
[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.6246, 0.4008, 0.8757, 0.5088, 0.4101, 0.5392, 0.6644, 0.5133],
[0.6198, 0.4105, 0.7950, 0.3267, 0.3675, 0.3767, 0.6038, 0.6167],
[0.6203, 0.4072, 0.8892, 0.3523, 0.3783, 0.3017, 0.5898, 0.5478],
[0.6200, 0.4112, 0.8862, 0.4100, 0.3638, 0.4917, 0.6088, 0.6050],
[0.6201, 0.4151, 0.8588, 0.5467, 0.3700, 0.3950, 0.5637, 0.5933]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5829, 0.3921, 0.8264, 0.3159, 0.3731, 0.5240, 0.5861, 0.5414],
[0.6574, 0.4408, 0.8602, 0.5335, 0.3847, 0.4092, 0.5730, 0.5130],
[0.6363, 0.4418, 0.8349, 0.5432, 0.3740, 0.5134, 0.6518, 0.5425],
[0.5697, 0.3814, 0.8596, 0.4887, 0.4200, 0.5548, 0.6287, 0.5410],
[0.6425, 0.4493, 0.8188, 0.2990, 0.3808, 0.4217, 0.5833, 0.5963],
[0.6742, 0.4422, 0.8950, 0.3099, 0.3901, 0.3213, 0.6032, 0.5729],
[0.6124, 0.4264, 0.8670, 0.3953, 0.3919, 0.5078, 0.5886, 0.5685],
[0.5960, 0.4155, 0.8576, 0.5290, 0.3820, 0.4110, 0.5455, 0.5905]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6132, 0.4118, 0.8200, 0.3633, 0.3562, 0.5400, 0.5787, 0.5136],
[0.6271, 0.4045, 0.8537, 0.5900, 0.3750, 0.4417, 0.5989, 0.4649],
[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.6246, 0.4008, 0.8757, 0.5088, 0.4101, 0.5392, 0.6644, 0.5133],
[0.6198, 0.4105, 0.7950, 0.3267, 0.3675, 0.3767, 0.6037, 0.6167],
[0.6203, 0.4072, 0.8892, 0.3523, 0.3783, 0.3017, 0.5898, 0.5478],
[0.6200, 0.4112, 0.8863, 0.4100, 0.3638, 0.4917, 0.6087, 0.6050],
[0.6202, 0.4151, 0.8587, 0.5467, 0.3700, 0.3950, 0.5638, 0.5933]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.08523785881698132
step: 44
running loss: 0.0019372240640223026
Train Steps: 44/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6133, 0.4066, 0.6787, 0.2617, 0.3800, 0.2433, 0.5147, 0.5358],
[0.6239, 0.4061, 0.8850, 0.4600, 0.4225, 0.5200, 0.6138, 0.5450],
[0.6182, 0.3998, 0.8793, 0.4191, 0.3552, 0.4285, 0.6038, 0.5312],
[0.6125, 0.3974, 0.7725, 0.2517, 0.3538, 0.3317, 0.5887, 0.5500],
[0.6267, 0.4065, 0.8313, 0.2467, 0.4788, 0.1733, 0.6312, 0.5133],
[0.6124, 0.4075, 0.7696, 0.4153, 0.3475, 0.3767, 0.5157, 0.5427],
[0.6307, 0.3998, 0.8500, 0.5233, 0.3850, 0.5050, 0.7446, 0.5320],
[0.6058, 0.3978, 0.8287, 0.3600, 0.3400, 0.4050, 0.5529, 0.5461]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5574, 0.3708, 0.7304, 0.2770, 0.3952, 0.2549, 0.5315, 0.5325],
[0.5851, 0.4072, 0.8954, 0.4923, 0.4134, 0.6094, 0.6331, 0.5524],
[0.7421, 0.4717, 0.8658, 0.4165, 0.3477, 0.4763, 0.6099, 0.5323],
[0.6102, 0.3866, 0.7828, 0.2630, 0.3653, 0.3681, 0.5750, 0.5749],
[0.6527, 0.4293, 0.8477, 0.2623, 0.4776, 0.2003, 0.6449, 0.5496],
[0.7032, 0.4611, 0.8211, 0.4001, 0.3383, 0.4056, 0.5390, 0.5727],
[0.6002, 0.3951, 0.8682, 0.5551, 0.3725, 0.5488, 0.6113, 0.5342],
[0.5485, 0.3695, 0.8289, 0.3966, 0.3556, 0.4300, 0.5648, 0.5475]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6133, 0.4065, 0.6787, 0.2617, 0.3800, 0.2433, 0.5147, 0.5358],
[0.6239, 0.4061, 0.8850, 0.4600, 0.4225, 0.5200, 0.6137, 0.5450],
[0.6182, 0.3998, 0.8793, 0.4191, 0.3552, 0.4285, 0.6038, 0.5312],
[0.6125, 0.3974, 0.7725, 0.2517, 0.3537, 0.3317, 0.5888, 0.5500],
[0.6266, 0.4065, 0.8313, 0.2467, 0.4787, 0.1733, 0.6313, 0.5133],
[0.6124, 0.4075, 0.7696, 0.4153, 0.3475, 0.3767, 0.5157, 0.5427],
[0.6307, 0.3998, 0.8500, 0.5233, 0.3850, 0.5050, 0.7446, 0.5320],
[0.6058, 0.3978, 0.8288, 0.3600, 0.3400, 0.4050, 0.5529, 0.5461]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.08670229942072183
step: 45
running loss: 0.0019267177649049294
Train Steps: 45/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6222, 0.4172, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633],
[0.6265, 0.4071, 0.8875, 0.3367, 0.3975, 0.3350, 0.6312, 0.5250],
[0.6100, 0.4016, 0.8600, 0.5067, 0.4612, 0.5233, 0.5086, 0.5519],
[0.6150, 0.3935, 0.8696, 0.5158, 0.4647, 0.5329, 0.6041, 0.5153],
[0.6250, 0.4103, 0.8950, 0.4400, 0.3912, 0.5650, 0.6050, 0.5133],
[ nan, nan, 0.7412, 0.2200, 0.4450, 0.1517, 0.5312, 0.4983],
[0.6169, 0.4108, 0.6821, 0.2722, 0.3825, 0.2550, 0.5550, 0.5717],
[0.6236, 0.4081, 0.8575, 0.3000, 0.3713, 0.3033, 0.5550, 0.5633]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6801, 0.4410, 0.8683, 0.5659, 0.3392, 0.4688, 0.5803, 0.5495],
[0.6600, 0.4212, 0.8819, 0.3557, 0.3762, 0.3373, 0.6782, 0.5341],
[0.6769, 0.4397, 0.8591, 0.5386, 0.4188, 0.5211, 0.5393, 0.5377],
[0.6893, 0.4491, 0.8465, 0.5392, 0.4218, 0.5473, 0.6143, 0.5291],
[0.7045, 0.4556, 0.8790, 0.4567, 0.3647, 0.5870, 0.6346, 0.5346],
[0.2349, 0.1266, 0.7190, 0.2019, 0.4143, 0.1636, 0.5454, 0.5321],
[0.6809, 0.4381, 0.6721, 0.2559, 0.3333, 0.2282, 0.5364, 0.5570],
[0.6265, 0.4215, 0.8322, 0.3383, 0.3416, 0.3138, 0.5845, 0.5514]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6222, 0.4171, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633],
[0.6265, 0.4071, 0.8875, 0.3367, 0.3975, 0.3350, 0.6313, 0.5250],
[0.6100, 0.4016, 0.8600, 0.5067, 0.4613, 0.5233, 0.5086, 0.5519],
[0.6150, 0.3935, 0.8696, 0.5158, 0.4647, 0.5329, 0.6041, 0.5153],
[0.6250, 0.4103, 0.8950, 0.4400, 0.3913, 0.5650, 0.6050, 0.5133],
[0.0000, 0.0000, 0.7412, 0.2200, 0.4450, 0.1517, 0.5312, 0.4983],
[0.6169, 0.4108, 0.6821, 0.2722, 0.3825, 0.2550, 0.5550, 0.5717],
[0.6236, 0.4081, 0.8575, 0.3000, 0.3713, 0.3033, 0.5550, 0.5633]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0021, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0021, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.08878360188100487
step: 46
running loss: 0.0019300783017609754
Train Steps: 46/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6276, 0.4235, 0.8888, 0.5333, 0.3800, 0.3117, 0.5427, 0.6164],
[0.6307, 0.4045, 0.8025, 0.5833, 0.3775, 0.4867, 0.6892, 0.5459],
[ nan, nan, 0.6793, 0.2110, 0.4012, 0.2167, 0.5112, 0.5583],
[0.6132, 0.4118, 0.8200, 0.3633, 0.3563, 0.5400, 0.5787, 0.5136],
[0.6164, 0.3972, 0.7818, 0.3381, 0.3599, 0.3387, 0.5880, 0.5153],
[0.6164, 0.4119, 0.7913, 0.2650, 0.3538, 0.3500, 0.5614, 0.5038],
[0.6082, 0.4042, 0.6975, 0.1917, 0.4100, 0.1983, 0.5502, 0.5578],
[0.6277, 0.4083, 0.8350, 0.2717, 0.4562, 0.1800, 0.5918, 0.4878]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7055, 0.4578, 0.8519, 0.5879, 0.3761, 0.3916, 0.5511, 0.5944],
[0.7292, 0.4616, 0.8460, 0.5709, 0.3622, 0.4798, 0.6770, 0.4983],
[0.0664, 0.0312, 0.7004, 0.2303, 0.4082, 0.1988, 0.5215, 0.5506],
[0.6563, 0.4132, 0.8240, 0.3713, 0.3363, 0.5313, 0.5989, 0.5189],
[0.6488, 0.4153, 0.8015, 0.3351, 0.3190, 0.3517, 0.6047, 0.5187],
[0.7151, 0.4625, 0.7876, 0.2750, 0.3320, 0.3584, 0.5924, 0.4999],
[0.6842, 0.4461, 0.6953, 0.2469, 0.3832, 0.1930, 0.5175, 0.5420],
[0.6422, 0.3944, 0.8310, 0.2808, 0.4452, 0.2402, 0.5940, 0.5098]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6276, 0.4235, 0.8888, 0.5333, 0.3800, 0.3117, 0.5427, 0.6164],
[0.6307, 0.4045, 0.8025, 0.5833, 0.3775, 0.4867, 0.6892, 0.5459],
[0.0000, 0.0000, 0.6793, 0.2110, 0.4013, 0.2167, 0.5113, 0.5583],
[0.6132, 0.4118, 0.8200, 0.3633, 0.3562, 0.5400, 0.5787, 0.5136],
[0.6164, 0.3972, 0.7818, 0.3381, 0.3599, 0.3387, 0.5880, 0.5153],
[0.6164, 0.4119, 0.7912, 0.2650, 0.3537, 0.3500, 0.5614, 0.5038],
[0.6082, 0.4042, 0.6975, 0.1917, 0.4100, 0.1983, 0.5502, 0.5578],
[0.6277, 0.4083, 0.8350, 0.2717, 0.4563, 0.1800, 0.5918, 0.4878]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.09005057823378593
step: 47
running loss: 0.0019159697496550197
Train Steps: 47/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6204, 0.4013, 0.8075, 0.2400, 0.4313, 0.2050, 0.5800, 0.5150],
[0.6185, 0.4129, 0.8900, 0.4567, 0.3937, 0.5417, 0.5734, 0.5110],
[0.6136, 0.4029, 0.8263, 0.3350, 0.3625, 0.3067, 0.5675, 0.5167],
[0.6204, 0.4055, 0.8438, 0.5733, 0.4574, 0.4801, 0.5487, 0.5617],
[0.6264, 0.4035, 0.8888, 0.4883, 0.4050, 0.5217, 0.6361, 0.4791],
[0.6264, 0.4248, 0.8938, 0.4183, 0.3875, 0.4100, 0.5400, 0.5350],
[0.6078, 0.4033, 0.8019, 0.3055, 0.3450, 0.4200, 0.6025, 0.5550],
[0.6113, 0.4088, 0.6859, 0.2208, 0.4363, 0.1700, 0.5188, 0.5533]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6486, 0.4020, 0.7514, 0.2730, 0.4087, 0.2175, 0.5757, 0.5366],
[0.6411, 0.4125, 0.8790, 0.4814, 0.3593, 0.5086, 0.5643, 0.5240],
[0.6816, 0.4637, 0.7844, 0.3338, 0.3328, 0.2747, 0.5542, 0.5338],
[0.6323, 0.3974, 0.7978, 0.5710, 0.4151, 0.4028, 0.5774, 0.5467],
[0.5792, 0.3522, 0.8565, 0.4896, 0.3740, 0.4974, 0.6258, 0.4819],
[0.6051, 0.3964, 0.8591, 0.4106, 0.3487, 0.3718, 0.5399, 0.5469],
[0.5822, 0.3830, 0.7570, 0.2944, 0.3506, 0.4014, 0.6029, 0.5421],
[0.3315, 0.2145, 0.6800, 0.2316, 0.4172, 0.1543, 0.5413, 0.5392]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6204, 0.4013, 0.8075, 0.2400, 0.4313, 0.2050, 0.5800, 0.5150],
[0.6186, 0.4129, 0.8900, 0.4567, 0.3938, 0.5417, 0.5734, 0.5110],
[0.6136, 0.4029, 0.8263, 0.3350, 0.3625, 0.3067, 0.5675, 0.5167],
[0.6204, 0.4055, 0.8438, 0.5733, 0.4574, 0.4801, 0.5487, 0.5617],
[0.6264, 0.4035, 0.8888, 0.4883, 0.4050, 0.5217, 0.6361, 0.4791],
[0.6264, 0.4248, 0.8938, 0.4183, 0.3875, 0.4100, 0.5400, 0.5350],
[0.6078, 0.4033, 0.8019, 0.3055, 0.3450, 0.4200, 0.6025, 0.5550],
[0.6113, 0.4088, 0.6859, 0.2208, 0.4363, 0.1700, 0.5188, 0.5533]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0026, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0026, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.09267542359884828
step: 48
running loss: 0.0019307379916426726
Train Steps: 48/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466],
[0.6143, 0.4040, 0.8237, 0.3333, 0.4075, 0.2117, 0.5137, 0.4973],
[0.6198, 0.4164, 0.8700, 0.5067, 0.4625, 0.5650, 0.5464, 0.5197],
[0.6339, 0.4102, 0.9088, 0.4767, 0.3925, 0.5283, 0.7509, 0.5390],
[0.6030, 0.3969, 0.7988, 0.3917, 0.3450, 0.3667, 0.5266, 0.4700],
[0.6192, 0.4128, 0.8513, 0.5617, 0.4200, 0.5267, 0.5850, 0.5633],
[0.6175, 0.3997, 0.6737, 0.2500, 0.4313, 0.1933, 0.5513, 0.5750],
[0.6308, 0.3990, 0.8688, 0.5183, 0.3950, 0.4983, 0.6388, 0.5133]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6052, 0.3889, 0.7422, 0.3402, 0.3384, 0.3641, 0.5236, 0.5260],
[0.6399, 0.4004, 0.7969, 0.3118, 0.4094, 0.1803, 0.5158, 0.5109],
[0.5728, 0.3562, 0.8510, 0.4912, 0.4429, 0.4912, 0.5814, 0.5052],
[0.5621, 0.3503, 0.8764, 0.4556, 0.4044, 0.5215, 0.6876, 0.5352],
[0.6308, 0.4028, 0.8012, 0.3729, 0.3408, 0.3155, 0.5477, 0.5014],
[0.6521, 0.4160, 0.8504, 0.5561, 0.4178, 0.4928, 0.5914, 0.5374],
[0.5205, 0.3282, 0.6716, 0.2172, 0.4256, 0.1459, 0.5180, 0.5464],
[0.6104, 0.3535, 0.8501, 0.5325, 0.3972, 0.4680, 0.6415, 0.4927]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466],
[0.6143, 0.4040, 0.8238, 0.3333, 0.4075, 0.2117, 0.5137, 0.4973],
[0.6198, 0.4164, 0.8700, 0.5067, 0.4625, 0.5650, 0.5464, 0.5197],
[0.6339, 0.4102, 0.9087, 0.4767, 0.3925, 0.5283, 0.7509, 0.5390],
[0.6030, 0.3969, 0.7987, 0.3917, 0.3450, 0.3667, 0.5266, 0.4700],
[0.6192, 0.4128, 0.8512, 0.5617, 0.4200, 0.5267, 0.5850, 0.5633],
[0.6175, 0.3997, 0.6737, 0.2500, 0.4313, 0.1933, 0.5512, 0.5750],
[0.6308, 0.3990, 0.8687, 0.5183, 0.3950, 0.4983, 0.6388, 0.5133]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.09376236831303686
step: 49
running loss: 0.0019135177206742217
Train Steps: 49/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6147, 0.4112, 0.7988, 0.3200, 0.3775, 0.2767, 0.5150, 0.5550],
[0.6265, 0.4088, 0.8025, 0.1850, 0.4163, 0.2500, 0.6290, 0.4947],
[0.6068, 0.3963, 0.8650, 0.4317, 0.4037, 0.5083, 0.5253, 0.4999],
[0.6269, 0.4073, 0.8900, 0.4933, 0.3625, 0.4183, 0.6288, 0.5150],
[0.6329, 0.4055, 0.9050, 0.4783, 0.3613, 0.3917, 0.6464, 0.5019],
[0.6339, 0.4112, 0.8838, 0.5067, 0.4000, 0.5433, 0.7549, 0.5378],
[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466],
[0.6199, 0.4102, 0.8950, 0.4417, 0.4012, 0.5367, 0.6112, 0.5967]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6403, 0.4320, 0.7649, 0.3199, 0.3983, 0.2335, 0.4917, 0.5320],
[0.5692, 0.3730, 0.7705, 0.2126, 0.4442, 0.1903, 0.5995, 0.5071],
[0.5403, 0.3438, 0.8224, 0.4247, 0.4037, 0.4621, 0.5542, 0.4882],
[0.5514, 0.3663, 0.8637, 0.4957, 0.3862, 0.3813, 0.6040, 0.5017],
[0.6259, 0.3877, 0.8745, 0.4758, 0.3988, 0.3611, 0.6208, 0.5046],
[0.5511, 0.3389, 0.8570, 0.5071, 0.4225, 0.5230, 0.6351, 0.5395],
[0.5870, 0.3975, 0.7331, 0.3451, 0.3606, 0.3595, 0.5102, 0.5234],
[0.6117, 0.3787, 0.8476, 0.4176, 0.4175, 0.4941, 0.5977, 0.5509]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6147, 0.4112, 0.7987, 0.3200, 0.3775, 0.2767, 0.5150, 0.5550],
[0.6265, 0.4088, 0.8025, 0.1850, 0.4162, 0.2500, 0.6290, 0.4947],
[0.6068, 0.3963, 0.8650, 0.4317, 0.4038, 0.5083, 0.5253, 0.4999],
[0.6269, 0.4073, 0.8900, 0.4933, 0.3625, 0.4183, 0.6288, 0.5150],
[0.6329, 0.4055, 0.9050, 0.4783, 0.3613, 0.3917, 0.6464, 0.5019],
[0.6339, 0.4112, 0.8838, 0.5067, 0.4000, 0.5433, 0.7549, 0.5378],
[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466],
[0.6199, 0.4102, 0.8950, 0.4417, 0.4013, 0.5367, 0.6112, 0.5967]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.09513336268719286
step: 50
running loss: 0.0019026672537438571
Train Steps: 50/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6142, 0.4127, 0.7575, 0.3067, 0.3438, 0.4383, 0.5778, 0.5207],
[0.6198, 0.4101, 0.8838, 0.5283, 0.3763, 0.5267, 0.5913, 0.5567],
[0.6264, 0.4248, 0.8938, 0.4183, 0.3875, 0.4100, 0.5400, 0.5350],
[0.6286, 0.4034, 0.8191, 0.2414, 0.4262, 0.2393, 0.6365, 0.5356],
[0.6339, 0.4118, 0.7988, 0.5800, 0.3912, 0.4583, 0.7343, 0.5760],
[0.6286, 0.4097, 0.8107, 0.2414, 0.4425, 0.2483, 0.6745, 0.5385],
[0.6102, 0.3999, 0.8750, 0.5133, 0.3825, 0.4750, 0.5637, 0.5083],
[0.6293, 0.4097, 0.8800, 0.2517, 0.5262, 0.2600, 0.7430, 0.5378]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5291, 0.3672, 0.7294, 0.2730, 0.3650, 0.3765, 0.5397, 0.5277],
[0.5886, 0.3764, 0.8469, 0.5366, 0.3838, 0.5122, 0.5506, 0.5424],
[0.5200, 0.3578, 0.8842, 0.4014, 0.3746, 0.3781, 0.5141, 0.5359],
[0.5578, 0.3773, 0.7889, 0.2673, 0.4389, 0.2098, 0.5802, 0.5160],
[0.5594, 0.3759, 0.8057, 0.5207, 0.3739, 0.4169, 0.6299, 0.5353],
[0.6054, 0.4064, 0.7891, 0.2735, 0.4530, 0.2321, 0.6273, 0.5279],
[0.6244, 0.3972, 0.8628, 0.5094, 0.3892, 0.4647, 0.5318, 0.5040],
[0.5981, 0.3899, 0.8339, 0.2679, 0.5203, 0.2410, 0.6810, 0.5113]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6142, 0.4127, 0.7575, 0.3067, 0.3438, 0.4383, 0.5778, 0.5207],
[0.6198, 0.4101, 0.8838, 0.5283, 0.3762, 0.5267, 0.5913, 0.5567],
[0.6264, 0.4248, 0.8938, 0.4183, 0.3875, 0.4100, 0.5400, 0.5350],
[0.6286, 0.4034, 0.8191, 0.2414, 0.4262, 0.2393, 0.6365, 0.5356],
[0.6339, 0.4118, 0.7987, 0.5800, 0.3913, 0.4583, 0.7343, 0.5760],
[0.6286, 0.4097, 0.8107, 0.2414, 0.4425, 0.2483, 0.6745, 0.5385],
[0.6102, 0.3999, 0.8750, 0.5133, 0.3825, 0.4750, 0.5638, 0.5083],
[0.6293, 0.4097, 0.8800, 0.2517, 0.5263, 0.2600, 0.7430, 0.5378]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.09657937183510512
step: 51
running loss: 0.0018937131732373552
Train Steps: 51/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6286, 0.4040, 0.8696, 0.3047, 0.3924, 0.2887, 0.6300, 0.5367],
[0.6207, 0.4081, 0.7662, 0.2067, 0.3962, 0.3200, 0.6312, 0.5300],
[0.6161, 0.4099, 0.8738, 0.4383, 0.3788, 0.5483, 0.5605, 0.5019],
[0.6243, 0.4128, 0.7762, 0.2717, 0.3825, 0.3133, 0.6212, 0.5417],
[0.6353, 0.4128, 0.9138, 0.3533, 0.4688, 0.3250, 0.7145, 0.5991],
[0.6269, 0.4073, 0.8900, 0.4933, 0.3625, 0.4183, 0.6288, 0.5150],
[ nan, nan, 0.7525, 0.2291, 0.3838, 0.3017, 0.6050, 0.5667],
[0.6030, 0.3969, 0.7988, 0.3917, 0.3450, 0.3667, 0.5266, 0.4700]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6311, 0.4221, 0.8473, 0.2995, 0.4195, 0.2622, 0.6039, 0.5202],
[0.7261, 0.5016, 0.7322, 0.2343, 0.3933, 0.3053, 0.5926, 0.5256],
[0.6551, 0.4545, 0.8713, 0.4405, 0.3823, 0.5575, 0.5866, 0.5082],
[0.6100, 0.4321, 0.7779, 0.2898, 0.4315, 0.2631, 0.6073, 0.5497],
[0.4372, 0.2929, 0.9085, 0.3609, 0.4803, 0.3184, 0.6927, 0.5634],
[0.6183, 0.4245, 0.8867, 0.5138, 0.3870, 0.4361, 0.6212, 0.5193],
[0.1437, 0.1349, 0.7505, 0.2220, 0.3988, 0.2872, 0.5788, 0.5707],
[0.6677, 0.4697, 0.8175, 0.4028, 0.3731, 0.3748, 0.5594, 0.5090]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6286, 0.4040, 0.8696, 0.3047, 0.3924, 0.2887, 0.6300, 0.5367],
[0.6207, 0.4081, 0.7663, 0.2067, 0.3963, 0.3200, 0.6313, 0.5300],
[0.6161, 0.4099, 0.8737, 0.4383, 0.3787, 0.5483, 0.5605, 0.5019],
[0.6243, 0.4128, 0.7763, 0.2717, 0.3825, 0.3133, 0.6212, 0.5417],
[0.6353, 0.4128, 0.9137, 0.3533, 0.4688, 0.3250, 0.7145, 0.5991],
[0.6269, 0.4073, 0.8900, 0.4933, 0.3625, 0.4183, 0.6288, 0.5150],
[0.0000, 0.0000, 0.7525, 0.2291, 0.3837, 0.3017, 0.6050, 0.5667],
[0.6030, 0.3969, 0.7987, 0.3917, 0.3450, 0.3667, 0.5266, 0.4700]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0023, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0023, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0988936327630654
step: 52
running loss: 0.00190180063005895
Train Steps: 52/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6202, 0.4079, 0.8025, 0.2500, 0.3763, 0.3217, 0.6125, 0.5533],
[0.6168, 0.4081, 0.8438, 0.3367, 0.3500, 0.4667, 0.6212, 0.5400],
[0.6219, 0.4089, 0.8938, 0.4800, 0.3825, 0.4450, 0.5850, 0.5200],
[0.6200, 0.4098, 0.8237, 0.2917, 0.4012, 0.2967, 0.6000, 0.5683],
[0.6361, 0.4071, 0.9100, 0.4783, 0.3738, 0.3967, 0.6670, 0.5332],
[0.6286, 0.4040, 0.8696, 0.3047, 0.3924, 0.2887, 0.6300, 0.5367],
[0.6364, 0.4144, 0.8625, 0.3083, 0.4913, 0.2000, 0.6448, 0.5274],
[0.6091, 0.3997, 0.8314, 0.4334, 0.3788, 0.4550, 0.5213, 0.5656]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5353, 0.3823, 0.7938, 0.2598, 0.3850, 0.3384, 0.6041, 0.5397],
[0.5435, 0.3924, 0.8487, 0.3284, 0.3678, 0.4744, 0.6533, 0.5549],
[0.6516, 0.4569, 0.8807, 0.4752, 0.3808, 0.4926, 0.6206, 0.5455],
[0.5597, 0.3985, 0.8237, 0.2700, 0.4093, 0.3204, 0.6297, 0.5742],
[0.6297, 0.4217, 0.9052, 0.4837, 0.4001, 0.4403, 0.6905, 0.5351],
[0.5590, 0.3859, 0.8605, 0.2797, 0.4072, 0.2892, 0.6317, 0.5315],
[0.5734, 0.4131, 0.8632, 0.3005, 0.4720, 0.2418, 0.6259, 0.5304],
[0.6172, 0.4364, 0.8233, 0.4241, 0.3716, 0.4831, 0.6026, 0.5529]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6202, 0.4079, 0.8025, 0.2500, 0.3762, 0.3217, 0.6125, 0.5533],
[0.6168, 0.4081, 0.8438, 0.3367, 0.3500, 0.4667, 0.6212, 0.5400],
[0.6219, 0.4089, 0.8938, 0.4800, 0.3825, 0.4450, 0.5850, 0.5200],
[0.6200, 0.4098, 0.8238, 0.2917, 0.4013, 0.2967, 0.6000, 0.5683],
[0.6361, 0.4071, 0.9100, 0.4783, 0.3738, 0.3967, 0.6670, 0.5332],
[0.6286, 0.4040, 0.8696, 0.3047, 0.3924, 0.2887, 0.6300, 0.5367],
[0.6364, 0.4144, 0.8625, 0.3083, 0.4913, 0.2000, 0.6448, 0.5274],
[0.6091, 0.3997, 0.8314, 0.4334, 0.3787, 0.4550, 0.5213, 0.5656]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.09974715590942651
step: 53
running loss: 0.001882021809611821
Train Steps: 53/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6147, 0.4081, 0.8538, 0.3400, 0.3663, 0.3150, 0.5142, 0.4875],
[0.6169, 0.4052, 0.8742, 0.4779, 0.4288, 0.4917, 0.5763, 0.5617],
[0.6115, 0.4081, 0.6725, 0.2433, 0.4088, 0.1933, 0.5167, 0.5544],
[0.6275, 0.4050, 0.9038, 0.3767, 0.3838, 0.3533, 0.7074, 0.5575],
[0.6292, 0.4010, 0.8988, 0.4800, 0.3638, 0.3817, 0.6357, 0.5051],
[0.6223, 0.4171, 0.8750, 0.5500, 0.4050, 0.4817, 0.5675, 0.5600],
[0.6293, 0.3982, 0.8700, 0.5300, 0.3763, 0.4717, 0.7050, 0.5297],
[0.6150, 0.3949, 0.8800, 0.4033, 0.3825, 0.4900, 0.5875, 0.5483]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6275, 0.4306, 0.8911, 0.3299, 0.3758, 0.3486, 0.5929, 0.5505],
[0.5658, 0.4011, 0.9082, 0.4369, 0.4359, 0.5329, 0.6209, 0.5843],
[0.7188, 0.4968, 0.7221, 0.2397, 0.4145, 0.2572, 0.5564, 0.5696],
[0.6036, 0.4003, 0.9182, 0.3324, 0.4068, 0.3903, 0.7308, 0.5581],
[0.5868, 0.3989, 0.9414, 0.4409, 0.3893, 0.4048, 0.6734, 0.5355],
[0.6512, 0.4482, 0.9158, 0.5223, 0.4085, 0.5194, 0.6330, 0.5632],
[0.6254, 0.4223, 0.8987, 0.4838, 0.3649, 0.5039, 0.7165, 0.5501],
[0.5276, 0.3468, 0.8923, 0.3737, 0.3886, 0.5233, 0.6415, 0.5414]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6147, 0.4081, 0.8537, 0.3400, 0.3663, 0.3150, 0.5142, 0.4875],
[0.6169, 0.4052, 0.8742, 0.4779, 0.4288, 0.4917, 0.5763, 0.5617],
[0.6115, 0.4081, 0.6725, 0.2433, 0.4087, 0.1933, 0.5167, 0.5544],
[0.6275, 0.4050, 0.9038, 0.3767, 0.3837, 0.3533, 0.7074, 0.5575],
[0.6292, 0.4010, 0.8988, 0.4800, 0.3638, 0.3817, 0.6357, 0.5051],
[0.6223, 0.4171, 0.8750, 0.5500, 0.4050, 0.4817, 0.5675, 0.5600],
[0.6293, 0.3982, 0.8700, 0.5300, 0.3762, 0.4717, 0.7050, 0.5297],
[0.6150, 0.3949, 0.8800, 0.4033, 0.3825, 0.4900, 0.5875, 0.5483]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.10123581916559488
step: 54
running loss: 0.0018747373919554607
Train Steps: 54/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.7192, 0.2346, 0.4037, 0.2050, 0.5138, 0.5650],
[0.6199, 0.4112, 0.8475, 0.3717, 0.3550, 0.4350, 0.6063, 0.6083],
[ nan, nan, 0.7425, 0.2117, 0.3937, 0.2433, 0.5438, 0.5567],
[0.6168, 0.4055, 0.7575, 0.2950, 0.4050, 0.2717, 0.5938, 0.6167],
[0.6333, 0.4037, 0.8638, 0.5733, 0.4012, 0.4717, 0.6369, 0.4938],
[0.6286, 0.4034, 0.8191, 0.2414, 0.4262, 0.2393, 0.6365, 0.5356],
[0.6275, 0.4048, 0.8488, 0.2883, 0.4463, 0.2033, 0.6321, 0.5155],
[0.6275, 0.4013, 0.8850, 0.2833, 0.4975, 0.2233, 0.7058, 0.5343]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.2724, 0.1738, 0.7532, 0.2123, 0.3912, 0.2749, 0.5379, 0.5518],
[0.7120, 0.4843, 0.8970, 0.3871, 0.3452, 0.4813, 0.6276, 0.5857],
[0.2392, 0.1629, 0.7932, 0.2384, 0.3899, 0.2904, 0.5817, 0.5716],
[0.7815, 0.5277, 0.8028, 0.2982, 0.3764, 0.3326, 0.6129, 0.6341],
[0.7014, 0.4486, 0.9404, 0.5730, 0.3902, 0.5327, 0.6732, 0.5283],
[0.6658, 0.4433, 0.8476, 0.2791, 0.4124, 0.2763, 0.6565, 0.5462],
[0.7444, 0.4732, 0.8730, 0.2678, 0.4320, 0.2968, 0.6825, 0.5032],
[0.6798, 0.4357, 0.8951, 0.2959, 0.4816, 0.3000, 0.7251, 0.5187]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.7192, 0.2346, 0.4038, 0.2050, 0.5138, 0.5650],
[0.6199, 0.4112, 0.8475, 0.3717, 0.3550, 0.4350, 0.6062, 0.6083],
[0.0000, 0.0000, 0.7425, 0.2117, 0.3938, 0.2433, 0.5437, 0.5567],
[0.6168, 0.4055, 0.7575, 0.2950, 0.4050, 0.2717, 0.5938, 0.6167],
[0.6334, 0.4037, 0.8637, 0.5733, 0.4013, 0.4717, 0.6369, 0.4938],
[0.6286, 0.4034, 0.8191, 0.2414, 0.4262, 0.2393, 0.6365, 0.5356],
[0.6275, 0.4048, 0.8487, 0.2883, 0.4462, 0.2033, 0.6321, 0.5155],
[0.6275, 0.4013, 0.8850, 0.2833, 0.4975, 0.2233, 0.7058, 0.5343]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0053, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0053, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.1065472379559651
step: 55
running loss: 0.0019372225082902746
Train Steps: 55/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6128, 0.4022, 0.8738, 0.5067, 0.4983, 0.5231, 0.5364, 0.5064],
[0.6160, 0.4086, 0.8775, 0.3983, 0.3750, 0.3783, 0.5128, 0.4882],
[0.6132, 0.4066, 0.7259, 0.2402, 0.3588, 0.3300, 0.6000, 0.5600],
[0.6289, 0.4024, 0.9088, 0.4567, 0.3937, 0.5633, 0.7058, 0.5609],
[0.6361, 0.4071, 0.9100, 0.4783, 0.3738, 0.3967, 0.6670, 0.5332],
[0.6219, 0.4089, 0.8938, 0.4800, 0.3825, 0.4450, 0.5850, 0.5200],
[0.6350, 0.4118, 0.8363, 0.2717, 0.4850, 0.1700, 0.6441, 0.5170],
[0.6336, 0.4191, 0.8938, 0.5167, 0.3937, 0.3517, 0.7343, 0.5748]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5691, 0.3698, 0.9165, 0.4752, 0.4648, 0.4836, 0.5714, 0.5409],
[0.5765, 0.3781, 0.8772, 0.3890, 0.3343, 0.3800, 0.5563, 0.5370],
[0.6562, 0.4239, 0.7415, 0.2279, 0.3311, 0.3317, 0.6071, 0.5846],
[0.6207, 0.3919, 0.9110, 0.4470, 0.3838, 0.5880, 0.6730, 0.5643],
[0.6225, 0.3718, 0.9335, 0.4698, 0.3647, 0.3998, 0.6734, 0.5408],
[0.6486, 0.4084, 0.9166, 0.4715, 0.3560, 0.4715, 0.6107, 0.5510],
[0.6746, 0.4125, 0.8632, 0.2376, 0.4625, 0.2011, 0.6717, 0.5324],
[0.5819, 0.3607, 0.9126, 0.4763, 0.3888, 0.3742, 0.6958, 0.5375]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6128, 0.4022, 0.8737, 0.5067, 0.4983, 0.5231, 0.5364, 0.5064],
[0.6160, 0.4086, 0.8775, 0.3983, 0.3750, 0.3783, 0.5128, 0.4882],
[0.6132, 0.4066, 0.7259, 0.2402, 0.3587, 0.3300, 0.6000, 0.5600],
[0.6289, 0.4024, 0.9087, 0.4567, 0.3938, 0.5633, 0.7058, 0.5609],
[0.6361, 0.4071, 0.9100, 0.4783, 0.3738, 0.3967, 0.6670, 0.5332],
[0.6219, 0.4089, 0.8938, 0.4800, 0.3825, 0.4450, 0.5850, 0.5200],
[0.6350, 0.4118, 0.8363, 0.2717, 0.4850, 0.1700, 0.6441, 0.5170],
[0.6336, 0.4191, 0.8938, 0.5167, 0.3938, 0.3517, 0.7343, 0.5748]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.10731903073610738
step: 56
running loss: 0.0019164112631447747
Train Steps: 56/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6307, 0.4045, 0.8025, 0.5833, 0.3775, 0.4867, 0.6892, 0.5459],
[0.6114, 0.4018, 0.7213, 0.1967, 0.3763, 0.2700, 0.5875, 0.5533],
[0.6192, 0.3980, 0.7078, 0.2750, 0.4250, 0.2100, 0.5450, 0.5783],
[0.6165, 0.4106, 0.7575, 0.1733, 0.3838, 0.2650, 0.5680, 0.5116],
[0.6111, 0.4033, 0.8300, 0.3267, 0.3588, 0.3333, 0.5444, 0.5637],
[0.6218, 0.4185, 0.7338, 0.2650, 0.4625, 0.1950, 0.5687, 0.5800],
[0.6086, 0.3940, 0.8712, 0.4783, 0.4025, 0.4900, 0.5498, 0.5390],
[0.6102, 0.3999, 0.8750, 0.5133, 0.3825, 0.4750, 0.5637, 0.5083]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6403, 0.3795, 0.8980, 0.5622, 0.3909, 0.4747, 0.7285, 0.5281],
[0.6636, 0.4230, 0.7843, 0.2408, 0.3759, 0.2624, 0.5990, 0.5570],
[0.4426, 0.2650, 0.7819, 0.2717, 0.4223, 0.2305, 0.5698, 0.5799],
[0.6475, 0.3757, 0.8123, 0.2576, 0.3823, 0.2330, 0.6141, 0.4856],
[0.5844, 0.3666, 0.9030, 0.3338, 0.3551, 0.3270, 0.5759, 0.5615],
[0.5405, 0.3511, 0.7870, 0.2629, 0.4318, 0.2087, 0.6067, 0.5856],
[0.6199, 0.3592, 0.9353, 0.5180, 0.4166, 0.4974, 0.6105, 0.5446],
[0.6197, 0.3734, 0.9563, 0.5340, 0.3956, 0.4882, 0.6105, 0.5443]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6307, 0.4045, 0.8025, 0.5833, 0.3775, 0.4867, 0.6892, 0.5459],
[0.6114, 0.4018, 0.7212, 0.1967, 0.3762, 0.2700, 0.5875, 0.5533],
[0.6192, 0.3980, 0.7078, 0.2750, 0.4250, 0.2100, 0.5450, 0.5783],
[0.6165, 0.4106, 0.7575, 0.1733, 0.3837, 0.2650, 0.5680, 0.5116],
[0.6111, 0.4033, 0.8300, 0.3267, 0.3587, 0.3333, 0.5444, 0.5637],
[0.6218, 0.4185, 0.7337, 0.2650, 0.4625, 0.1950, 0.5688, 0.5800],
[0.6086, 0.3940, 0.8712, 0.4783, 0.4025, 0.4900, 0.5498, 0.5390],
[0.6102, 0.3999, 0.8750, 0.5133, 0.3825, 0.4750, 0.5638, 0.5083]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0022, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0022, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.10952302097575739
step: 57
running loss: 0.0019214565083466209
Train Steps: 57/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6258, 0.4038, 0.8750, 0.4883, 0.3900, 0.5500, 0.6375, 0.5217],
[0.6127, 0.4084, 0.8700, 0.4467, 0.3987, 0.4317, 0.5013, 0.5471],
[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459],
[0.6261, 0.4131, 0.8938, 0.3550, 0.4000, 0.2683, 0.6188, 0.5283],
[0.6226, 0.4185, 0.8850, 0.5500, 0.3800, 0.4250, 0.5625, 0.5617],
[0.6182, 0.3987, 0.7878, 0.2889, 0.3699, 0.3260, 0.6086, 0.5367],
[0.6343, 0.4097, 0.9287, 0.4367, 0.4313, 0.3600, 0.7248, 0.5841],
[0.6125, 0.3999, 0.8750, 0.4883, 0.4750, 0.4700, 0.5533, 0.5617]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6365, 0.3743, 0.8675, 0.4952, 0.4117, 0.5146, 0.6097, 0.5063],
[0.5609, 0.3361, 0.8477, 0.4395, 0.3576, 0.3986, 0.4763, 0.5326],
[0.6198, 0.3910, 0.8201, 0.2905, 0.4859, 0.1939, 0.6222, 0.5119],
[0.5869, 0.3545, 0.8819, 0.3543, 0.3917, 0.2430, 0.6047, 0.5221],
[0.5527, 0.3526, 0.8673, 0.5385, 0.3781, 0.4188, 0.5554, 0.5453],
[0.5270, 0.3048, 0.7687, 0.2961, 0.3601, 0.3038, 0.5805, 0.5237],
[0.6488, 0.4108, 0.8584, 0.4499, 0.4041, 0.3312, 0.6700, 0.5362],
[0.6019, 0.3609, 0.8609, 0.4872, 0.4596, 0.4562, 0.5581, 0.5371]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6258, 0.4038, 0.8750, 0.4883, 0.3900, 0.5500, 0.6375, 0.5217],
[0.6127, 0.4084, 0.8700, 0.4467, 0.3988, 0.4317, 0.5013, 0.5471],
[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459],
[0.6261, 0.4131, 0.8938, 0.3550, 0.4000, 0.2683, 0.6187, 0.5283],
[0.6226, 0.4185, 0.8850, 0.5500, 0.3800, 0.4250, 0.5625, 0.5617],
[0.6182, 0.3987, 0.7878, 0.2889, 0.3699, 0.3260, 0.6086, 0.5367],
[0.6343, 0.4097, 0.9287, 0.4367, 0.4313, 0.3600, 0.7248, 0.5841],
[0.6125, 0.3999, 0.8750, 0.4883, 0.4750, 0.4700, 0.5533, 0.5617]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.11065401375526562
step: 58
running loss: 0.0019078278233666487
Train Steps: 58/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6284, 0.4029, 0.8838, 0.3783, 0.3975, 0.2850, 0.6335, 0.5090],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098],
[0.6311, 0.3998, 0.7975, 0.5767, 0.3838, 0.4850, 0.7327, 0.5343],
[0.6292, 0.4010, 0.8988, 0.4800, 0.3638, 0.3817, 0.6357, 0.5051],
[0.6226, 0.4125, 0.8800, 0.4900, 0.4512, 0.5600, 0.6275, 0.5517],
[0.6289, 0.4019, 0.8113, 0.5467, 0.3875, 0.5017, 0.7367, 0.5332],
[0.6257, 0.4167, 0.8775, 0.3433, 0.3563, 0.4133, 0.6200, 0.5667],
[0.6325, 0.4165, 0.9000, 0.4617, 0.3813, 0.4900, 0.7485, 0.5447]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6700, 0.4326, 0.8465, 0.3759, 0.4052, 0.2541, 0.5767, 0.4936],
[0.6088, 0.3693, 0.8447, 0.4587, 0.3971, 0.4752, 0.5430, 0.5230],
[0.6091, 0.3827, 0.7853, 0.5151, 0.3908, 0.4268, 0.6323, 0.5240],
[0.6106, 0.3826, 0.8802, 0.4890, 0.3949, 0.3110, 0.5897, 0.5250],
[0.6589, 0.4166, 0.8583, 0.4883, 0.4730, 0.5148, 0.5638, 0.5646],
[0.6102, 0.3873, 0.8047, 0.5130, 0.3933, 0.4348, 0.6198, 0.5365],
[0.5807, 0.3623, 0.8555, 0.3527, 0.3793, 0.3696, 0.5950, 0.5563],
[0.5650, 0.3652, 0.8887, 0.4821, 0.4247, 0.4604, 0.6303, 0.5394]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6284, 0.4029, 0.8838, 0.3783, 0.3975, 0.2850, 0.6335, 0.5090],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098],
[0.6311, 0.3998, 0.7975, 0.5767, 0.3837, 0.4850, 0.7327, 0.5343],
[0.6292, 0.4010, 0.8988, 0.4800, 0.3638, 0.3817, 0.6357, 0.5051],
[0.6226, 0.4125, 0.8800, 0.4900, 0.4512, 0.5600, 0.6275, 0.5517],
[0.6289, 0.4019, 0.8112, 0.5467, 0.3875, 0.5017, 0.7367, 0.5332],
[0.6257, 0.4167, 0.8775, 0.3433, 0.3562, 0.4133, 0.6200, 0.5667],
[0.6325, 0.4165, 0.9000, 0.4617, 0.3812, 0.4900, 0.7485, 0.5447]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.11230159673141316
step: 59
running loss: 0.0019034168937527654
Train Steps: 59/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6286, 0.4097, 0.8107, 0.2414, 0.4425, 0.2483, 0.6745, 0.5385],
[0.6164, 0.4076, 0.8838, 0.4117, 0.3713, 0.5550, 0.6238, 0.5350],
[0.6164, 0.3956, 0.8757, 0.5088, 0.4300, 0.5320, 0.6022, 0.5202],
[0.6239, 0.4123, 0.8313, 0.2550, 0.4500, 0.2050, 0.6175, 0.5400],
[0.6202, 0.4066, 0.8746, 0.3376, 0.3717, 0.3090, 0.5842, 0.5165],
[0.6286, 0.4274, 0.8500, 0.4500, 0.4525, 0.2583, 0.5440, 0.6209],
[0.6246, 0.4126, 0.8850, 0.4833, 0.4200, 0.5350, 0.6112, 0.5250],
[0.6227, 0.4193, 0.8838, 0.4933, 0.3663, 0.3733, 0.5637, 0.5633]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5976, 0.3865, 0.7750, 0.2826, 0.4411, 0.2298, 0.6490, 0.5309],
[0.5556, 0.3312, 0.8283, 0.3899, 0.3939, 0.5214, 0.6137, 0.5141],
[0.6032, 0.3724, 0.7987, 0.5199, 0.4078, 0.4533, 0.5771, 0.5130],
[0.5418, 0.3389, 0.7947, 0.2667, 0.4400, 0.1755, 0.5935, 0.5198],
[0.5723, 0.3736, 0.8127, 0.3381, 0.3666, 0.2736, 0.5842, 0.5161],
[0.6249, 0.4152, 0.7927, 0.4392, 0.4423, 0.2585, 0.5467, 0.5873],
[0.5716, 0.3700, 0.8444, 0.4802, 0.4240, 0.4934, 0.5635, 0.5217],
[0.5619, 0.3722, 0.7979, 0.4927, 0.3437, 0.3396, 0.5290, 0.5390]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6286, 0.4097, 0.8107, 0.2414, 0.4425, 0.2483, 0.6745, 0.5385],
[0.6164, 0.4076, 0.8838, 0.4117, 0.3713, 0.5550, 0.6237, 0.5350],
[0.6164, 0.3956, 0.8757, 0.5088, 0.4300, 0.5320, 0.6022, 0.5202],
[0.6239, 0.4123, 0.8313, 0.2550, 0.4500, 0.2050, 0.6175, 0.5400],
[0.6202, 0.4066, 0.8746, 0.3376, 0.3717, 0.3090, 0.5842, 0.5165],
[0.6286, 0.4274, 0.8500, 0.4500, 0.4525, 0.2583, 0.5440, 0.6209],
[0.6246, 0.4126, 0.8850, 0.4833, 0.4200, 0.5350, 0.6112, 0.5250],
[0.6227, 0.4193, 0.8838, 0.4933, 0.3663, 0.3733, 0.5638, 0.5633]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.11372045130701736
step: 60
running loss: 0.001895340855116956
Train Steps: 60/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6275, 0.4003, 0.9100, 0.3783, 0.4388, 0.3133, 0.7058, 0.5343],
[0.6229, 0.4066, 0.8513, 0.5717, 0.4500, 0.5050, 0.6025, 0.5350],
[0.6268, 0.4052, 0.8175, 0.2250, 0.4688, 0.1917, 0.6375, 0.5267],
[0.6164, 0.4076, 0.8838, 0.4117, 0.3713, 0.5550, 0.6238, 0.5350],
[0.6274, 0.4099, 0.8625, 0.3233, 0.4400, 0.1983, 0.5876, 0.4869],
[0.6098, 0.3991, 0.8638, 0.4717, 0.4263, 0.4967, 0.5212, 0.5650],
[ nan, nan, 0.7525, 0.2291, 0.3838, 0.3017, 0.6050, 0.5667],
[0.6085, 0.4008, 0.8588, 0.5200, 0.4959, 0.4977, 0.5175, 0.5283]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6158, 0.4215, 0.8445, 0.3986, 0.4052, 0.2963, 0.6601, 0.5171],
[0.6921, 0.4721, 0.8280, 0.5742, 0.4215, 0.4660, 0.6214, 0.5356],
[0.6141, 0.4159, 0.7788, 0.2511, 0.4412, 0.1787, 0.6674, 0.5213],
[0.6449, 0.4211, 0.8393, 0.3993, 0.3831, 0.5536, 0.6376, 0.5329],
[0.6885, 0.4565, 0.8322, 0.3377, 0.4438, 0.2241, 0.6034, 0.5038],
[0.6514, 0.4302, 0.8149, 0.5266, 0.4088, 0.4930, 0.5682, 0.5626],
[0.1568, 0.1365, 0.7287, 0.2559, 0.3713, 0.2906, 0.6051, 0.5638],
[0.6785, 0.4605, 0.8245, 0.5355, 0.4814, 0.4635, 0.5484, 0.5490]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6275, 0.4003, 0.9100, 0.3783, 0.4387, 0.3133, 0.7058, 0.5343],
[0.6229, 0.4066, 0.8512, 0.5717, 0.4500, 0.5050, 0.6025, 0.5350],
[0.6268, 0.4052, 0.8175, 0.2250, 0.4688, 0.1917, 0.6375, 0.5267],
[0.6164, 0.4076, 0.8838, 0.4117, 0.3713, 0.5550, 0.6237, 0.5350],
[0.6274, 0.4099, 0.8625, 0.3233, 0.4400, 0.1983, 0.5876, 0.4869],
[0.6098, 0.3991, 0.8637, 0.4717, 0.4263, 0.4967, 0.5213, 0.5650],
[0.0000, 0.0000, 0.7525, 0.2291, 0.3837, 0.3017, 0.6050, 0.5667],
[0.6084, 0.4008, 0.8587, 0.5200, 0.4959, 0.4977, 0.5175, 0.5283]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.11536864080699161
step: 61
running loss: 0.0018912891935572395
Train Steps: 61/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6218, 0.4137, 0.7263, 0.2233, 0.4075, 0.2650, 0.6212, 0.5783],
[0.6196, 0.4094, 0.7562, 0.2817, 0.3937, 0.3183, 0.6013, 0.6183],
[0.6145, 0.4007, 0.8775, 0.4533, 0.4562, 0.5533, 0.6088, 0.5533],
[0.6125, 0.4035, 0.7825, 0.3100, 0.3463, 0.4900, 0.5832, 0.5637],
[0.6085, 0.4008, 0.8588, 0.5200, 0.4959, 0.4977, 0.5175, 0.5283],
[0.6176, 0.4030, 0.8850, 0.4850, 0.3688, 0.4050, 0.5312, 0.5783],
[0.6182, 0.3998, 0.8793, 0.4191, 0.3552, 0.4285, 0.6038, 0.5312],
[0.6302, 0.4007, 0.8850, 0.5500, 0.3613, 0.4517, 0.6335, 0.5012]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6308, 0.4368, 0.7588, 0.2792, 0.4103, 0.2608, 0.6189, 0.5617],
[0.6197, 0.4305, 0.7728, 0.3165, 0.4232, 0.3204, 0.6322, 0.5996],
[0.6046, 0.4186, 0.8744, 0.4556, 0.4631, 0.5276, 0.6331, 0.5470],
[0.5291, 0.3804, 0.7644, 0.3500, 0.3569, 0.4627, 0.6394, 0.5231],
[0.6324, 0.4379, 0.8579, 0.5266, 0.5035, 0.4578, 0.5769, 0.5433],
[0.6046, 0.4234, 0.8726, 0.4919, 0.3836, 0.4204, 0.5508, 0.5633],
[0.5945, 0.4069, 0.8636, 0.4195, 0.3478, 0.3993, 0.6374, 0.5284],
[0.6733, 0.4624, 0.8645, 0.5685, 0.3725, 0.4319, 0.6626, 0.5058]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6218, 0.4137, 0.7262, 0.2233, 0.4075, 0.2650, 0.6212, 0.5783],
[0.6196, 0.4094, 0.7563, 0.2817, 0.3938, 0.3183, 0.6012, 0.6183],
[0.6145, 0.4007, 0.8775, 0.4533, 0.4563, 0.5533, 0.6087, 0.5533],
[0.6125, 0.4035, 0.7825, 0.3100, 0.3462, 0.4900, 0.5832, 0.5637],
[0.6084, 0.4008, 0.8587, 0.5200, 0.4959, 0.4977, 0.5175, 0.5283],
[0.6176, 0.4030, 0.8850, 0.4850, 0.3688, 0.4050, 0.5312, 0.5783],
[0.6182, 0.3998, 0.8793, 0.4191, 0.3552, 0.4285, 0.6038, 0.5312],
[0.6302, 0.4007, 0.8850, 0.5500, 0.3613, 0.4517, 0.6335, 0.5012]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.11608802812406793
step: 62
running loss: 0.0018723875503881924
Train Steps: 62/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6273, 0.4100, 0.7137, 0.2133, 0.4000, 0.2650, 0.6075, 0.5633],
[0.6214, 0.4116, 0.7750, 0.2317, 0.4487, 0.1883, 0.6200, 0.5400],
[0.6214, 0.4040, 0.8838, 0.3500, 0.3600, 0.5183, 0.6362, 0.5200],
[0.6245, 0.4115, 0.8700, 0.4883, 0.4625, 0.5517, 0.6100, 0.5217],
[0.6271, 0.4040, 0.9138, 0.3750, 0.4625, 0.2617, 0.7232, 0.5413],
[0.6117, 0.4019, 0.8538, 0.4067, 0.3513, 0.3583, 0.5663, 0.5133],
[0.6234, 0.4023, 0.8888, 0.4633, 0.3975, 0.5767, 0.6400, 0.5183],
[0.6170, 0.4102, 0.7468, 0.3695, 0.3463, 0.3767, 0.5238, 0.5823]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4617, 0.3219, 0.7192, 0.2454, 0.3976, 0.2679, 0.6069, 0.5669],
[0.6731, 0.4611, 0.7892, 0.2466, 0.4606, 0.2235, 0.6119, 0.5364],
[0.5985, 0.4165, 0.8816, 0.3927, 0.3924, 0.5346, 0.6360, 0.5497],
[0.6380, 0.4531, 0.8811, 0.4980, 0.4677, 0.5485, 0.6470, 0.5719],
[0.5778, 0.3894, 0.9415, 0.3813, 0.4868, 0.3180, 0.7241, 0.5422],
[0.6515, 0.4434, 0.8502, 0.4100, 0.3677, 0.3639, 0.5602, 0.5561],
[0.6955, 0.4848, 0.9014, 0.4948, 0.4301, 0.5923, 0.6377, 0.5528],
[0.5887, 0.4287, 0.7657, 0.3732, 0.3652, 0.4024, 0.5393, 0.5895]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6273, 0.4099, 0.7138, 0.2133, 0.4000, 0.2650, 0.6075, 0.5633],
[0.6214, 0.4116, 0.7750, 0.2317, 0.4487, 0.1883, 0.6200, 0.5400],
[0.6214, 0.4040, 0.8838, 0.3500, 0.3600, 0.5183, 0.6363, 0.5200],
[0.6245, 0.4115, 0.8700, 0.4883, 0.4625, 0.5517, 0.6100, 0.5217],
[0.6271, 0.4040, 0.9137, 0.3750, 0.4625, 0.2617, 0.7232, 0.5413],
[0.6116, 0.4019, 0.8537, 0.4067, 0.3512, 0.3583, 0.5663, 0.5133],
[0.6234, 0.4023, 0.8888, 0.4633, 0.3975, 0.5767, 0.6400, 0.5183],
[0.6170, 0.4102, 0.7468, 0.3695, 0.3462, 0.3767, 0.5238, 0.5823]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.11741927900584415
step: 63
running loss: 0.0018637980794578436
Train Steps: 63/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6230, 0.4152, 0.7588, 0.2283, 0.4012, 0.2883, 0.6200, 0.5767],
[0.6275, 0.4003, 0.9100, 0.3783, 0.4388, 0.3133, 0.7058, 0.5343],
[0.6179, 0.4008, 0.7505, 0.2678, 0.4368, 0.1891, 0.5831, 0.5263],
[0.6219, 0.4114, 0.8175, 0.2817, 0.3925, 0.2783, 0.5900, 0.5350],
[0.6090, 0.4045, 0.7250, 0.2100, 0.4075, 0.2300, 0.5476, 0.5663],
[0.6084, 0.3981, 0.8588, 0.5233, 0.4600, 0.5367, 0.5680, 0.5006],
[0.6275, 0.4071, 0.8075, 0.2100, 0.4700, 0.1533, 0.6148, 0.4834],
[0.6346, 0.4144, 0.9088, 0.4667, 0.3850, 0.4333, 0.7121, 0.5899]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5823, 0.3989, 0.7990, 0.2686, 0.4015, 0.3397, 0.6064, 0.5830],
[0.5737, 0.3859, 0.9048, 0.3874, 0.4089, 0.3633, 0.6578, 0.5424],
[0.6790, 0.4570, 0.7580, 0.2675, 0.4338, 0.2390, 0.5607, 0.5454],
[0.5070, 0.3484, 0.7983, 0.2682, 0.4036, 0.3215, 0.6074, 0.5580],
[0.4992, 0.3424, 0.7282, 0.2410, 0.4013, 0.2917, 0.5396, 0.5811],
[0.5697, 0.3986, 0.8845, 0.5299, 0.4589, 0.5847, 0.5493, 0.5481],
[0.6039, 0.4162, 0.8152, 0.2024, 0.4612, 0.2351, 0.6230, 0.5262],
[0.6638, 0.4316, 0.9216, 0.4938, 0.4082, 0.4667, 0.6866, 0.5826]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6230, 0.4152, 0.7588, 0.2283, 0.4013, 0.2883, 0.6200, 0.5767],
[0.6275, 0.4003, 0.9100, 0.3783, 0.4387, 0.3133, 0.7058, 0.5343],
[0.6179, 0.4008, 0.7505, 0.2678, 0.4368, 0.1891, 0.5831, 0.5263],
[0.6219, 0.4114, 0.8175, 0.2817, 0.3925, 0.2783, 0.5900, 0.5350],
[0.6090, 0.4045, 0.7250, 0.2100, 0.4075, 0.2300, 0.5476, 0.5663],
[0.6084, 0.3981, 0.8587, 0.5233, 0.4600, 0.5367, 0.5680, 0.5006],
[0.6275, 0.4071, 0.8075, 0.2100, 0.4700, 0.1533, 0.6148, 0.4834],
[0.6346, 0.4144, 0.9087, 0.4667, 0.3850, 0.4333, 0.7121, 0.5899]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.11882246885215864
step: 64
running loss: 0.0018566010758149787
Train Steps: 64/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6203, 0.4021, 0.8780, 0.5031, 0.3667, 0.3882, 0.5842, 0.5405],
[0.6200, 0.3913, 0.8788, 0.5217, 0.4075, 0.5100, 0.6060, 0.4913],
[0.6127, 0.4119, 0.8650, 0.5300, 0.4512, 0.5250, 0.5260, 0.5461],
[0.6230, 0.4113, 0.7213, 0.1983, 0.4325, 0.2367, 0.6262, 0.5400],
[ nan, nan, 0.8675, 0.2833, 0.5350, 0.1983, 0.6678, 0.5621],
[0.6148, 0.3996, 0.8488, 0.3867, 0.3488, 0.4067, 0.5863, 0.5000],
[0.6266, 0.4067, 0.8588, 0.2867, 0.4300, 0.2850, 0.6325, 0.5267],
[0.6133, 0.4066, 0.6787, 0.2617, 0.3800, 0.2433, 0.5147, 0.5358]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7349, 0.4675, 0.9156, 0.5079, 0.3783, 0.4450, 0.5984, 0.5317],
[0.6379, 0.4151, 0.8800, 0.5041, 0.3912, 0.5593, 0.5922, 0.5318],
[0.6555, 0.4495, 0.8806, 0.5197, 0.4423, 0.5433, 0.5737, 0.5766],
[0.5777, 0.3901, 0.7510, 0.2130, 0.4300, 0.2646, 0.6502, 0.5579],
[0.3214, 0.2092, 0.8647, 0.2586, 0.5082, 0.2396, 0.6842, 0.5704],
[0.6745, 0.4494, 0.8771, 0.3857, 0.3560, 0.4396, 0.5858, 0.5374],
[0.6192, 0.3965, 0.8787, 0.2707, 0.4508, 0.3048, 0.6362, 0.5435],
[0.5929, 0.4056, 0.7187, 0.2436, 0.3843, 0.2642, 0.5445, 0.5340]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6203, 0.4020, 0.8780, 0.5031, 0.3667, 0.3882, 0.5842, 0.5405],
[0.6199, 0.3913, 0.8788, 0.5217, 0.4075, 0.5100, 0.6060, 0.4913],
[0.6127, 0.4119, 0.8650, 0.5300, 0.4512, 0.5250, 0.5260, 0.5461],
[0.6230, 0.4113, 0.7212, 0.1983, 0.4325, 0.2367, 0.6263, 0.5400],
[0.0000, 0.0000, 0.8675, 0.2833, 0.5350, 0.1983, 0.6678, 0.5621],
[0.6148, 0.3996, 0.8487, 0.3867, 0.3487, 0.4067, 0.5863, 0.5000],
[0.6266, 0.4067, 0.8587, 0.2867, 0.4300, 0.2850, 0.6325, 0.5267],
[0.6133, 0.4065, 0.6787, 0.2617, 0.3800, 0.2433, 0.5147, 0.5358]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0032, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0032, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.12204406381351873
step: 65
running loss: 0.001877600981746442
Train Steps: 65/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6124, 0.4069, 0.8314, 0.5001, 0.3738, 0.4650, 0.5167, 0.5402],
[0.6162, 0.4134, 0.6700, 0.2467, 0.3962, 0.2533, 0.5737, 0.5467],
[0.6126, 0.4073, 0.8750, 0.5133, 0.3800, 0.4333, 0.4986, 0.5378],
[0.6110, 0.3984, 0.8750, 0.4933, 0.4625, 0.4950, 0.5578, 0.5676],
[0.6156, 0.4125, 0.8850, 0.4833, 0.4550, 0.5817, 0.5765, 0.5084],
[0.6311, 0.3998, 0.7975, 0.5767, 0.3838, 0.4850, 0.7327, 0.5343],
[0.6169, 0.4052, 0.8742, 0.4779, 0.4288, 0.4917, 0.5763, 0.5617],
[0.6086, 0.4019, 0.7782, 0.4278, 0.3625, 0.4350, 0.5150, 0.5285]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6549, 0.4234, 0.8641, 0.4460, 0.3999, 0.4543, 0.6240, 0.5543],
[0.5980, 0.3909, 0.7557, 0.2231, 0.3643, 0.2611, 0.6287, 0.5349],
[0.6213, 0.4000, 0.9014, 0.4747, 0.3929, 0.4499, 0.5685, 0.5125],
[0.6375, 0.4072, 0.9264, 0.4221, 0.4738, 0.5030, 0.6107, 0.5567],
[0.6489, 0.4262, 0.9240, 0.4144, 0.4471, 0.5674, 0.6234, 0.5403],
[0.6403, 0.4147, 0.8330, 0.4742, 0.3766, 0.4779, 0.7220, 0.5145],
[0.6165, 0.4096, 0.8961, 0.4373, 0.4341, 0.4900, 0.6077, 0.5471],
[0.6455, 0.4126, 0.8287, 0.3788, 0.3643, 0.4262, 0.5727, 0.5199]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6123, 0.4069, 0.8314, 0.5001, 0.3738, 0.4650, 0.5167, 0.5402],
[0.6162, 0.4134, 0.6700, 0.2467, 0.3963, 0.2533, 0.5738, 0.5467],
[0.6126, 0.4073, 0.8750, 0.5133, 0.3800, 0.4333, 0.4986, 0.5378],
[0.6110, 0.3984, 0.8750, 0.4933, 0.4625, 0.4950, 0.5578, 0.5676],
[0.6155, 0.4124, 0.8850, 0.4833, 0.4550, 0.5817, 0.5765, 0.5084],
[0.6311, 0.3998, 0.7975, 0.5767, 0.3837, 0.4850, 0.7327, 0.5343],
[0.6169, 0.4052, 0.8742, 0.4779, 0.4288, 0.4917, 0.5763, 0.5617],
[0.6086, 0.4019, 0.7782, 0.4278, 0.3625, 0.4350, 0.5150, 0.5285]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.12342670414363965
step: 66
running loss: 0.001870101577933934
Train Steps: 66/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6293, 0.4097, 0.8800, 0.2517, 0.5262, 0.2600, 0.7430, 0.5378],
[0.6286, 0.4078, 0.8063, 0.2267, 0.4788, 0.1533, 0.5953, 0.4913],
[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334],
[0.6286, 0.4060, 0.9188, 0.4333, 0.3675, 0.4167, 0.7034, 0.5528],
[0.6339, 0.4123, 0.8638, 0.5367, 0.4075, 0.5467, 0.7517, 0.5436],
[0.6164, 0.3956, 0.8757, 0.5088, 0.4300, 0.5320, 0.6022, 0.5202],
[0.6296, 0.3989, 0.9000, 0.4150, 0.3613, 0.3867, 0.6400, 0.5100],
[0.6196, 0.4094, 0.7562, 0.2817, 0.3937, 0.3183, 0.6013, 0.6183]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6517, 0.3950, 0.8952, 0.2544, 0.5097, 0.2601, 0.6829, 0.5222],
[0.5733, 0.3255, 0.7971, 0.2400, 0.4828, 0.2072, 0.5727, 0.5022],
[0.5915, 0.3806, 0.7819, 0.2226, 0.3704, 0.3152, 0.5553, 0.5218],
[0.6712, 0.3939, 0.9119, 0.4217, 0.3616, 0.4310, 0.6332, 0.5328],
[0.5975, 0.3927, 0.8889, 0.5248, 0.4028, 0.5850, 0.6696, 0.5266],
[0.6125, 0.3791, 0.8563, 0.5179, 0.4040, 0.5349, 0.5519, 0.5101],
[0.5716, 0.3439, 0.9131, 0.4123, 0.3465, 0.3948, 0.5630, 0.5008],
[0.6269, 0.3833, 0.7719, 0.2893, 0.4000, 0.3447, 0.5547, 0.5907]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6293, 0.4097, 0.8800, 0.2517, 0.5263, 0.2600, 0.7430, 0.5378],
[0.6286, 0.4078, 0.8062, 0.2267, 0.4787, 0.1533, 0.5953, 0.4913],
[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334],
[0.6286, 0.4060, 0.9187, 0.4333, 0.3675, 0.4167, 0.7034, 0.5528],
[0.6339, 0.4123, 0.8637, 0.5367, 0.4075, 0.5467, 0.7517, 0.5436],
[0.6164, 0.3956, 0.8757, 0.5088, 0.4300, 0.5320, 0.6022, 0.5202],
[0.6296, 0.3989, 0.9000, 0.4150, 0.3613, 0.3867, 0.6400, 0.5100],
[0.6196, 0.4094, 0.7563, 0.2817, 0.3938, 0.3183, 0.6012, 0.6183]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.12444062257418409
step: 67
running loss: 0.0018573227249878222
Train Steps: 67/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6203, 0.4076, 0.8611, 0.2878, 0.4050, 0.2554, 0.5907, 0.5496],
[0.6254, 0.4076, 0.8700, 0.3267, 0.4150, 0.3083, 0.7050, 0.5609],
[0.6212, 0.4159, 0.8675, 0.5783, 0.4088, 0.4317, 0.5613, 0.5917],
[0.6275, 0.4013, 0.8850, 0.2833, 0.4975, 0.2233, 0.7058, 0.5343],
[0.6228, 0.4119, 0.7938, 0.2233, 0.4674, 0.1773, 0.6188, 0.5433],
[0.6236, 0.4081, 0.8575, 0.3000, 0.3713, 0.3033, 0.5550, 0.5633],
[0.6178, 0.4012, 0.8900, 0.4495, 0.3891, 0.5617, 0.5972, 0.4879],
[0.6257, 0.4034, 0.8287, 0.2333, 0.3925, 0.2717, 0.6330, 0.4901]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6532, 0.3863, 0.8381, 0.2773, 0.4113, 0.2732, 0.5710, 0.5276],
[0.6314, 0.3613, 0.8673, 0.3157, 0.4232, 0.2928, 0.6520, 0.5310],
[0.5641, 0.3614, 0.8284, 0.5704, 0.3935, 0.4518, 0.5438, 0.5686],
[0.6321, 0.3723, 0.8681, 0.2921, 0.5005, 0.2325, 0.6820, 0.5124],
[0.6510, 0.3914, 0.7841, 0.2322, 0.4774, 0.1835, 0.5655, 0.5282],
[0.5351, 0.3280, 0.8166, 0.3076, 0.3767, 0.2982, 0.5308, 0.5306],
[0.5455, 0.3412, 0.8776, 0.4614, 0.3899, 0.5606, 0.5658, 0.4976],
[0.5498, 0.3304, 0.8194, 0.2611, 0.3887, 0.2648, 0.5999, 0.4929]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6203, 0.4076, 0.8611, 0.2878, 0.4050, 0.2554, 0.5907, 0.5496],
[0.6254, 0.4076, 0.8700, 0.3267, 0.4150, 0.3083, 0.7050, 0.5609],
[0.6212, 0.4159, 0.8675, 0.5783, 0.4087, 0.4317, 0.5612, 0.5917],
[0.6275, 0.4013, 0.8850, 0.2833, 0.4975, 0.2233, 0.7058, 0.5343],
[0.6228, 0.4119, 0.7937, 0.2233, 0.4674, 0.1773, 0.6187, 0.5433],
[0.6236, 0.4081, 0.8575, 0.3000, 0.3713, 0.3033, 0.5550, 0.5633],
[0.6178, 0.4012, 0.8900, 0.4495, 0.3891, 0.5617, 0.5972, 0.4879],
[0.6257, 0.4034, 0.8288, 0.2333, 0.3925, 0.2717, 0.6330, 0.4901]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.1254878489417024
step: 68
running loss: 0.0018454095432603294
Train Steps: 68/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6197, 0.4051, 0.7812, 0.2650, 0.3513, 0.4050, 0.6112, 0.5500],
[0.6136, 0.4060, 0.8025, 0.3217, 0.3650, 0.3000, 0.5060, 0.5646],
[ nan, nan, 0.8938, 0.2850, 0.4662, 0.3117, 0.7406, 0.5528],
[0.6031, 0.3986, 0.7462, 0.2833, 0.3638, 0.2717, 0.5253, 0.4726],
[0.6138, 0.4101, 0.8800, 0.5083, 0.4637, 0.5950, 0.5587, 0.5077],
[0.6225, 0.4196, 0.8788, 0.3467, 0.3750, 0.3400, 0.5413, 0.5433],
[ nan, nan, 0.7240, 0.2722, 0.3900, 0.2567, 0.5168, 0.5933],
[0.6198, 0.4114, 0.8263, 0.3283, 0.3550, 0.3583, 0.5813, 0.5667]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6844, 0.4405, 0.7799, 0.3047, 0.3637, 0.3610, 0.6419, 0.5207],
[0.7517, 0.4813, 0.7875, 0.3211, 0.4087, 0.2684, 0.5113, 0.5277],
[0.3289, 0.1807, 0.9043, 0.3134, 0.4653, 0.2704, 0.7535, 0.5364],
[0.6930, 0.4234, 0.7588, 0.2919, 0.3988, 0.2571, 0.5680, 0.4735],
[0.6735, 0.4149, 0.8795, 0.5366, 0.4842, 0.5513, 0.5983, 0.5389],
[0.6846, 0.4375, 0.8348, 0.3652, 0.3751, 0.2941, 0.5715, 0.5281],
[0.2488, 0.1441, 0.7344, 0.2680, 0.4080, 0.2224, 0.5436, 0.5447],
[0.7038, 0.4378, 0.8358, 0.3522, 0.3714, 0.3495, 0.5815, 0.5219]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6197, 0.4051, 0.7812, 0.2650, 0.3512, 0.4050, 0.6112, 0.5500],
[0.6136, 0.4060, 0.8025, 0.3217, 0.3650, 0.3000, 0.5060, 0.5646],
[0.0000, 0.0000, 0.8938, 0.2850, 0.4663, 0.3117, 0.7406, 0.5528],
[0.6031, 0.3986, 0.7462, 0.2833, 0.3638, 0.2717, 0.5253, 0.4726],
[0.6138, 0.4101, 0.8800, 0.5083, 0.4638, 0.5950, 0.5587, 0.5077],
[0.6225, 0.4196, 0.8788, 0.3467, 0.3750, 0.3400, 0.5412, 0.5433],
[0.0000, 0.0000, 0.7240, 0.2722, 0.3900, 0.2567, 0.5168, 0.5933],
[0.6198, 0.4114, 0.8263, 0.3283, 0.3550, 0.3583, 0.5813, 0.5667]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0049, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0049, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.13038400636287406
step: 69
running loss: 0.0018896232806213632
Train Steps: 69/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6219, 0.3934, 0.8688, 0.5267, 0.4313, 0.4967, 0.5988, 0.4983],
[0.6250, 0.4008, 0.8950, 0.4183, 0.3550, 0.4383, 0.6361, 0.4927],
[0.6201, 0.4050, 0.7757, 0.2234, 0.4459, 0.1798, 0.5975, 0.5426],
[0.6100, 0.4016, 0.8600, 0.5067, 0.4612, 0.5233, 0.5086, 0.5519],
[0.6185, 0.4067, 0.8838, 0.4450, 0.4037, 0.4733, 0.5213, 0.5142],
[0.6223, 0.3990, 0.8037, 0.2800, 0.4000, 0.2283, 0.5864, 0.5208],
[0.6364, 0.4154, 0.8938, 0.3717, 0.4500, 0.2583, 0.6448, 0.5285],
[0.6128, 0.4115, 0.7934, 0.3778, 0.3450, 0.4033, 0.5337, 0.5456]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5951, 0.3895, 0.8416, 0.5235, 0.4252, 0.4983, 0.6261, 0.4952],
[0.5503, 0.3507, 0.8777, 0.4197, 0.3331, 0.4423, 0.6457, 0.5161],
[0.6041, 0.3976, 0.7719, 0.2042, 0.4376, 0.1779, 0.6123, 0.5478],
[0.5624, 0.3707, 0.8516, 0.5060, 0.4581, 0.5141, 0.5622, 0.5226],
[0.5725, 0.3693, 0.8532, 0.4400, 0.3778, 0.4570, 0.5595, 0.5110],
[0.5750, 0.3745, 0.7993, 0.2587, 0.4015, 0.2159, 0.6403, 0.5213],
[0.6475, 0.4099, 0.8714, 0.3639, 0.4452, 0.2523, 0.6694, 0.5656],
[0.6218, 0.3965, 0.7890, 0.3606, 0.3206, 0.4008, 0.5353, 0.5258]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6219, 0.3934, 0.8687, 0.5267, 0.4313, 0.4967, 0.5987, 0.4983],
[0.6250, 0.4008, 0.8950, 0.4183, 0.3550, 0.4383, 0.6361, 0.4927],
[0.6201, 0.4050, 0.7757, 0.2234, 0.4459, 0.1798, 0.5975, 0.5426],
[0.6100, 0.4016, 0.8600, 0.5067, 0.4613, 0.5233, 0.5086, 0.5519],
[0.6185, 0.4067, 0.8838, 0.4450, 0.4038, 0.4733, 0.5213, 0.5142],
[0.6223, 0.3990, 0.8037, 0.2800, 0.4000, 0.2283, 0.5864, 0.5208],
[0.6364, 0.4154, 0.8938, 0.3717, 0.4500, 0.2583, 0.6448, 0.5285],
[0.6128, 0.4115, 0.7934, 0.3778, 0.3450, 0.4033, 0.5337, 0.5456]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.13097077485872433
step: 70
running loss: 0.0018710110694103476
Train Steps: 70/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6186, 0.4013, 0.8191, 0.3188, 0.4279, 0.2060, 0.5767, 0.5411],
[0.6037, 0.4020, 0.8300, 0.4033, 0.3575, 0.4883, 0.5647, 0.5631],
[0.6250, 0.4008, 0.8950, 0.4183, 0.3550, 0.4383, 0.6361, 0.4927],
[ nan, nan, 0.6900, 0.1917, 0.3937, 0.2367, 0.5240, 0.5246],
[0.6069, 0.3975, 0.8625, 0.5083, 0.4388, 0.5483, 0.5650, 0.4967],
[0.6260, 0.4153, 0.9000, 0.4533, 0.4025, 0.2633, 0.6223, 0.4967],
[0.6276, 0.4095, 0.8237, 0.2250, 0.4662, 0.1783, 0.6171, 0.4869],
[0.6361, 0.4165, 0.9038, 0.5017, 0.3750, 0.3783, 0.6448, 0.5309]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6149, 0.4330, 0.7990, 0.2836, 0.4278, 0.1979, 0.5801, 0.5593],
[0.6108, 0.4046, 0.8090, 0.4209, 0.3469, 0.4819, 0.6012, 0.5438],
[0.5945, 0.3862, 0.8863, 0.4450, 0.3350, 0.4499, 0.6335, 0.5160],
[0.1991, 0.1424, 0.7229, 0.2248, 0.4367, 0.1982, 0.5435, 0.5702],
[0.5651, 0.3826, 0.8614, 0.5356, 0.4345, 0.5389, 0.5768, 0.5182],
[0.6056, 0.3988, 0.8797, 0.4604, 0.4088, 0.2651, 0.6134, 0.5259],
[0.6272, 0.4085, 0.8028, 0.2248, 0.4821, 0.1933, 0.6165, 0.5272],
[0.5926, 0.4070, 0.8533, 0.4843, 0.3864, 0.3605, 0.6208, 0.5338]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6186, 0.4013, 0.8191, 0.3188, 0.4279, 0.2060, 0.5767, 0.5411],
[0.6037, 0.4020, 0.8300, 0.4033, 0.3575, 0.4883, 0.5647, 0.5631],
[0.6250, 0.4008, 0.8950, 0.4183, 0.3550, 0.4383, 0.6361, 0.4927],
[0.0000, 0.0000, 0.6900, 0.1917, 0.3938, 0.2367, 0.5240, 0.5246],
[0.6069, 0.3975, 0.8625, 0.5083, 0.4387, 0.5483, 0.5650, 0.4967],
[0.6260, 0.4153, 0.9000, 0.4533, 0.4025, 0.2633, 0.6223, 0.4967],
[0.6276, 0.4095, 0.8238, 0.2250, 0.4663, 0.1783, 0.6171, 0.4869],
[0.6361, 0.4165, 0.9038, 0.5017, 0.3750, 0.3783, 0.6448, 0.5309]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.1323865795857273
step: 71
running loss: 0.0018645997124750325
Train Steps: 71/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6219, 0.3934, 0.8688, 0.5267, 0.4313, 0.4967, 0.5988, 0.4983],
[0.6249, 0.4142, 0.8350, 0.3283, 0.3613, 0.3700, 0.6188, 0.5400],
[0.6282, 0.4034, 0.7830, 0.2080, 0.4532, 0.2080, 0.6404, 0.5323],
[0.6271, 0.4005, 0.8450, 0.6067, 0.3850, 0.4983, 0.6069, 0.4649],
[0.6189, 0.4049, 0.8888, 0.4417, 0.4213, 0.5200, 0.5988, 0.5633],
[0.6162, 0.4134, 0.6700, 0.2467, 0.3962, 0.2533, 0.5737, 0.5467],
[0.6109, 0.4015, 0.7668, 0.3639, 0.3513, 0.3667, 0.5200, 0.5641],
[0.6196, 0.4068, 0.7645, 0.2234, 0.4575, 0.1737, 0.5926, 0.5284]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5403, 0.3588, 0.8773, 0.5526, 0.4269, 0.4926, 0.5876, 0.5006],
[0.5450, 0.3859, 0.8281, 0.3307, 0.3718, 0.3166, 0.6227, 0.5600],
[0.6058, 0.4103, 0.8098, 0.2198, 0.4384, 0.1634, 0.6116, 0.5619],
[0.5277, 0.3507, 0.8685, 0.5997, 0.3702, 0.4894, 0.5950, 0.4821],
[0.5591, 0.3835, 0.9010, 0.4585, 0.4093, 0.5428, 0.6151, 0.5703],
[0.5242, 0.3608, 0.7226, 0.2736, 0.3663, 0.2387, 0.5913, 0.5539],
[0.5398, 0.3709, 0.8187, 0.3559, 0.3501, 0.3463, 0.5325, 0.5561],
[0.5712, 0.3901, 0.7794, 0.2210, 0.4508, 0.1871, 0.6098, 0.5435]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6219, 0.3934, 0.8687, 0.5267, 0.4313, 0.4967, 0.5987, 0.4983],
[0.6249, 0.4142, 0.8350, 0.3283, 0.3613, 0.3700, 0.6187, 0.5400],
[0.6282, 0.4034, 0.7830, 0.2080, 0.4532, 0.2080, 0.6404, 0.5323],
[0.6271, 0.4005, 0.8450, 0.6067, 0.3850, 0.4983, 0.6069, 0.4649],
[0.6189, 0.4049, 0.8888, 0.4417, 0.4212, 0.5200, 0.5987, 0.5633],
[0.6162, 0.4134, 0.6700, 0.2467, 0.3963, 0.2533, 0.5738, 0.5467],
[0.6109, 0.4015, 0.7668, 0.3639, 0.3512, 0.3667, 0.5200, 0.5641],
[0.6196, 0.4068, 0.7645, 0.2234, 0.4575, 0.1737, 0.5926, 0.5284]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.13352739083347842
step: 72
running loss: 0.0018545470949094226
Train Steps: 72/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6214, 0.4116, 0.7750, 0.2317, 0.4487, 0.1883, 0.6200, 0.5400],
[0.6200, 0.4055, 0.8011, 0.2988, 0.3842, 0.2798, 0.5949, 0.5183],
[0.6182, 0.4058, 0.8738, 0.4350, 0.3563, 0.3400, 0.5290, 0.5822],
[0.6114, 0.4018, 0.7213, 0.1967, 0.3763, 0.2700, 0.5875, 0.5533],
[0.6086, 0.4019, 0.7782, 0.4278, 0.3625, 0.4350, 0.5150, 0.5285],
[0.6264, 0.4067, 0.9050, 0.4183, 0.3775, 0.4600, 0.6308, 0.4862],
[0.6109, 0.4003, 0.8650, 0.4883, 0.4775, 0.4867, 0.5175, 0.5683],
[0.6086, 0.3998, 0.8788, 0.4450, 0.4025, 0.4650, 0.5306, 0.5103]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5702, 0.3739, 0.7809, 0.2329, 0.4572, 0.1862, 0.6156, 0.5310],
[0.6047, 0.4196, 0.8026, 0.3138, 0.4052, 0.2717, 0.6298, 0.5326],
[0.5253, 0.3631, 0.8580, 0.4306, 0.3677, 0.3510, 0.5075, 0.5822],
[0.5306, 0.3709, 0.7307, 0.2197, 0.3811, 0.2467, 0.5953, 0.5587],
[0.6008, 0.4069, 0.7982, 0.4377, 0.3647, 0.4292, 0.5564, 0.5311],
[0.5620, 0.3893, 0.8881, 0.4307, 0.3675, 0.4510, 0.6316, 0.5068],
[0.4929, 0.3426, 0.8852, 0.4981, 0.4812, 0.4883, 0.5724, 0.5553],
[0.5472, 0.3816, 0.8672, 0.4665, 0.3976, 0.4679, 0.5754, 0.5143]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6214, 0.4116, 0.7750, 0.2317, 0.4487, 0.1883, 0.6200, 0.5400],
[0.6201, 0.4055, 0.8011, 0.2988, 0.3842, 0.2798, 0.5949, 0.5183],
[0.6182, 0.4058, 0.8737, 0.4350, 0.3562, 0.3400, 0.5290, 0.5822],
[0.6114, 0.4018, 0.7212, 0.1967, 0.3762, 0.2700, 0.5875, 0.5533],
[0.6086, 0.4019, 0.7782, 0.4278, 0.3625, 0.4350, 0.5150, 0.5285],
[0.6264, 0.4067, 0.9050, 0.4183, 0.3775, 0.4600, 0.6308, 0.4862],
[0.6109, 0.4003, 0.8650, 0.4883, 0.4775, 0.4867, 0.5175, 0.5683],
[0.6086, 0.3998, 0.8788, 0.4450, 0.4025, 0.4650, 0.5306, 0.5103]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.13450522517086938
step: 73
running loss: 0.0018425373311077998
Train Steps: 73/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6346, 0.4165, 0.9138, 0.3983, 0.3875, 0.4317, 0.7469, 0.5471],
[0.6222, 0.4172, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633],
[0.6152, 0.4131, 0.6863, 0.2567, 0.3625, 0.3300, 0.5765, 0.5305],
[ nan, nan, 0.6992, 0.2791, 0.3950, 0.2383, 0.5483, 0.5819],
[0.6261, 0.4045, 0.8865, 0.5369, 0.3895, 0.4859, 0.6683, 0.5249],
[0.6274, 0.4270, 0.8938, 0.4967, 0.3550, 0.4283, 0.5700, 0.5733],
[0.6307, 0.4029, 0.8650, 0.5200, 0.3763, 0.4017, 0.7311, 0.5366],
[0.6143, 0.4055, 0.8150, 0.2767, 0.3825, 0.2567, 0.5173, 0.4901]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5932, 0.4021, 0.9224, 0.4201, 0.4089, 0.4184, 0.6681, 0.5319],
[0.6426, 0.4420, 0.9131, 0.5361, 0.3849, 0.4679, 0.5603, 0.5626],
[0.5596, 0.3877, 0.7069, 0.2391, 0.3801, 0.3218, 0.5559, 0.5568],
[0.3145, 0.2176, 0.6766, 0.2093, 0.3874, 0.2276, 0.5255, 0.5453],
[0.6297, 0.4334, 0.8823, 0.5122, 0.3979, 0.5125, 0.6349, 0.5204],
[0.6396, 0.4406, 0.8905, 0.4983, 0.3858, 0.4697, 0.5679, 0.5379],
[0.6697, 0.4546, 0.8755, 0.4976, 0.4065, 0.3941, 0.6260, 0.5066],
[0.5101, 0.3365, 0.7944, 0.2642, 0.3986, 0.2635, 0.5119, 0.5375]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6346, 0.4165, 0.9137, 0.3983, 0.3875, 0.4317, 0.7469, 0.5471],
[0.6222, 0.4171, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633],
[0.6152, 0.4131, 0.6862, 0.2567, 0.3625, 0.3300, 0.5765, 0.5305],
[0.0000, 0.0000, 0.6992, 0.2791, 0.3950, 0.2383, 0.5483, 0.5819],
[0.6261, 0.4045, 0.8865, 0.5369, 0.3895, 0.4859, 0.6683, 0.5249],
[0.6274, 0.4270, 0.8938, 0.4967, 0.3550, 0.4283, 0.5700, 0.5733],
[0.6307, 0.4029, 0.8650, 0.5200, 0.3762, 0.4017, 0.7311, 0.5366],
[0.6143, 0.4055, 0.8150, 0.2767, 0.3825, 0.2567, 0.5173, 0.4901]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0034, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0034, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.13787507318193093
step: 74
running loss: 0.0018631766646206882
Train Steps: 74/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6201, 0.4065, 0.7300, 0.1933, 0.4075, 0.2533, 0.6162, 0.5483],
[0.6161, 0.4024, 0.8838, 0.4583, 0.3688, 0.3733, 0.5311, 0.5344],
[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459],
[0.6275, 0.4048, 0.8488, 0.2883, 0.4463, 0.2033, 0.6321, 0.5155],
[0.6258, 0.4038, 0.8750, 0.4883, 0.3900, 0.5500, 0.6375, 0.5217],
[0.6072, 0.4029, 0.7037, 0.2150, 0.3912, 0.2267, 0.5516, 0.5507],
[0.6048, 0.3928, 0.8538, 0.5433, 0.3875, 0.5117, 0.5266, 0.4719],
[ nan, nan, 0.6900, 0.1917, 0.3937, 0.2367, 0.5240, 0.5246]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5797, 0.3975, 0.7268, 0.2070, 0.3868, 0.2786, 0.5860, 0.5435],
[0.6807, 0.4556, 0.8901, 0.5002, 0.3596, 0.4272, 0.5110, 0.5236],
[0.5820, 0.3928, 0.8670, 0.3012, 0.4777, 0.2253, 0.6494, 0.5298],
[0.6709, 0.4309, 0.8455, 0.2722, 0.4336, 0.2452, 0.6256, 0.5038],
[0.7241, 0.4788, 0.8761, 0.5397, 0.3933, 0.6080, 0.6220, 0.5062],
[0.5731, 0.3881, 0.6840, 0.2172, 0.3951, 0.2544, 0.5523, 0.5419],
[0.6635, 0.4368, 0.8471, 0.5739, 0.3895, 0.5456, 0.5621, 0.5044],
[0.0911, 0.0716, 0.7280, 0.2380, 0.4164, 0.2594, 0.5111, 0.5556]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6201, 0.4065, 0.7300, 0.1933, 0.4075, 0.2533, 0.6162, 0.5483],
[0.6161, 0.4024, 0.8838, 0.4583, 0.3688, 0.3733, 0.5311, 0.5344],
[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459],
[0.6275, 0.4048, 0.8487, 0.2883, 0.4462, 0.2033, 0.6321, 0.5155],
[0.6258, 0.4038, 0.8750, 0.4883, 0.3900, 0.5500, 0.6375, 0.5217],
[0.6072, 0.4029, 0.7038, 0.2150, 0.3913, 0.2267, 0.5516, 0.5507],
[0.6048, 0.3928, 0.8537, 0.5433, 0.3875, 0.5117, 0.5266, 0.4719],
[0.0000, 0.0000, 0.6900, 0.1917, 0.3938, 0.2367, 0.5240, 0.5246]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.13911375048337504
step: 75
running loss: 0.0018548500064450005
Train Steps: 75/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6145, 0.3983, 0.8700, 0.5017, 0.4400, 0.4800, 0.5375, 0.5750],
[0.6300, 0.4102, 0.9088, 0.4433, 0.4088, 0.3067, 0.6820, 0.5540],
[0.6072, 0.4029, 0.7037, 0.2150, 0.3912, 0.2267, 0.5516, 0.5507],
[0.6346, 0.4144, 0.9088, 0.4667, 0.3850, 0.4333, 0.7121, 0.5899],
[0.6201, 0.4082, 0.8827, 0.3715, 0.3825, 0.2712, 0.5845, 0.5412],
[0.6201, 0.4027, 0.8029, 0.2728, 0.4042, 0.2310, 0.5980, 0.5391],
[0.6115, 0.4005, 0.8838, 0.3867, 0.3763, 0.4700, 0.5800, 0.5550],
[0.6284, 0.4029, 0.8838, 0.3783, 0.3975, 0.2850, 0.6335, 0.5090]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6325, 0.4128, 0.8378, 0.4977, 0.4163, 0.5059, 0.5350, 0.5198],
[0.4977, 0.3286, 0.8924, 0.4457, 0.3964, 0.3302, 0.6415, 0.5278],
[0.5240, 0.3414, 0.6580, 0.1917, 0.3814, 0.2373, 0.5462, 0.5343],
[0.6375, 0.4162, 0.8675, 0.4607, 0.3843, 0.4125, 0.6786, 0.5469],
[0.6242, 0.3876, 0.8634, 0.3314, 0.3710, 0.2785, 0.5657, 0.5215],
[0.5205, 0.3214, 0.7670, 0.2383, 0.4139, 0.2655, 0.5800, 0.5364],
[0.6382, 0.4089, 0.8369, 0.3992, 0.3415, 0.5122, 0.5060, 0.5114],
[0.6169, 0.4138, 0.8641, 0.3638, 0.3694, 0.2957, 0.6184, 0.4895]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6145, 0.3983, 0.8700, 0.5017, 0.4400, 0.4800, 0.5375, 0.5750],
[0.6300, 0.4102, 0.9087, 0.4433, 0.4087, 0.3067, 0.6820, 0.5540],
[0.6072, 0.4029, 0.7038, 0.2150, 0.3913, 0.2267, 0.5516, 0.5507],
[0.6346, 0.4144, 0.9087, 0.4667, 0.3850, 0.4333, 0.7121, 0.5899],
[0.6201, 0.4082, 0.8827, 0.3715, 0.3825, 0.2712, 0.5845, 0.5412],
[0.6201, 0.4027, 0.8029, 0.2728, 0.4042, 0.2310, 0.5980, 0.5391],
[0.6115, 0.4005, 0.8838, 0.3867, 0.3762, 0.4700, 0.5800, 0.5550],
[0.6284, 0.4029, 0.8838, 0.3783, 0.3975, 0.2850, 0.6335, 0.5090]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.14055398636264727
step: 76
running loss: 0.0018493945574032534
Train Steps: 76/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6197, 0.4091, 0.8800, 0.4783, 0.3538, 0.4767, 0.5950, 0.5550],
[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586],
[ nan, nan, 0.7625, 0.2433, 0.3713, 0.2867, 0.5235, 0.5220],
[0.6193, 0.4108, 0.7425, 0.2350, 0.3887, 0.2750, 0.5900, 0.5717],
[0.6126, 0.4067, 0.8638, 0.5383, 0.4188, 0.4850, 0.5016, 0.5392],
[0.6257, 0.4034, 0.8287, 0.2333, 0.3925, 0.2717, 0.6330, 0.4901],
[0.6225, 0.4196, 0.8788, 0.3467, 0.3750, 0.3400, 0.5413, 0.5433],
[0.6132, 0.4118, 0.8200, 0.3633, 0.3563, 0.5400, 0.5787, 0.5136]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7221, 0.4383, 0.8886, 0.4777, 0.3893, 0.4451, 0.5912, 0.5377],
[0.5946, 0.3824, 0.8502, 0.2653, 0.4305, 0.2288, 0.7005, 0.5474],
[0.0674, 0.0377, 0.7684, 0.2331, 0.3859, 0.2675, 0.5374, 0.5340],
[0.6066, 0.3915, 0.7468, 0.2663, 0.3789, 0.2621, 0.5982, 0.5673],
[0.7450, 0.4842, 0.8662, 0.5883, 0.4239, 0.4681, 0.5471, 0.5095],
[0.6306, 0.4095, 0.8095, 0.2387, 0.3810, 0.2444, 0.6396, 0.4975],
[0.6211, 0.4149, 0.8376, 0.3492, 0.3540, 0.3035, 0.5393, 0.5472],
[0.6774, 0.4275, 0.8233, 0.3700, 0.3682, 0.5086, 0.5857, 0.5150]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6197, 0.4091, 0.8800, 0.4783, 0.3537, 0.4767, 0.5950, 0.5550],
[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586],
[0.0000, 0.0000, 0.7625, 0.2433, 0.3713, 0.2867, 0.5235, 0.5220],
[0.6193, 0.4108, 0.7425, 0.2350, 0.3887, 0.2750, 0.5900, 0.5717],
[0.6126, 0.4067, 0.8637, 0.5383, 0.4187, 0.4850, 0.5016, 0.5392],
[0.6257, 0.4034, 0.8288, 0.2333, 0.3925, 0.2717, 0.6330, 0.4901],
[0.6225, 0.4196, 0.8788, 0.3467, 0.3750, 0.3400, 0.5412, 0.5433],
[0.6132, 0.4118, 0.8200, 0.3633, 0.3562, 0.5400, 0.5787, 0.5136]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.14160173939308152
step: 77
running loss: 0.0018389836284815782
Train Steps: 77/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6264, 0.4049, 0.8988, 0.4633, 0.3813, 0.4983, 0.6326, 0.4843],
[0.6200, 0.3993, 0.8519, 0.4923, 0.3962, 0.4717, 0.6013, 0.5433],
[0.6222, 0.4169, 0.8638, 0.5650, 0.4313, 0.4783, 0.5637, 0.5633],
[0.6175, 0.4013, 0.7734, 0.2783, 0.4475, 0.1786, 0.5790, 0.5351],
[0.6168, 0.4081, 0.8438, 0.3367, 0.3500, 0.4667, 0.6212, 0.5400],
[0.6152, 0.4131, 0.6863, 0.2567, 0.3625, 0.3300, 0.5765, 0.5305],
[0.6053, 0.4035, 0.6897, 0.1916, 0.4000, 0.2117, 0.5440, 0.5168],
[0.6175, 0.3997, 0.6737, 0.2500, 0.4313, 0.1933, 0.5513, 0.5750]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6685, 0.4316, 0.9437, 0.4782, 0.3725, 0.5001, 0.6333, 0.4880],
[0.6572, 0.4154, 0.9135, 0.4934, 0.3772, 0.4707, 0.6351, 0.5345],
[0.6967, 0.4506, 0.9175, 0.5615, 0.4209, 0.4681, 0.6014, 0.5842],
[0.5686, 0.3843, 0.8098, 0.2375, 0.4232, 0.1728, 0.5963, 0.5342],
[0.6842, 0.4281, 0.8738, 0.3398, 0.3418, 0.4645, 0.6383, 0.5833],
[0.5826, 0.3776, 0.7209, 0.2505, 0.3553, 0.3277, 0.5802, 0.5649],
[0.4752, 0.2821, 0.7004, 0.1778, 0.3955, 0.1971, 0.5591, 0.5399],
[0.4212, 0.2661, 0.7238, 0.2077, 0.4278, 0.1912, 0.5486, 0.5777]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6264, 0.4049, 0.8988, 0.4633, 0.3812, 0.4983, 0.6326, 0.4843],
[0.6200, 0.3993, 0.8519, 0.4923, 0.3963, 0.4717, 0.6012, 0.5433],
[0.6222, 0.4169, 0.8637, 0.5650, 0.4313, 0.4783, 0.5638, 0.5633],
[0.6175, 0.4013, 0.7734, 0.2783, 0.4475, 0.1786, 0.5790, 0.5351],
[0.6168, 0.4081, 0.8438, 0.3367, 0.3500, 0.4667, 0.6212, 0.5400],
[0.6152, 0.4131, 0.6862, 0.2567, 0.3625, 0.3300, 0.5765, 0.5305],
[0.6054, 0.4035, 0.6897, 0.1916, 0.4000, 0.2117, 0.5440, 0.5168],
[0.6175, 0.3997, 0.6737, 0.2500, 0.4313, 0.1933, 0.5512, 0.5750]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0021, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0021, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.14373794820858166
step: 78
running loss: 0.001842794207802329
Train Steps: 78/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6193, 0.4108, 0.7425, 0.2350, 0.3887, 0.2750, 0.5900, 0.5717],
[0.6300, 0.4133, 0.8538, 0.2167, 0.5587, 0.2250, 0.7390, 0.5413],
[0.6226, 0.4098, 0.8912, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098],
[0.6226, 0.4125, 0.8800, 0.4900, 0.4512, 0.5600, 0.6275, 0.5517],
[0.6186, 0.4154, 0.6825, 0.2633, 0.4150, 0.2300, 0.5713, 0.5517],
[0.6264, 0.4067, 0.9050, 0.4183, 0.3775, 0.4600, 0.6308, 0.4862],
[0.6201, 0.4036, 0.8596, 0.3850, 0.3492, 0.3785, 0.5978, 0.5131]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6005, 0.3883, 0.7376, 0.2639, 0.3651, 0.2618, 0.5934, 0.5770],
[0.5534, 0.3800, 0.8344, 0.2513, 0.5063, 0.2552, 0.7289, 0.5471],
[0.6056, 0.3878, 0.8910, 0.4077, 0.4137, 0.2377, 0.5669, 0.5622],
[0.6107, 0.3752, 0.8548, 0.4358, 0.3673, 0.5117, 0.5738, 0.5285],
[0.5490, 0.3539, 0.8691, 0.4588, 0.4263, 0.5274, 0.5895, 0.5428],
[0.5000, 0.3380, 0.6937, 0.2551, 0.4053, 0.2099, 0.5916, 0.5737],
[0.5854, 0.3727, 0.8872, 0.4041, 0.3371, 0.4301, 0.6151, 0.5077],
[0.6438, 0.4108, 0.8618, 0.3766, 0.3392, 0.3494, 0.5652, 0.5354]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6193, 0.4108, 0.7425, 0.2350, 0.3887, 0.2750, 0.5900, 0.5717],
[0.6300, 0.4133, 0.8537, 0.2167, 0.5587, 0.2250, 0.7390, 0.5413],
[0.6226, 0.4098, 0.8913, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098],
[0.6226, 0.4125, 0.8800, 0.4900, 0.4512, 0.5600, 0.6275, 0.5517],
[0.6186, 0.4154, 0.6825, 0.2633, 0.4150, 0.2300, 0.5713, 0.5517],
[0.6264, 0.4067, 0.9050, 0.4183, 0.3775, 0.4600, 0.6308, 0.4862],
[0.6201, 0.4036, 0.8596, 0.3850, 0.3492, 0.3785, 0.5978, 0.5131]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.14473954314598814
step: 79
running loss: 0.0018321461157720018
Train Steps: 79/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6100, 0.4016, 0.8600, 0.5067, 0.4612, 0.5233, 0.5086, 0.5519],
[0.6268, 0.4094, 0.9038, 0.4300, 0.3700, 0.3483, 0.6262, 0.5167],
[0.6132, 0.4066, 0.7259, 0.2402, 0.3588, 0.3300, 0.6000, 0.5600],
[0.6260, 0.4161, 0.9000, 0.3833, 0.4450, 0.2133, 0.6237, 0.4986],
[0.6200, 0.4039, 0.8880, 0.4799, 0.3625, 0.4285, 0.5866, 0.5148],
[0.6246, 0.4090, 0.6964, 0.2027, 0.3925, 0.2683, 0.6088, 0.5583],
[0.6168, 0.4029, 0.8523, 0.3417, 0.3588, 0.5000, 0.6125, 0.5400],
[0.6162, 0.3949, 0.8838, 0.4517, 0.4250, 0.5183, 0.5837, 0.5500]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5663, 0.3640, 0.8650, 0.4958, 0.4625, 0.4853, 0.5205, 0.5457],
[0.6266, 0.4113, 0.8763, 0.3917, 0.3851, 0.3266, 0.6356, 0.5400],
[0.6017, 0.4096, 0.7041, 0.2273, 0.3641, 0.3217, 0.6051, 0.5864],
[0.6583, 0.4444, 0.8952, 0.3599, 0.4401, 0.2048, 0.6525, 0.5195],
[0.5728, 0.3495, 0.8861, 0.4576, 0.3689, 0.3999, 0.5798, 0.5363],
[0.6590, 0.4320, 0.6928, 0.2192, 0.3806, 0.2505, 0.6148, 0.5537],
[0.6123, 0.3829, 0.8421, 0.3424, 0.3509, 0.4881, 0.6346, 0.5532],
[0.5733, 0.3608, 0.9131, 0.4369, 0.4142, 0.5019, 0.5784, 0.5521]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6100, 0.4016, 0.8600, 0.5067, 0.4613, 0.5233, 0.5086, 0.5519],
[0.6268, 0.4094, 0.9038, 0.4300, 0.3700, 0.3483, 0.6263, 0.5167],
[0.6132, 0.4066, 0.7259, 0.2402, 0.3587, 0.3300, 0.6000, 0.5600],
[0.6260, 0.4161, 0.9000, 0.3833, 0.4450, 0.2133, 0.6237, 0.4986],
[0.6201, 0.4039, 0.8880, 0.4799, 0.3625, 0.4285, 0.5866, 0.5148],
[0.6246, 0.4090, 0.6964, 0.2027, 0.3925, 0.2683, 0.6087, 0.5583],
[0.6168, 0.4029, 0.8523, 0.3417, 0.3587, 0.5000, 0.6125, 0.5400],
[0.6162, 0.3949, 0.8838, 0.4517, 0.4250, 0.5183, 0.5838, 0.5500]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.14520067651756108
step: 80
running loss: 0.0018150084564695136
Train Steps: 80/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6272, 0.4071, 0.8738, 0.5600, 0.3675, 0.3783, 0.5926, 0.4742],
[0.6182, 0.3967, 0.8263, 0.3065, 0.3526, 0.4161, 0.6192, 0.5290],
[0.6076, 0.3958, 0.8700, 0.4667, 0.4546, 0.5046, 0.5231, 0.4960],
[0.6268, 0.4102, 0.8938, 0.3667, 0.4025, 0.2833, 0.6275, 0.5183],
[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150],
[0.6128, 0.4118, 0.8638, 0.5333, 0.4625, 0.5267, 0.5193, 0.5475],
[0.6173, 0.4013, 0.8713, 0.4640, 0.4800, 0.5700, 0.6025, 0.5600],
[0.6299, 0.4008, 0.8450, 0.5350, 0.4213, 0.5000, 0.6350, 0.5100]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7075, 0.4653, 0.8551, 0.4899, 0.3809, 0.3419, 0.6343, 0.4962],
[0.7156, 0.4710, 0.7829, 0.2770, 0.3385, 0.3715, 0.6403, 0.5497],
[0.6334, 0.4071, 0.8531, 0.3993, 0.4389, 0.4503, 0.5759, 0.5201],
[0.6304, 0.4207, 0.8709, 0.3307, 0.4067, 0.2475, 0.6356, 0.5532],
[0.5920, 0.3828, 0.8642, 0.4004, 0.4326, 0.5304, 0.6126, 0.5525],
[0.6249, 0.4180, 0.8541, 0.4851, 0.4458, 0.4441, 0.5536, 0.5530],
[0.4778, 0.3300, 0.8495, 0.3993, 0.4294, 0.5057, 0.6012, 0.5509],
[0.5924, 0.4014, 0.8258, 0.4693, 0.4127, 0.4612, 0.6556, 0.5125]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6272, 0.4071, 0.8737, 0.5600, 0.3675, 0.3783, 0.5926, 0.4742],
[0.6182, 0.3967, 0.8263, 0.3065, 0.3526, 0.4161, 0.6192, 0.5290],
[0.6076, 0.3958, 0.8700, 0.4667, 0.4546, 0.5046, 0.5231, 0.4960],
[0.6268, 0.4102, 0.8938, 0.3667, 0.4025, 0.2833, 0.6275, 0.5183],
[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150],
[0.6128, 0.4118, 0.8637, 0.5333, 0.4625, 0.5267, 0.5193, 0.5475],
[0.6173, 0.4013, 0.8713, 0.4640, 0.4800, 0.5700, 0.6025, 0.5600],
[0.6299, 0.4008, 0.8450, 0.5350, 0.4212, 0.5000, 0.6350, 0.5100]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.1471182822715491
step: 81
running loss: 0.0018162750897722112
Train Steps: 81/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6117, 0.4018, 0.6562, 0.1967, 0.3738, 0.2550, 0.5280, 0.5103],
[0.6161, 0.4024, 0.8838, 0.4583, 0.3688, 0.3733, 0.5311, 0.5344],
[ nan, nan, 0.7412, 0.2200, 0.4450, 0.1517, 0.5312, 0.4983],
[0.6053, 0.4035, 0.6897, 0.1916, 0.4000, 0.2117, 0.5440, 0.5168],
[0.6165, 0.4106, 0.7575, 0.1733, 0.3838, 0.2650, 0.5680, 0.5116],
[0.6203, 0.4096, 0.8862, 0.4267, 0.3538, 0.4117, 0.6025, 0.5650],
[0.6166, 0.4008, 0.8563, 0.5667, 0.4388, 0.4933, 0.5575, 0.5567],
[0.6179, 0.4118, 0.7278, 0.4237, 0.3588, 0.3400, 0.5675, 0.5917]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6829, 0.4525, 0.6718, 0.2448, 0.4178, 0.2707, 0.5433, 0.5212],
[0.6605, 0.4421, 0.9349, 0.4715, 0.4095, 0.4238, 0.5632, 0.5242],
[0.1362, 0.0846, 0.7230, 0.2268, 0.4773, 0.2087, 0.5771, 0.5049],
[0.7012, 0.4477, 0.6752, 0.2197, 0.4411, 0.2342, 0.5737, 0.5244],
[0.7194, 0.4713, 0.7563, 0.2293, 0.4259, 0.2597, 0.6057, 0.4829],
[0.5869, 0.3943, 0.9245, 0.4066, 0.3863, 0.4469, 0.6174, 0.5767],
[0.6784, 0.4460, 0.8884, 0.5537, 0.4868, 0.5206, 0.5965, 0.5378],
[0.6576, 0.4474, 0.7983, 0.4115, 0.3844, 0.3781, 0.5655, 0.5796]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6116, 0.4018, 0.6562, 0.1967, 0.3738, 0.2550, 0.5280, 0.5103],
[0.6161, 0.4024, 0.8838, 0.4583, 0.3688, 0.3733, 0.5311, 0.5344],
[0.0000, 0.0000, 0.7412, 0.2200, 0.4450, 0.1517, 0.5312, 0.4983],
[0.6054, 0.4035, 0.6897, 0.1916, 0.4000, 0.2117, 0.5440, 0.5168],
[0.6165, 0.4106, 0.7575, 0.1733, 0.3837, 0.2650, 0.5680, 0.5116],
[0.6203, 0.4096, 0.8863, 0.4267, 0.3537, 0.4117, 0.6025, 0.5650],
[0.6166, 0.4008, 0.8562, 0.5667, 0.4387, 0.4933, 0.5575, 0.5567],
[0.6179, 0.4118, 0.7278, 0.4237, 0.3587, 0.3400, 0.5675, 0.5917]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.1490206648595631
step: 82
running loss: 0.0018173251812141843
Train Steps: 82/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6222, 0.4169, 0.8638, 0.5650, 0.4313, 0.4783, 0.5637, 0.5633],
[0.6198, 0.4115, 0.7762, 0.2717, 0.3713, 0.3200, 0.5837, 0.5683],
[0.6198, 0.4101, 0.8838, 0.5283, 0.3763, 0.5267, 0.5913, 0.5567],
[0.6201, 0.4029, 0.8776, 0.4602, 0.3683, 0.4203, 0.5938, 0.5450],
[0.6086, 0.3998, 0.8788, 0.4450, 0.4025, 0.4650, 0.5306, 0.5103],
[0.6339, 0.4102, 0.9088, 0.4767, 0.3925, 0.5283, 0.7509, 0.5390],
[0.6125, 0.3983, 0.8750, 0.4867, 0.4275, 0.4783, 0.5413, 0.5717],
[0.6272, 0.4120, 0.9038, 0.4117, 0.3725, 0.3200, 0.6175, 0.5250]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6113, 0.4148, 0.8368, 0.5495, 0.4525, 0.4887, 0.5821, 0.5630],
[0.6829, 0.4633, 0.7749, 0.2959, 0.3903, 0.3291, 0.5708, 0.5146],
[0.6550, 0.4410, 0.8355, 0.5153, 0.4186, 0.5387, 0.5706, 0.5386],
[0.6351, 0.4176, 0.8367, 0.4638, 0.4074, 0.4470, 0.5879, 0.5185],
[0.5865, 0.3998, 0.8404, 0.4334, 0.4042, 0.4874, 0.5415, 0.4974],
[0.6618, 0.4470, 0.8834, 0.4661, 0.4353, 0.5668, 0.7026, 0.5230],
[0.6311, 0.4185, 0.8328, 0.4574, 0.4471, 0.4798, 0.5398, 0.5308],
[0.6300, 0.4266, 0.8661, 0.3974, 0.4017, 0.3521, 0.6201, 0.4980]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6222, 0.4169, 0.8637, 0.5650, 0.4313, 0.4783, 0.5638, 0.5633],
[0.6198, 0.4115, 0.7763, 0.2717, 0.3713, 0.3200, 0.5838, 0.5683],
[0.6198, 0.4101, 0.8838, 0.5283, 0.3762, 0.5267, 0.5913, 0.5567],
[0.6201, 0.4029, 0.8776, 0.4602, 0.3683, 0.4203, 0.5938, 0.5450],
[0.6086, 0.3998, 0.8788, 0.4450, 0.4025, 0.4650, 0.5306, 0.5103],
[0.6339, 0.4102, 0.9087, 0.4767, 0.3925, 0.5283, 0.7509, 0.5390],
[0.6125, 0.3983, 0.8750, 0.4867, 0.4275, 0.4783, 0.5412, 0.5717],
[0.6272, 0.4120, 0.9038, 0.4117, 0.3725, 0.3200, 0.6175, 0.5250]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.14975211105775088
step: 83
running loss: 0.001804242301900613
Train Steps: 83/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6143, 0.4040, 0.8237, 0.3333, 0.4075, 0.2117, 0.5137, 0.4973],
[0.6129, 0.3925, 0.8720, 0.5246, 0.4534, 0.5515, 0.6026, 0.5114],
[0.6114, 0.4018, 0.7213, 0.1967, 0.3763, 0.2700, 0.5875, 0.5533],
[0.6198, 0.4164, 0.8700, 0.5067, 0.4625, 0.5650, 0.5464, 0.5197],
[0.6075, 0.4000, 0.8513, 0.5183, 0.4510, 0.5329, 0.5180, 0.5280],
[0.6127, 0.4084, 0.8700, 0.4467, 0.3987, 0.4317, 0.5013, 0.5471],
[0.6026, 0.3979, 0.8550, 0.4233, 0.3613, 0.5233, 0.5582, 0.4967],
[0.6198, 0.4114, 0.8263, 0.3283, 0.3550, 0.3583, 0.5813, 0.5667]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6903, 0.4541, 0.8041, 0.3519, 0.4225, 0.2267, 0.5705, 0.4859],
[0.5929, 0.3934, 0.8567, 0.5297, 0.4653, 0.5290, 0.6259, 0.4991],
[0.6601, 0.4450, 0.6932, 0.2327, 0.3852, 0.2471, 0.6020, 0.5289],
[0.5416, 0.3797, 0.8674, 0.5292, 0.4690, 0.5223, 0.5841, 0.5070],
[0.5711, 0.3844, 0.8338, 0.5346, 0.4663, 0.5404, 0.5545, 0.5090],
[0.6060, 0.4009, 0.8575, 0.4630, 0.3739, 0.4338, 0.4998, 0.5272],
[0.6225, 0.3925, 0.8570, 0.4345, 0.3532, 0.4917, 0.6009, 0.5021],
[0.6001, 0.4009, 0.8238, 0.3495, 0.3516, 0.3660, 0.5789, 0.5336]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6143, 0.4040, 0.8238, 0.3333, 0.4075, 0.2117, 0.5137, 0.4973],
[0.6129, 0.3925, 0.8720, 0.5246, 0.4534, 0.5515, 0.6026, 0.5114],
[0.6114, 0.4018, 0.7212, 0.1967, 0.3762, 0.2700, 0.5875, 0.5533],
[0.6198, 0.4164, 0.8700, 0.5067, 0.4625, 0.5650, 0.5464, 0.5197],
[0.6075, 0.4000, 0.8512, 0.5183, 0.4510, 0.5329, 0.5180, 0.5280],
[0.6127, 0.4084, 0.8700, 0.4467, 0.3988, 0.4317, 0.5013, 0.5471],
[0.6026, 0.3979, 0.8550, 0.4233, 0.3613, 0.5233, 0.5582, 0.4967],
[0.6198, 0.4114, 0.8263, 0.3283, 0.3550, 0.3583, 0.5813, 0.5667]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.15045929490588605
step: 84
running loss: 0.0017911820822129293
Train Steps: 84/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6197, 0.4091, 0.8800, 0.4783, 0.3538, 0.4767, 0.5950, 0.5550],
[0.6072, 0.4029, 0.7037, 0.2150, 0.3912, 0.2267, 0.5516, 0.5507],
[0.6150, 0.4097, 0.7468, 0.3194, 0.3825, 0.2633, 0.5463, 0.5800],
[0.6236, 0.4084, 0.7738, 0.2133, 0.3663, 0.3233, 0.5813, 0.5567],
[0.6329, 0.4175, 0.8550, 0.2333, 0.5425, 0.2250, 0.7398, 0.5609],
[0.6137, 0.4084, 0.8076, 0.3889, 0.3650, 0.3150, 0.5356, 0.5896],
[0.6234, 0.4179, 0.7825, 0.3450, 0.3813, 0.2867, 0.5675, 0.5617],
[0.6212, 0.4159, 0.8675, 0.5783, 0.4088, 0.4317, 0.5613, 0.5917]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5609, 0.3478, 0.9110, 0.5086, 0.3812, 0.5075, 0.5569, 0.5241],
[0.6739, 0.4449, 0.7094, 0.2639, 0.4078, 0.2612, 0.5407, 0.5280],
[0.5018, 0.3333, 0.7566, 0.3187, 0.3691, 0.3055, 0.4783, 0.5424],
[0.6060, 0.4071, 0.7797, 0.2923, 0.3817, 0.3736, 0.5510, 0.5038],
[0.6098, 0.4134, 0.8727, 0.2888, 0.5322, 0.2752, 0.7309, 0.5040],
[0.5934, 0.3906, 0.8474, 0.4316, 0.3445, 0.3416, 0.5021, 0.5575],
[0.5262, 0.3429, 0.8057, 0.3826, 0.3886, 0.3141, 0.5591, 0.5266],
[0.5721, 0.3836, 0.8637, 0.6086, 0.4031, 0.4786, 0.5398, 0.5554]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6197, 0.4091, 0.8800, 0.4783, 0.3537, 0.4767, 0.5950, 0.5550],
[0.6072, 0.4029, 0.7038, 0.2150, 0.3913, 0.2267, 0.5516, 0.5507],
[0.6150, 0.4097, 0.7468, 0.3194, 0.3825, 0.2633, 0.5462, 0.5800],
[0.6236, 0.4084, 0.7738, 0.2133, 0.3663, 0.3233, 0.5813, 0.5567],
[0.6329, 0.4175, 0.8550, 0.2333, 0.5425, 0.2250, 0.7398, 0.5609],
[0.6137, 0.4084, 0.8076, 0.3889, 0.3650, 0.3150, 0.5356, 0.5896],
[0.6234, 0.4179, 0.7825, 0.3450, 0.3812, 0.2867, 0.5675, 0.5617],
[0.6212, 0.4159, 0.8675, 0.5783, 0.4087, 0.4317, 0.5612, 0.5917]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.15215556626208127
step: 85
running loss: 0.0017900654854362502
Train Steps: 85/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6329, 0.4175, 0.8550, 0.2333, 0.5425, 0.2250, 0.7398, 0.5609],
[0.6229, 0.4086, 0.7538, 0.2600, 0.4775, 0.1617, 0.5900, 0.5383],
[0.6230, 0.4152, 0.7588, 0.2283, 0.4012, 0.2883, 0.6200, 0.5767],
[0.6268, 0.4094, 0.9038, 0.4300, 0.3700, 0.3483, 0.6262, 0.5167],
[0.6261, 0.4131, 0.8938, 0.3550, 0.4000, 0.2683, 0.6188, 0.5283],
[ nan, nan, 0.7512, 0.2117, 0.4288, 0.2000, 0.5600, 0.5617],
[ nan, nan, 0.7192, 0.2346, 0.4037, 0.2050, 0.5138, 0.5650],
[0.6130, 0.4072, 0.8550, 0.4567, 0.3638, 0.3667, 0.5290, 0.5892]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6643, 0.4457, 0.8618, 0.2849, 0.5180, 0.2876, 0.6996, 0.5425],
[0.7646, 0.5065, 0.7449, 0.2939, 0.4197, 0.1968, 0.5505, 0.5345],
[0.6854, 0.4418, 0.7921, 0.3072, 0.3834, 0.3308, 0.5712, 0.5596],
[0.6527, 0.4247, 0.8917, 0.4491, 0.3591, 0.4004, 0.5751, 0.5346],
[0.6775, 0.4342, 0.9259, 0.4055, 0.3780, 0.2888, 0.5830, 0.5323],
[0.2793, 0.1801, 0.7538, 0.2756, 0.4184, 0.2544, 0.5126, 0.5533],
[0.0762, 0.0398, 0.7043, 0.2500, 0.3781, 0.2918, 0.4472, 0.5579],
[0.6697, 0.4160, 0.8804, 0.4967, 0.3482, 0.4281, 0.4500, 0.5749]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6329, 0.4175, 0.8550, 0.2333, 0.5425, 0.2250, 0.7398, 0.5609],
[0.6229, 0.4086, 0.7538, 0.2600, 0.4775, 0.1617, 0.5900, 0.5383],
[0.6230, 0.4152, 0.7588, 0.2283, 0.4013, 0.2883, 0.6200, 0.5767],
[0.6268, 0.4094, 0.9038, 0.4300, 0.3700, 0.3483, 0.6263, 0.5167],
[0.6261, 0.4131, 0.8938, 0.3550, 0.4000, 0.2683, 0.6187, 0.5283],
[0.0000, 0.0000, 0.7513, 0.2117, 0.4288, 0.2000, 0.5600, 0.5617],
[0.0000, 0.0000, 0.7192, 0.2346, 0.4038, 0.2050, 0.5138, 0.5650],
[0.6130, 0.4072, 0.8550, 0.4567, 0.3638, 0.3667, 0.5290, 0.5892]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0037, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0037, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.15586218307726085
step: 86
running loss: 0.0018123509660146612
Train Steps: 86/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383],
[0.6236, 0.4081, 0.8575, 0.3000, 0.3713, 0.3033, 0.5550, 0.5633],
[0.6274, 0.4117, 0.8100, 0.5801, 0.4000, 0.4583, 0.5582, 0.6118],
[0.6151, 0.4125, 0.8738, 0.4417, 0.3575, 0.3783, 0.5138, 0.5483],
[0.6120, 0.4014, 0.6863, 0.2817, 0.3700, 0.2783, 0.5513, 0.5667],
[0.6185, 0.4098, 0.8838, 0.4900, 0.4537, 0.5800, 0.6288, 0.5400],
[0.6249, 0.4138, 0.9038, 0.4517, 0.3862, 0.4917, 0.6138, 0.5333],
[0.6083, 0.3957, 0.8638, 0.4950, 0.4363, 0.5083, 0.5346, 0.4980]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5563, 0.3623, 0.9090, 0.4497, 0.4262, 0.5491, 0.6082, 0.5700],
[0.6014, 0.4059, 0.8575, 0.3241, 0.3529, 0.2868, 0.5669, 0.5697],
[0.6375, 0.4184, 0.8368, 0.5489, 0.3802, 0.4560, 0.5802, 0.6651],
[0.6058, 0.3839, 0.8531, 0.4630, 0.3414, 0.3593, 0.4970, 0.5782],
[0.5963, 0.3940, 0.7217, 0.2645, 0.3463, 0.2958, 0.5310, 0.5844],
[0.6387, 0.3952, 0.9072, 0.4854, 0.4515, 0.5408, 0.5929, 0.5492],
[0.6590, 0.4444, 0.8863, 0.4673, 0.3424, 0.4635, 0.6213, 0.5645],
[0.5478, 0.3320, 0.8871, 0.4691, 0.4188, 0.4898, 0.5487, 0.5225]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383],
[0.6236, 0.4081, 0.8575, 0.3000, 0.3713, 0.3033, 0.5550, 0.5633],
[0.6274, 0.4117, 0.8100, 0.5801, 0.4000, 0.4583, 0.5582, 0.6118],
[0.6151, 0.4125, 0.8737, 0.4417, 0.3575, 0.3783, 0.5138, 0.5483],
[0.6120, 0.4013, 0.6862, 0.2817, 0.3700, 0.2783, 0.5512, 0.5667],
[0.6185, 0.4098, 0.8838, 0.4900, 0.4538, 0.5800, 0.6288, 0.5400],
[0.6249, 0.4138, 0.9038, 0.4517, 0.3862, 0.4917, 0.6137, 0.5333],
[0.6083, 0.3957, 0.8637, 0.4950, 0.4363, 0.5083, 0.5346, 0.4980]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.15654120134422556
step: 87
running loss: 0.001799324153381903
Train Steps: 87/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6357, 0.4118, 0.8400, 0.2500, 0.5413, 0.1633, 0.6725, 0.5586],
[0.6236, 0.3967, 0.8675, 0.5400, 0.3862, 0.4517, 0.5825, 0.5200],
[0.6113, 0.4006, 0.8700, 0.5350, 0.3638, 0.3767, 0.5097, 0.4882],
[0.6161, 0.4099, 0.8738, 0.4383, 0.3788, 0.5483, 0.5605, 0.5019],
[0.6106, 0.4022, 0.7125, 0.2650, 0.3713, 0.2700, 0.5431, 0.5123],
[0.6125, 0.4010, 0.8650, 0.4567, 0.3663, 0.3900, 0.5600, 0.5567],
[0.6199, 0.4102, 0.8950, 0.4417, 0.4012, 0.5367, 0.6112, 0.5967],
[0.6189, 0.4033, 0.8650, 0.5267, 0.4487, 0.5150, 0.5925, 0.5050]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5790, 0.3507, 0.8852, 0.2404, 0.5145, 0.1579, 0.6487, 0.5750],
[0.5448, 0.3536, 0.8686, 0.5279, 0.3656, 0.4509, 0.5883, 0.5766],
[0.6526, 0.4043, 0.8698, 0.4957, 0.3553, 0.3628, 0.5310, 0.5696],
[0.5740, 0.3852, 0.8894, 0.4132, 0.3652, 0.5292, 0.5823, 0.5577],
[0.5861, 0.3909, 0.7450, 0.2332, 0.3718, 0.2609, 0.5354, 0.5544],
[0.5748, 0.3649, 0.8456, 0.4180, 0.3466, 0.3991, 0.5565, 0.6004],
[0.6497, 0.3969, 0.8797, 0.4306, 0.3741, 0.5402, 0.5959, 0.6054],
[0.6204, 0.3975, 0.8895, 0.4839, 0.4497, 0.4924, 0.5877, 0.5582]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6357, 0.4118, 0.8400, 0.2500, 0.5412, 0.1633, 0.6725, 0.5586],
[0.6236, 0.3967, 0.8675, 0.5400, 0.3862, 0.4517, 0.5825, 0.5200],
[0.6113, 0.4006, 0.8700, 0.5350, 0.3638, 0.3767, 0.5097, 0.4882],
[0.6161, 0.4099, 0.8737, 0.4383, 0.3787, 0.5483, 0.5605, 0.5019],
[0.6106, 0.4022, 0.7125, 0.2650, 0.3713, 0.2700, 0.5431, 0.5123],
[0.6125, 0.4010, 0.8650, 0.4567, 0.3663, 0.3900, 0.5600, 0.5567],
[0.6199, 0.4102, 0.8950, 0.4417, 0.4013, 0.5367, 0.6112, 0.5967],
[0.6189, 0.4033, 0.8650, 0.5267, 0.4487, 0.5150, 0.5925, 0.5050]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.1574872225173749
step: 88
running loss: 0.001789627528606533
Train Steps: 88/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5413, 0.5683],
[0.6201, 0.3970, 0.8413, 0.4950, 0.4413, 0.5183, 0.6088, 0.5400],
[0.6163, 0.4006, 0.8788, 0.4683, 0.3663, 0.4883, 0.5887, 0.5017],
[0.6257, 0.4024, 0.8672, 0.5422, 0.4196, 0.5198, 0.6694, 0.5204],
[0.6140, 0.4070, 0.8700, 0.5000, 0.4612, 0.4900, 0.5260, 0.5852],
[0.6218, 0.4098, 0.7238, 0.1850, 0.4238, 0.2517, 0.6288, 0.5350],
[0.6267, 0.4080, 0.8438, 0.2633, 0.4763, 0.1800, 0.6259, 0.5240],
[0.6211, 0.3993, 0.7650, 0.1933, 0.4575, 0.1550, 0.5965, 0.4895]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6563, 0.4143, 0.8711, 0.5141, 0.3567, 0.3754, 0.5637, 0.5939],
[0.4888, 0.3187, 0.8533, 0.4704, 0.4120, 0.5141, 0.5794, 0.5805],
[0.5305, 0.3432, 0.8643, 0.4474, 0.3680, 0.4902, 0.5796, 0.5600],
[0.5621, 0.3650, 0.8665, 0.5146, 0.3924, 0.5260, 0.6470, 0.5585],
[0.5229, 0.3579, 0.8662, 0.4833, 0.4403, 0.4909, 0.5109, 0.5972],
[0.6561, 0.4365, 0.7485, 0.2128, 0.4266, 0.2200, 0.5967, 0.5774],
[0.6677, 0.4292, 0.8820, 0.2452, 0.4535, 0.1810, 0.6232, 0.5437],
[0.5569, 0.3679, 0.7763, 0.1875, 0.4438, 0.1674, 0.5821, 0.5393]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5412, 0.5683],
[0.6201, 0.3970, 0.8413, 0.4950, 0.4412, 0.5183, 0.6087, 0.5400],
[0.6163, 0.4006, 0.8788, 0.4683, 0.3663, 0.4883, 0.5888, 0.5017],
[0.6257, 0.4024, 0.8672, 0.5422, 0.4196, 0.5198, 0.6694, 0.5204],
[0.6140, 0.4070, 0.8700, 0.5000, 0.4613, 0.4900, 0.5260, 0.5852],
[0.6218, 0.4098, 0.7237, 0.1850, 0.4238, 0.2517, 0.6288, 0.5350],
[0.6267, 0.4080, 0.8438, 0.2633, 0.4762, 0.1800, 0.6259, 0.5240],
[0.6211, 0.3993, 0.7650, 0.1933, 0.4575, 0.1550, 0.5965, 0.4895]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.15884605079190806
step: 89
running loss: 0.0017847870875495287
Train Steps: 89/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6248, 0.4032, 0.7738, 0.1900, 0.4813, 0.1400, 0.5941, 0.4904],
[0.6130, 0.4072, 0.8550, 0.4567, 0.3638, 0.3667, 0.5290, 0.5892],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5413, 0.5683],
[0.6171, 0.4127, 0.8900, 0.4800, 0.4325, 0.5783, 0.5769, 0.5090],
[0.6284, 0.4093, 0.8900, 0.4700, 0.3650, 0.3850, 0.6212, 0.5167],
[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758],
[ nan, nan, 0.6859, 0.2194, 0.4150, 0.1867, 0.5153, 0.5729],
[0.6282, 0.4092, 0.8000, 0.2183, 0.4500, 0.2383, 0.6787, 0.5364]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5701, 0.3899, 0.7749, 0.2235, 0.4891, 0.1285, 0.6125, 0.5358],
[0.6624, 0.4344, 0.8536, 0.4378, 0.3787, 0.3752, 0.5085, 0.5879],
[0.6781, 0.4539, 0.8667, 0.5125, 0.3853, 0.3703, 0.5882, 0.5832],
[0.6412, 0.4408, 0.9126, 0.4809, 0.4415, 0.5653, 0.5623, 0.5423],
[0.6393, 0.4321, 0.8859, 0.4558, 0.3700, 0.3787, 0.6376, 0.5289],
[0.5884, 0.4076, 0.9018, 0.4764, 0.4055, 0.5284, 0.6674, 0.5022],
[0.1344, 0.0866, 0.6973, 0.2091, 0.4333, 0.1891, 0.5127, 0.5675],
[0.6251, 0.4193, 0.7968, 0.2227, 0.4558, 0.2134, 0.6566, 0.5755]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6248, 0.4032, 0.7738, 0.1900, 0.4812, 0.1400, 0.5941, 0.4904],
[0.6130, 0.4072, 0.8550, 0.4567, 0.3638, 0.3667, 0.5290, 0.5892],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5412, 0.5683],
[0.6171, 0.4127, 0.8900, 0.4800, 0.4325, 0.5783, 0.5769, 0.5090],
[0.6284, 0.4092, 0.8900, 0.4700, 0.3650, 0.3850, 0.6212, 0.5167],
[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758],
[0.0000, 0.0000, 0.6859, 0.2194, 0.4150, 0.1867, 0.5153, 0.5729],
[0.6282, 0.4092, 0.8000, 0.2183, 0.4500, 0.2383, 0.6787, 0.5364]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.1597334560356103
step: 90
running loss: 0.0017748161781734476
Valid Steps: 10/10 Loss: nan 1.0033
--------------------------------------------------
Epoch: 3 Train Loss: 0.0018 Valid Loss: nan
--------------------------------------------------
size of train loader is: 90
torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6069, 0.3975, 0.8625, 0.5083, 0.4388, 0.5483, 0.5650, 0.4967],
[0.6164, 0.4119, 0.7913, 0.2650, 0.3538, 0.3500, 0.5614, 0.5038],
[0.6277, 0.4057, 0.8300, 0.2650, 0.4363, 0.1850, 0.6140, 0.4823],
[0.6211, 0.4069, 0.8750, 0.5117, 0.4150, 0.4900, 0.5875, 0.5167],
[0.6199, 0.4112, 0.8475, 0.3717, 0.3550, 0.4350, 0.6063, 0.6083],
[0.6101, 0.4042, 0.7775, 0.2617, 0.3713, 0.2817, 0.5440, 0.5650],
[0.6130, 0.4072, 0.8550, 0.4567, 0.3638, 0.3667, 0.5290, 0.5892],
[0.6031, 0.3986, 0.7462, 0.2833, 0.3638, 0.2717, 0.5253, 0.4726]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5968, 0.4003, 0.8611, 0.5263, 0.4863, 0.5078, 0.5804, 0.5099],
[0.5379, 0.3639, 0.7909, 0.2545, 0.3858, 0.3378, 0.6020, 0.4907],
[0.5206, 0.3413, 0.8314, 0.2572, 0.4827, 0.1848, 0.6728, 0.4873],
[0.6144, 0.4080, 0.8864, 0.5306, 0.4392, 0.4873, 0.6470, 0.5047],
[0.6072, 0.4264, 0.8403, 0.3939, 0.3851, 0.4020, 0.6346, 0.5666],
[0.5697, 0.3890, 0.7807, 0.2813, 0.4378, 0.2358, 0.5794, 0.5491],
[0.6462, 0.4159, 0.8569, 0.4667, 0.4047, 0.3509, 0.5302, 0.5521],
[0.5676, 0.3707, 0.7575, 0.2766, 0.4180, 0.2593, 0.5911, 0.4781]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6069, 0.3975, 0.8625, 0.5083, 0.4387, 0.5483, 0.5650, 0.4967],
[0.6164, 0.4119, 0.7912, 0.2650, 0.3537, 0.3500, 0.5614, 0.5038],
[0.6277, 0.4056, 0.8300, 0.2650, 0.4363, 0.1850, 0.6140, 0.4823],
[0.6211, 0.4069, 0.8750, 0.5117, 0.4150, 0.4900, 0.5875, 0.5167],
[0.6199, 0.4112, 0.8475, 0.3717, 0.3550, 0.4350, 0.6062, 0.6083],
[0.6101, 0.4042, 0.7775, 0.2617, 0.3713, 0.2817, 0.5440, 0.5650],
[0.6130, 0.4072, 0.8550, 0.4567, 0.3638, 0.3667, 0.5290, 0.5892],
[0.6031, 0.3986, 0.7462, 0.2833, 0.3638, 0.2717, 0.5253, 0.4726]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0011329366825520992
step: 1
running loss: 0.0011329366825520992
Train Steps: 1/90 Loss: 0.0011 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6203, 0.4021, 0.8780, 0.5031, 0.3667, 0.3882, 0.5842, 0.5405],
[0.6128, 0.4116, 0.8450, 0.4583, 0.3675, 0.4867, 0.5337, 0.5446],
[0.6197, 0.3930, 0.8793, 0.4736, 0.4152, 0.5464, 0.6308, 0.5235],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3513, 0.4050, 0.6112, 0.5500],
[0.6214, 0.4112, 0.7838, 0.2117, 0.3650, 0.3133, 0.5675, 0.5083],
[0.6200, 0.4098, 0.8237, 0.2917, 0.4012, 0.2967, 0.6000, 0.5683],
[0.6289, 0.4081, 0.8720, 0.3487, 0.3900, 0.3183, 0.6703, 0.5376],
[0.6165, 0.4106, 0.7575, 0.1733, 0.3838, 0.2650, 0.5680, 0.5116]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6306, 0.3991, 0.8891, 0.5327, 0.4077, 0.3841, 0.5966, 0.4759],
[0.5868, 0.3788, 0.8220, 0.5059, 0.4200, 0.4516, 0.5521, 0.5059],
[0.5743, 0.3819, 0.8683, 0.4992, 0.4607, 0.5130, 0.6418, 0.4970],
[0.5523, 0.3709, 0.7587, 0.2767, 0.3894, 0.3869, 0.5942, 0.5189],
[0.5849, 0.3792, 0.7901, 0.2298, 0.3933, 0.2529, 0.5977, 0.4827],
[0.6309, 0.4188, 0.8185, 0.3005, 0.4504, 0.2756, 0.6154, 0.5288],
[0.6407, 0.4076, 0.8784, 0.3673, 0.4201, 0.2635, 0.6971, 0.5146],
[0.5239, 0.3321, 0.7461, 0.2019, 0.4320, 0.2133, 0.5811, 0.4603]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6203, 0.4020, 0.8780, 0.5031, 0.3667, 0.3882, 0.5842, 0.5405],
[0.6128, 0.4116, 0.8450, 0.4583, 0.3675, 0.4867, 0.5337, 0.5446],
[0.6197, 0.3930, 0.8793, 0.4736, 0.4152, 0.5464, 0.6308, 0.5235],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3512, 0.4050, 0.6112, 0.5500],
[0.6214, 0.4112, 0.7837, 0.2117, 0.3650, 0.3133, 0.5675, 0.5083],
[0.6200, 0.4098, 0.8238, 0.2917, 0.4013, 0.2967, 0.6000, 0.5683],
[0.6289, 0.4081, 0.8720, 0.3487, 0.3900, 0.3183, 0.6703, 0.5376],
[0.6165, 0.4106, 0.7575, 0.1733, 0.3837, 0.2650, 0.5680, 0.5116]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0023326061200350523
step: 2
running loss: 0.0011663030600175261
Train Steps: 2/90 Loss: 0.0012 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6207, 0.4081, 0.7662, 0.2067, 0.3962, 0.3200, 0.6312, 0.5300],
[0.6271, 0.4040, 0.9000, 0.3250, 0.4938, 0.2300, 0.7192, 0.5413],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3788, 0.4900, 0.7121, 0.5864],
[0.6332, 0.4118, 0.9238, 0.4267, 0.4012, 0.4733, 0.7525, 0.5436],
[0.6250, 0.4103, 0.8950, 0.4400, 0.3912, 0.5650, 0.6050, 0.5133],
[ nan, nan, 0.6900, 0.1917, 0.3937, 0.2367, 0.5240, 0.5246],
[0.6160, 0.4086, 0.8775, 0.3983, 0.3750, 0.3783, 0.5128, 0.4882],
[0.6300, 0.4133, 0.8538, 0.2167, 0.5587, 0.2250, 0.7390, 0.5413]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5860, 0.3922, 0.7268, 0.2220, 0.3817, 0.2936, 0.5812, 0.4967],
[0.4988, 0.3249, 0.8917, 0.3148, 0.4922, 0.2506, 0.6934, 0.4801],
[0.7497, 0.4933, 0.8419, 0.5241, 0.3644, 0.4834, 0.6657, 0.5144],
[0.7188, 0.4813, 0.8878, 0.4690, 0.3864, 0.4804, 0.6865, 0.5008],
[0.7292, 0.4875, 0.8690, 0.4671, 0.3839, 0.5779, 0.5837, 0.4822],
[0.0061, 0.0024, 0.7012, 0.2367, 0.3962, 0.2293, 0.4864, 0.4885],
[0.7251, 0.4817, 0.8466, 0.4170, 0.3446, 0.3731, 0.5056, 0.4686],
[0.6953, 0.4570, 0.8304, 0.2385, 0.5326, 0.2588, 0.6773, 0.4800]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6207, 0.4081, 0.7663, 0.2067, 0.3963, 0.3200, 0.6313, 0.5300],
[0.6271, 0.4040, 0.9000, 0.3250, 0.4938, 0.2300, 0.7192, 0.5413],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3787, 0.4900, 0.7121, 0.5864],
[0.6332, 0.4118, 0.9237, 0.4267, 0.4013, 0.4733, 0.7525, 0.5436],
[0.6250, 0.4103, 0.8950, 0.4400, 0.3913, 0.5650, 0.6050, 0.5133],
[0.0000, 0.0000, 0.6900, 0.1917, 0.3938, 0.2367, 0.5240, 0.5246],
[0.6160, 0.4086, 0.8775, 0.3983, 0.3750, 0.3783, 0.5128, 0.4882],
[0.6300, 0.4133, 0.8537, 0.2167, 0.5587, 0.2250, 0.7390, 0.5413]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0023, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0023, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.004649204900488257
step: 3
running loss: 0.0015497349668294191
Train Steps: 3/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6260, 0.4253, 0.8938, 0.4400, 0.3675, 0.3650, 0.5675, 0.5767],
[0.6300, 0.4133, 0.8538, 0.2167, 0.5587, 0.2250, 0.7390, 0.5413],
[0.6151, 0.4125, 0.8738, 0.4417, 0.3575, 0.3783, 0.5138, 0.5483],
[0.6099, 0.4030, 0.8638, 0.5117, 0.4983, 0.4965, 0.5086, 0.5388],
[0.6211, 0.3935, 0.8636, 0.4841, 0.4417, 0.5126, 0.6331, 0.5268],
[0.6086, 0.3940, 0.8712, 0.4783, 0.4025, 0.4900, 0.5498, 0.5390],
[0.6142, 0.3982, 0.8650, 0.4883, 0.3912, 0.4317, 0.5315, 0.5350],
[0.6267, 0.4065, 0.8313, 0.2467, 0.4788, 0.1733, 0.6312, 0.5133]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6228, 0.4140, 0.8659, 0.4301, 0.3465, 0.3910, 0.6165, 0.5447],
[0.6294, 0.4215, 0.8306, 0.2009, 0.5087, 0.2778, 0.7287, 0.4982],
[0.5685, 0.3807, 0.8171, 0.4263, 0.3248, 0.3840, 0.5332, 0.5097],
[0.6234, 0.4169, 0.8464, 0.4805, 0.4680, 0.4954, 0.5454, 0.4970],
[0.6373, 0.4156, 0.8276, 0.4305, 0.3745, 0.5263, 0.6380, 0.4825],
[0.5885, 0.3843, 0.8212, 0.4443, 0.3774, 0.5082, 0.5607, 0.4995],
[0.5832, 0.3737, 0.8340, 0.4706, 0.3457, 0.4484, 0.5524, 0.4831],
[0.6135, 0.4110, 0.8132, 0.1869, 0.4392, 0.1840, 0.6581, 0.4998]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6260, 0.4253, 0.8938, 0.4400, 0.3675, 0.3650, 0.5675, 0.5767],
[0.6300, 0.4133, 0.8537, 0.2167, 0.5587, 0.2250, 0.7390, 0.5413],
[0.6151, 0.4125, 0.8737, 0.4417, 0.3575, 0.3783, 0.5138, 0.5483],
[0.6098, 0.4030, 0.8637, 0.5117, 0.4983, 0.4965, 0.5086, 0.5388],
[0.6211, 0.3935, 0.8636, 0.4841, 0.4417, 0.5126, 0.6331, 0.5268],
[0.6086, 0.3940, 0.8712, 0.4783, 0.4025, 0.4900, 0.5498, 0.5390],
[0.6143, 0.3982, 0.8650, 0.4883, 0.3913, 0.4317, 0.5315, 0.5350],
[0.6266, 0.4065, 0.8313, 0.2467, 0.4787, 0.1733, 0.6313, 0.5133]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.00562284019542858
step: 4
running loss: 0.001405710048857145
Train Steps: 4/90 Loss: 0.0014 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6199, 0.4015, 0.8716, 0.5228, 0.3833, 0.4772, 0.5883, 0.5148],
[ nan, nan, 0.8488, 0.2300, 0.5563, 0.2100, 0.7390, 0.5679],
[0.6201, 0.4004, 0.8786, 0.5043, 0.3833, 0.5138, 0.5997, 0.5092],
[0.6364, 0.4154, 0.8938, 0.3717, 0.4500, 0.2583, 0.6448, 0.5285],
[0.6185, 0.4080, 0.8625, 0.3483, 0.3788, 0.2650, 0.5320, 0.5272],
[ nan, nan, 0.6688, 0.2513, 0.4113, 0.2117, 0.5193, 0.5933],
[0.6201, 0.4098, 0.8575, 0.3617, 0.3700, 0.3550, 0.5988, 0.5667],
[0.6109, 0.4041, 0.6975, 0.3167, 0.3513, 0.3383, 0.5153, 0.5319]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6993, 0.4755, 0.8851, 0.5005, 0.3740, 0.4976, 0.6179, 0.5072],
[0.4512, 0.3040, 0.8451, 0.2089, 0.4832, 0.2711, 0.7245, 0.5286],
[0.6676, 0.4357, 0.8666, 0.4902, 0.3854, 0.5505, 0.5973, 0.4928],
[0.6404, 0.4130, 0.8976, 0.3328, 0.4247, 0.2651, 0.6338, 0.5441],
[0.6596, 0.4259, 0.8557, 0.3324, 0.3837, 0.2897, 0.5354, 0.5428],
[0.2002, 0.1357, 0.6766, 0.1868, 0.3779, 0.2244, 0.5412, 0.5682],
[0.6832, 0.4638, 0.8442, 0.3196, 0.3664, 0.3608, 0.6115, 0.5717],
[0.5639, 0.3835, 0.7373, 0.2500, 0.3418, 0.3510, 0.5388, 0.5312]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6199, 0.4015, 0.8716, 0.5228, 0.3833, 0.4772, 0.5883, 0.5148],
[0.0000, 0.0000, 0.8487, 0.2300, 0.5562, 0.2100, 0.7390, 0.5679],
[0.6201, 0.4004, 0.8786, 0.5043, 0.3833, 0.5138, 0.5997, 0.5092],
[0.6364, 0.4154, 0.8938, 0.3717, 0.4500, 0.2583, 0.6448, 0.5285],
[0.6186, 0.4080, 0.8625, 0.3483, 0.3787, 0.2650, 0.5320, 0.5272],
[0.0000, 0.0000, 0.6688, 0.2513, 0.4112, 0.2117, 0.5193, 0.5933],
[0.6201, 0.4098, 0.8575, 0.3617, 0.3700, 0.3550, 0.5987, 0.5667],
[0.6109, 0.4041, 0.6975, 0.3167, 0.3512, 0.3383, 0.5153, 0.5319]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0065, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0065, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.01212452695472166
step: 5
running loss: 0.002424905390944332
Train Steps: 5/90 Loss: 0.0024 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6236, 0.3966, 0.8850, 0.4967, 0.3638, 0.4017, 0.5850, 0.5183],
[0.6273, 0.4110, 0.8900, 0.3817, 0.4188, 0.2167, 0.5858, 0.4835],
[0.6188, 0.4099, 0.7400, 0.2433, 0.3962, 0.2750, 0.6162, 0.5467],
[0.6353, 0.4128, 0.9138, 0.3533, 0.4688, 0.3250, 0.7145, 0.5991],
[0.6154, 0.4048, 0.7100, 0.2067, 0.4338, 0.1667, 0.5413, 0.5220],
[0.6087, 0.3976, 0.8337, 0.3867, 0.3713, 0.3117, 0.5938, 0.5300],
[0.6226, 0.4001, 0.8438, 0.5733, 0.3862, 0.4250, 0.5750, 0.5283],
[0.6075, 0.4007, 0.8275, 0.4917, 0.4050, 0.5100, 0.5167, 0.5280]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5911, 0.3556, 0.8988, 0.4392, 0.3467, 0.4394, 0.5725, 0.5445],
[0.6665, 0.4088, 0.9202, 0.3296, 0.4442, 0.2362, 0.6043, 0.5236],
[0.5699, 0.3660, 0.7474, 0.1740, 0.3935, 0.3022, 0.5830, 0.5746],
[0.5511, 0.3537, 0.9361, 0.3323, 0.4631, 0.3199, 0.7435, 0.5976],
[0.3874, 0.2319, 0.7176, 0.1733, 0.4439, 0.1785, 0.5358, 0.5427],
[0.6752, 0.4473, 0.8615, 0.3541, 0.3713, 0.3553, 0.5935, 0.5718],
[0.5413, 0.3587, 0.8534, 0.5498, 0.3760, 0.4432, 0.5977, 0.5819],
[0.6556, 0.4265, 0.8246, 0.4529, 0.4112, 0.5356, 0.5225, 0.5649]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6236, 0.3965, 0.8850, 0.4967, 0.3638, 0.4017, 0.5850, 0.5183],
[0.6273, 0.4110, 0.8900, 0.3817, 0.4187, 0.2167, 0.5858, 0.4835],
[0.6188, 0.4099, 0.7400, 0.2433, 0.3963, 0.2750, 0.6162, 0.5467],
[0.6353, 0.4128, 0.9137, 0.3533, 0.4688, 0.3250, 0.7145, 0.5991],
[0.6154, 0.4048, 0.7100, 0.2067, 0.4338, 0.1667, 0.5413, 0.5220],
[0.6087, 0.3976, 0.8338, 0.3867, 0.3713, 0.3117, 0.5938, 0.5300],
[0.6226, 0.4001, 0.8438, 0.5733, 0.3862, 0.4250, 0.5750, 0.5283],
[0.6075, 0.4006, 0.8275, 0.4917, 0.4050, 0.5100, 0.5167, 0.5280]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0024, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0024, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.014573542110156268
step: 6
running loss: 0.0024289236850260445
Train Steps: 6/90 Loss: 0.0024 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6277, 0.4118, 0.8988, 0.3833, 0.3950, 0.2650, 0.6290, 0.4938],
[ nan, nan, 0.7648, 0.2722, 0.3962, 0.2183, 0.5060, 0.5422],
[0.6279, 0.4050, 0.8025, 0.2200, 0.4313, 0.2733, 0.6820, 0.5320],
[0.6252, 0.4158, 0.8988, 0.4083, 0.3788, 0.4783, 0.6225, 0.5633],
[0.6230, 0.4113, 0.7213, 0.1983, 0.4325, 0.2367, 0.6262, 0.5400],
[0.6296, 0.4060, 0.9100, 0.3267, 0.4726, 0.3367, 0.7446, 0.5355],
[0.6229, 0.4198, 0.7662, 0.2700, 0.4700, 0.2133, 0.5675, 0.5783],
[0.6246, 0.4126, 0.8850, 0.4833, 0.4200, 0.5350, 0.6112, 0.5250]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6546, 0.4125, 0.9096, 0.4107, 0.3861, 0.2479, 0.6083, 0.5739],
[ 0.0055, -0.0085, 0.7559, 0.2674, 0.3948, 0.2246, 0.4803, 0.5537],
[ 0.5819, 0.3834, 0.7958, 0.2445, 0.4335, 0.2698, 0.6186, 0.5927],
[ 0.7106, 0.4729, 0.9110, 0.4499, 0.3817, 0.4728, 0.6339, 0.5947],
[ 0.5566, 0.3425, 0.7486, 0.2117, 0.4368, 0.2164, 0.6001, 0.5948],
[ 0.5981, 0.3679, 0.8987, 0.3423, 0.4487, 0.3167, 0.6891, 0.5739],
[ 0.6130, 0.3963, 0.7683, 0.2571, 0.4715, 0.2283, 0.5340, 0.6134],
[ 0.6651, 0.4216, 0.9075, 0.5245, 0.4099, 0.5539, 0.5701, 0.5658]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6277, 0.4117, 0.8988, 0.3833, 0.3950, 0.2650, 0.6290, 0.4938],
[0.0000, 0.0000, 0.7648, 0.2722, 0.3963, 0.2183, 0.5060, 0.5422],
[0.6279, 0.4050, 0.8025, 0.2200, 0.4313, 0.2733, 0.6820, 0.5320],
[0.6252, 0.4158, 0.8988, 0.4083, 0.3787, 0.4783, 0.6225, 0.5633],
[0.6230, 0.4113, 0.7212, 0.1983, 0.4325, 0.2367, 0.6263, 0.5400],
[0.6296, 0.4060, 0.9100, 0.3267, 0.4726, 0.3367, 0.7446, 0.5355],
[0.6229, 0.4198, 0.7663, 0.2700, 0.4700, 0.2133, 0.5675, 0.5783],
[0.6246, 0.4126, 0.8850, 0.4833, 0.4200, 0.5350, 0.6112, 0.5250]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.015636640891898423
step: 7
running loss: 0.0022338058416997747
Train Steps: 7/90 Loss: 0.0022 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6350, 0.4144, 0.9250, 0.4100, 0.4125, 0.3750, 0.7129, 0.5945],
[0.6053, 0.4035, 0.6897, 0.1916, 0.4000, 0.2117, 0.5440, 0.5168],
[0.6202, 0.4079, 0.8025, 0.2500, 0.3763, 0.3217, 0.6125, 0.5533],
[0.6172, 0.4055, 0.8175, 0.2650, 0.3550, 0.3683, 0.5787, 0.5550],
[0.6230, 0.4152, 0.7588, 0.2283, 0.4012, 0.2883, 0.6200, 0.5767],
[0.6136, 0.4029, 0.8263, 0.3350, 0.3625, 0.3067, 0.5675, 0.5167],
[0.6346, 0.4144, 0.9088, 0.4667, 0.3850, 0.4333, 0.7121, 0.5899],
[0.6239, 0.4206, 0.8750, 0.5400, 0.3688, 0.4850, 0.5737, 0.5700]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5450, 0.3389, 0.9121, 0.4218, 0.4478, 0.3192, 0.7040, 0.5919],
[0.4682, 0.2779, 0.7069, 0.2023, 0.4132, 0.1661, 0.5391, 0.5515],
[0.5974, 0.3781, 0.8077, 0.2790, 0.4024, 0.2788, 0.5935, 0.5618],
[0.5002, 0.3248, 0.8132, 0.3105, 0.3683, 0.3401, 0.5391, 0.5600],
[0.5790, 0.3737, 0.7905, 0.2610, 0.4246, 0.2579, 0.5991, 0.5909],
[0.5536, 0.3923, 0.8460, 0.3414, 0.3876, 0.2783, 0.5599, 0.5604],
[0.5235, 0.3519, 0.9101, 0.4799, 0.4183, 0.3825, 0.6948, 0.6061],
[0.6200, 0.4087, 0.8988, 0.5803, 0.4056, 0.4541, 0.5931, 0.5973]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6350, 0.4144, 0.9250, 0.4100, 0.4125, 0.3750, 0.7129, 0.5945],
[0.6054, 0.4035, 0.6897, 0.1916, 0.4000, 0.2117, 0.5440, 0.5168],
[0.6202, 0.4079, 0.8025, 0.2500, 0.3762, 0.3217, 0.6125, 0.5533],
[0.6172, 0.4055, 0.8175, 0.2650, 0.3550, 0.3683, 0.5788, 0.5550],
[0.6230, 0.4152, 0.7588, 0.2283, 0.4013, 0.2883, 0.6200, 0.5767],
[0.6136, 0.4029, 0.8263, 0.3350, 0.3625, 0.3067, 0.5675, 0.5167],
[0.6346, 0.4144, 0.9087, 0.4667, 0.3850, 0.4333, 0.7121, 0.5899],
[0.6239, 0.4206, 0.8750, 0.5400, 0.3688, 0.4850, 0.5738, 0.5700]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0020, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0020, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.017651385918725282
step: 8
running loss: 0.0022064232398406602
Train Steps: 8/90 Loss: 0.0022 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.6900, 0.1917, 0.3937, 0.2367, 0.5240, 0.5246],
[0.6198, 0.4164, 0.8700, 0.5067, 0.4625, 0.5650, 0.5464, 0.5197],
[0.6202, 0.4066, 0.8398, 0.2648, 0.3925, 0.2627, 0.5845, 0.5124],
[0.6299, 0.4303, 0.7963, 0.3933, 0.4850, 0.2283, 0.5480, 0.6222],
[0.6198, 0.4101, 0.8838, 0.5283, 0.3763, 0.5267, 0.5913, 0.5567],
[0.6162, 0.4014, 0.8800, 0.5333, 0.3750, 0.4817, 0.5988, 0.5283],
[0.6176, 0.4030, 0.8850, 0.4850, 0.3688, 0.4050, 0.5312, 0.5783],
[ nan, nan, 0.6859, 0.2194, 0.4150, 0.1867, 0.5153, 0.5729]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.0428, 0.0314, 0.7288, 0.2345, 0.4140, 0.2244, 0.5735, 0.5468],
[0.7112, 0.4756, 0.9116, 0.5149, 0.4737, 0.5195, 0.6098, 0.5295],
[0.6298, 0.4101, 0.8339, 0.2671, 0.4087, 0.2395, 0.6392, 0.5416],
[0.6986, 0.4763, 0.8342, 0.3661, 0.4985, 0.2606, 0.5705, 0.6165],
[0.7682, 0.4894, 0.9038, 0.5506, 0.3864, 0.5193, 0.6369, 0.5682],
[0.7155, 0.4652, 0.8983, 0.5525, 0.3863, 0.4746, 0.6439, 0.5403],
[0.6947, 0.4640, 0.9098, 0.4999, 0.3746, 0.4000, 0.5840, 0.5835],
[0.1006, 0.0617, 0.7249, 0.2260, 0.4266, 0.1740, 0.5654, 0.5623]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.6900, 0.1917, 0.3938, 0.2367, 0.5240, 0.5246],
[0.6198, 0.4164, 0.8700, 0.5067, 0.4625, 0.5650, 0.5464, 0.5197],
[0.6202, 0.4066, 0.8398, 0.2648, 0.3925, 0.2627, 0.5845, 0.5124],
[0.6299, 0.4303, 0.7962, 0.3933, 0.4850, 0.2283, 0.5480, 0.6222],
[0.6198, 0.4101, 0.8838, 0.5283, 0.3762, 0.5267, 0.5913, 0.5567],
[0.6162, 0.4014, 0.8800, 0.5333, 0.3750, 0.4817, 0.5987, 0.5283],
[0.6176, 0.4030, 0.8850, 0.4850, 0.3688, 0.4050, 0.5312, 0.5783],
[0.0000, 0.0000, 0.6859, 0.2194, 0.4150, 0.1867, 0.5153, 0.5729]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0020, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0020, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.019613695156294852
step: 9
running loss: 0.002179299461810539
Train Steps: 9/90 Loss: 0.0022 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6200, 0.3998, 0.8850, 0.3950, 0.3500, 0.4650, 0.6138, 0.5400],
[0.6286, 0.4055, 0.9000, 0.4717, 0.3763, 0.4683, 0.7018, 0.5494],
[0.6160, 0.4093, 0.8314, 0.4417, 0.3675, 0.4583, 0.5250, 0.5808],
[0.6224, 0.4061, 0.8988, 0.4300, 0.3838, 0.4750, 0.6112, 0.5483],
[0.6321, 0.4048, 0.8738, 0.5617, 0.3875, 0.4417, 0.6361, 0.4927],
[0.6064, 0.4019, 0.8650, 0.4517, 0.4037, 0.5367, 0.5703, 0.5609],
[0.6188, 0.4099, 0.7400, 0.2433, 0.3962, 0.2750, 0.6162, 0.5467],
[0.6072, 0.4029, 0.7037, 0.2150, 0.3912, 0.2267, 0.5516, 0.5507]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6030, 0.4097, 0.8930, 0.4494, 0.3813, 0.4447, 0.6150, 0.5515],
[0.6140, 0.4132, 0.9168, 0.5096, 0.3778, 0.4366, 0.7009, 0.5404],
[0.5959, 0.4015, 0.8532, 0.4779, 0.3983, 0.4302, 0.5673, 0.5675],
[0.6657, 0.4229, 0.9223, 0.4793, 0.3905, 0.4876, 0.6136, 0.5228],
[0.6222, 0.3936, 0.8991, 0.5774, 0.3917, 0.4128, 0.6241, 0.4926],
[0.5483, 0.3770, 0.8813, 0.4745, 0.4251, 0.5456, 0.6047, 0.5475],
[0.5623, 0.3769, 0.7501, 0.2297, 0.4064, 0.2503, 0.5999, 0.5592],
[0.5206, 0.3534, 0.7160, 0.2273, 0.4247, 0.2127, 0.5603, 0.5618]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6200, 0.3998, 0.8850, 0.3950, 0.3500, 0.4650, 0.6137, 0.5400],
[0.6286, 0.4055, 0.9000, 0.4717, 0.3762, 0.4683, 0.7018, 0.5494],
[0.6160, 0.4092, 0.8314, 0.4417, 0.3675, 0.4583, 0.5250, 0.5808],
[0.6224, 0.4061, 0.8988, 0.4300, 0.3837, 0.4750, 0.6112, 0.5483],
[0.6321, 0.4048, 0.8737, 0.5617, 0.3875, 0.4417, 0.6361, 0.4927],
[0.6064, 0.4019, 0.8650, 0.4517, 0.4038, 0.5367, 0.5703, 0.5609],
[0.6188, 0.4099, 0.7400, 0.2433, 0.3963, 0.2750, 0.6162, 0.5467],
[0.6072, 0.4029, 0.7038, 0.2150, 0.3913, 0.2267, 0.5516, 0.5507]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.020335583365522325
step: 10
running loss: 0.0020335583365522327
Train Steps: 10/90 Loss: 0.0020 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.8850, 0.2817, 0.5112, 0.2183, 0.7184, 0.5436],
[0.6199, 0.4060, 0.8888, 0.4667, 0.3800, 0.5050, 0.6188, 0.5433],
[0.6127, 0.4084, 0.8700, 0.4467, 0.3987, 0.4317, 0.5013, 0.5471],
[0.6193, 0.4079, 0.7288, 0.2500, 0.4250, 0.2550, 0.5989, 0.6266],
[0.6213, 0.4131, 0.8438, 0.3550, 0.3513, 0.4400, 0.5716, 0.5123],
[0.6222, 0.4169, 0.8638, 0.5650, 0.4313, 0.4783, 0.5637, 0.5633],
[0.6214, 0.3982, 0.8938, 0.4517, 0.3663, 0.4083, 0.5863, 0.5050],
[0.6189, 0.4049, 0.8888, 0.4417, 0.4213, 0.5200, 0.5988, 0.5633]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.1967, 0.1461, 0.8668, 0.2789, 0.5008, 0.2300, 0.7540, 0.5135],
[0.6227, 0.4107, 0.8813, 0.4764, 0.3725, 0.5147, 0.6305, 0.5193],
[0.6610, 0.4424, 0.8588, 0.4559, 0.3658, 0.4232, 0.5012, 0.5153],
[0.5926, 0.3841, 0.7065, 0.2488, 0.4126, 0.2771, 0.6147, 0.5956],
[0.6309, 0.4225, 0.8329, 0.3700, 0.3376, 0.4131, 0.5710, 0.5053],
[0.5498, 0.3652, 0.8582, 0.5761, 0.4092, 0.4807, 0.5568, 0.5532],
[0.6210, 0.4160, 0.8617, 0.4565, 0.3626, 0.3940, 0.5778, 0.4699],
[0.6542, 0.4385, 0.8640, 0.4484, 0.4057, 0.5174, 0.6278, 0.5312]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.8850, 0.2817, 0.5113, 0.2183, 0.7184, 0.5436],
[0.6199, 0.4060, 0.8888, 0.4667, 0.3800, 0.5050, 0.6187, 0.5433],
[0.6127, 0.4084, 0.8700, 0.4467, 0.3988, 0.4317, 0.5013, 0.5471],
[0.6193, 0.4078, 0.7287, 0.2500, 0.4250, 0.2550, 0.5989, 0.6266],
[0.6213, 0.4131, 0.8438, 0.3550, 0.3512, 0.4400, 0.5716, 0.5123],
[0.6222, 0.4169, 0.8637, 0.5650, 0.4313, 0.4783, 0.5638, 0.5633],
[0.6214, 0.3982, 0.8938, 0.4517, 0.3663, 0.4083, 0.5863, 0.5050],
[0.6189, 0.4049, 0.8888, 0.4417, 0.4212, 0.5200, 0.5987, 0.5633]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.02176640962716192
step: 11
running loss: 0.0019787645115601745
Train Steps: 11/90 Loss: 0.0020 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6254, 0.3993, 0.8988, 0.4767, 0.3987, 0.5517, 0.6955, 0.5285],
[0.6200, 0.4112, 0.8862, 0.4100, 0.3638, 0.4917, 0.6088, 0.6050],
[0.6199, 0.4065, 0.7598, 0.2385, 0.4317, 0.1981, 0.5933, 0.5221],
[0.6277, 0.4103, 0.8087, 0.5717, 0.4188, 0.4750, 0.5663, 0.6083],
[0.6250, 0.4116, 0.8700, 0.4850, 0.4650, 0.5567, 0.6088, 0.5183],
[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837],
[0.6130, 0.4072, 0.8550, 0.4567, 0.3638, 0.3667, 0.5290, 0.5892],
[0.6129, 0.4114, 0.6950, 0.2467, 0.4050, 0.2133, 0.5363, 0.5550]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5811, 0.3768, 0.9099, 0.4876, 0.3926, 0.5734, 0.6679, 0.5131],
[0.5699, 0.4015, 0.8979, 0.4165, 0.3709, 0.4824, 0.6132, 0.5498],
[0.5431, 0.3632, 0.7523, 0.2119, 0.4363, 0.2313, 0.5866, 0.4968],
[0.5687, 0.3855, 0.8256, 0.5647, 0.3947, 0.4864, 0.5870, 0.5849],
[0.6221, 0.4016, 0.9093, 0.4778, 0.4513, 0.5638, 0.6455, 0.5084],
[0.4819, 0.3230, 0.6971, 0.3072, 0.3550, 0.3079, 0.5256, 0.5407],
[0.5666, 0.3805, 0.8646, 0.4635, 0.3537, 0.3870, 0.5214, 0.5420],
[0.5962, 0.4013, 0.7175, 0.2607, 0.3857, 0.2391, 0.5381, 0.5099]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6254, 0.3993, 0.8988, 0.4767, 0.3988, 0.5517, 0.6955, 0.5285],
[0.6200, 0.4112, 0.8863, 0.4100, 0.3638, 0.4917, 0.6087, 0.6050],
[0.6199, 0.4065, 0.7598, 0.2385, 0.4317, 0.1981, 0.5933, 0.5221],
[0.6277, 0.4103, 0.8087, 0.5717, 0.4187, 0.4750, 0.5663, 0.6083],
[0.6251, 0.4116, 0.8700, 0.4850, 0.4650, 0.5567, 0.6087, 0.5183],
[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837],
[0.6130, 0.4072, 0.8550, 0.4567, 0.3638, 0.3667, 0.5290, 0.5892],
[0.6129, 0.4114, 0.6950, 0.2467, 0.4050, 0.2133, 0.5362, 0.5550]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.02287836465984583
step: 12
running loss: 0.0019065303883204858
Train Steps: 12/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6214, 0.4112, 0.7838, 0.2117, 0.3650, 0.3133, 0.5675, 0.5083],
[0.6162, 0.4014, 0.8800, 0.5333, 0.3750, 0.4817, 0.5988, 0.5283],
[0.6200, 0.4059, 0.8700, 0.4900, 0.4163, 0.5000, 0.6162, 0.5467],
[0.6182, 0.4099, 0.7812, 0.3000, 0.3937, 0.2367, 0.5325, 0.5750],
[0.6350, 0.4144, 0.9250, 0.4100, 0.4125, 0.3750, 0.7129, 0.5945],
[0.6317, 0.4038, 0.8287, 0.5900, 0.3800, 0.4717, 0.6295, 0.4986],
[0.6157, 0.3956, 0.8323, 0.4138, 0.3479, 0.4431, 0.5914, 0.5131],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5935, 0.3896, 0.7540, 0.1949, 0.3524, 0.3019, 0.5652, 0.5206],
[0.5673, 0.3691, 0.8442, 0.5159, 0.3690, 0.4971, 0.5622, 0.5308],
[0.5962, 0.3964, 0.8590, 0.4969, 0.3963, 0.5442, 0.5967, 0.5409],
[0.4966, 0.3253, 0.7469, 0.2914, 0.4054, 0.2778, 0.5003, 0.5784],
[0.5631, 0.3603, 0.8656, 0.3860, 0.4165, 0.3810, 0.6919, 0.5644],
[0.5929, 0.3764, 0.8253, 0.5604, 0.3623, 0.4864, 0.5951, 0.5051],
[0.5627, 0.3630, 0.8148, 0.3790, 0.3547, 0.4484, 0.5368, 0.5210],
[0.5737, 0.4015, 0.8589, 0.4194, 0.4251, 0.5275, 0.5585, 0.5323]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6214, 0.4112, 0.7837, 0.2117, 0.3650, 0.3133, 0.5675, 0.5083],
[0.6162, 0.4014, 0.8800, 0.5333, 0.3750, 0.4817, 0.5987, 0.5283],
[0.6199, 0.4059, 0.8700, 0.4900, 0.4162, 0.5000, 0.6162, 0.5467],
[0.6182, 0.4099, 0.7812, 0.3000, 0.3938, 0.2367, 0.5325, 0.5750],
[0.6350, 0.4144, 0.9250, 0.4100, 0.4125, 0.3750, 0.7129, 0.5945],
[0.6317, 0.4038, 0.8288, 0.5900, 0.3800, 0.4717, 0.6295, 0.4986],
[0.6157, 0.3956, 0.8323, 0.4138, 0.3479, 0.4431, 0.5914, 0.5131],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.02397310920059681
step: 13
running loss: 0.0018440853231228315
Train Steps: 13/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6277, 0.4083, 0.8350, 0.2717, 0.4562, 0.1800, 0.5918, 0.4878],
[0.6175, 0.4091, 0.7863, 0.2800, 0.3638, 0.3583, 0.6188, 0.5433],
[0.6172, 0.4055, 0.8175, 0.2650, 0.3550, 0.3683, 0.5787, 0.5550],
[0.6059, 0.4002, 0.7562, 0.2767, 0.3538, 0.3033, 0.5529, 0.5455],
[0.6307, 0.4029, 0.8650, 0.5200, 0.3763, 0.4017, 0.7311, 0.5366],
[0.6296, 0.4045, 0.9138, 0.4100, 0.4232, 0.4242, 0.7422, 0.5297],
[0.6275, 0.4111, 0.8463, 0.2617, 0.4487, 0.1983, 0.6211, 0.4904],
[0.6200, 0.4055, 0.8011, 0.2988, 0.3842, 0.2798, 0.5949, 0.5183]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5830, 0.3639, 0.7772, 0.2662, 0.4585, 0.2378, 0.5365, 0.5227],
[0.5380, 0.3593, 0.7519, 0.2464, 0.3452, 0.3739, 0.5676, 0.5757],
[0.5398, 0.3570, 0.7709, 0.2866, 0.3395, 0.4024, 0.5126, 0.5589],
[0.5468, 0.3776, 0.7313, 0.2644, 0.3622, 0.3308, 0.5612, 0.5544],
[0.5890, 0.3941, 0.8587, 0.5155, 0.3783, 0.4066, 0.6172, 0.5367],
[0.6245, 0.4113, 0.8901, 0.4214, 0.3851, 0.4393, 0.6568, 0.5655],
[0.5801, 0.3806, 0.8156, 0.2517, 0.4710, 0.2306, 0.5710, 0.5322],
[0.5394, 0.3569, 0.7571, 0.2928, 0.4019, 0.3020, 0.5815, 0.5393]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6277, 0.4083, 0.8350, 0.2717, 0.4563, 0.1800, 0.5918, 0.4878],
[0.6175, 0.4091, 0.7862, 0.2800, 0.3638, 0.3583, 0.6187, 0.5433],
[0.6172, 0.4055, 0.8175, 0.2650, 0.3550, 0.3683, 0.5788, 0.5550],
[0.6059, 0.4002, 0.7563, 0.2767, 0.3537, 0.3033, 0.5529, 0.5455],
[0.6307, 0.4029, 0.8650, 0.5200, 0.3762, 0.4017, 0.7311, 0.5366],
[0.6296, 0.4045, 0.9137, 0.4100, 0.4232, 0.4242, 0.7422, 0.5297],
[0.6275, 0.4111, 0.8462, 0.2617, 0.4487, 0.1983, 0.6211, 0.4904],
[0.6201, 0.4055, 0.8011, 0.2988, 0.3842, 0.2798, 0.5949, 0.5183]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.025551110040396452
step: 14
running loss: 0.0018250792885997466
Train Steps: 14/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6250, 0.4013, 0.8525, 0.5417, 0.4037, 0.5117, 0.6325, 0.5017],
[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334],
[0.6246, 0.4008, 0.8757, 0.5088, 0.4101, 0.5392, 0.6644, 0.5133],
[0.6262, 0.4052, 0.8888, 0.4700, 0.3675, 0.5117, 0.6350, 0.5233],
[0.6267, 0.4080, 0.8438, 0.2633, 0.4763, 0.1800, 0.6259, 0.5240],
[0.6361, 0.4165, 0.9038, 0.5017, 0.3750, 0.3783, 0.6448, 0.5309],
[0.6219, 0.4089, 0.8938, 0.4800, 0.3825, 0.4450, 0.5850, 0.5200],
[0.6325, 0.4066, 0.8438, 0.5350, 0.3925, 0.5267, 0.7113, 0.5795]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5966, 0.3827, 0.8279, 0.5126, 0.3845, 0.5103, 0.5687, 0.5114],
[0.6408, 0.4424, 0.7315, 0.2028, 0.3657, 0.2999, 0.5820, 0.5476],
[0.6043, 0.3967, 0.8429, 0.4752, 0.3932, 0.5304, 0.6078, 0.5437],
[0.5796, 0.3996, 0.8783, 0.4260, 0.3826, 0.5202, 0.6104, 0.5483],
[0.6333, 0.4238, 0.8142, 0.2279, 0.4601, 0.1983, 0.5953, 0.5282],
[0.6257, 0.4307, 0.8559, 0.4417, 0.3964, 0.3713, 0.5981, 0.5385],
[0.6219, 0.4237, 0.8560, 0.4450, 0.3656, 0.4629, 0.5451, 0.5470],
[0.5676, 0.3878, 0.8360, 0.4887, 0.3789, 0.5326, 0.6601, 0.5957]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6250, 0.4013, 0.8525, 0.5417, 0.4038, 0.5117, 0.6325, 0.5017],
[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334],
[0.6246, 0.4008, 0.8757, 0.5088, 0.4101, 0.5392, 0.6644, 0.5133],
[0.6262, 0.4052, 0.8888, 0.4700, 0.3675, 0.5117, 0.6350, 0.5233],
[0.6267, 0.4080, 0.8438, 0.2633, 0.4762, 0.1800, 0.6259, 0.5240],
[0.6361, 0.4165, 0.9038, 0.5017, 0.3750, 0.3783, 0.6448, 0.5309],
[0.6219, 0.4089, 0.8938, 0.4800, 0.3825, 0.4450, 0.5850, 0.5200],
[0.6325, 0.4066, 0.8438, 0.5350, 0.3925, 0.5267, 0.7113, 0.5795]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.026409554469864815
step: 15
running loss: 0.0017606369646576544
Train Steps: 15/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6210, 0.4164, 0.7202, 0.2930, 0.4025, 0.2483, 0.5687, 0.5567],
[0.6198, 0.4075, 0.8650, 0.5617, 0.4150, 0.4367, 0.5450, 0.5650],
[0.6126, 0.4073, 0.8750, 0.5133, 0.3800, 0.4333, 0.4986, 0.5378],
[0.6258, 0.4038, 0.8750, 0.4883, 0.3900, 0.5500, 0.6375, 0.5217],
[0.6179, 0.4040, 0.7412, 0.1850, 0.3825, 0.2783, 0.5837, 0.5600],
[0.6135, 0.3994, 0.7913, 0.3050, 0.3625, 0.3050, 0.5837, 0.5050],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3513, 0.4050, 0.6112, 0.5500],
[0.6150, 0.3949, 0.8800, 0.4033, 0.3825, 0.4900, 0.5875, 0.5483]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5237, 0.3421, 0.7651, 0.2634, 0.4441, 0.2637, 0.6147, 0.5645],
[0.6785, 0.4316, 0.8797, 0.5774, 0.3911, 0.4217, 0.5852, 0.5596],
[0.6267, 0.4133, 0.8920, 0.5273, 0.3849, 0.4389, 0.5403, 0.5284],
[0.6243, 0.3974, 0.8944, 0.5076, 0.4023, 0.5420, 0.6750, 0.5255],
[0.7272, 0.4969, 0.7238, 0.2236, 0.3934, 0.2854, 0.6170, 0.5553],
[0.6593, 0.4337, 0.7901, 0.2948, 0.3699, 0.3122, 0.6406, 0.5055],
[0.6604, 0.4426, 0.7870, 0.2455, 0.3581, 0.3741, 0.6380, 0.5378],
[0.5822, 0.3795, 0.8651, 0.4301, 0.3749, 0.4536, 0.6211, 0.5225]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6210, 0.4164, 0.7202, 0.2930, 0.4025, 0.2483, 0.5688, 0.5567],
[0.6198, 0.4075, 0.8650, 0.5617, 0.4150, 0.4367, 0.5450, 0.5650],
[0.6126, 0.4073, 0.8750, 0.5133, 0.3800, 0.4333, 0.4986, 0.5378],
[0.6258, 0.4038, 0.8750, 0.4883, 0.3900, 0.5500, 0.6375, 0.5217],
[0.6179, 0.4040, 0.7412, 0.1850, 0.3825, 0.2783, 0.5838, 0.5600],
[0.6135, 0.3994, 0.7912, 0.3050, 0.3625, 0.3050, 0.5838, 0.5050],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3512, 0.4050, 0.6112, 0.5500],
[0.6150, 0.3949, 0.8800, 0.4033, 0.3825, 0.4900, 0.5875, 0.5483]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.02758348052157089
step: 16
running loss: 0.0017239675325981807
Train Steps: 16/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6304, 0.4024, 0.8925, 0.4800, 0.3937, 0.4817, 0.7485, 0.5297],
[0.6187, 0.4104, 0.7126, 0.2069, 0.3950, 0.2517, 0.5913, 0.5683],
[0.6201, 0.4055, 0.7717, 0.1919, 0.4250, 0.2079, 0.5871, 0.5044],
[0.6275, 0.4024, 0.7722, 0.2080, 0.4392, 0.2234, 0.6435, 0.5290],
[0.6206, 0.4001, 0.8900, 0.3933, 0.3588, 0.3567, 0.5837, 0.5083],
[0.6122, 0.3993, 0.8738, 0.4667, 0.4517, 0.4879, 0.5155, 0.4927],
[ nan, nan, 0.7515, 0.2708, 0.3987, 0.2267, 0.5162, 0.5567],
[0.6112, 0.4029, 0.8638, 0.4800, 0.4875, 0.5083, 0.5763, 0.5567]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7156, 0.4425, 0.8823, 0.4837, 0.3652, 0.4849, 0.7299, 0.5256],
[0.7126, 0.4818, 0.7093, 0.2302, 0.3714, 0.2479, 0.5777, 0.5423],
[0.7234, 0.4645, 0.7586, 0.2182, 0.4175, 0.2038, 0.6208, 0.5105],
[0.6508, 0.4159, 0.7700, 0.2354, 0.4291, 0.2011, 0.6831, 0.5272],
[0.7000, 0.4389, 0.9155, 0.4157, 0.3596, 0.3509, 0.5941, 0.5133],
[0.7093, 0.4505, 0.9017, 0.4934, 0.4225, 0.5042, 0.5203, 0.5092],
[0.1840, 0.1324, 0.7520, 0.2711, 0.3754, 0.2328, 0.5478, 0.5738],
[0.6669, 0.4338, 0.9112, 0.4935, 0.4624, 0.4776, 0.6183, 0.5521]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6304, 0.4024, 0.8925, 0.4800, 0.3938, 0.4817, 0.7485, 0.5297],
[0.6187, 0.4103, 0.7126, 0.2069, 0.3950, 0.2517, 0.5913, 0.5683],
[0.6202, 0.4055, 0.7717, 0.1919, 0.4250, 0.2079, 0.5871, 0.5044],
[0.6275, 0.4024, 0.7722, 0.2080, 0.4392, 0.2234, 0.6435, 0.5290],
[0.6206, 0.4001, 0.8900, 0.3933, 0.3587, 0.3567, 0.5838, 0.5083],
[0.6122, 0.3993, 0.8737, 0.4667, 0.4517, 0.4879, 0.5155, 0.4927],
[0.0000, 0.0000, 0.7515, 0.2708, 0.3988, 0.2267, 0.5163, 0.5567],
[0.6112, 0.4029, 0.8637, 0.4800, 0.4875, 0.5083, 0.5763, 0.5567]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0021, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0021, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.029665038164239377
step: 17
running loss: 0.0017450022449552575
Train Steps: 17/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6226, 0.4001, 0.8438, 0.5733, 0.3862, 0.4250, 0.5750, 0.5283],
[0.6289, 0.4032, 0.8419, 0.5446, 0.4075, 0.5017, 0.6312, 0.5117],
[0.6118, 0.4052, 0.8463, 0.3917, 0.3538, 0.3450, 0.5053, 0.5593],
[0.6212, 0.4159, 0.8675, 0.5783, 0.4088, 0.4317, 0.5613, 0.5917],
[0.6226, 0.4098, 0.8912, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367],
[0.6182, 0.3972, 0.8552, 0.5914, 0.3683, 0.4181, 0.5688, 0.5378],
[0.6102, 0.4001, 0.7738, 0.3583, 0.3463, 0.3800, 0.5524, 0.5689],
[0.6276, 0.4235, 0.8888, 0.5333, 0.3800, 0.3117, 0.5427, 0.6164]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6093, 0.3796, 0.8609, 0.5016, 0.3703, 0.3870, 0.6474, 0.5185],
[0.7249, 0.4409, 0.8565, 0.4559, 0.3879, 0.4894, 0.6929, 0.4906],
[0.6259, 0.4103, 0.8489, 0.3080, 0.3685, 0.3349, 0.5577, 0.5404],
[0.6718, 0.4446, 0.8509, 0.4925, 0.4141, 0.4078, 0.6081, 0.5764],
[0.6810, 0.4354, 0.8846, 0.3431, 0.4289, 0.2577, 0.6137, 0.5327],
[0.6487, 0.4090, 0.8828, 0.5071, 0.3807, 0.4111, 0.6443, 0.5090],
[0.6511, 0.4149, 0.7971, 0.2856, 0.3502, 0.3732, 0.6101, 0.5407],
[0.6062, 0.3869, 0.8544, 0.4510, 0.4083, 0.3646, 0.6009, 0.5720]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6226, 0.4001, 0.8438, 0.5733, 0.3862, 0.4250, 0.5750, 0.5283],
[0.6289, 0.4031, 0.8419, 0.5446, 0.4075, 0.5017, 0.6313, 0.5117],
[0.6118, 0.4052, 0.8462, 0.3917, 0.3537, 0.3450, 0.5053, 0.5593],
[0.6212, 0.4159, 0.8675, 0.5783, 0.4087, 0.4317, 0.5612, 0.5917],
[0.6226, 0.4098, 0.8913, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367],
[0.6182, 0.3972, 0.8552, 0.5914, 0.3683, 0.4181, 0.5688, 0.5378],
[0.6102, 0.4001, 0.7738, 0.3583, 0.3462, 0.3800, 0.5524, 0.5689],
[0.6276, 0.4235, 0.8888, 0.5333, 0.3800, 0.3117, 0.5427, 0.6164]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03151935857022181
step: 18
running loss: 0.001751075476123434
Train Steps: 18/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6225, 0.4191, 0.8500, 0.4167, 0.3688, 0.3233, 0.5650, 0.5650],
[0.6081, 0.3950, 0.8538, 0.4667, 0.3850, 0.4917, 0.5342, 0.4954],
[0.6169, 0.4108, 0.6821, 0.2722, 0.3825, 0.2550, 0.5550, 0.5717],
[0.6260, 0.4106, 0.8025, 0.2583, 0.4550, 0.1867, 0.6281, 0.4869],
[0.6108, 0.4011, 0.8037, 0.3400, 0.3700, 0.2933, 0.5658, 0.5617],
[0.6333, 0.4037, 0.8638, 0.5733, 0.4012, 0.4717, 0.6369, 0.4938],
[0.6250, 0.4131, 0.8688, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367],
[0.6200, 0.4098, 0.8237, 0.2917, 0.4012, 0.2967, 0.6000, 0.5683]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6285, 0.4289, 0.8369, 0.3992, 0.3666, 0.3394, 0.5768, 0.5714],
[0.5382, 0.3461, 0.9028, 0.4570, 0.3757, 0.4687, 0.5894, 0.5244],
[0.6505, 0.4122, 0.6919, 0.2711, 0.3828, 0.2432, 0.5745, 0.5503],
[0.6192, 0.3904, 0.8273, 0.2519, 0.4510, 0.1801, 0.6629, 0.5030],
[0.6138, 0.3868, 0.8164, 0.3509, 0.3933, 0.3060, 0.6069, 0.5410],
[0.6278, 0.3900, 0.8875, 0.5938, 0.4004, 0.4714, 0.6583, 0.5202],
[0.6803, 0.4378, 0.8683, 0.3065, 0.4459, 0.2154, 0.6347, 0.5347],
[0.6068, 0.3959, 0.8165, 0.3017, 0.3987, 0.2889, 0.6404, 0.5753]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6225, 0.4191, 0.8500, 0.4167, 0.3688, 0.3233, 0.5650, 0.5650],
[0.6081, 0.3950, 0.8537, 0.4667, 0.3850, 0.4917, 0.5342, 0.4954],
[0.6169, 0.4108, 0.6821, 0.2722, 0.3825, 0.2550, 0.5550, 0.5717],
[0.6260, 0.4106, 0.8025, 0.2583, 0.4550, 0.1867, 0.6281, 0.4869],
[0.6108, 0.4011, 0.8037, 0.3400, 0.3700, 0.2933, 0.5658, 0.5617],
[0.6334, 0.4037, 0.8637, 0.5733, 0.4013, 0.4717, 0.6369, 0.4938],
[0.6250, 0.4131, 0.8687, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367],
[0.6200, 0.4098, 0.8238, 0.2917, 0.4013, 0.2967, 0.6000, 0.5683]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.032034559291787446
step: 19
running loss: 0.0016860294364098656
Train Steps: 19/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6257, 0.4024, 0.8672, 0.5422, 0.4196, 0.5198, 0.6694, 0.5204],
[0.6236, 0.3977, 0.8985, 0.4806, 0.3835, 0.5216, 0.6613, 0.5166],
[0.6038, 0.3946, 0.8413, 0.4883, 0.3563, 0.4550, 0.5266, 0.4693],
[0.6136, 0.4117, 0.8700, 0.5167, 0.4188, 0.5083, 0.5147, 0.5495],
[0.6250, 0.4110, 0.7238, 0.2067, 0.4263, 0.1883, 0.5625, 0.5633],
[0.6258, 0.4143, 0.8525, 0.2617, 0.4950, 0.1667, 0.6219, 0.4967],
[0.6260, 0.4120, 0.8013, 0.2350, 0.4888, 0.1533, 0.6281, 0.4895],
[0.6209, 0.3920, 0.8650, 0.5367, 0.4400, 0.5067, 0.6025, 0.4950]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5812, 0.3663, 0.8780, 0.5663, 0.4113, 0.5094, 0.6484, 0.5449],
[0.6205, 0.3792, 0.8964, 0.5088, 0.3694, 0.5186, 0.6588, 0.5418],
[0.5394, 0.3596, 0.8567, 0.5064, 0.3538, 0.4711, 0.5429, 0.5481],
[0.5951, 0.3821, 0.9107, 0.5731, 0.4070, 0.5004, 0.5472, 0.5524],
[0.6014, 0.3876, 0.7242, 0.2879, 0.4193, 0.1686, 0.5552, 0.5635],
[0.6758, 0.4629, 0.8608, 0.2929, 0.4783, 0.1708, 0.6264, 0.5358],
[0.7078, 0.4596, 0.8143, 0.2689, 0.4817, 0.1511, 0.6334, 0.5194],
[0.6756, 0.4203, 0.8839, 0.5290, 0.4115, 0.5091, 0.5758, 0.5183]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6257, 0.4024, 0.8672, 0.5422, 0.4196, 0.5198, 0.6694, 0.5204],
[0.6236, 0.3977, 0.8985, 0.4806, 0.3835, 0.5216, 0.6613, 0.5166],
[0.6038, 0.3946, 0.8413, 0.4883, 0.3562, 0.4550, 0.5266, 0.4693],
[0.6136, 0.4117, 0.8700, 0.5167, 0.4187, 0.5083, 0.5147, 0.5495],
[0.6250, 0.4110, 0.7237, 0.2067, 0.4263, 0.1883, 0.5625, 0.5633],
[0.6258, 0.4143, 0.8525, 0.2617, 0.4950, 0.1667, 0.6219, 0.4967],
[0.6259, 0.4120, 0.8012, 0.2350, 0.4888, 0.1533, 0.6281, 0.4895],
[0.6209, 0.3920, 0.8650, 0.5367, 0.4400, 0.5067, 0.6025, 0.4950]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03298321762122214
step: 20
running loss: 0.0016491608810611069
Train Steps: 20/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.8900, 0.3217, 0.5038, 0.2233, 0.6694, 0.5609],
[0.6097, 0.3988, 0.8650, 0.5250, 0.4213, 0.5200, 0.5675, 0.5050],
[0.6271, 0.4020, 0.8375, 0.6083, 0.3925, 0.4867, 0.6037, 0.4626],
[0.6152, 0.4131, 0.6863, 0.2567, 0.3625, 0.3300, 0.5765, 0.5305],
[0.6267, 0.4065, 0.8313, 0.2467, 0.4788, 0.1733, 0.6312, 0.5133],
[0.6205, 0.4016, 0.8350, 0.2717, 0.3987, 0.2550, 0.5787, 0.5133],
[0.6064, 0.4019, 0.8650, 0.4517, 0.4037, 0.5367, 0.5703, 0.5609],
[0.6200, 0.3993, 0.8639, 0.3687, 0.3658, 0.3139, 0.6002, 0.5374]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.1661, 0.0989, 0.8938, 0.3742, 0.4654, 0.1780, 0.6484, 0.5681],
[0.6539, 0.4123, 0.8830, 0.5821, 0.4425, 0.5081, 0.5056, 0.5100],
[0.6937, 0.4245, 0.8564, 0.6342, 0.4042, 0.4477, 0.6047, 0.4869],
[0.7473, 0.4797, 0.6982, 0.3150, 0.3798, 0.3226, 0.5214, 0.5388],
[0.6735, 0.4346, 0.8389, 0.2927, 0.4800, 0.1470, 0.5898, 0.5247],
[0.6678, 0.4201, 0.8428, 0.2941, 0.4032, 0.2558, 0.5571, 0.5247],
[0.6108, 0.3926, 0.8709, 0.4782, 0.4101, 0.5413, 0.5579, 0.5436],
[0.6580, 0.4124, 0.8757, 0.4204, 0.3782, 0.2969, 0.5750, 0.5194]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.8900, 0.3217, 0.5038, 0.2233, 0.6694, 0.5609],
[0.6097, 0.3988, 0.8650, 0.5250, 0.4212, 0.5200, 0.5675, 0.5050],
[0.6271, 0.4020, 0.8375, 0.6083, 0.3925, 0.4867, 0.6037, 0.4626],
[0.6152, 0.4131, 0.6862, 0.2567, 0.3625, 0.3300, 0.5765, 0.5305],
[0.6266, 0.4065, 0.8313, 0.2467, 0.4787, 0.1733, 0.6313, 0.5133],
[0.6205, 0.4015, 0.8350, 0.2717, 0.3988, 0.2550, 0.5788, 0.5133],
[0.6064, 0.4019, 0.8650, 0.4517, 0.4038, 0.5367, 0.5703, 0.5609],
[0.6200, 0.3993, 0.8639, 0.3687, 0.3658, 0.3139, 0.6002, 0.5374]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.034703588928095996
step: 21
running loss: 0.001652551853718857
Train Steps: 21/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6275, 0.4013, 0.8850, 0.2833, 0.4975, 0.2233, 0.7058, 0.5343],
[0.6175, 0.4013, 0.7734, 0.2783, 0.4475, 0.1786, 0.5790, 0.5351],
[0.6148, 0.4076, 0.8666, 0.4820, 0.4138, 0.5067, 0.5250, 0.5767],
[0.6250, 0.4103, 0.8950, 0.4400, 0.3912, 0.5650, 0.6050, 0.5133],
[0.6057, 0.4011, 0.8750, 0.4267, 0.4400, 0.5800, 0.5845, 0.5585],
[0.6198, 0.4075, 0.8650, 0.5617, 0.4150, 0.4367, 0.5450, 0.5650],
[0.6201, 0.4082, 0.8827, 0.3715, 0.3825, 0.2712, 0.5845, 0.5412],
[0.6260, 0.4161, 0.9000, 0.3833, 0.4450, 0.2133, 0.6237, 0.4986]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6097, 0.3810, 0.8444, 0.3163, 0.4960, 0.2205, 0.6758, 0.5090],
[0.6230, 0.4154, 0.7445, 0.3101, 0.4256, 0.1573, 0.5326, 0.5013],
[0.6116, 0.4013, 0.8533, 0.5269, 0.4231, 0.5081, 0.5280, 0.5487],
[0.5224, 0.3296, 0.8872, 0.4637, 0.4107, 0.5685, 0.5906, 0.5198],
[0.4906, 0.3321, 0.8419, 0.4613, 0.4652, 0.5174, 0.5737, 0.5340],
[0.6110, 0.3884, 0.8540, 0.6034, 0.4019, 0.4349, 0.5250, 0.5502],
[0.6076, 0.3926, 0.8540, 0.3914, 0.3840, 0.2692, 0.5650, 0.5152],
[0.6196, 0.4102, 0.8748, 0.4050, 0.4474, 0.2056, 0.5809, 0.5021]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6275, 0.4013, 0.8850, 0.2833, 0.4975, 0.2233, 0.7058, 0.5343],
[0.6175, 0.4013, 0.7734, 0.2783, 0.4475, 0.1786, 0.5790, 0.5351],
[0.6148, 0.4076, 0.8666, 0.4820, 0.4137, 0.5067, 0.5250, 0.5767],
[0.6250, 0.4103, 0.8950, 0.4400, 0.3913, 0.5650, 0.6050, 0.5133],
[0.6057, 0.4011, 0.8750, 0.4267, 0.4400, 0.5800, 0.5845, 0.5585],
[0.6198, 0.4075, 0.8650, 0.5617, 0.4150, 0.4367, 0.5450, 0.5650],
[0.6201, 0.4082, 0.8827, 0.3715, 0.3825, 0.2712, 0.5845, 0.5412],
[0.6260, 0.4161, 0.9000, 0.3833, 0.4450, 0.2133, 0.6237, 0.4986]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03575298085343093
step: 22
running loss: 0.0016251354933377695
Train Steps: 22/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6199, 0.3952, 0.8573, 0.5374, 0.4075, 0.4687, 0.5942, 0.5377],
[0.6205, 0.4062, 0.8337, 0.2683, 0.3675, 0.4283, 0.6338, 0.5250],
[0.6310, 0.4017, 0.8563, 0.5800, 0.3688, 0.4750, 0.6326, 0.5006],
[0.6179, 0.4008, 0.8600, 0.4015, 0.3932, 0.2515, 0.5711, 0.5438],
[0.6157, 0.3956, 0.8323, 0.4138, 0.3479, 0.4431, 0.5914, 0.5131],
[0.6226, 0.4098, 0.8912, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367],
[0.6148, 0.4053, 0.8750, 0.4550, 0.4850, 0.5218, 0.5863, 0.5567],
[0.6206, 0.4123, 0.7175, 0.2400, 0.3887, 0.2933, 0.6225, 0.5750]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5948, 0.3777, 0.8598, 0.5559, 0.4323, 0.4669, 0.5633, 0.5099],
[0.5748, 0.3623, 0.8276, 0.3119, 0.4020, 0.3961, 0.6031, 0.4939],
[0.5953, 0.3702, 0.8583, 0.6192, 0.4189, 0.4924, 0.5780, 0.4961],
[0.5731, 0.3803, 0.8354, 0.3893, 0.4161, 0.2656, 0.5426, 0.5256],
[0.6213, 0.3960, 0.8607, 0.4340, 0.3896, 0.4437, 0.5424, 0.4852],
[0.5919, 0.3985, 0.8903, 0.4316, 0.4365, 0.2533, 0.5274, 0.5285],
[0.5917, 0.3857, 0.8968, 0.4565, 0.4929, 0.4819, 0.5501, 0.5295],
[0.6593, 0.4371, 0.7370, 0.2946, 0.4135, 0.2788, 0.5746, 0.5380]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6199, 0.3952, 0.8573, 0.5374, 0.4075, 0.4687, 0.5942, 0.5377],
[0.6205, 0.4062, 0.8338, 0.2683, 0.3675, 0.4283, 0.6338, 0.5250],
[0.6310, 0.4017, 0.8562, 0.5800, 0.3688, 0.4750, 0.6326, 0.5006],
[0.6179, 0.4008, 0.8600, 0.4015, 0.3932, 0.2515, 0.5711, 0.5438],
[0.6157, 0.3956, 0.8323, 0.4138, 0.3479, 0.4431, 0.5914, 0.5131],
[0.6226, 0.4098, 0.8913, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367],
[0.6148, 0.4053, 0.8750, 0.4550, 0.4850, 0.5218, 0.5863, 0.5567],
[0.6206, 0.4123, 0.7175, 0.2400, 0.3887, 0.2933, 0.6225, 0.5750]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03661173034925014
step: 23
running loss: 0.0015918143630108755
Train Steps: 23/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6132, 0.4037, 0.6963, 0.2217, 0.4100, 0.1950, 0.5395, 0.5175],
[0.6086, 0.3981, 0.8700, 0.4750, 0.4512, 0.5283, 0.5324, 0.5038],
[0.6260, 0.4214, 0.8538, 0.5500, 0.3663, 0.3767, 0.5587, 0.5983],
[0.6271, 0.4024, 0.9000, 0.3517, 0.3700, 0.4517, 0.6931, 0.5285],
[ nan, nan, 0.7725, 0.2611, 0.3675, 0.2733, 0.5413, 0.5167],
[0.6200, 0.4070, 0.8938, 0.4183, 0.3538, 0.4567, 0.6175, 0.5400],
[0.6289, 0.4019, 0.8113, 0.5467, 0.3875, 0.5017, 0.7367, 0.5332],
[0.6274, 0.4003, 0.8638, 0.5967, 0.3688, 0.4900, 0.6108, 0.4661]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6434, 0.4394, 0.7563, 0.2616, 0.4180, 0.1771, 0.5199, 0.4975],
[0.6028, 0.4039, 0.8736, 0.4948, 0.4675, 0.5166, 0.5356, 0.5194],
[0.6994, 0.4571, 0.8777, 0.5358, 0.4021, 0.4242, 0.5314, 0.5979],
[0.6870, 0.4445, 0.9097, 0.3819, 0.3974, 0.4629, 0.6863, 0.5208],
[0.1170, 0.0916, 0.7732, 0.2960, 0.3928, 0.2935, 0.5456, 0.5585],
[0.7068, 0.4634, 0.9245, 0.4283, 0.4178, 0.5128, 0.6311, 0.5296],
[0.6364, 0.4310, 0.8491, 0.5356, 0.3984, 0.5179, 0.6621, 0.5221],
[0.7051, 0.4599, 0.8635, 0.5810, 0.4164, 0.4868, 0.6125, 0.5172]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6132, 0.4037, 0.6963, 0.2217, 0.4100, 0.1950, 0.5395, 0.5175],
[0.6086, 0.3981, 0.8700, 0.4750, 0.4512, 0.5283, 0.5324, 0.5038],
[0.6260, 0.4214, 0.8537, 0.5500, 0.3663, 0.3767, 0.5587, 0.5983],
[0.6271, 0.4024, 0.9000, 0.3517, 0.3700, 0.4517, 0.6931, 0.5285],
[0.0000, 0.0000, 0.7725, 0.2611, 0.3675, 0.2733, 0.5412, 0.5167],
[0.6200, 0.4070, 0.8938, 0.4183, 0.3537, 0.4567, 0.6175, 0.5400],
[0.6289, 0.4019, 0.8112, 0.5467, 0.3875, 0.5017, 0.7367, 0.5332],
[0.6274, 0.4003, 0.8637, 0.5967, 0.3688, 0.4900, 0.6108, 0.4661]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03813450282905251
step: 24
running loss: 0.001588937617877188
Train Steps: 24/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6198, 0.4115, 0.7762, 0.2717, 0.3713, 0.3200, 0.5837, 0.5683],
[0.6257, 0.4060, 0.8300, 0.2333, 0.4688, 0.2583, 0.7050, 0.5633],
[0.6353, 0.4128, 0.9138, 0.3533, 0.4688, 0.3250, 0.7145, 0.5991],
[0.6286, 0.4274, 0.8500, 0.4500, 0.4525, 0.2583, 0.5440, 0.6209],
[0.6185, 0.4079, 0.8838, 0.4617, 0.4838, 0.5650, 0.6175, 0.5850],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5413, 0.5683],
[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758],
[0.6283, 0.4283, 0.7477, 0.3542, 0.5125, 0.1917, 0.5500, 0.6167]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5181, 0.3658, 0.7687, 0.2471, 0.3332, 0.3298, 0.5577, 0.5300],
[0.5627, 0.3805, 0.8305, 0.2223, 0.4413, 0.2407, 0.6896, 0.5307],
[0.4681, 0.3387, 0.8765, 0.3318, 0.4165, 0.3352, 0.7017, 0.5461],
[0.5176, 0.3823, 0.8142, 0.4260, 0.4169, 0.3081, 0.5115, 0.5719],
[0.5179, 0.3504, 0.8527, 0.4173, 0.4445, 0.5811, 0.5924, 0.5427],
[0.5762, 0.4029, 0.8374, 0.5142, 0.3543, 0.3983, 0.5364, 0.5255],
[0.5836, 0.3958, 0.8593, 0.4602, 0.3841, 0.5372, 0.6346, 0.4635],
[0.5452, 0.3705, 0.7265, 0.3065, 0.4365, 0.2370, 0.5239, 0.5725]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6198, 0.4115, 0.7763, 0.2717, 0.3713, 0.3200, 0.5838, 0.5683],
[0.6257, 0.4060, 0.8300, 0.2333, 0.4688, 0.2583, 0.7050, 0.5633],
[0.6353, 0.4128, 0.9137, 0.3533, 0.4688, 0.3250, 0.7145, 0.5991],
[0.6286, 0.4274, 0.8500, 0.4500, 0.4525, 0.2583, 0.5440, 0.6209],
[0.6184, 0.4079, 0.8838, 0.4617, 0.4837, 0.5650, 0.6175, 0.5850],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5412, 0.5683],
[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758],
[0.6283, 0.4283, 0.7477, 0.3542, 0.5125, 0.1917, 0.5500, 0.6167]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0023, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0023, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.040397314936853945
step: 25
running loss: 0.0016158925974741579
Train Steps: 25/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.7553, 0.2722, 0.3875, 0.2550, 0.5125, 0.5633],
[0.6228, 0.4119, 0.7938, 0.2233, 0.4674, 0.1773, 0.6188, 0.5433],
[0.6132, 0.4118, 0.8200, 0.3633, 0.3563, 0.5400, 0.5787, 0.5136],
[0.6251, 0.4163, 0.8662, 0.4467, 0.3625, 0.3567, 0.6038, 0.5533],
[0.6185, 0.4098, 0.8838, 0.4900, 0.4537, 0.5800, 0.6288, 0.5400],
[0.6202, 0.4064, 0.7879, 0.2179, 0.4567, 0.1725, 0.5955, 0.5478],
[0.6278, 0.4253, 0.8875, 0.5017, 0.4113, 0.2750, 0.5413, 0.6196],
[0.6145, 0.4008, 0.8750, 0.5383, 0.3975, 0.4650, 0.5563, 0.5533]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.0116, 0.0246, 0.7393, 0.2538, 0.3489, 0.2734, 0.5412, 0.5697],
[0.6360, 0.4286, 0.8073, 0.2053, 0.4622, 0.1909, 0.6346, 0.5329],
[0.5926, 0.4112, 0.8407, 0.3210, 0.3518, 0.5539, 0.6553, 0.5225],
[0.6690, 0.4513, 0.8514, 0.4062, 0.3517, 0.3713, 0.6100, 0.5537],
[0.6008, 0.3862, 0.8725, 0.4734, 0.4421, 0.6024, 0.6467, 0.5385],
[0.5480, 0.3798, 0.7652, 0.2324, 0.4457, 0.1914, 0.6148, 0.5599],
[0.6214, 0.4346, 0.8467, 0.4490, 0.4235, 0.3341, 0.5924, 0.6016],
[0.6507, 0.4407, 0.8519, 0.5101, 0.3846, 0.4925, 0.6274, 0.5505]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.7553, 0.2722, 0.3875, 0.2550, 0.5125, 0.5633],
[0.6228, 0.4119, 0.7937, 0.2233, 0.4674, 0.1773, 0.6187, 0.5433],
[0.6132, 0.4118, 0.8200, 0.3633, 0.3562, 0.5400, 0.5787, 0.5136],
[0.6252, 0.4162, 0.8662, 0.4467, 0.3625, 0.3567, 0.6037, 0.5533],
[0.6185, 0.4098, 0.8838, 0.4900, 0.4538, 0.5800, 0.6288, 0.5400],
[0.6202, 0.4064, 0.7879, 0.2179, 0.4567, 0.1725, 0.5955, 0.5478],
[0.6278, 0.4253, 0.8875, 0.5017, 0.4112, 0.2750, 0.5413, 0.6196],
[0.6145, 0.4008, 0.8750, 0.5383, 0.3975, 0.4650, 0.5562, 0.5533]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04119387164246291
step: 26
running loss: 0.0015843796785562658
Train Steps: 26/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6157, 0.3956, 0.8323, 0.4138, 0.3479, 0.4431, 0.5914, 0.5131],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3513, 0.4050, 0.6112, 0.5500],
[0.6277, 0.4083, 0.8350, 0.2717, 0.4562, 0.1800, 0.5918, 0.4878],
[0.6200, 0.4112, 0.8862, 0.4100, 0.3638, 0.4917, 0.6088, 0.6050],
[ nan, nan, 0.8488, 0.2300, 0.5563, 0.2100, 0.7390, 0.5679],
[0.6164, 0.4066, 0.6625, 0.3033, 0.3775, 0.2967, 0.5725, 0.5833],
[ nan, nan, 0.7097, 0.2346, 0.4250, 0.1850, 0.5175, 0.5583],
[0.6263, 0.4030, 0.9000, 0.4767, 0.3800, 0.5167, 0.6415, 0.4771]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7681, 0.5108, 0.8592, 0.4223, 0.3623, 0.4802, 0.6189, 0.5313],
[0.7198, 0.4836, 0.8040, 0.2694, 0.3555, 0.4219, 0.6543, 0.5635],
[0.5966, 0.3962, 0.8460, 0.2799, 0.4625, 0.2163, 0.6013, 0.5294],
[0.6678, 0.4680, 0.8998, 0.4368, 0.3742, 0.5103, 0.6602, 0.6020],
[0.1118, 0.0834, 0.8835, 0.2769, 0.5051, 0.2371, 0.7420, 0.5724],
[0.6195, 0.4208, 0.7383, 0.3169, 0.3674, 0.2995, 0.5883, 0.6082],
[0.1565, 0.1337, 0.7329, 0.2517, 0.4242, 0.1904, 0.5244, 0.5901],
[0.7288, 0.4908, 0.9129, 0.4972, 0.3733, 0.5528, 0.6372, 0.5112]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6157, 0.3956, 0.8323, 0.4138, 0.3479, 0.4431, 0.5914, 0.5131],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3512, 0.4050, 0.6112, 0.5500],
[0.6277, 0.4083, 0.8350, 0.2717, 0.4563, 0.1800, 0.5918, 0.4878],
[0.6200, 0.4112, 0.8863, 0.4100, 0.3638, 0.4917, 0.6087, 0.6050],
[0.0000, 0.0000, 0.8487, 0.2300, 0.5562, 0.2100, 0.7390, 0.5679],
[0.6164, 0.4066, 0.6625, 0.3033, 0.3775, 0.2967, 0.5725, 0.5833],
[0.0000, 0.0000, 0.7097, 0.2346, 0.4250, 0.1850, 0.5175, 0.5583],
[0.6263, 0.4029, 0.9000, 0.4767, 0.3800, 0.5167, 0.6415, 0.4771]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0027, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0027, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.043881157762371004
step: 27
running loss: 0.0016252280652730002
Train Steps: 27/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6092, 0.4001, 0.8638, 0.4867, 0.4288, 0.5367, 0.5484, 0.5064],
[0.6304, 0.4024, 0.8925, 0.4800, 0.3937, 0.4817, 0.7485, 0.5297],
[0.6311, 0.3998, 0.7975, 0.5767, 0.3838, 0.4850, 0.7327, 0.5343],
[0.6263, 0.4030, 0.9000, 0.4767, 0.3800, 0.5167, 0.6415, 0.4771],
[0.6187, 0.4104, 0.7126, 0.2069, 0.3950, 0.2517, 0.5913, 0.5683],
[0.6102, 0.4001, 0.7738, 0.3583, 0.3463, 0.3800, 0.5524, 0.5689],
[0.6243, 0.4128, 0.7762, 0.2717, 0.3825, 0.3133, 0.6212, 0.5417],
[0.6339, 0.4102, 0.9088, 0.4767, 0.3925, 0.5283, 0.7509, 0.5390]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5978, 0.3811, 0.8802, 0.4775, 0.4360, 0.5232, 0.5414, 0.5480],
[0.6242, 0.3893, 0.8940, 0.4716, 0.3845, 0.4669, 0.7091, 0.5600],
[0.5777, 0.3764, 0.8253, 0.5264, 0.3796, 0.4584, 0.6991, 0.5487],
[0.5385, 0.3593, 0.9121, 0.4667, 0.3836, 0.5002, 0.6042, 0.5307],
[0.5272, 0.3532, 0.7427, 0.2166, 0.3878, 0.2256, 0.5639, 0.5856],
[0.5912, 0.3912, 0.8115, 0.3456, 0.3531, 0.3754, 0.5573, 0.6048],
[0.5342, 0.3543, 0.8327, 0.2611, 0.4037, 0.2601, 0.6445, 0.5905],
[0.5617, 0.3802, 0.9341, 0.4721, 0.4119, 0.5319, 0.7273, 0.6080]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6092, 0.4001, 0.8637, 0.4867, 0.4288, 0.5367, 0.5484, 0.5064],
[0.6304, 0.4024, 0.8925, 0.4800, 0.3938, 0.4817, 0.7485, 0.5297],
[0.6311, 0.3998, 0.7975, 0.5767, 0.3837, 0.4850, 0.7327, 0.5343],
[0.6263, 0.4029, 0.9000, 0.4767, 0.3800, 0.5167, 0.6415, 0.4771],
[0.6187, 0.4103, 0.7126, 0.2069, 0.3950, 0.2517, 0.5913, 0.5683],
[0.6102, 0.4001, 0.7738, 0.3583, 0.3462, 0.3800, 0.5524, 0.5689],
[0.6243, 0.4128, 0.7763, 0.2717, 0.3825, 0.3133, 0.6212, 0.5417],
[0.6339, 0.4102, 0.9087, 0.4767, 0.3925, 0.5283, 0.7509, 0.5390]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04513794963713735
step: 28
running loss: 0.0016120696298977627
Train Steps: 28/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6055, 0.4015, 0.7425, 0.2033, 0.4113, 0.1883, 0.5217, 0.4823],
[0.6223, 0.4171, 0.8750, 0.5500, 0.4050, 0.4817, 0.5675, 0.5600],
[0.6296, 0.4060, 0.9100, 0.3267, 0.4726, 0.3367, 0.7446, 0.5355],
[0.6219, 0.3934, 0.8688, 0.5267, 0.4313, 0.4967, 0.5988, 0.4983],
[0.6267, 0.4080, 0.8438, 0.2633, 0.4763, 0.1800, 0.6259, 0.5240],
[0.6198, 0.4130, 0.8762, 0.4117, 0.3650, 0.4900, 0.5707, 0.5103],
[0.6131, 0.4037, 0.6907, 0.2819, 0.3688, 0.2700, 0.5217, 0.5680],
[0.6075, 0.4007, 0.8275, 0.4917, 0.4050, 0.5100, 0.5167, 0.5280]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4372, 0.2758, 0.7354, 0.1883, 0.3909, 0.1579, 0.5633, 0.5465],
[0.6577, 0.4155, 0.8830, 0.5415, 0.3977, 0.4813, 0.6043, 0.5893],
[0.5946, 0.3737, 0.8991, 0.3180, 0.4474, 0.3089, 0.7670, 0.5524],
[0.5719, 0.3405, 0.8579, 0.5194, 0.4275, 0.4948, 0.6411, 0.5257],
[0.4898, 0.3002, 0.8607, 0.2459, 0.4668, 0.1549, 0.6598, 0.5464],
[0.5073, 0.3276, 0.8746, 0.3994, 0.3560, 0.4804, 0.6034, 0.5596],
[0.5150, 0.3232, 0.6938, 0.2471, 0.3633, 0.2815, 0.5660, 0.5930],
[0.5969, 0.3752, 0.8305, 0.4599, 0.3981, 0.4965, 0.5806, 0.5713]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6055, 0.4015, 0.7425, 0.2033, 0.4112, 0.1883, 0.5217, 0.4823],
[0.6223, 0.4171, 0.8750, 0.5500, 0.4050, 0.4817, 0.5675, 0.5600],
[0.6296, 0.4060, 0.9100, 0.3267, 0.4726, 0.3367, 0.7446, 0.5355],
[0.6219, 0.3934, 0.8687, 0.5267, 0.4313, 0.4967, 0.5987, 0.4983],
[0.6267, 0.4080, 0.8438, 0.2633, 0.4762, 0.1800, 0.6259, 0.5240],
[0.6198, 0.4130, 0.8763, 0.4117, 0.3650, 0.4900, 0.5707, 0.5103],
[0.6131, 0.4036, 0.6907, 0.2819, 0.3688, 0.2700, 0.5217, 0.5680],
[0.6075, 0.4006, 0.8275, 0.4917, 0.4050, 0.5100, 0.5167, 0.5280]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0024, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0024, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04752955154981464
step: 29
running loss: 0.0016389500534418843
Train Steps: 29/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6201, 0.4027, 0.8029, 0.2728, 0.4042, 0.2310, 0.5980, 0.5391],
[0.6190, 0.4135, 0.8000, 0.4883, 0.3566, 0.3647, 0.5613, 0.5900],
[0.6353, 0.4128, 0.8488, 0.2600, 0.5525, 0.1616, 0.6694, 0.5540],
[0.6093, 0.3990, 0.8400, 0.4333, 0.3688, 0.4633, 0.5560, 0.5656],
[0.6169, 0.4052, 0.8742, 0.4779, 0.4288, 0.4917, 0.5763, 0.5617],
[0.6133, 0.4066, 0.6787, 0.2617, 0.3800, 0.2433, 0.5147, 0.5358],
[0.6186, 0.3967, 0.7337, 0.1992, 0.4120, 0.2508, 0.6105, 0.5395],
[0.6311, 0.4008, 0.7935, 0.5746, 0.3900, 0.5033, 0.6955, 0.5366]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5865, 0.3450, 0.7975, 0.2635, 0.4103, 0.2449, 0.6346, 0.5429],
[0.6215, 0.3994, 0.8307, 0.4658, 0.3353, 0.3533, 0.5554, 0.5437],
[0.2566, 0.1509, 0.8737, 0.2176, 0.5307, 0.1564, 0.7105, 0.5645],
[0.6468, 0.3995, 0.8455, 0.4233, 0.3543, 0.4662, 0.5918, 0.5448],
[0.5884, 0.3784, 0.8735, 0.4595, 0.4237, 0.4856, 0.5844, 0.5492],
[0.5698, 0.3733, 0.7134, 0.2465, 0.3807, 0.2194, 0.5472, 0.5236],
[0.6155, 0.3682, 0.7660, 0.2156, 0.3963, 0.2318, 0.6159, 0.5211],
[0.6217, 0.3869, 0.8140, 0.5425, 0.3716, 0.5056, 0.6957, 0.5169]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6201, 0.4027, 0.8029, 0.2728, 0.4042, 0.2310, 0.5980, 0.5391],
[0.6190, 0.4135, 0.8000, 0.4883, 0.3566, 0.3647, 0.5612, 0.5900],
[0.6353, 0.4128, 0.8487, 0.2600, 0.5525, 0.1616, 0.6694, 0.5540],
[0.6093, 0.3990, 0.8400, 0.4333, 0.3688, 0.4633, 0.5560, 0.5656],
[0.6169, 0.4052, 0.8742, 0.4779, 0.4288, 0.4917, 0.5763, 0.5617],
[0.6133, 0.4065, 0.6787, 0.2617, 0.3800, 0.2433, 0.5147, 0.5358],
[0.6186, 0.3967, 0.7337, 0.1992, 0.4120, 0.2508, 0.6105, 0.5395],
[0.6311, 0.4008, 0.7935, 0.5746, 0.3900, 0.5033, 0.6955, 0.5366]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0038, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0038, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05135433666873723
step: 30
running loss: 0.0017118112222912411
Train Steps: 30/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6212, 0.4033, 0.8938, 0.4167, 0.3813, 0.4267, 0.5613, 0.5583],
[0.6283, 0.4283, 0.7477, 0.3542, 0.5125, 0.1917, 0.5500, 0.6167],
[0.6261, 0.4066, 0.8325, 0.2150, 0.4763, 0.2667, 0.7002, 0.5633],
[0.6333, 0.4037, 0.8638, 0.5733, 0.4012, 0.4717, 0.6369, 0.4938],
[0.6357, 0.4139, 0.8450, 0.5883, 0.3775, 0.4950, 0.6488, 0.5297],
[0.6200, 0.4086, 0.8414, 0.2974, 0.4117, 0.2274, 0.5869, 0.5391],
[ nan, nan, 0.6900, 0.1917, 0.3937, 0.2367, 0.5240, 0.5246],
[0.6102, 0.4005, 0.8688, 0.5100, 0.4813, 0.5400, 0.5404, 0.5064]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5668, 0.3629, 0.8842, 0.4258, 0.3682, 0.4059, 0.5781, 0.5503],
[0.6187, 0.3936, 0.7304, 0.2942, 0.4803, 0.2003, 0.5441, 0.5974],
[0.6314, 0.3861, 0.8064, 0.1883, 0.4717, 0.2359, 0.7089, 0.5526],
[0.6939, 0.4356, 0.8328, 0.5578, 0.3852, 0.4608, 0.6231, 0.4841],
[0.6649, 0.4234, 0.8089, 0.5228, 0.3513, 0.4833, 0.6610, 0.4989],
[0.6308, 0.4149, 0.8182, 0.2647, 0.4233, 0.2208, 0.5827, 0.5212],
[0.1004, 0.0594, 0.6898, 0.1966, 0.4079, 0.2105, 0.5226, 0.5340],
[0.6396, 0.4302, 0.8272, 0.4877, 0.4743, 0.4958, 0.5450, 0.5044]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6212, 0.4033, 0.8938, 0.4167, 0.3812, 0.4267, 0.5612, 0.5583],
[0.6283, 0.4283, 0.7477, 0.3542, 0.5125, 0.1917, 0.5500, 0.6167],
[0.6261, 0.4066, 0.8325, 0.2150, 0.4762, 0.2667, 0.7002, 0.5633],
[0.6334, 0.4037, 0.8637, 0.5733, 0.4013, 0.4717, 0.6369, 0.4938],
[0.6357, 0.4139, 0.8450, 0.5883, 0.3775, 0.4950, 0.6488, 0.5297],
[0.6199, 0.4086, 0.8414, 0.2974, 0.4117, 0.2274, 0.5869, 0.5391],
[0.0000, 0.0000, 0.6900, 0.1917, 0.3938, 0.2367, 0.5240, 0.5246],
[0.6102, 0.4005, 0.8687, 0.5100, 0.4812, 0.5400, 0.5404, 0.5064]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.052187160414177924
step: 31
running loss: 0.0016834567875541266
Train Steps: 31/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6203, 0.4096, 0.8862, 0.4267, 0.3538, 0.4117, 0.6025, 0.5650],
[0.6201, 0.4116, 0.8725, 0.4733, 0.3700, 0.3217, 0.5386, 0.5767],
[0.6129, 0.4114, 0.6950, 0.2467, 0.4050, 0.2133, 0.5363, 0.5550],
[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383],
[0.6264, 0.4067, 0.9050, 0.4183, 0.3775, 0.4600, 0.6308, 0.4862],
[0.6179, 0.4118, 0.7278, 0.4237, 0.3588, 0.3400, 0.5675, 0.5917],
[0.6082, 0.4024, 0.8738, 0.4017, 0.3688, 0.3950, 0.5306, 0.5136],
[ nan, nan, 0.8300, 0.3150, 0.3588, 0.3383, 0.5208, 0.5194]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6223, 0.4037, 0.8574, 0.4101, 0.3940, 0.3909, 0.6264, 0.5640],
[0.6208, 0.4085, 0.8440, 0.4685, 0.4030, 0.3002, 0.5461, 0.5567],
[0.6917, 0.4606, 0.6627, 0.2580, 0.4542, 0.2239, 0.5561, 0.5403],
[0.6006, 0.3673, 0.7958, 0.3297, 0.3836, 0.3588, 0.6420, 0.5311],
[0.6163, 0.3988, 0.8610, 0.4075, 0.4042, 0.4429, 0.6372, 0.4826],
[0.6346, 0.4224, 0.7407, 0.3825, 0.3826, 0.3340, 0.5764, 0.5770],
[0.5733, 0.3838, 0.8238, 0.4076, 0.3889, 0.3602, 0.5383, 0.4948],
[0.4540, 0.2950, 0.7634, 0.2964, 0.3890, 0.3205, 0.5472, 0.5035]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6203, 0.4096, 0.8863, 0.4267, 0.3537, 0.4117, 0.6025, 0.5650],
[0.6201, 0.4116, 0.8725, 0.4733, 0.3700, 0.3217, 0.5386, 0.5767],
[0.6129, 0.4114, 0.6950, 0.2467, 0.4050, 0.2133, 0.5362, 0.5550],
[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383],
[0.6264, 0.4067, 0.9050, 0.4183, 0.3775, 0.4600, 0.6308, 0.4862],
[0.6179, 0.4118, 0.7278, 0.4237, 0.3587, 0.3400, 0.5675, 0.5917],
[0.6082, 0.4024, 0.8737, 0.4017, 0.3688, 0.3950, 0.5306, 0.5136],
[0.0000, 0.0000, 0.8300, 0.3150, 0.3587, 0.3383, 0.5208, 0.5194]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0053, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0053, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05747255013557151
step: 32
running loss: 0.0017960171917366097
Train Steps: 32/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6137, 0.4084, 0.8076, 0.3889, 0.3650, 0.3150, 0.5356, 0.5896],
[0.6182, 0.3982, 0.7541, 0.2379, 0.3959, 0.2792, 0.6079, 0.5389],
[0.6275, 0.4157, 0.8337, 0.5800, 0.3763, 0.4200, 0.5547, 0.6125],
[0.6129, 0.4069, 0.8750, 0.5067, 0.3875, 0.4233, 0.5235, 0.5881],
[0.6109, 0.3943, 0.8525, 0.4950, 0.4338, 0.4800, 0.5449, 0.5383],
[0.6276, 0.4095, 0.8237, 0.2250, 0.4662, 0.1783, 0.6171, 0.4869],
[0.6156, 0.4125, 0.8850, 0.4833, 0.4550, 0.5817, 0.5765, 0.5084],
[0.6110, 0.3984, 0.8750, 0.4933, 0.4625, 0.4950, 0.5578, 0.5676]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6144, 0.4203, 0.7985, 0.3863, 0.3475, 0.2884, 0.5326, 0.5545],
[0.5494, 0.3584, 0.7314, 0.2205, 0.3959, 0.2670, 0.5991, 0.5164],
[0.6711, 0.4399, 0.7896, 0.5625, 0.3788, 0.4291, 0.5623, 0.5686],
[0.5554, 0.3771, 0.8378, 0.5346, 0.3878, 0.4062, 0.5128, 0.5303],
[0.6204, 0.4052, 0.8259, 0.4745, 0.4359, 0.4610, 0.5449, 0.5183],
[0.6332, 0.4169, 0.7866, 0.2161, 0.5003, 0.2074, 0.6308, 0.4744],
[0.5956, 0.4142, 0.8529, 0.4707, 0.4455, 0.5582, 0.5868, 0.5015],
[0.6420, 0.4306, 0.8381, 0.4839, 0.4555, 0.4854, 0.5397, 0.5353]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6137, 0.4084, 0.8076, 0.3889, 0.3650, 0.3150, 0.5356, 0.5896],
[0.6182, 0.3982, 0.7541, 0.2379, 0.3959, 0.2792, 0.6079, 0.5389],
[0.6275, 0.4157, 0.8338, 0.5800, 0.3762, 0.4200, 0.5547, 0.6125],
[0.6129, 0.4069, 0.8750, 0.5067, 0.3875, 0.4233, 0.5235, 0.5881],
[0.6109, 0.3943, 0.8525, 0.4950, 0.4338, 0.4800, 0.5449, 0.5383],
[0.6276, 0.4095, 0.8238, 0.2250, 0.4663, 0.1783, 0.6171, 0.4869],
[0.6155, 0.4124, 0.8850, 0.4833, 0.4550, 0.5817, 0.5765, 0.5084],
[0.6110, 0.3984, 0.8750, 0.4933, 0.4625, 0.4950, 0.5578, 0.5676]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.058107397344429046
step: 33
running loss: 0.001760830222558456
Train Steps: 33/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6190, 0.4135, 0.8000, 0.4883, 0.3566, 0.3647, 0.5613, 0.5900],
[0.6229, 0.4066, 0.8513, 0.5717, 0.4500, 0.5050, 0.6025, 0.5350],
[ nan, nan, 0.7515, 0.2708, 0.3987, 0.2267, 0.5162, 0.5567],
[0.6200, 0.4049, 0.8638, 0.5617, 0.4125, 0.5100, 0.6013, 0.5317],
[0.6082, 0.4042, 0.6975, 0.1917, 0.4100, 0.1983, 0.5502, 0.5578],
[0.6030, 0.3969, 0.7988, 0.3917, 0.3450, 0.3667, 0.5266, 0.4700],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098],
[0.6164, 0.3972, 0.7818, 0.3381, 0.3599, 0.3387, 0.5880, 0.5153]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6827, 0.4496, 0.8256, 0.4827, 0.3709, 0.3676, 0.5322, 0.5571],
[0.6665, 0.4444, 0.8460, 0.5793, 0.4669, 0.4921, 0.5802, 0.5466],
[0.1378, 0.0869, 0.7551, 0.2594, 0.4420, 0.2424, 0.4932, 0.5484],
[0.6830, 0.4586, 0.8622, 0.5962, 0.4376, 0.4989, 0.5673, 0.5239],
[0.6869, 0.4526, 0.6950, 0.2222, 0.4388, 0.2058, 0.5477, 0.5366],
[0.6921, 0.4603, 0.8187, 0.4140, 0.3610, 0.3888, 0.5339, 0.5119],
[0.6835, 0.4319, 0.8662, 0.4696, 0.3985, 0.5319, 0.5821, 0.5164],
[0.6697, 0.4426, 0.7883, 0.3365, 0.3718, 0.3618, 0.5934, 0.5166]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6190, 0.4135, 0.8000, 0.4883, 0.3566, 0.3647, 0.5612, 0.5900],
[0.6229, 0.4066, 0.8512, 0.5717, 0.4500, 0.5050, 0.6025, 0.5350],
[0.0000, 0.0000, 0.7515, 0.2708, 0.3988, 0.2267, 0.5163, 0.5567],
[0.6199, 0.4049, 0.8637, 0.5617, 0.4125, 0.5100, 0.6012, 0.5317],
[0.6082, 0.4042, 0.6975, 0.1917, 0.4100, 0.1983, 0.5502, 0.5578],
[0.6030, 0.3969, 0.7987, 0.3917, 0.3450, 0.3667, 0.5266, 0.4700],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098],
[0.6164, 0.3972, 0.7818, 0.3381, 0.3599, 0.3387, 0.5880, 0.5153]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.059539014648180455
step: 34
running loss: 0.0017511474896523664
Train Steps: 34/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6205, 0.4004, 0.8938, 0.4883, 0.3663, 0.5000, 0.6357, 0.4947],
[0.6193, 0.4165, 0.8838, 0.4700, 0.4150, 0.4867, 0.5427, 0.5261],
[0.6201, 0.4116, 0.8725, 0.4733, 0.3700, 0.3217, 0.5386, 0.5767],
[0.6186, 0.4060, 0.8750, 0.5050, 0.3538, 0.4367, 0.5813, 0.6083],
[0.6307, 0.4029, 0.8650, 0.5200, 0.3763, 0.4017, 0.7311, 0.5366],
[0.6162, 0.4014, 0.8800, 0.5333, 0.3750, 0.4817, 0.5988, 0.5283],
[0.6357, 0.4139, 0.8450, 0.5883, 0.3775, 0.4950, 0.6488, 0.5297],
[0.6177, 0.4086, 0.8738, 0.3950, 0.3775, 0.5600, 0.6225, 0.5700]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6581, 0.4109, 0.8762, 0.4965, 0.3920, 0.4964, 0.5997, 0.5183],
[0.5823, 0.3867, 0.8585, 0.4944, 0.4278, 0.4738, 0.5168, 0.5337],
[0.6553, 0.4376, 0.8685, 0.4777, 0.3748, 0.3175, 0.5004, 0.5822],
[0.6329, 0.4304, 0.8425, 0.5011, 0.4032, 0.4497, 0.5394, 0.5825],
[0.6444, 0.4426, 0.8537, 0.5210, 0.4073, 0.3890, 0.6372, 0.5359],
[0.6312, 0.4139, 0.8603, 0.5559, 0.4056, 0.4757, 0.5384, 0.5498],
[0.6495, 0.4212, 0.8286, 0.5655, 0.3784, 0.5000, 0.6258, 0.5397],
[0.6462, 0.4144, 0.8579, 0.4170, 0.3991, 0.5355, 0.5896, 0.5531]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6205, 0.4004, 0.8938, 0.4883, 0.3663, 0.5000, 0.6357, 0.4947],
[0.6193, 0.4165, 0.8838, 0.4700, 0.4150, 0.4867, 0.5427, 0.5261],
[0.6201, 0.4116, 0.8725, 0.4733, 0.3700, 0.3217, 0.5386, 0.5767],
[0.6186, 0.4060, 0.8750, 0.5050, 0.3537, 0.4367, 0.5813, 0.6083],
[0.6307, 0.4029, 0.8650, 0.5200, 0.3762, 0.4017, 0.7311, 0.5366],
[0.6162, 0.4014, 0.8800, 0.5333, 0.3750, 0.4817, 0.5987, 0.5283],
[0.6357, 0.4139, 0.8450, 0.5883, 0.3775, 0.4950, 0.6488, 0.5297],
[0.6177, 0.4085, 0.8737, 0.3950, 0.3775, 0.5600, 0.6225, 0.5700]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06021460593910888
step: 35
running loss: 0.001720417312545968
Train Steps: 35/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6200, 0.4071, 0.7338, 0.1917, 0.4200, 0.2450, 0.6150, 0.5517],
[0.6261, 0.4066, 0.8325, 0.2150, 0.4763, 0.2667, 0.7002, 0.5633],
[0.6092, 0.4001, 0.8638, 0.4867, 0.4288, 0.5367, 0.5484, 0.5064],
[0.6230, 0.4113, 0.7213, 0.1983, 0.4325, 0.2367, 0.6262, 0.5400],
[0.6126, 0.4039, 0.8237, 0.3967, 0.3625, 0.3600, 0.5894, 0.6138],
[0.6182, 0.4099, 0.7812, 0.3000, 0.3937, 0.2367, 0.5325, 0.5750],
[0.6157, 0.3956, 0.8323, 0.4138, 0.3479, 0.4431, 0.5914, 0.5131],
[0.6229, 0.4066, 0.8513, 0.5717, 0.4500, 0.5050, 0.6025, 0.5350]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6218, 0.4113, 0.7499, 0.2620, 0.3945, 0.2552, 0.5913, 0.5554],
[0.6403, 0.4063, 0.8377, 0.2635, 0.4469, 0.2516, 0.6621, 0.5564],
[0.5643, 0.3632, 0.8689, 0.5466, 0.3856, 0.5353, 0.5056, 0.4891],
[0.6050, 0.4061, 0.7295, 0.2546, 0.4117, 0.2465, 0.6089, 0.5497],
[0.5580, 0.3757, 0.8355, 0.4600, 0.3196, 0.3810, 0.5580, 0.6032],
[0.5661, 0.3794, 0.7924, 0.3434, 0.3821, 0.2560, 0.4986, 0.5691],
[0.5372, 0.3464, 0.8553, 0.4697, 0.3184, 0.4471, 0.5288, 0.5201],
[0.5403, 0.3731, 0.8659, 0.6326, 0.4140, 0.4998, 0.5535, 0.5452]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6200, 0.4071, 0.7337, 0.1917, 0.4200, 0.2450, 0.6150, 0.5517],
[0.6261, 0.4066, 0.8325, 0.2150, 0.4762, 0.2667, 0.7002, 0.5633],
[0.6092, 0.4001, 0.8637, 0.4867, 0.4288, 0.5367, 0.5484, 0.5064],
[0.6230, 0.4113, 0.7212, 0.1983, 0.4325, 0.2367, 0.6263, 0.5400],
[0.6126, 0.4038, 0.8238, 0.3967, 0.3625, 0.3600, 0.5894, 0.6138],
[0.6182, 0.4099, 0.7812, 0.3000, 0.3938, 0.2367, 0.5325, 0.5750],
[0.6157, 0.3956, 0.8323, 0.4138, 0.3479, 0.4431, 0.5914, 0.5131],
[0.6229, 0.4066, 0.8512, 0.5717, 0.4500, 0.5050, 0.6025, 0.5350]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06144377455348149
step: 36
running loss: 0.0017067715153744859
Train Steps: 36/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6148, 0.4076, 0.8666, 0.4820, 0.4138, 0.5067, 0.5250, 0.5767],
[ nan, nan, 0.7612, 0.3250, 0.4037, 0.2533, 0.5438, 0.5767],
[0.6216, 0.4100, 0.7350, 0.2067, 0.4325, 0.2050, 0.5950, 0.5333],
[0.6102, 0.4005, 0.8688, 0.5100, 0.4813, 0.5400, 0.5404, 0.5064],
[0.6226, 0.4125, 0.8800, 0.4900, 0.4512, 0.5600, 0.6275, 0.5517],
[0.6286, 0.4097, 0.8107, 0.2414, 0.4425, 0.2483, 0.6745, 0.5385],
[0.6257, 0.4024, 0.8612, 0.5352, 0.4361, 0.5253, 0.6680, 0.5166],
[0.6132, 0.4066, 0.7259, 0.2402, 0.3588, 0.3300, 0.6000, 0.5600]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5900, 0.3929, 0.9066, 0.5424, 0.3696, 0.5060, 0.5424, 0.5662],
[0.2800, 0.1911, 0.7943, 0.3393, 0.3765, 0.2683, 0.5316, 0.5769],
[0.5682, 0.3823, 0.7468, 0.2356, 0.3920, 0.2099, 0.5797, 0.5402],
[0.5947, 0.3937, 0.8851, 0.5474, 0.4331, 0.5075, 0.5386, 0.5139],
[0.6052, 0.4075, 0.9037, 0.5253, 0.4177, 0.5480, 0.5937, 0.5712],
[0.6961, 0.4666, 0.8221, 0.2895, 0.4008, 0.2437, 0.6741, 0.5568],
[0.6450, 0.4200, 0.8834, 0.5708, 0.3868, 0.5175, 0.6314, 0.5497],
[0.6174, 0.4091, 0.7355, 0.2822, 0.3222, 0.3458, 0.5709, 0.5829]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6148, 0.4076, 0.8666, 0.4820, 0.4137, 0.5067, 0.5250, 0.5767],
[0.0000, 0.0000, 0.7613, 0.3250, 0.4038, 0.2533, 0.5437, 0.5767],
[0.6216, 0.4100, 0.7350, 0.2067, 0.4325, 0.2050, 0.5950, 0.5333],
[0.6102, 0.4005, 0.8687, 0.5100, 0.4812, 0.5400, 0.5404, 0.5064],
[0.6226, 0.4125, 0.8800, 0.4900, 0.4512, 0.5600, 0.6275, 0.5517],
[0.6286, 0.4097, 0.8107, 0.2414, 0.4425, 0.2483, 0.6745, 0.5385],
[0.6257, 0.4024, 0.8612, 0.5352, 0.4361, 0.5253, 0.6680, 0.5166],
[0.6132, 0.4066, 0.7259, 0.2402, 0.3587, 0.3300, 0.6000, 0.5600]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0026, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0026, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0640558628947474
step: 37
running loss: 0.0017312395376958758
Train Steps: 37/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6129, 0.4114, 0.6950, 0.2467, 0.4050, 0.2133, 0.5363, 0.5550],
[0.6058, 0.3986, 0.8324, 0.4626, 0.3838, 0.4983, 0.5147, 0.5466],
[0.6339, 0.4149, 0.8800, 0.5000, 0.3900, 0.5283, 0.7541, 0.5424],
[0.6250, 0.4103, 0.8950, 0.4400, 0.3912, 0.5650, 0.6050, 0.5133],
[0.6141, 0.4038, 0.8650, 0.4833, 0.4839, 0.5176, 0.5787, 0.5600],
[0.6086, 0.4019, 0.7782, 0.4278, 0.3625, 0.4350, 0.5150, 0.5285],
[0.6143, 0.4040, 0.8237, 0.3333, 0.4075, 0.2117, 0.5137, 0.4973],
[ nan, nan, 0.6488, 0.1817, 0.4325, 0.1867, 0.5475, 0.5733]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6463, 0.4486, 0.7205, 0.2611, 0.3622, 0.2387, 0.5730, 0.5696],
[0.5679, 0.3821, 0.8604, 0.4857, 0.3614, 0.4933, 0.5540, 0.5588],
[0.5808, 0.3955, 0.9359, 0.5488, 0.3764, 0.5652, 0.7324, 0.5749],
[0.6251, 0.4041, 0.9236, 0.4773, 0.3702, 0.5895, 0.6485, 0.5471],
[0.6711, 0.4540, 0.9037, 0.5153, 0.4514, 0.5124, 0.6330, 0.5645],
[0.5877, 0.3802, 0.8120, 0.4371, 0.3248, 0.4588, 0.5510, 0.5464],
[0.5369, 0.3578, 0.8401, 0.3343, 0.3902, 0.2322, 0.5598, 0.5353],
[0.2642, 0.1942, 0.7214, 0.2071, 0.4413, 0.2090, 0.5914, 0.5881]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6129, 0.4114, 0.6950, 0.2467, 0.4050, 0.2133, 0.5362, 0.5550],
[0.6058, 0.3986, 0.8324, 0.4626, 0.3837, 0.4983, 0.5147, 0.5466],
[0.6339, 0.4149, 0.8800, 0.5000, 0.3900, 0.5283, 0.7541, 0.5424],
[0.6250, 0.4103, 0.8950, 0.4400, 0.3913, 0.5650, 0.6050, 0.5133],
[0.6141, 0.4038, 0.8650, 0.4833, 0.4839, 0.5176, 0.5788, 0.5600],
[0.6086, 0.4019, 0.7782, 0.4278, 0.3625, 0.4350, 0.5150, 0.5285],
[0.6143, 0.4040, 0.8238, 0.3333, 0.4075, 0.2117, 0.5137, 0.4973],
[0.0000, 0.0000, 0.6488, 0.1817, 0.4325, 0.1867, 0.5475, 0.5733]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0028, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0028, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0668318530661054
step: 38
running loss: 0.0017587329754238262
Train Steps: 38/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6300, 0.4102, 0.9088, 0.4433, 0.4088, 0.3067, 0.6820, 0.5540],
[0.6268, 0.4102, 0.8938, 0.3667, 0.4025, 0.2833, 0.6275, 0.5183],
[0.6307, 0.3998, 0.8500, 0.5233, 0.3850, 0.5050, 0.7446, 0.5320],
[0.6137, 0.4038, 0.8563, 0.4050, 0.3813, 0.2550, 0.5106, 0.4954],
[0.6185, 0.4098, 0.8838, 0.4900, 0.4537, 0.5800, 0.6288, 0.5400],
[0.6236, 0.3977, 0.8985, 0.4806, 0.3835, 0.5216, 0.6613, 0.5166],
[0.6201, 0.4082, 0.8827, 0.3715, 0.3825, 0.2712, 0.5845, 0.5412],
[0.6107, 0.4050, 0.8700, 0.4850, 0.4470, 0.4848, 0.5043, 0.5431]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4808, 0.3253, 0.8920, 0.4184, 0.4204, 0.3435, 0.6587, 0.5698],
[0.5491, 0.3737, 0.8658, 0.3256, 0.4150, 0.3050, 0.6280, 0.5679],
[0.5523, 0.3764, 0.8521, 0.4818, 0.3708, 0.5154, 0.6665, 0.5470],
[0.5079, 0.3312, 0.8279, 0.3715, 0.3946, 0.2913, 0.5220, 0.5341],
[0.6193, 0.3941, 0.8742, 0.4529, 0.4648, 0.5880, 0.6097, 0.5398],
[0.6312, 0.4041, 0.8724, 0.4444, 0.4001, 0.5414, 0.6760, 0.5446],
[0.5933, 0.3861, 0.8602, 0.3223, 0.3764, 0.2990, 0.6152, 0.5545],
[0.5005, 0.3396, 0.8607, 0.4584, 0.4423, 0.4931, 0.5061, 0.5280]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6300, 0.4102, 0.9087, 0.4433, 0.4087, 0.3067, 0.6820, 0.5540],
[0.6268, 0.4102, 0.8938, 0.3667, 0.4025, 0.2833, 0.6275, 0.5183],
[0.6307, 0.3998, 0.8500, 0.5233, 0.3850, 0.5050, 0.7446, 0.5320],
[0.6137, 0.4038, 0.8562, 0.4050, 0.3812, 0.2550, 0.5106, 0.4954],
[0.6185, 0.4098, 0.8838, 0.4900, 0.4538, 0.5800, 0.6288, 0.5400],
[0.6236, 0.3977, 0.8985, 0.4806, 0.3835, 0.5216, 0.6613, 0.5166],
[0.6201, 0.4082, 0.8827, 0.3715, 0.3825, 0.2712, 0.5845, 0.5412],
[0.6107, 0.4050, 0.8700, 0.4850, 0.4470, 0.4848, 0.5043, 0.5431]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06857802328886464
step: 39
running loss: 0.0017584108535606319
Train Steps: 39/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6357, 0.4139, 0.8450, 0.5883, 0.3775, 0.4950, 0.6488, 0.5297],
[0.6183, 0.4076, 0.8838, 0.4517, 0.3813, 0.4483, 0.5775, 0.5633],
[0.6218, 0.4098, 0.7238, 0.1850, 0.4238, 0.2517, 0.6288, 0.5350],
[0.6250, 0.4131, 0.8688, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367],
[0.6098, 0.3991, 0.8638, 0.4717, 0.4263, 0.4967, 0.5212, 0.5650],
[0.6102, 0.4001, 0.7738, 0.3583, 0.3463, 0.3800, 0.5524, 0.5689],
[0.6350, 0.4043, 0.8738, 0.5650, 0.3850, 0.4750, 0.6401, 0.4950],
[0.6227, 0.4083, 0.8938, 0.4800, 0.3800, 0.2950, 0.5737, 0.5350]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5491, 0.3530, 0.8468, 0.5286, 0.3845, 0.5185, 0.7065, 0.5212],
[0.6097, 0.3884, 0.9029, 0.4055, 0.4121, 0.4778, 0.6226, 0.5578],
[0.6146, 0.4019, 0.7406, 0.1859, 0.4536, 0.2654, 0.6394, 0.5445],
[0.6019, 0.3787, 0.8673, 0.2497, 0.4574, 0.2452, 0.6368, 0.5177],
[0.5598, 0.3475, 0.8746, 0.4580, 0.4476, 0.5110, 0.5642, 0.5375],
[0.5357, 0.3467, 0.7885, 0.3384, 0.3596, 0.4130, 0.5556, 0.5617],
[0.5348, 0.3464, 0.8776, 0.5457, 0.4168, 0.5147, 0.6626, 0.5053],
[0.5515, 0.3683, 0.8907, 0.4461, 0.4028, 0.3392, 0.6119, 0.5656]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6357, 0.4139, 0.8450, 0.5883, 0.3775, 0.4950, 0.6488, 0.5297],
[0.6183, 0.4076, 0.8838, 0.4517, 0.3812, 0.4483, 0.5775, 0.5633],
[0.6218, 0.4098, 0.7237, 0.1850, 0.4238, 0.2517, 0.6288, 0.5350],
[0.6250, 0.4131, 0.8687, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367],
[0.6098, 0.3991, 0.8637, 0.4717, 0.4263, 0.4967, 0.5213, 0.5650],
[0.6102, 0.4001, 0.7738, 0.3583, 0.3462, 0.3800, 0.5524, 0.5689],
[0.6350, 0.4043, 0.8737, 0.5650, 0.3850, 0.4750, 0.6401, 0.4950],
[0.6227, 0.4083, 0.8938, 0.4800, 0.3800, 0.2950, 0.5738, 0.5350]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06985682185040787
step: 40
running loss: 0.0017464205462601966
Train Steps: 40/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6272, 0.4045, 0.8538, 0.5900, 0.3750, 0.4417, 0.5989, 0.4649],
[0.6104, 0.4029, 0.8738, 0.4900, 0.4088, 0.4533, 0.5070, 0.5510],
[0.6350, 0.4118, 0.8363, 0.2717, 0.4850, 0.1700, 0.6441, 0.5170],
[0.6274, 0.4087, 0.8375, 0.5700, 0.4025, 0.4800, 0.5700, 0.6117],
[0.6173, 0.4013, 0.8713, 0.4640, 0.4800, 0.5700, 0.6025, 0.5600],
[0.6201, 0.4102, 0.7288, 0.2417, 0.4150, 0.2383, 0.6100, 0.5500],
[0.6120, 0.4014, 0.6863, 0.2817, 0.3700, 0.2783, 0.5513, 0.5667],
[ nan, nan, 0.7240, 0.2722, 0.3900, 0.2567, 0.5168, 0.5933]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6196, 0.3877, 0.8643, 0.5624, 0.3899, 0.4373, 0.6491, 0.4795],
[0.5921, 0.3826, 0.9056, 0.4820, 0.4337, 0.4751, 0.5843, 0.5186],
[0.6419, 0.3869, 0.8472, 0.2046, 0.5146, 0.2001, 0.6809, 0.5151],
[0.6691, 0.4310, 0.8642, 0.5447, 0.4198, 0.4953, 0.6364, 0.5944],
[0.7202, 0.4597, 0.9144, 0.4096, 0.4746, 0.5625, 0.6505, 0.5424],
[0.6505, 0.4100, 0.7622, 0.2280, 0.4200, 0.2682, 0.6104, 0.5503],
[0.5771, 0.3638, 0.7290, 0.2275, 0.3697, 0.3242, 0.5733, 0.5296],
[0.0531, 0.0196, 0.7404, 0.2252, 0.4170, 0.2659, 0.5337, 0.5396]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6271, 0.4045, 0.8537, 0.5900, 0.3750, 0.4417, 0.5989, 0.4649],
[0.6104, 0.4029, 0.8737, 0.4900, 0.4087, 0.4533, 0.5070, 0.5510],
[0.6350, 0.4118, 0.8363, 0.2717, 0.4850, 0.1700, 0.6441, 0.5170],
[0.6274, 0.4087, 0.8375, 0.5700, 0.4025, 0.4800, 0.5700, 0.6117],
[0.6173, 0.4013, 0.8713, 0.4640, 0.4800, 0.5700, 0.6025, 0.5600],
[0.6201, 0.4102, 0.7287, 0.2417, 0.4150, 0.2383, 0.6100, 0.5500],
[0.6120, 0.4013, 0.6862, 0.2817, 0.3700, 0.2783, 0.5512, 0.5667],
[0.0000, 0.0000, 0.7240, 0.2722, 0.3900, 0.2567, 0.5168, 0.5933]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07106089597800747
step: 41
running loss: 0.0017331925848294504
Train Steps: 41/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6277, 0.4057, 0.8300, 0.2650, 0.4363, 0.1850, 0.6140, 0.4823],
[0.6200, 0.3998, 0.8850, 0.3950, 0.3500, 0.4650, 0.6138, 0.5400],
[0.6256, 0.4199, 0.8638, 0.5800, 0.3987, 0.4383, 0.5600, 0.5950],
[0.6199, 0.3952, 0.8573, 0.5374, 0.4075, 0.4687, 0.5942, 0.5377],
[0.6226, 0.4098, 0.8912, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367],
[0.6090, 0.4010, 0.7838, 0.3483, 0.3538, 0.3783, 0.5462, 0.5077],
[0.6139, 0.4019, 0.7137, 0.2150, 0.4375, 0.1533, 0.5293, 0.5006],
[0.6159, 0.4085, 0.6900, 0.2283, 0.4088, 0.1950, 0.5123, 0.5397]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6513, 0.4053, 0.8174, 0.2385, 0.4802, 0.2250, 0.6510, 0.4989],
[0.6342, 0.3939, 0.8911, 0.4020, 0.3887, 0.5048, 0.6225, 0.5364],
[0.6598, 0.4216, 0.8528, 0.5737, 0.4386, 0.4707, 0.5988, 0.5928],
[0.6260, 0.4001, 0.8529, 0.5291, 0.4325, 0.5023, 0.6193, 0.5269],
[0.5934, 0.3801, 0.8919, 0.4087, 0.4370, 0.2679, 0.5986, 0.5490],
[0.5857, 0.3637, 0.7795, 0.3259, 0.3542, 0.3958, 0.5541, 0.5063],
[0.3791, 0.2412, 0.6990, 0.1641, 0.4398, 0.1908, 0.5585, 0.4823],
[0.5369, 0.3439, 0.6833, 0.2231, 0.4152, 0.2109, 0.5087, 0.5430]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6277, 0.4056, 0.8300, 0.2650, 0.4363, 0.1850, 0.6140, 0.4823],
[0.6200, 0.3998, 0.8850, 0.3950, 0.3500, 0.4650, 0.6137, 0.5400],
[0.6256, 0.4199, 0.8637, 0.5800, 0.3988, 0.4383, 0.5600, 0.5950],
[0.6199, 0.3952, 0.8573, 0.5374, 0.4075, 0.4687, 0.5942, 0.5377],
[0.6226, 0.4098, 0.8913, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367],
[0.6090, 0.4010, 0.7837, 0.3483, 0.3537, 0.3783, 0.5462, 0.5077],
[0.6139, 0.4019, 0.7138, 0.2150, 0.4375, 0.1533, 0.5293, 0.5006],
[0.6159, 0.4085, 0.6900, 0.2283, 0.4087, 0.1950, 0.5123, 0.5397]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07297768600983545
step: 42
running loss: 0.0017375639526151297
Train Steps: 42/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6146, 0.4124, 0.8800, 0.4867, 0.3800, 0.4500, 0.5106, 0.5524],
[0.6185, 0.4079, 0.8838, 0.4617, 0.4838, 0.5650, 0.6175, 0.5850],
[0.6245, 0.4100, 0.7762, 0.2583, 0.4963, 0.1517, 0.5875, 0.5417],
[0.6175, 0.4013, 0.7734, 0.2783, 0.4475, 0.1786, 0.5790, 0.5351],
[0.6218, 0.4137, 0.7263, 0.2233, 0.4075, 0.2650, 0.6212, 0.5783],
[0.6093, 0.3990, 0.8400, 0.4333, 0.3688, 0.4633, 0.5560, 0.5656],
[0.6102, 0.4005, 0.8688, 0.5100, 0.4813, 0.5400, 0.5404, 0.5064],
[0.6274, 0.4003, 0.8638, 0.5967, 0.3688, 0.4900, 0.6108, 0.4661]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5348, 0.3344, 0.8918, 0.5236, 0.3754, 0.4113, 0.5386, 0.5193],
[0.6320, 0.3968, 0.8734, 0.4376, 0.4709, 0.5201, 0.6116, 0.5432],
[0.6034, 0.3844, 0.7373, 0.2353, 0.4592, 0.1258, 0.5958, 0.5342],
[0.5810, 0.3819, 0.7541, 0.2476, 0.4223, 0.1637, 0.5635, 0.5006],
[0.6223, 0.3896, 0.7139, 0.2423, 0.4031, 0.2472, 0.5769, 0.5434],
[0.5928, 0.3790, 0.8403, 0.4260, 0.3608, 0.4231, 0.5573, 0.5454],
[0.6233, 0.3942, 0.8505, 0.5002, 0.4849, 0.4924, 0.5449, 0.4821],
[0.6497, 0.4057, 0.8433, 0.5769, 0.3865, 0.4554, 0.6365, 0.4721]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6146, 0.4124, 0.8800, 0.4867, 0.3800, 0.4500, 0.5106, 0.5524],
[0.6184, 0.4079, 0.8838, 0.4617, 0.4837, 0.5650, 0.6175, 0.5850],
[0.6245, 0.4100, 0.7763, 0.2583, 0.4963, 0.1517, 0.5875, 0.5417],
[0.6175, 0.4013, 0.7734, 0.2783, 0.4475, 0.1786, 0.5790, 0.5351],
[0.6218, 0.4137, 0.7262, 0.2233, 0.4075, 0.2650, 0.6212, 0.5783],
[0.6093, 0.3990, 0.8400, 0.4333, 0.3688, 0.4633, 0.5560, 0.5656],
[0.6102, 0.4005, 0.8687, 0.5100, 0.4812, 0.5400, 0.5404, 0.5064],
[0.6274, 0.4003, 0.8637, 0.5967, 0.3688, 0.4900, 0.6108, 0.4661]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07371883763698861
step: 43
running loss: 0.0017143915729532235
Train Steps: 43/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6286, 0.4040, 0.8696, 0.3047, 0.3924, 0.2887, 0.6300, 0.5367],
[0.6250, 0.3993, 0.9138, 0.4333, 0.3763, 0.5217, 0.6995, 0.5320],
[0.6151, 0.4058, 0.7068, 0.2680, 0.3400, 0.4083, 0.5775, 0.5733],
[0.6272, 0.4071, 0.8738, 0.5600, 0.3675, 0.3783, 0.5926, 0.4742],
[0.6201, 0.4065, 0.7300, 0.1933, 0.4075, 0.2533, 0.6162, 0.5483],
[0.6260, 0.4106, 0.8025, 0.2583, 0.4550, 0.1867, 0.6281, 0.4869],
[0.6276, 0.4095, 0.8237, 0.2250, 0.4662, 0.1783, 0.6171, 0.4869],
[0.6203, 0.4076, 0.8611, 0.2878, 0.4050, 0.2554, 0.5907, 0.5496]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6772, 0.4490, 0.8220, 0.3402, 0.4000, 0.2432, 0.6008, 0.5333],
[0.6473, 0.4303, 0.8864, 0.4997, 0.3895, 0.5120, 0.6969, 0.5476],
[0.5202, 0.3567, 0.6952, 0.2878, 0.3395, 0.3716, 0.5097, 0.5642],
[0.5861, 0.4021, 0.8474, 0.6113, 0.3800, 0.3585, 0.5587, 0.4985],
[0.6097, 0.4207, 0.7052, 0.2364, 0.4152, 0.2074, 0.5507, 0.5604],
[0.5311, 0.3470, 0.7862, 0.2609, 0.4629, 0.1725, 0.5829, 0.5163],
[0.6151, 0.4042, 0.7916, 0.2439, 0.4920, 0.1672, 0.5747, 0.4947],
[0.6339, 0.4210, 0.8235, 0.2968, 0.4063, 0.2324, 0.5447, 0.5461]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6286, 0.4040, 0.8696, 0.3047, 0.3924, 0.2887, 0.6300, 0.5367],
[0.6250, 0.3993, 0.9137, 0.4333, 0.3762, 0.5217, 0.6995, 0.5320],
[0.6151, 0.4058, 0.7068, 0.2680, 0.3400, 0.4083, 0.5775, 0.5733],
[0.6272, 0.4071, 0.8737, 0.5600, 0.3675, 0.3783, 0.5926, 0.4742],
[0.6201, 0.4065, 0.7300, 0.1933, 0.4075, 0.2533, 0.6162, 0.5483],
[0.6260, 0.4106, 0.8025, 0.2583, 0.4550, 0.1867, 0.6281, 0.4869],
[0.6276, 0.4095, 0.8238, 0.2250, 0.4663, 0.1783, 0.6171, 0.4869],
[0.6203, 0.4076, 0.8611, 0.2878, 0.4050, 0.2554, 0.5907, 0.5496]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07493773492751643
step: 44
running loss: 0.0017031303392617372
Train Steps: 44/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.7525, 0.2291, 0.3838, 0.3017, 0.6050, 0.5667],
[0.6227, 0.4193, 0.8838, 0.4933, 0.3663, 0.3733, 0.5637, 0.5633],
[0.6193, 0.4079, 0.7288, 0.2500, 0.4250, 0.2550, 0.5989, 0.6266],
[0.6277, 0.4057, 0.8300, 0.2650, 0.4363, 0.1850, 0.6140, 0.4823],
[ nan, nan, 0.7981, 0.3194, 0.3625, 0.3167, 0.5040, 0.5563],
[0.6276, 0.4002, 0.8800, 0.5533, 0.3575, 0.4400, 0.6132, 0.4672],
[0.6110, 0.4047, 0.8700, 0.4483, 0.3713, 0.3967, 0.5088, 0.5517],
[0.6272, 0.4120, 0.9038, 0.4117, 0.3725, 0.3200, 0.6175, 0.5250]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.1702, 0.1298, 0.7268, 0.2563, 0.3765, 0.2613, 0.5716, 0.5468],
[0.7073, 0.4773, 0.8548, 0.5149, 0.3481, 0.3462, 0.5311, 0.5441],
[0.7714, 0.5124, 0.7089, 0.2594, 0.4090, 0.2234, 0.5770, 0.6174],
[0.7612, 0.5006, 0.8099, 0.2706, 0.4542, 0.1748, 0.6107, 0.5040],
[0.2474, 0.1812, 0.7453, 0.3121, 0.3465, 0.2823, 0.4903, 0.5219],
[0.8275, 0.5585, 0.8661, 0.5414, 0.3792, 0.4369, 0.6221, 0.5096],
[0.6594, 0.4703, 0.8696, 0.4741, 0.3748, 0.3802, 0.4978, 0.5200],
[0.7095, 0.4710, 0.8922, 0.4212, 0.3628, 0.2994, 0.5741, 0.5112]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.7525, 0.2291, 0.3837, 0.3017, 0.6050, 0.5667],
[0.6227, 0.4193, 0.8838, 0.4933, 0.3663, 0.3733, 0.5638, 0.5633],
[0.6193, 0.4078, 0.7287, 0.2500, 0.4250, 0.2550, 0.5989, 0.6266],
[0.6277, 0.4056, 0.8300, 0.2650, 0.4363, 0.1850, 0.6140, 0.4823],
[0.0000, 0.0000, 0.7981, 0.3194, 0.3625, 0.3167, 0.5040, 0.5563],
[0.6276, 0.4002, 0.8800, 0.5533, 0.3575, 0.4400, 0.6132, 0.4672],
[0.6110, 0.4047, 0.8700, 0.4483, 0.3713, 0.3967, 0.5088, 0.5517],
[0.6272, 0.4120, 0.9038, 0.4117, 0.3725, 0.3200, 0.6175, 0.5250]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0050, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0050, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07991487270919606
step: 45
running loss: 0.0017758860602043569
Train Steps: 45/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6274, 0.4087, 0.8375, 0.5700, 0.4025, 0.4800, 0.5700, 0.6117],
[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334],
[0.6259, 0.4133, 0.8200, 0.2317, 0.5025, 0.1533, 0.6250, 0.4947],
[0.6182, 0.3982, 0.7541, 0.2379, 0.3959, 0.2792, 0.6079, 0.5389],
[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395],
[0.6073, 0.3932, 0.8363, 0.5817, 0.4425, 0.5117, 0.5204, 0.4817],
[0.6124, 0.4030, 0.8650, 0.4867, 0.4999, 0.5106, 0.5137, 0.5773],
[0.6250, 0.3993, 0.9138, 0.4333, 0.3763, 0.5217, 0.6995, 0.5320]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6370, 0.4299, 0.8304, 0.5609, 0.3799, 0.4245, 0.5558, 0.6125],
[0.6131, 0.4136, 0.7523, 0.2322, 0.3399, 0.2686, 0.5923, 0.5328],
[0.6087, 0.4224, 0.8043, 0.2357, 0.4771, 0.1322, 0.6005, 0.4889],
[0.5696, 0.3804, 0.7569, 0.2403, 0.3683, 0.2328, 0.5821, 0.5382],
[0.5883, 0.3892, 0.8575, 0.5295, 0.3315, 0.3194, 0.5310, 0.5377],
[0.6072, 0.3977, 0.8384, 0.5736, 0.4364, 0.4315, 0.4989, 0.5056],
[0.6448, 0.4398, 0.8627, 0.4838, 0.4578, 0.4607, 0.4873, 0.5472],
[0.6714, 0.4410, 0.9013, 0.4527, 0.3524, 0.4750, 0.7102, 0.5378]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6274, 0.4087, 0.8375, 0.5700, 0.4025, 0.4800, 0.5700, 0.6117],
[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334],
[0.6259, 0.4132, 0.8200, 0.2317, 0.5025, 0.1533, 0.6250, 0.4947],
[0.6182, 0.3982, 0.7541, 0.2379, 0.3959, 0.2792, 0.6079, 0.5389],
[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395],
[0.6073, 0.3932, 0.8363, 0.5817, 0.4425, 0.5117, 0.5204, 0.4817],
[0.6124, 0.4030, 0.8650, 0.4867, 0.4999, 0.5106, 0.5137, 0.5773],
[0.6250, 0.3993, 0.9137, 0.4333, 0.3762, 0.5217, 0.6995, 0.5320]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.08066413854248822
step: 46
running loss: 0.0017535682291845264
Train Steps: 46/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6214, 0.4116, 0.7750, 0.2317, 0.4487, 0.1883, 0.6200, 0.5400],
[0.6276, 0.4120, 0.8738, 0.3133, 0.4225, 0.2217, 0.6203, 0.4892],
[0.6350, 0.4118, 0.8363, 0.2717, 0.4850, 0.1700, 0.6441, 0.5170],
[0.6145, 0.4008, 0.8750, 0.5383, 0.3975, 0.4650, 0.5563, 0.5533],
[0.6276, 0.4095, 0.8237, 0.2250, 0.4662, 0.1783, 0.6171, 0.4869],
[0.6058, 0.3986, 0.8324, 0.4626, 0.3838, 0.4983, 0.5147, 0.5466],
[0.6353, 0.4128, 0.9138, 0.3533, 0.4688, 0.3250, 0.7145, 0.5991],
[0.6143, 0.4055, 0.8150, 0.2767, 0.3825, 0.2567, 0.5173, 0.4901]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5871, 0.3827, 0.7595, 0.2599, 0.4304, 0.1861, 0.5773, 0.5302],
[0.5781, 0.3907, 0.8509, 0.3644, 0.4057, 0.2110, 0.5864, 0.4940],
[0.5893, 0.3861, 0.8078, 0.2766, 0.4622, 0.1781, 0.6135, 0.5363],
[0.5620, 0.3663, 0.8583, 0.5443, 0.3683, 0.4701, 0.5473, 0.5656],
[0.6003, 0.3920, 0.8042, 0.2455, 0.4554, 0.1913, 0.5968, 0.4997],
[0.6014, 0.4023, 0.8215, 0.4718, 0.3669, 0.4867, 0.5102, 0.5505],
[0.5840, 0.3870, 0.8857, 0.3702, 0.4207, 0.2885, 0.6763, 0.5843],
[0.5322, 0.3514, 0.7657, 0.3172, 0.3484, 0.2597, 0.5061, 0.5328]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6214, 0.4116, 0.7750, 0.2317, 0.4487, 0.1883, 0.6200, 0.5400],
[0.6276, 0.4120, 0.8737, 0.3133, 0.4225, 0.2217, 0.6203, 0.4892],
[0.6350, 0.4118, 0.8363, 0.2717, 0.4850, 0.1700, 0.6441, 0.5170],
[0.6145, 0.4008, 0.8750, 0.5383, 0.3975, 0.4650, 0.5562, 0.5533],
[0.6276, 0.4095, 0.8238, 0.2250, 0.4663, 0.1783, 0.6171, 0.4869],
[0.6058, 0.3986, 0.8324, 0.4626, 0.3837, 0.4983, 0.5147, 0.5466],
[0.6353, 0.4128, 0.9137, 0.3533, 0.4688, 0.3250, 0.7145, 0.5991],
[0.6143, 0.4055, 0.8150, 0.2767, 0.3825, 0.2567, 0.5173, 0.4901]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.08150381379527971
step: 47
running loss: 0.0017341236977719088
Train Steps: 47/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6227, 0.4193, 0.8838, 0.4933, 0.3663, 0.3733, 0.5637, 0.5633],
[0.6085, 0.4008, 0.8588, 0.5200, 0.4959, 0.4977, 0.5175, 0.5283],
[0.6213, 0.4001, 0.7712, 0.2117, 0.4338, 0.1800, 0.5850, 0.5183],
[ nan, nan, 0.7240, 0.2722, 0.3900, 0.2567, 0.5168, 0.5933],
[0.6213, 0.4131, 0.8438, 0.3550, 0.3513, 0.4400, 0.5716, 0.5123],
[0.6299, 0.4303, 0.7963, 0.3933, 0.4850, 0.2283, 0.5480, 0.6222],
[0.6292, 0.4010, 0.8988, 0.4800, 0.3638, 0.3817, 0.6357, 0.5051],
[0.6201, 0.4065, 0.7300, 0.1933, 0.4075, 0.2533, 0.6162, 0.5483]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6507, 0.4312, 0.8895, 0.5101, 0.3482, 0.3958, 0.5736, 0.5568],
[ 0.6158, 0.4013, 0.8695, 0.5192, 0.4944, 0.5012, 0.5342, 0.5290],
[ 0.7051, 0.4321, 0.7647, 0.2217, 0.4441, 0.1759, 0.5999, 0.5217],
[-0.0247, 0.0039, 0.7466, 0.2767, 0.3981, 0.2568, 0.5355, 0.5709],
[ 0.7045, 0.4758, 0.8790, 0.3624, 0.3280, 0.4345, 0.5924, 0.5202],
[ 0.6245, 0.4351, 0.8443, 0.3931, 0.4787, 0.2461, 0.5647, 0.6040],
[ 0.7088, 0.4377, 0.9097, 0.4705, 0.3590, 0.4088, 0.6427, 0.5270],
[ 0.6248, 0.4281, 0.7528, 0.2074, 0.4034, 0.2537, 0.6343, 0.5507]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6227, 0.4193, 0.8838, 0.4933, 0.3663, 0.3733, 0.5638, 0.5633],
[0.6084, 0.4008, 0.8587, 0.5200, 0.4959, 0.4977, 0.5175, 0.5283],
[0.6213, 0.4001, 0.7713, 0.2117, 0.4338, 0.1800, 0.5850, 0.5183],
[0.0000, 0.0000, 0.7240, 0.2722, 0.3900, 0.2567, 0.5168, 0.5933],
[0.6213, 0.4131, 0.8438, 0.3550, 0.3512, 0.4400, 0.5716, 0.5123],
[0.6299, 0.4303, 0.7962, 0.3933, 0.4850, 0.2283, 0.5480, 0.6222],
[0.6292, 0.4010, 0.8988, 0.4800, 0.3638, 0.3817, 0.6357, 0.5051],
[0.6201, 0.4065, 0.7300, 0.1933, 0.4075, 0.2533, 0.6162, 0.5483]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.08213754411553964
step: 48
running loss: 0.001711198835740409
Train Steps: 48/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6193, 0.4108, 0.7438, 0.2700, 0.3650, 0.3683, 0.6238, 0.5717],
[0.6128, 0.4118, 0.8638, 0.5333, 0.4625, 0.5267, 0.5193, 0.5475],
[0.6234, 0.4179, 0.7825, 0.3450, 0.3813, 0.2867, 0.5675, 0.5617],
[0.6099, 0.4030, 0.8638, 0.5117, 0.4983, 0.4965, 0.5086, 0.5388],
[0.6189, 0.3911, 0.8800, 0.4917, 0.3713, 0.4800, 0.6038, 0.4833],
[0.6131, 0.4064, 0.8638, 0.5200, 0.4788, 0.4783, 0.5258, 0.5867],
[0.6190, 0.4135, 0.8000, 0.4883, 0.3566, 0.3647, 0.5613, 0.5900],
[0.6133, 0.4094, 0.8495, 0.4028, 0.3588, 0.3200, 0.5003, 0.5407]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5959, 0.4000, 0.7621, 0.2510, 0.3706, 0.3683, 0.6783, 0.5539],
[0.6303, 0.4155, 0.8891, 0.5091, 0.4621, 0.4924, 0.5939, 0.5456],
[0.5692, 0.3708, 0.8184, 0.3110, 0.3984, 0.2670, 0.6072, 0.5645],
[0.5968, 0.3888, 0.8988, 0.4949, 0.5172, 0.4731, 0.5595, 0.5253],
[0.6241, 0.3917, 0.8970, 0.4466, 0.3830, 0.4809, 0.6115, 0.4860],
[0.6153, 0.4076, 0.8837, 0.4904, 0.4676, 0.4800, 0.5875, 0.5728],
[0.5677, 0.3693, 0.8548, 0.4486, 0.3512, 0.3619, 0.5806, 0.5470],
[0.5376, 0.3586, 0.8915, 0.3900, 0.3824, 0.2972, 0.5508, 0.5358]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6193, 0.4108, 0.7437, 0.2700, 0.3650, 0.3683, 0.6237, 0.5717],
[0.6128, 0.4118, 0.8637, 0.5333, 0.4625, 0.5267, 0.5193, 0.5475],
[0.6234, 0.4179, 0.7825, 0.3450, 0.3812, 0.2867, 0.5675, 0.5617],
[0.6098, 0.4030, 0.8637, 0.5117, 0.4983, 0.4965, 0.5086, 0.5388],
[0.6189, 0.3911, 0.8800, 0.4917, 0.3713, 0.4800, 0.6037, 0.4833],
[0.6132, 0.4063, 0.8637, 0.5200, 0.4787, 0.4783, 0.5258, 0.5867],
[0.6190, 0.4135, 0.8000, 0.4883, 0.3566, 0.3647, 0.5612, 0.5900],
[0.6133, 0.4094, 0.8495, 0.4028, 0.3587, 0.3200, 0.5003, 0.5407]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.08310104586416855
step: 49
running loss: 0.001695939711513644
Train Steps: 49/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6109, 0.4003, 0.8650, 0.4883, 0.4775, 0.4867, 0.5175, 0.5683],
[0.6073, 0.3932, 0.8363, 0.5817, 0.4425, 0.5117, 0.5204, 0.4817],
[0.6222, 0.3937, 0.8350, 0.5617, 0.4138, 0.4600, 0.5800, 0.5233],
[0.6184, 0.4079, 0.8350, 0.3700, 0.3675, 0.2883, 0.5312, 0.5783],
[0.6109, 0.4036, 0.7188, 0.1750, 0.3850, 0.2550, 0.5863, 0.5567],
[0.6216, 0.4100, 0.7350, 0.2067, 0.4325, 0.2050, 0.5950, 0.5333],
[0.6078, 0.4033, 0.8019, 0.3055, 0.3450, 0.4200, 0.6025, 0.5550],
[0.6364, 0.4144, 0.8625, 0.3083, 0.4913, 0.2000, 0.6448, 0.5274]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5848, 0.3844, 0.8986, 0.4746, 0.4875, 0.5192, 0.5734, 0.5595],
[0.5635, 0.3480, 0.8617, 0.5607, 0.4685, 0.5106, 0.5479, 0.5005],
[0.6011, 0.3629, 0.8678, 0.5411, 0.4214, 0.4758, 0.5868, 0.5364],
[0.5875, 0.3733, 0.8663, 0.3486, 0.3731, 0.3224, 0.5392, 0.5639],
[0.6006, 0.3898, 0.7459, 0.2103, 0.4047, 0.2789, 0.5768, 0.5538],
[0.5433, 0.3653, 0.7747, 0.2095, 0.4477, 0.2071, 0.6094, 0.5367],
[0.5403, 0.3561, 0.8304, 0.2777, 0.3716, 0.4511, 0.6204, 0.5646],
[0.6354, 0.4143, 0.8928, 0.3292, 0.4869, 0.2185, 0.6488, 0.5354]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6109, 0.4003, 0.8650, 0.4883, 0.4775, 0.4867, 0.5175, 0.5683],
[0.6073, 0.3932, 0.8363, 0.5817, 0.4425, 0.5117, 0.5204, 0.4817],
[0.6222, 0.3937, 0.8350, 0.5617, 0.4137, 0.4600, 0.5800, 0.5233],
[0.6184, 0.4079, 0.8350, 0.3700, 0.3675, 0.2883, 0.5312, 0.5783],
[0.6108, 0.4036, 0.7188, 0.1750, 0.3850, 0.2550, 0.5863, 0.5567],
[0.6216, 0.4100, 0.7350, 0.2067, 0.4325, 0.2050, 0.5950, 0.5333],
[0.6078, 0.4033, 0.8019, 0.3055, 0.3450, 0.4200, 0.6025, 0.5550],
[0.6364, 0.4144, 0.8625, 0.3083, 0.4913, 0.2000, 0.6448, 0.5274]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.08384644222678617
step: 50
running loss: 0.0016769288445357233
Train Steps: 50/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150],
[0.6193, 0.4034, 0.7757, 0.2347, 0.3733, 0.2919, 0.5930, 0.4926],
[0.6257, 0.4024, 0.8672, 0.5422, 0.4196, 0.5198, 0.6694, 0.5204],
[0.6142, 0.3982, 0.8650, 0.4883, 0.3912, 0.4317, 0.5315, 0.5350],
[0.6160, 0.4093, 0.8314, 0.4417, 0.3675, 0.4583, 0.5250, 0.5808],
[0.6222, 0.4108, 0.8938, 0.4233, 0.3600, 0.3817, 0.5825, 0.5283],
[0.6187, 0.4104, 0.7126, 0.2069, 0.3950, 0.2517, 0.5913, 0.5683],
[0.6177, 0.4086, 0.8738, 0.3950, 0.3775, 0.5600, 0.6225, 0.5700]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6018, 0.3981, 0.8972, 0.4834, 0.4861, 0.6041, 0.6385, 0.5484],
[0.5998, 0.4012, 0.7800, 0.2538, 0.4224, 0.2867, 0.6259, 0.5099],
[0.6428, 0.4122, 0.8682, 0.5459, 0.4503, 0.5400, 0.6588, 0.5392],
[0.6533, 0.3981, 0.8786, 0.5066, 0.4169, 0.4677, 0.5248, 0.5279],
[0.5899, 0.3816, 0.8542, 0.4554, 0.3995, 0.4642, 0.5371, 0.5860],
[0.7126, 0.4692, 0.8975, 0.4193, 0.3818, 0.3942, 0.5930, 0.5641],
[0.6259, 0.4239, 0.7293, 0.2223, 0.4088, 0.2643, 0.5765, 0.5782],
[0.5646, 0.3629, 0.8836, 0.3953, 0.4145, 0.5627, 0.6421, 0.5542]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150],
[0.6193, 0.4034, 0.7757, 0.2347, 0.3733, 0.2919, 0.5930, 0.4926],
[0.6257, 0.4024, 0.8672, 0.5422, 0.4196, 0.5198, 0.6694, 0.5204],
[0.6143, 0.3982, 0.8650, 0.4883, 0.3913, 0.4317, 0.5315, 0.5350],
[0.6160, 0.4092, 0.8314, 0.4417, 0.3675, 0.4583, 0.5250, 0.5808],
[0.6222, 0.4108, 0.8938, 0.4233, 0.3600, 0.3817, 0.5825, 0.5283],
[0.6187, 0.4103, 0.7126, 0.2069, 0.3950, 0.2517, 0.5913, 0.5683],
[0.6177, 0.4085, 0.8737, 0.3950, 0.3775, 0.5600, 0.6225, 0.5700]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.08451496018096805
step: 51
running loss: 0.0016571560819797655
Train Steps: 51/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6339, 0.4102, 0.8588, 0.3133, 0.4425, 0.2117, 0.6417, 0.5089],
[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383],
[0.6202, 0.3983, 0.8555, 0.5429, 0.3842, 0.4370, 0.5866, 0.5398],
[0.6180, 0.4064, 0.7200, 0.2467, 0.4275, 0.2367, 0.5963, 0.6217],
[0.6199, 0.4065, 0.7598, 0.2385, 0.4317, 0.1981, 0.5933, 0.5221],
[0.6307, 0.4029, 0.8988, 0.4817, 0.3937, 0.3500, 0.7311, 0.5378],
[ nan, nan, 0.8463, 0.2550, 0.5850, 0.2133, 0.7129, 0.6072],
[0.6239, 0.4174, 0.8425, 0.5733, 0.4825, 0.4500, 0.5625, 0.5933]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6809, 0.4253, 0.8568, 0.2991, 0.4494, 0.2359, 0.6058, 0.5163],
[0.5803, 0.3767, 0.8677, 0.4200, 0.4125, 0.6332, 0.5489, 0.5271],
[0.6340, 0.3932, 0.8501, 0.5158, 0.3730, 0.5077, 0.5502, 0.5099],
[0.5400, 0.3482, 0.6996, 0.2484, 0.4044, 0.2768, 0.5484, 0.6001],
[0.6741, 0.4330, 0.7321, 0.2190, 0.4196, 0.2534, 0.5463, 0.5307],
[0.6390, 0.4043, 0.8925, 0.4650, 0.3780, 0.3900, 0.6473, 0.5288],
[0.4883, 0.3077, 0.8510, 0.2756, 0.5270, 0.3071, 0.6809, 0.5730],
[0.5779, 0.3868, 0.8395, 0.5546, 0.4571, 0.4585, 0.5455, 0.6070]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6339, 0.4102, 0.8587, 0.3133, 0.4425, 0.2117, 0.6417, 0.5089],
[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383],
[0.6202, 0.3983, 0.8555, 0.5429, 0.3842, 0.4370, 0.5866, 0.5398],
[0.6180, 0.4064, 0.7200, 0.2467, 0.4275, 0.2367, 0.5962, 0.6217],
[0.6199, 0.4065, 0.7598, 0.2385, 0.4317, 0.1981, 0.5933, 0.5221],
[0.6307, 0.4029, 0.8988, 0.4817, 0.3938, 0.3500, 0.7311, 0.5378],
[0.0000, 0.0000, 0.8462, 0.2550, 0.5850, 0.2133, 0.7129, 0.6072],
[0.6239, 0.4174, 0.8425, 0.5733, 0.4825, 0.4500, 0.5625, 0.5933]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0064, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0064, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.09093694994226098
step: 52
running loss: 0.0017487874988896342
Train Steps: 52/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6293, 0.4024, 0.8750, 0.5000, 0.4012, 0.5733, 0.7121, 0.5633],
[0.6201, 0.4055, 0.7717, 0.1919, 0.4250, 0.2079, 0.5871, 0.5044],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5413, 0.5683],
[0.6198, 0.4130, 0.8762, 0.4117, 0.3650, 0.4900, 0.5707, 0.5103],
[0.6258, 0.4143, 0.8525, 0.2617, 0.4950, 0.1667, 0.6219, 0.4967],
[0.6239, 0.4061, 0.8850, 0.4600, 0.4225, 0.5200, 0.6138, 0.5450],
[0.6182, 0.4099, 0.7812, 0.3000, 0.3937, 0.2367, 0.5325, 0.5750],
[0.6182, 0.4058, 0.8738, 0.4350, 0.3563, 0.3400, 0.5290, 0.5822]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5538, 0.3485, 0.8356, 0.5000, 0.4175, 0.6157, 0.6252, 0.5638],
[0.5602, 0.3685, 0.7444, 0.2204, 0.4513, 0.2355, 0.6059, 0.5304],
[0.5542, 0.3638, 0.8654, 0.5291, 0.3889, 0.3825, 0.5489, 0.5775],
[0.6536, 0.4437, 0.8621, 0.4250, 0.3704, 0.5169, 0.5454, 0.5253],
[0.5912, 0.4080, 0.8529, 0.2716, 0.5181, 0.1879, 0.6456, 0.5222],
[0.6205, 0.4104, 0.8665, 0.4365, 0.4210, 0.5852, 0.6185, 0.5612],
[0.4969, 0.3367, 0.7763, 0.3154, 0.4192, 0.2654, 0.5452, 0.5896],
[0.6335, 0.4119, 0.8561, 0.4200, 0.3686, 0.3731, 0.5136, 0.5897]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6293, 0.4024, 0.8750, 0.5000, 0.4013, 0.5733, 0.7121, 0.5633],
[0.6202, 0.4055, 0.7717, 0.1919, 0.4250, 0.2079, 0.5871, 0.5044],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5412, 0.5683],
[0.6198, 0.4130, 0.8763, 0.4117, 0.3650, 0.4900, 0.5707, 0.5103],
[0.6258, 0.4143, 0.8525, 0.2617, 0.4950, 0.1667, 0.6219, 0.4967],
[0.6239, 0.4061, 0.8850, 0.4600, 0.4225, 0.5200, 0.6137, 0.5450],
[0.6182, 0.4099, 0.7812, 0.3000, 0.3938, 0.2367, 0.5325, 0.5750],
[0.6182, 0.4058, 0.8737, 0.4350, 0.3562, 0.3400, 0.5290, 0.5822]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0920837412122637
step: 53
running loss: 0.0017374290794766737
Train Steps: 53/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6263, 0.4233, 0.7924, 0.4626, 0.3788, 0.2883, 0.5573, 0.6047],
[0.6261, 0.4131, 0.8938, 0.3550, 0.4000, 0.2683, 0.6188, 0.5283],
[0.6300, 0.4013, 0.8938, 0.5350, 0.3675, 0.4600, 0.6456, 0.4973],
[0.6219, 0.4089, 0.8938, 0.4800, 0.3825, 0.4450, 0.5850, 0.5200],
[0.6179, 0.4040, 0.7412, 0.1850, 0.3825, 0.2783, 0.5837, 0.5600],
[0.6111, 0.4033, 0.8300, 0.3267, 0.3588, 0.3333, 0.5444, 0.5637],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533],
[0.6164, 0.3972, 0.7818, 0.3381, 0.3599, 0.3387, 0.5880, 0.5153]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6361, 0.4294, 0.7938, 0.4831, 0.4019, 0.3325, 0.5618, 0.6023],
[0.6089, 0.4054, 0.8951, 0.3480, 0.4153, 0.2785, 0.6387, 0.5254],
[0.6143, 0.3938, 0.8661, 0.5296, 0.3820, 0.4893, 0.6041, 0.4902],
[0.6072, 0.4022, 0.8795, 0.4778, 0.3956, 0.4922, 0.5996, 0.5346],
[0.5502, 0.3681, 0.7329, 0.2432, 0.4047, 0.3000, 0.6031, 0.5652],
[0.5602, 0.3857, 0.8316, 0.3321, 0.3668, 0.3287, 0.5372, 0.5738],
[0.5965, 0.4166, 0.8792, 0.4442, 0.4421, 0.5145, 0.5707, 0.5443],
[0.5677, 0.3775, 0.7882, 0.3297, 0.3547, 0.3545, 0.6025, 0.5210]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6263, 0.4232, 0.7924, 0.4626, 0.3787, 0.2883, 0.5573, 0.6047],
[0.6261, 0.4131, 0.8938, 0.3550, 0.4000, 0.2683, 0.6187, 0.5283],
[0.6300, 0.4013, 0.8938, 0.5350, 0.3675, 0.4600, 0.6456, 0.4973],
[0.6219, 0.4089, 0.8938, 0.4800, 0.3825, 0.4450, 0.5850, 0.5200],
[0.6179, 0.4040, 0.7412, 0.1850, 0.3825, 0.2783, 0.5838, 0.5600],
[0.6111, 0.4033, 0.8300, 0.3267, 0.3587, 0.3333, 0.5444, 0.5637],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533],
[0.6164, 0.3972, 0.7818, 0.3381, 0.3599, 0.3387, 0.5880, 0.5153]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0925499573640991
step: 54
running loss: 0.0017138880993351686
Train Steps: 54/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6151, 0.4085, 0.8750, 0.4367, 0.3887, 0.4367, 0.5066, 0.5846],
[0.6282, 0.4029, 0.8988, 0.3000, 0.4250, 0.4183, 0.7042, 0.5575],
[0.6203, 0.4072, 0.8892, 0.3523, 0.3783, 0.3017, 0.5898, 0.5478],
[0.6118, 0.4052, 0.8463, 0.3917, 0.3538, 0.3450, 0.5053, 0.5593],
[0.6271, 0.4040, 0.9138, 0.3750, 0.4625, 0.2617, 0.7232, 0.5413],
[0.6106, 0.4022, 0.7125, 0.2650, 0.3713, 0.2700, 0.5431, 0.5123],
[0.6264, 0.4049, 0.8988, 0.4633, 0.3813, 0.4983, 0.6326, 0.4843],
[0.6216, 0.4100, 0.7350, 0.2067, 0.4325, 0.2050, 0.5950, 0.5333]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6453, 0.4232, 0.8670, 0.4669, 0.3818, 0.4092, 0.4712, 0.5853],
[0.5555, 0.3425, 0.8555, 0.3448, 0.4047, 0.3914, 0.6735, 0.5412],
[0.5939, 0.3750, 0.8760, 0.3566, 0.3731, 0.2931, 0.6047, 0.5714],
[0.5895, 0.4000, 0.8453, 0.4075, 0.3547, 0.3354, 0.4997, 0.5532],
[0.5426, 0.3417, 0.9176, 0.4015, 0.4547, 0.2686, 0.7097, 0.5357],
[0.6337, 0.4331, 0.7227, 0.2762, 0.3751, 0.2437, 0.5495, 0.5227],
[0.5736, 0.3552, 0.8865, 0.4961, 0.3587, 0.5078, 0.6134, 0.4761],
[0.5949, 0.4000, 0.7421, 0.2326, 0.4343, 0.1824, 0.5836, 0.5334]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6151, 0.4085, 0.8750, 0.4367, 0.3887, 0.4367, 0.5066, 0.5846],
[0.6282, 0.4029, 0.8988, 0.3000, 0.4250, 0.4183, 0.7042, 0.5575],
[0.6203, 0.4072, 0.8892, 0.3523, 0.3783, 0.3017, 0.5898, 0.5478],
[0.6118, 0.4052, 0.8462, 0.3917, 0.3537, 0.3450, 0.5053, 0.5593],
[0.6271, 0.4040, 0.9137, 0.3750, 0.4625, 0.2617, 0.7232, 0.5413],
[0.6106, 0.4022, 0.7125, 0.2650, 0.3713, 0.2700, 0.5431, 0.5123],
[0.6264, 0.4049, 0.8988, 0.4633, 0.3812, 0.4983, 0.6326, 0.4843],
[0.6216, 0.4100, 0.7350, 0.2067, 0.4325, 0.2050, 0.5950, 0.5333]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0932905454246793
step: 55
running loss: 0.001696191734994169
Train Steps: 55/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383],
[0.6182, 0.4099, 0.7812, 0.3000, 0.3937, 0.2367, 0.5325, 0.5750],
[0.6275, 0.4013, 0.8850, 0.2833, 0.4975, 0.2233, 0.7058, 0.5343],
[0.6109, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117],
[0.6280, 0.4055, 0.8600, 0.5317, 0.3800, 0.4700, 0.6275, 0.5133],
[0.6283, 0.4283, 0.7477, 0.3542, 0.5125, 0.1917, 0.5500, 0.6167],
[0.6091, 0.3997, 0.8314, 0.4334, 0.3788, 0.4550, 0.5213, 0.5656],
[0.6202, 0.4053, 0.8638, 0.5283, 0.4546, 0.5108, 0.5900, 0.5133]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5960, 0.3916, 0.8328, 0.3137, 0.3090, 0.3448, 0.6383, 0.5323],
[0.5227, 0.3610, 0.7821, 0.2958, 0.3755, 0.2210, 0.5449, 0.5759],
[0.5617, 0.3655, 0.8606, 0.2810, 0.4852, 0.2073, 0.7063, 0.5246],
[0.6541, 0.4277, 0.8747, 0.4585, 0.3404, 0.4017, 0.5486, 0.5071],
[0.6761, 0.4527, 0.8541, 0.5255, 0.3467, 0.4580, 0.6511, 0.4972],
[0.5504, 0.3616, 0.7424, 0.3120, 0.4642, 0.1758, 0.5704, 0.5991],
[0.6524, 0.4272, 0.8397, 0.4339, 0.3420, 0.4341, 0.5560, 0.5430],
[0.6357, 0.4008, 0.8463, 0.5149, 0.4319, 0.4953, 0.5789, 0.5273]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383],
[0.6182, 0.4099, 0.7812, 0.3000, 0.3938, 0.2367, 0.5325, 0.5750],
[0.6275, 0.4013, 0.8850, 0.2833, 0.4975, 0.2233, 0.7058, 0.5343],
[0.6108, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117],
[0.6280, 0.4055, 0.8600, 0.5317, 0.3800, 0.4700, 0.6275, 0.5133],
[0.6283, 0.4283, 0.7477, 0.3542, 0.5125, 0.1917, 0.5500, 0.6167],
[0.6091, 0.3997, 0.8314, 0.4334, 0.3787, 0.4550, 0.5213, 0.5656],
[0.6202, 0.4053, 0.8637, 0.5283, 0.4546, 0.5108, 0.5900, 0.5133]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.09418759748223238
step: 56
running loss: 0.0016819213836112925
Train Steps: 56/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6361, 0.4165, 0.9038, 0.5017, 0.3750, 0.3783, 0.6448, 0.5309],
[0.6227, 0.4049, 0.8750, 0.5367, 0.3775, 0.3667, 0.5725, 0.5317],
[0.6201, 0.4064, 0.8688, 0.5050, 0.4225, 0.5100, 0.6138, 0.5500],
[0.6198, 0.4105, 0.7950, 0.3267, 0.3675, 0.3767, 0.6038, 0.6167],
[0.6250, 0.4106, 0.8700, 0.3717, 0.3588, 0.4967, 0.6038, 0.5167],
[0.6224, 0.4179, 0.8700, 0.5683, 0.4037, 0.4683, 0.5650, 0.5600],
[0.6127, 0.4115, 0.7163, 0.2883, 0.3625, 0.2950, 0.5327, 0.5495],
[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6676, 0.4368, 0.8900, 0.4799, 0.3935, 0.3156, 0.6512, 0.5184],
[0.7548, 0.4830, 0.8803, 0.5309, 0.3699, 0.3366, 0.6227, 0.5090],
[0.6117, 0.3932, 0.8814, 0.4646, 0.4048, 0.4646, 0.6164, 0.5311],
[0.5857, 0.3969, 0.8048, 0.2933, 0.3470, 0.3339, 0.6369, 0.5901],
[0.6177, 0.4172, 0.8760, 0.3511, 0.3644, 0.4374, 0.6449, 0.5348],
[0.6561, 0.4186, 0.8780, 0.5503, 0.3889, 0.4274, 0.5882, 0.5325],
[0.6282, 0.4230, 0.7384, 0.2648, 0.3612, 0.2285, 0.5473, 0.5478],
[0.6170, 0.4053, 0.7809, 0.3479, 0.3499, 0.3602, 0.5553, 0.5295]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6361, 0.4165, 0.9038, 0.5017, 0.3750, 0.3783, 0.6448, 0.5309],
[0.6227, 0.4049, 0.8750, 0.5367, 0.3775, 0.3667, 0.5725, 0.5317],
[0.6201, 0.4064, 0.8687, 0.5050, 0.4225, 0.5100, 0.6137, 0.5500],
[0.6198, 0.4105, 0.7950, 0.3267, 0.3675, 0.3767, 0.6037, 0.6167],
[0.6250, 0.4105, 0.8700, 0.3717, 0.3587, 0.4967, 0.6037, 0.5167],
[0.6224, 0.4179, 0.8700, 0.5683, 0.4038, 0.4683, 0.5650, 0.5600],
[0.6127, 0.4114, 0.7163, 0.2883, 0.3625, 0.2950, 0.5327, 0.5495],
[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.09527627841453068
step: 57
running loss: 0.001671513656395275
Train Steps: 57/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6182, 0.3987, 0.7878, 0.2889, 0.3699, 0.3260, 0.6086, 0.5367],
[0.6262, 0.4085, 0.8438, 0.3150, 0.4025, 0.2633, 0.6339, 0.4810],
[0.6178, 0.4012, 0.8900, 0.4495, 0.3891, 0.5617, 0.5972, 0.4879],
[0.6126, 0.4073, 0.8750, 0.5133, 0.3800, 0.4333, 0.4986, 0.5378],
[0.6082, 0.4024, 0.8738, 0.4017, 0.3688, 0.3950, 0.5306, 0.5136],
[0.6179, 0.4008, 0.7505, 0.2678, 0.4368, 0.1891, 0.5831, 0.5263],
[0.6256, 0.4199, 0.8638, 0.5800, 0.3987, 0.4383, 0.5600, 0.5950],
[0.6305, 0.3983, 0.8950, 0.4833, 0.3688, 0.4683, 0.6375, 0.5117]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5923, 0.3882, 0.7885, 0.2782, 0.3581, 0.2975, 0.6219, 0.5589],
[0.6705, 0.4474, 0.8350, 0.2856, 0.4068, 0.2243, 0.6166, 0.4929],
[0.6653, 0.4542, 0.8764, 0.4276, 0.3875, 0.5155, 0.6295, 0.5115],
[0.6140, 0.4167, 0.8751, 0.5256, 0.3806, 0.4165, 0.5473, 0.5524],
[0.6482, 0.4520, 0.8684, 0.3917, 0.3614, 0.3510, 0.5551, 0.5411],
[0.7469, 0.4962, 0.7565, 0.2374, 0.4311, 0.1452, 0.5950, 0.5401],
[0.6686, 0.4340, 0.8478, 0.5763, 0.3875, 0.4165, 0.5866, 0.6031],
[0.5929, 0.3802, 0.9192, 0.4869, 0.3647, 0.4593, 0.6552, 0.5192]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6182, 0.3987, 0.7878, 0.2889, 0.3699, 0.3260, 0.6086, 0.5367],
[0.6262, 0.4085, 0.8438, 0.3150, 0.4025, 0.2633, 0.6339, 0.4810],
[0.6178, 0.4012, 0.8900, 0.4495, 0.3891, 0.5617, 0.5972, 0.4879],
[0.6126, 0.4073, 0.8750, 0.5133, 0.3800, 0.4333, 0.4986, 0.5378],
[0.6082, 0.4024, 0.8737, 0.4017, 0.3688, 0.3950, 0.5306, 0.5136],
[0.6179, 0.4008, 0.7505, 0.2678, 0.4368, 0.1891, 0.5831, 0.5263],
[0.6256, 0.4199, 0.8637, 0.5800, 0.3988, 0.4383, 0.5600, 0.5950],
[0.6305, 0.3983, 0.8950, 0.4833, 0.3688, 0.4683, 0.6375, 0.5117]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.09628399272332899
step: 58
running loss: 0.0016600688400573965
Train Steps: 58/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6199, 0.4015, 0.8716, 0.5228, 0.3833, 0.4772, 0.5883, 0.5148],
[0.6241, 0.4143, 0.8938, 0.4650, 0.4075, 0.5350, 0.6250, 0.5550],
[0.6107, 0.4013, 0.8700, 0.4650, 0.5049, 0.5176, 0.5850, 0.5550],
[0.6058, 0.3978, 0.8287, 0.3600, 0.3400, 0.4050, 0.5529, 0.5461],
[0.6199, 0.4112, 0.8475, 0.3717, 0.3550, 0.4350, 0.6063, 0.6083],
[0.6267, 0.4065, 0.8313, 0.2467, 0.4788, 0.1733, 0.6312, 0.5133],
[0.6251, 0.4163, 0.8662, 0.4467, 0.3625, 0.3567, 0.6038, 0.5533],
[0.6148, 0.3996, 0.8488, 0.3867, 0.3488, 0.4067, 0.5863, 0.5000]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6687, 0.4266, 0.8866, 0.5246, 0.3931, 0.4508, 0.5781, 0.4987],
[0.5809, 0.3803, 0.8802, 0.4642, 0.4092, 0.5018, 0.6329, 0.5567],
[0.6141, 0.4125, 0.8633, 0.4633, 0.4655, 0.4415, 0.5980, 0.5629],
[0.6745, 0.4543, 0.8192, 0.3643, 0.3462, 0.3749, 0.5754, 0.5205],
[0.6390, 0.4397, 0.8338, 0.3683, 0.3432, 0.4207, 0.5815, 0.5846],
[0.6567, 0.4287, 0.8254, 0.2548, 0.4760, 0.1247, 0.6478, 0.5078],
[0.6230, 0.4060, 0.8469, 0.4417, 0.3595, 0.3145, 0.5798, 0.5405],
[0.7041, 0.4520, 0.8424, 0.3891, 0.3473, 0.3727, 0.5912, 0.5173]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6199, 0.4015, 0.8716, 0.5228, 0.3833, 0.4772, 0.5883, 0.5148],
[0.6241, 0.4142, 0.8938, 0.4650, 0.4075, 0.5350, 0.6250, 0.5550],
[0.6107, 0.4013, 0.8700, 0.4650, 0.5049, 0.5176, 0.5850, 0.5550],
[0.6058, 0.3978, 0.8288, 0.3600, 0.3400, 0.4050, 0.5529, 0.5461],
[0.6199, 0.4112, 0.8475, 0.3717, 0.3550, 0.4350, 0.6062, 0.6083],
[0.6266, 0.4065, 0.8313, 0.2467, 0.4787, 0.1733, 0.6313, 0.5133],
[0.6252, 0.4162, 0.8662, 0.4467, 0.3625, 0.3567, 0.6037, 0.5533],
[0.6148, 0.3996, 0.8487, 0.3867, 0.3487, 0.4067, 0.5863, 0.5000]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.09704984255949967
step: 59
running loss: 0.0016449125857542317
Train Steps: 59/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6099, 0.4030, 0.8638, 0.5117, 0.4983, 0.4965, 0.5086, 0.5388],
[0.6147, 0.4107, 0.8137, 0.3333, 0.3750, 0.2683, 0.5006, 0.5412],
[0.6136, 0.3955, 0.8400, 0.3267, 0.3500, 0.4200, 0.5863, 0.5467],
[0.6192, 0.4128, 0.8513, 0.5617, 0.4200, 0.5267, 0.5850, 0.5633],
[0.6129, 0.4063, 0.8738, 0.5250, 0.4313, 0.4733, 0.5230, 0.5874],
[0.6161, 0.4040, 0.7525, 0.2133, 0.4125, 0.2067, 0.5787, 0.5117],
[0.6198, 0.4115, 0.7762, 0.2717, 0.3713, 0.3200, 0.5837, 0.5683],
[0.6131, 0.4037, 0.6907, 0.2819, 0.3688, 0.2700, 0.5217, 0.5680]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5524, 0.3684, 0.8810, 0.5297, 0.5100, 0.4835, 0.5320, 0.5300],
[0.5466, 0.3586, 0.8001, 0.3506, 0.3732, 0.2584, 0.5257, 0.5388],
[0.6086, 0.3828, 0.8570, 0.3213, 0.3544, 0.3979, 0.5820, 0.5188],
[0.6513, 0.4311, 0.8822, 0.5697, 0.4222, 0.5225, 0.6060, 0.5511],
[0.6884, 0.4478, 0.8747, 0.5551, 0.4310, 0.4643, 0.5607, 0.5479],
[0.8111, 0.5159, 0.7555, 0.2227, 0.4257, 0.2197, 0.5950, 0.4980],
[0.6200, 0.4054, 0.7956, 0.2775, 0.3638, 0.3102, 0.5975, 0.5639],
[0.5884, 0.3865, 0.7129, 0.2693, 0.3853, 0.2834, 0.5373, 0.5499]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6098, 0.4030, 0.8637, 0.5117, 0.4983, 0.4965, 0.5086, 0.5388],
[0.6147, 0.4107, 0.8138, 0.3333, 0.3750, 0.2683, 0.5006, 0.5412],
[0.6136, 0.3955, 0.8400, 0.3267, 0.3500, 0.4200, 0.5863, 0.5467],
[0.6192, 0.4128, 0.8512, 0.5617, 0.4200, 0.5267, 0.5850, 0.5633],
[0.6130, 0.4063, 0.8737, 0.5250, 0.4313, 0.4733, 0.5230, 0.5874],
[0.6161, 0.4040, 0.7525, 0.2133, 0.4125, 0.2067, 0.5788, 0.5117],
[0.6198, 0.4115, 0.7763, 0.2717, 0.3713, 0.3200, 0.5838, 0.5683],
[0.6131, 0.4036, 0.6907, 0.2819, 0.3688, 0.2700, 0.5217, 0.5680]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0983880981511902
step: 60
running loss: 0.00163980163585317
Train Steps: 60/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6275, 0.4024, 0.8600, 0.2283, 0.5350, 0.1800, 0.7074, 0.5413],
[ nan, nan, 0.7850, 0.2700, 0.4288, 0.1717, 0.5199, 0.4999],
[0.6125, 0.4076, 0.8488, 0.3883, 0.3700, 0.3683, 0.5026, 0.5505],
[0.6210, 0.4164, 0.7202, 0.2930, 0.4025, 0.2483, 0.5687, 0.5567],
[0.6200, 0.4059, 0.8700, 0.4900, 0.4163, 0.5000, 0.6162, 0.5467],
[0.6168, 0.4081, 0.8438, 0.3367, 0.3500, 0.4667, 0.6212, 0.5400],
[0.6128, 0.4115, 0.7934, 0.3778, 0.3450, 0.4033, 0.5337, 0.5456],
[0.6196, 0.4068, 0.7645, 0.2234, 0.4575, 0.1737, 0.5926, 0.5284]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5544, 0.3590, 0.8481, 0.2554, 0.5409, 0.2350, 0.6758, 0.5367],
[0.2139, 0.1506, 0.7774, 0.2641, 0.4452, 0.2224, 0.5098, 0.5522],
[0.7379, 0.4704, 0.8540, 0.4256, 0.3654, 0.3925, 0.4794, 0.5282],
[0.5526, 0.3593, 0.7588, 0.2905, 0.4331, 0.2762, 0.5581, 0.5591],
[0.6221, 0.4242, 0.8964, 0.5445, 0.4330, 0.5784, 0.5897, 0.5532],
[0.5752, 0.3930, 0.8614, 0.3583, 0.3594, 0.4973, 0.6189, 0.5515],
[0.7502, 0.4973, 0.8014, 0.4046, 0.3410, 0.4333, 0.5064, 0.5422],
[0.7757, 0.5141, 0.7650, 0.2587, 0.4693, 0.2058, 0.5800, 0.5271]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6275, 0.4024, 0.8600, 0.2283, 0.5350, 0.1800, 0.7074, 0.5413],
[0.0000, 0.0000, 0.7850, 0.2700, 0.4288, 0.1717, 0.5199, 0.4999],
[0.6125, 0.4076, 0.8487, 0.3883, 0.3700, 0.3683, 0.5026, 0.5505],
[0.6210, 0.4164, 0.7202, 0.2930, 0.4025, 0.2483, 0.5688, 0.5567],
[0.6199, 0.4059, 0.8700, 0.4900, 0.4162, 0.5000, 0.6162, 0.5467],
[0.6168, 0.4081, 0.8438, 0.3367, 0.3500, 0.4667, 0.6212, 0.5400],
[0.6128, 0.4115, 0.7934, 0.3778, 0.3450, 0.4033, 0.5337, 0.5456],
[0.6196, 0.4068, 0.7645, 0.2234, 0.4575, 0.1737, 0.5926, 0.5284]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0032, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0032, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.10155432714964263
step: 61
running loss: 0.001664825035240043
Train Steps: 61/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6136, 0.4060, 0.8025, 0.3217, 0.3650, 0.3000, 0.5060, 0.5646],
[0.6076, 0.3953, 0.8125, 0.3917, 0.3525, 0.4083, 0.5346, 0.4954],
[ nan, nan, 0.9050, 0.3500, 0.5138, 0.2300, 0.7359, 0.5702],
[0.6261, 0.4131, 0.8938, 0.3550, 0.4000, 0.2683, 0.6188, 0.5283],
[ nan, nan, 0.6935, 0.1930, 0.4150, 0.2250, 0.5450, 0.5650],
[0.6143, 0.4040, 0.8237, 0.3333, 0.4075, 0.2117, 0.5137, 0.4973],
[0.6263, 0.4057, 0.8800, 0.3833, 0.3650, 0.3717, 0.6375, 0.4804],
[ nan, nan, 0.8938, 0.2850, 0.4662, 0.3117, 0.7406, 0.5528]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7333, 0.5004, 0.7735, 0.3322, 0.3780, 0.3378, 0.4660, 0.5727],
[0.7130, 0.4630, 0.7946, 0.3756, 0.3519, 0.4460, 0.5214, 0.5315],
[0.3009, 0.2057, 0.8649, 0.3455, 0.5145, 0.2872, 0.6320, 0.5746],
[0.7436, 0.4856, 0.8686, 0.3659, 0.4083, 0.3257, 0.5701, 0.5233],
[0.2093, 0.1384, 0.6915, 0.2328, 0.4616, 0.2953, 0.5221, 0.5782],
[0.6982, 0.4350, 0.7919, 0.3409, 0.4342, 0.2717, 0.4762, 0.5167],
[0.8061, 0.5239, 0.8521, 0.3967, 0.3773, 0.4158, 0.5907, 0.5020],
[0.1672, 0.1115, 0.8612, 0.2978, 0.4808, 0.3562, 0.6760, 0.5824]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6136, 0.4060, 0.8025, 0.3217, 0.3650, 0.3000, 0.5060, 0.5646],
[0.6076, 0.3952, 0.8125, 0.3917, 0.3525, 0.4083, 0.5346, 0.4954],
[0.0000, 0.0000, 0.9050, 0.3500, 0.5138, 0.2300, 0.7359, 0.5702],
[0.6261, 0.4131, 0.8938, 0.3550, 0.4000, 0.2683, 0.6187, 0.5283],
[0.0000, 0.0000, 0.6935, 0.1930, 0.4150, 0.2250, 0.5450, 0.5650],
[0.6143, 0.4040, 0.8238, 0.3333, 0.4075, 0.2117, 0.5137, 0.4973],
[0.6263, 0.4057, 0.8800, 0.3833, 0.3650, 0.3717, 0.6375, 0.4804],
[0.0000, 0.0000, 0.8938, 0.2850, 0.4663, 0.3117, 0.7406, 0.5528]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0064, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0064, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.10794588641147129
step: 62
running loss: 0.0017410626840559885
Train Steps: 62/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6296, 0.3989, 0.9000, 0.4150, 0.3613, 0.3867, 0.6400, 0.5100],
[0.6236, 0.3966, 0.8850, 0.4967, 0.3638, 0.4017, 0.5850, 0.5183],
[0.6179, 0.4118, 0.7278, 0.4237, 0.3588, 0.3400, 0.5675, 0.5917],
[0.6098, 0.3991, 0.8638, 0.4717, 0.4263, 0.4967, 0.5212, 0.5650],
[ nan, nan, 0.6469, 0.1943, 0.4025, 0.2000, 0.5125, 0.5533],
[0.6173, 0.4013, 0.8713, 0.4640, 0.4800, 0.5700, 0.6025, 0.5600],
[0.6058, 0.3986, 0.8324, 0.4626, 0.3838, 0.4983, 0.5147, 0.5466],
[0.6072, 0.4029, 0.7037, 0.2150, 0.3912, 0.2267, 0.5516, 0.5507]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6443, 0.3973, 0.9186, 0.4363, 0.3844, 0.4203, 0.6107, 0.5025],
[0.5870, 0.3576, 0.9018, 0.4988, 0.3745, 0.4480, 0.5780, 0.5176],
[0.6250, 0.4147, 0.7870, 0.4136, 0.3721, 0.3787, 0.5733, 0.5922],
[0.5771, 0.3501, 0.8886, 0.4988, 0.4560, 0.5279, 0.5326, 0.5574],
[0.1619, 0.0922, 0.7203, 0.2126, 0.4333, 0.2041, 0.5526, 0.5699],
[0.4896, 0.3245, 0.9115, 0.4716, 0.4796, 0.5833, 0.5782, 0.5692],
[0.5880, 0.3797, 0.8613, 0.4694, 0.4195, 0.5210, 0.5192, 0.5485],
[0.6626, 0.4191, 0.7250, 0.2456, 0.4148, 0.2477, 0.5574, 0.5377]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6296, 0.3989, 0.9000, 0.4150, 0.3613, 0.3867, 0.6400, 0.5100],
[0.6236, 0.3965, 0.8850, 0.4967, 0.3638, 0.4017, 0.5850, 0.5183],
[0.6179, 0.4118, 0.7278, 0.4237, 0.3587, 0.3400, 0.5675, 0.5917],
[0.6098, 0.3991, 0.8637, 0.4717, 0.4263, 0.4967, 0.5213, 0.5650],
[0.0000, 0.0000, 0.6469, 0.1943, 0.4025, 0.2000, 0.5125, 0.5533],
[0.6173, 0.4013, 0.8713, 0.4640, 0.4800, 0.5700, 0.6025, 0.5600],
[0.6058, 0.3986, 0.8324, 0.4626, 0.3837, 0.4983, 0.5147, 0.5466],
[0.6072, 0.4029, 0.7038, 0.2150, 0.3913, 0.2267, 0.5516, 0.5507]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.1094864918559324
step: 63
running loss: 0.001737880823110038
Train Steps: 63/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6202, 0.4066, 0.8746, 0.3376, 0.3717, 0.3090, 0.5842, 0.5165],
[0.6236, 0.3967, 0.8675, 0.5400, 0.3862, 0.4517, 0.5825, 0.5200],
[0.6200, 0.3978, 0.8900, 0.4550, 0.3775, 0.5200, 0.6150, 0.5367],
[0.6204, 0.4007, 0.7838, 0.2100, 0.4475, 0.1733, 0.5825, 0.5167],
[0.6246, 0.4028, 0.8738, 0.4867, 0.4088, 0.5667, 0.6362, 0.5200],
[0.6339, 0.4081, 0.8425, 0.5417, 0.3850, 0.4833, 0.7335, 0.5760],
[0.6122, 0.4048, 0.7506, 0.3014, 0.3475, 0.3333, 0.5487, 0.5749],
[0.6225, 0.4191, 0.8500, 0.4167, 0.3688, 0.3233, 0.5650, 0.5650]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5513, 0.3592, 0.8662, 0.3485, 0.3772, 0.3205, 0.5762, 0.5387],
[0.4817, 0.3048, 0.8697, 0.5463, 0.3880, 0.4739, 0.5632, 0.5283],
[0.5399, 0.3348, 0.9029, 0.4546, 0.4078, 0.5403, 0.5872, 0.5457],
[0.4647, 0.2731, 0.7782, 0.2394, 0.4507, 0.1822, 0.5812, 0.5226],
[0.5025, 0.3091, 0.8910, 0.4677, 0.4300, 0.5890, 0.6320, 0.5428],
[0.5606, 0.3719, 0.8676, 0.5222, 0.4119, 0.4951, 0.6652, 0.5893],
[0.4988, 0.3030, 0.7705, 0.3064, 0.3635, 0.3410, 0.5255, 0.5430],
[0.4922, 0.3373, 0.8392, 0.3999, 0.3699, 0.3585, 0.5458, 0.5868]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6202, 0.4066, 0.8746, 0.3376, 0.3717, 0.3090, 0.5842, 0.5165],
[0.6236, 0.3967, 0.8675, 0.5400, 0.3862, 0.4517, 0.5825, 0.5200],
[0.6199, 0.3978, 0.8900, 0.4550, 0.3775, 0.5200, 0.6150, 0.5367],
[0.6204, 0.4007, 0.7837, 0.2100, 0.4475, 0.1733, 0.5825, 0.5167],
[0.6246, 0.4028, 0.8737, 0.4867, 0.4087, 0.5667, 0.6363, 0.5200],
[0.6339, 0.4081, 0.8425, 0.5417, 0.3850, 0.4833, 0.7335, 0.5760],
[0.6122, 0.4048, 0.7506, 0.3014, 0.3475, 0.3333, 0.5487, 0.5749],
[0.6225, 0.4191, 0.8500, 0.4167, 0.3688, 0.3233, 0.5650, 0.5650]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0029, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0029, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.11233921625535004
step: 64
running loss: 0.0017553002539898444
Train Steps: 64/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6204, 0.4055, 0.8438, 0.5733, 0.4574, 0.4801, 0.5487, 0.5617],
[0.6176, 0.4017, 0.8788, 0.5100, 0.4075, 0.5250, 0.5913, 0.5033],
[0.6193, 0.4079, 0.7288, 0.2500, 0.4250, 0.2550, 0.5989, 0.6266],
[0.6151, 0.4058, 0.7068, 0.2680, 0.3400, 0.4083, 0.5775, 0.5733],
[0.6276, 0.4120, 0.8738, 0.3133, 0.4225, 0.2217, 0.6203, 0.4892],
[0.6136, 0.3955, 0.8400, 0.3267, 0.3500, 0.4200, 0.5863, 0.5467],
[0.6086, 0.3940, 0.8712, 0.4783, 0.4025, 0.4900, 0.5498, 0.5390],
[0.6257, 0.4167, 0.8775, 0.3433, 0.3563, 0.4133, 0.6200, 0.5667]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4944, 0.3168, 0.8474, 0.5816, 0.4411, 0.4373, 0.5721, 0.5677],
[0.5039, 0.3218, 0.8871, 0.5070, 0.4029, 0.5259, 0.5760, 0.5276],
[0.4978, 0.3210, 0.7504, 0.2609, 0.4081, 0.2607, 0.6218, 0.6058],
[0.5300, 0.3422, 0.7354, 0.2737, 0.3297, 0.3932, 0.5870, 0.5635],
[0.4631, 0.3005, 0.8866, 0.3447, 0.4234, 0.2134, 0.6178, 0.4854],
[0.5129, 0.3247, 0.8528, 0.3257, 0.3440, 0.3944, 0.5765, 0.5320],
[0.4362, 0.2714, 0.8773, 0.4883, 0.3986, 0.4727, 0.5806, 0.5211],
[0.4654, 0.2932, 0.8854, 0.3447, 0.3446, 0.4048, 0.6510, 0.5646]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6204, 0.4055, 0.8438, 0.5733, 0.4574, 0.4801, 0.5487, 0.5617],
[0.6176, 0.4017, 0.8788, 0.5100, 0.4075, 0.5250, 0.5913, 0.5033],
[0.6193, 0.4078, 0.7287, 0.2500, 0.4250, 0.2550, 0.5989, 0.6266],
[0.6151, 0.4058, 0.7068, 0.2680, 0.3400, 0.4083, 0.5775, 0.5733],
[0.6276, 0.4120, 0.8737, 0.3133, 0.4225, 0.2217, 0.6203, 0.4892],
[0.6136, 0.3955, 0.8400, 0.3267, 0.3500, 0.4200, 0.5863, 0.5467],
[0.6086, 0.3940, 0.8712, 0.4783, 0.4025, 0.4900, 0.5498, 0.5390],
[0.6257, 0.4167, 0.8775, 0.3433, 0.3562, 0.4133, 0.6200, 0.5667]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0036, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0036, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.11592077181558125
step: 65
running loss: 0.0017833964894704807
Train Steps: 65/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6310, 0.4017, 0.8563, 0.5800, 0.3688, 0.4750, 0.6326, 0.5006],
[ nan, nan, 0.8750, 0.2467, 0.5138, 0.2617, 0.7382, 0.5552],
[0.6179, 0.3961, 0.8347, 0.6020, 0.3887, 0.4624, 0.5714, 0.5373],
[0.6115, 0.3998, 0.7063, 0.2383, 0.4037, 0.1950, 0.5320, 0.4993],
[0.6157, 0.4102, 0.8513, 0.3817, 0.3613, 0.3667, 0.5096, 0.5890],
[0.6304, 0.4024, 0.8925, 0.4800, 0.3937, 0.4817, 0.7485, 0.5297],
[0.6173, 0.4114, 0.7325, 0.2500, 0.4213, 0.1917, 0.5338, 0.5700],
[0.6182, 0.3982, 0.7541, 0.2379, 0.3959, 0.2792, 0.6079, 0.5389]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.5804, 0.3857, 0.8771, 0.5844, 0.3679, 0.4868, 0.6360, 0.5012],
[-0.0425, -0.0367, 0.8551, 0.2400, 0.4732, 0.2295, 0.6997, 0.5585],
[ 0.5929, 0.4005, 0.8401, 0.5809, 0.3690, 0.4718, 0.5810, 0.5505],
[ 0.5663, 0.3888, 0.7067, 0.2198, 0.3865, 0.2174, 0.5131, 0.5074],
[ 0.5684, 0.3669, 0.8644, 0.3607, 0.3334, 0.3551, 0.5328, 0.5657],
[ 0.5612, 0.3696, 0.8814, 0.4700, 0.3682, 0.4813, 0.6840, 0.5249],
[ 0.4214, 0.2801, 0.7307, 0.2213, 0.4080, 0.1993, 0.5412, 0.5526],
[ 0.5440, 0.3590, 0.7677, 0.2257, 0.3728, 0.2917, 0.5940, 0.5315]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6310, 0.4017, 0.8562, 0.5800, 0.3688, 0.4750, 0.6326, 0.5006],
[0.0000, 0.0000, 0.8750, 0.2467, 0.5138, 0.2617, 0.7382, 0.5552],
[0.6179, 0.3961, 0.8347, 0.6020, 0.3887, 0.4624, 0.5714, 0.5373],
[0.6115, 0.3998, 0.7063, 0.2383, 0.4038, 0.1950, 0.5320, 0.4993],
[0.6157, 0.4102, 0.8512, 0.3817, 0.3613, 0.3667, 0.5096, 0.5890],
[0.6304, 0.4024, 0.8925, 0.4800, 0.3938, 0.4817, 0.7485, 0.5297],
[0.6173, 0.4114, 0.7325, 0.2500, 0.4212, 0.1917, 0.5337, 0.5700],
[0.6182, 0.3982, 0.7541, 0.2379, 0.3959, 0.2792, 0.6079, 0.5389]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.11747965749236755
step: 66
running loss: 0.0017799948104904174
Train Steps: 66/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6128, 0.4084, 0.8738, 0.4683, 0.3613, 0.3700, 0.4960, 0.5397],
[0.6129, 0.4063, 0.8738, 0.5250, 0.4313, 0.4733, 0.5230, 0.5874],
[0.6261, 0.3987, 0.9045, 0.4208, 0.3600, 0.4633, 0.6570, 0.5162],
[0.6170, 0.4102, 0.7468, 0.3695, 0.3463, 0.3767, 0.5238, 0.5823],
[0.6300, 0.4133, 0.8538, 0.2167, 0.5587, 0.2250, 0.7390, 0.5413],
[0.6205, 0.4062, 0.8337, 0.2683, 0.3675, 0.4283, 0.6338, 0.5250],
[0.6239, 0.4061, 0.8850, 0.4600, 0.4225, 0.5200, 0.6138, 0.5450],
[0.6211, 0.3993, 0.7650, 0.1933, 0.4575, 0.1550, 0.5965, 0.4895]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6251, 0.4033, 0.8557, 0.5007, 0.3239, 0.3519, 0.5428, 0.5372],
[0.6137, 0.4180, 0.8449, 0.5570, 0.3967, 0.4510, 0.5643, 0.5701],
[0.5641, 0.3861, 0.8715, 0.4379, 0.3183, 0.4774, 0.6737, 0.5093],
[0.5425, 0.3741, 0.7356, 0.3609, 0.3198, 0.3816, 0.5545, 0.5847],
[0.3630, 0.2469, 0.8479, 0.2203, 0.5101, 0.2250, 0.7429, 0.5562],
[0.5277, 0.3549, 0.7876, 0.2757, 0.3350, 0.4166, 0.6158, 0.5284],
[0.5695, 0.3940, 0.8755, 0.4750, 0.3733, 0.5183, 0.6559, 0.5532],
[0.4964, 0.3130, 0.7487, 0.1767, 0.4193, 0.1578, 0.6286, 0.4901]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6127, 0.4084, 0.8737, 0.4683, 0.3613, 0.3700, 0.4960, 0.5397],
[0.6130, 0.4063, 0.8737, 0.5250, 0.4313, 0.4733, 0.5230, 0.5874],
[0.6261, 0.3987, 0.9045, 0.4208, 0.3600, 0.4633, 0.6570, 0.5162],
[0.6170, 0.4102, 0.7468, 0.3695, 0.3462, 0.3767, 0.5238, 0.5823],
[0.6300, 0.4133, 0.8537, 0.2167, 0.5587, 0.2250, 0.7390, 0.5413],
[0.6205, 0.4062, 0.8338, 0.2683, 0.3675, 0.4283, 0.6338, 0.5250],
[0.6239, 0.4061, 0.8850, 0.4600, 0.4225, 0.5200, 0.6137, 0.5450],
[0.6211, 0.3993, 0.7650, 0.1933, 0.4575, 0.1550, 0.5965, 0.4895]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0028, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0028, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.1202581440738868
step: 67
running loss: 0.001794897672744579
Train Steps: 67/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383],
[0.6250, 0.4116, 0.8700, 0.4850, 0.4650, 0.5567, 0.6088, 0.5183],
[0.6214, 0.3982, 0.8938, 0.4517, 0.3663, 0.4083, 0.5863, 0.5050],
[0.6151, 0.4125, 0.8738, 0.4417, 0.3575, 0.3783, 0.5138, 0.5483],
[0.6193, 0.4034, 0.7757, 0.2347, 0.3733, 0.2919, 0.5930, 0.4926],
[0.6090, 0.4045, 0.7250, 0.2100, 0.4075, 0.2300, 0.5476, 0.5663],
[0.6100, 0.4071, 0.7601, 0.3444, 0.3400, 0.4117, 0.5625, 0.5617],
[0.6339, 0.4118, 0.7988, 0.5800, 0.3912, 0.4583, 0.7343, 0.5760]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6612, 0.4562, 0.8680, 0.4165, 0.4319, 0.5259, 0.6222, 0.5346],
[0.5574, 0.3880, 0.8802, 0.4529, 0.4421, 0.5177, 0.6578, 0.5421],
[0.5582, 0.3715, 0.8900, 0.4436, 0.3643, 0.3686, 0.6026, 0.5147],
[0.5936, 0.4037, 0.8495, 0.4358, 0.3438, 0.3282, 0.5475, 0.5556],
[0.5840, 0.4030, 0.7509, 0.2079, 0.3725, 0.2356, 0.6260, 0.4932],
[0.4665, 0.3168, 0.7085, 0.2098, 0.3752, 0.2044, 0.5738, 0.5676],
[0.6158, 0.4249, 0.7574, 0.3089, 0.3399, 0.4049, 0.5947, 0.5401],
[0.5303, 0.3628, 0.7998, 0.4980, 0.3657, 0.4049, 0.6914, 0.5614]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383],
[0.6251, 0.4116, 0.8700, 0.4850, 0.4650, 0.5567, 0.6087, 0.5183],
[0.6214, 0.3982, 0.8938, 0.4517, 0.3663, 0.4083, 0.5863, 0.5050],
[0.6151, 0.4125, 0.8737, 0.4417, 0.3575, 0.3783, 0.5138, 0.5483],
[0.6193, 0.4034, 0.7757, 0.2347, 0.3733, 0.2919, 0.5930, 0.4926],
[0.6090, 0.4045, 0.7250, 0.2100, 0.4075, 0.2300, 0.5476, 0.5663],
[0.6100, 0.4071, 0.7601, 0.3444, 0.3400, 0.4117, 0.5625, 0.5617],
[0.6339, 0.4118, 0.7987, 0.5800, 0.3913, 0.4583, 0.7343, 0.5760]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.12180890384479426
step: 68
running loss: 0.0017913074094822684
Train Steps: 68/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6185, 0.4129, 0.8900, 0.4567, 0.3937, 0.5417, 0.5734, 0.5110],
[0.6283, 0.4283, 0.7477, 0.3542, 0.5125, 0.1917, 0.5500, 0.6167],
[0.6112, 0.4029, 0.8638, 0.4800, 0.4875, 0.5083, 0.5763, 0.5567],
[0.6189, 0.4029, 0.8375, 0.5767, 0.4745, 0.4829, 0.5551, 0.5598],
[0.6293, 0.4097, 0.8800, 0.2517, 0.5262, 0.2600, 0.7430, 0.5378],
[0.6272, 0.4045, 0.8538, 0.5900, 0.3750, 0.4417, 0.5989, 0.4649],
[0.6277, 0.4013, 0.8888, 0.4767, 0.3600, 0.3567, 0.6148, 0.4672],
[0.6196, 0.4088, 0.8888, 0.4583, 0.4500, 0.5683, 0.6138, 0.5883]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6241, 0.4234, 0.8645, 0.3934, 0.3759, 0.5098, 0.5802, 0.5197],
[0.6142, 0.4060, 0.7109, 0.2683, 0.4481, 0.1873, 0.5449, 0.5926],
[0.5609, 0.3858, 0.8440, 0.4253, 0.4511, 0.4539, 0.5817, 0.5489],
[0.6234, 0.4384, 0.8018, 0.4867, 0.4361, 0.4341, 0.5862, 0.5596],
[0.5419, 0.3619, 0.8450, 0.2001, 0.4939, 0.2217, 0.7119, 0.5358],
[0.6548, 0.4339, 0.8147, 0.5305, 0.3407, 0.3900, 0.5933, 0.4804],
[0.6723, 0.4529, 0.8368, 0.3916, 0.3305, 0.3355, 0.6153, 0.4993],
[0.6250, 0.4366, 0.8396, 0.3740, 0.4185, 0.5401, 0.6053, 0.5594]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6186, 0.4129, 0.8900, 0.4567, 0.3938, 0.5417, 0.5734, 0.5110],
[0.6283, 0.4283, 0.7477, 0.3542, 0.5125, 0.1917, 0.5500, 0.6167],
[0.6112, 0.4029, 0.8637, 0.4800, 0.4875, 0.5083, 0.5763, 0.5567],
[0.6189, 0.4029, 0.8375, 0.5767, 0.4745, 0.4829, 0.5551, 0.5598],
[0.6293, 0.4097, 0.8800, 0.2517, 0.5263, 0.2600, 0.7430, 0.5378],
[0.6271, 0.4045, 0.8537, 0.5900, 0.3750, 0.4417, 0.5989, 0.4649],
[0.6277, 0.4013, 0.8888, 0.4767, 0.3600, 0.3567, 0.6148, 0.4672],
[0.6196, 0.4088, 0.8888, 0.4583, 0.4500, 0.5683, 0.6137, 0.5883]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.12344274375936948
step: 69
running loss: 0.00178902527187492
Train Steps: 69/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6177, 0.4086, 0.8738, 0.3950, 0.3775, 0.5600, 0.6225, 0.5700],
[0.6271, 0.4040, 0.9138, 0.3750, 0.4625, 0.2617, 0.7232, 0.5413],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3788, 0.4900, 0.7121, 0.5864],
[0.6140, 0.4070, 0.8700, 0.5000, 0.4612, 0.4900, 0.5260, 0.5852],
[0.6239, 0.4107, 0.8162, 0.2763, 0.3625, 0.3600, 0.5988, 0.5700],
[0.6168, 0.4081, 0.8438, 0.3367, 0.3500, 0.4667, 0.6212, 0.5400],
[0.6197, 0.3930, 0.8793, 0.4736, 0.4152, 0.5464, 0.6308, 0.5235],
[0.6266, 0.4101, 0.8350, 0.2333, 0.3950, 0.2950, 0.6264, 0.4921]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7387, 0.4992, 0.8326, 0.3715, 0.3934, 0.5256, 0.6269, 0.5265],
[0.6438, 0.4278, 0.9021, 0.3559, 0.4733, 0.2499, 0.6971, 0.5084],
[0.6759, 0.4547, 0.8371, 0.5015, 0.4044, 0.4597, 0.6859, 0.5400],
[0.6668, 0.4625, 0.8443, 0.4836, 0.4699, 0.4555, 0.5151, 0.5617],
[0.5322, 0.3633, 0.7571, 0.2769, 0.3974, 0.3349, 0.5683, 0.5541],
[0.6474, 0.4479, 0.8151, 0.3181, 0.3610, 0.4445, 0.6198, 0.5369],
[0.6664, 0.4622, 0.8580, 0.4708, 0.4462, 0.5022, 0.6261, 0.5201],
[0.7322, 0.4684, 0.8168, 0.2213, 0.4268, 0.2554, 0.6238, 0.4816]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6177, 0.4085, 0.8737, 0.3950, 0.3775, 0.5600, 0.6225, 0.5700],
[0.6271, 0.4040, 0.9137, 0.3750, 0.4625, 0.2617, 0.7232, 0.5413],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3787, 0.4900, 0.7121, 0.5864],
[0.6140, 0.4070, 0.8700, 0.5000, 0.4613, 0.4900, 0.5260, 0.5852],
[0.6239, 0.4107, 0.8162, 0.2763, 0.3625, 0.3600, 0.5987, 0.5700],
[0.6168, 0.4081, 0.8438, 0.3367, 0.3500, 0.4667, 0.6212, 0.5400],
[0.6197, 0.3930, 0.8793, 0.4736, 0.4152, 0.5464, 0.6308, 0.5235],
[0.6266, 0.4101, 0.8350, 0.2333, 0.3950, 0.2950, 0.6264, 0.4921]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.12500527323572896
step: 70
running loss: 0.0017857896176532708
Train Steps: 70/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6106, 0.4022, 0.7125, 0.2650, 0.3713, 0.2700, 0.5431, 0.5123],
[0.6236, 0.3966, 0.8850, 0.4967, 0.3638, 0.4017, 0.5850, 0.5183],
[0.6147, 0.4107, 0.8137, 0.3333, 0.3750, 0.2683, 0.5006, 0.5412],
[0.6248, 0.4185, 0.8500, 0.5767, 0.4463, 0.4550, 0.5613, 0.5917],
[0.6193, 0.4165, 0.8838, 0.4700, 0.4150, 0.4867, 0.5427, 0.5261],
[ nan, nan, 0.8850, 0.3000, 0.5363, 0.2250, 0.7343, 0.5771],
[0.6222, 0.4169, 0.8638, 0.5650, 0.4313, 0.4783, 0.5637, 0.5633],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6740, 0.4580, 0.7269, 0.2416, 0.3939, 0.2809, 0.5639, 0.5228],
[0.6931, 0.4447, 0.8656, 0.4627, 0.3803, 0.4282, 0.6171, 0.5161],
[0.7225, 0.4748, 0.7947, 0.3181, 0.3930, 0.2757, 0.5183, 0.5355],
[0.7884, 0.5138, 0.8540, 0.5704, 0.4757, 0.4530, 0.5667, 0.5913],
[0.7516, 0.4976, 0.8647, 0.4521, 0.4303, 0.4952, 0.5614, 0.5281],
[0.2397, 0.1529, 0.8816, 0.2423, 0.5373, 0.2346, 0.7495, 0.5470],
[0.7616, 0.5046, 0.8529, 0.5398, 0.4444, 0.4879, 0.6154, 0.5691],
[0.7566, 0.5095, 0.8891, 0.4354, 0.4529, 0.5162, 0.6032, 0.5257]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6106, 0.4022, 0.7125, 0.2650, 0.3713, 0.2700, 0.5431, 0.5123],
[0.6236, 0.3965, 0.8850, 0.4967, 0.3638, 0.4017, 0.5850, 0.5183],
[0.6147, 0.4107, 0.8138, 0.3333, 0.3750, 0.2683, 0.5006, 0.5412],
[0.6248, 0.4185, 0.8500, 0.5767, 0.4462, 0.4550, 0.5612, 0.5917],
[0.6193, 0.4165, 0.8838, 0.4700, 0.4150, 0.4867, 0.5427, 0.5261],
[0.0000, 0.0000, 0.8850, 0.3000, 0.5362, 0.2250, 0.7343, 0.5771],
[0.6222, 0.4169, 0.8637, 0.5650, 0.4313, 0.4783, 0.5638, 0.5633],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0039, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0039, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.1288923279789742
step: 71
running loss: 0.0018153849011123128
Train Steps: 71/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6150, 0.3935, 0.8696, 0.5158, 0.4647, 0.5329, 0.6041, 0.5153],
[0.6282, 0.4092, 0.8000, 0.2183, 0.4500, 0.2383, 0.6787, 0.5364],
[0.6267, 0.4094, 0.8712, 0.3083, 0.4400, 0.2267, 0.6250, 0.5200],
[0.6226, 0.4185, 0.8850, 0.5500, 0.3800, 0.4250, 0.5625, 0.5617],
[0.6336, 0.4154, 0.8900, 0.2767, 0.4988, 0.2867, 0.7422, 0.5540],
[0.6173, 0.4013, 0.8713, 0.4640, 0.4800, 0.5700, 0.6025, 0.5600],
[0.6263, 0.4065, 0.9038, 0.4317, 0.3588, 0.4550, 0.6325, 0.5250],
[0.6222, 0.4172, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6854, 0.4290, 0.8553, 0.5348, 0.4771, 0.5437, 0.5710, 0.5228],
[0.7214, 0.4744, 0.7999, 0.2458, 0.4623, 0.2501, 0.6241, 0.5392],
[0.6655, 0.4104, 0.8681, 0.3181, 0.4673, 0.2397, 0.6046, 0.5253],
[0.7321, 0.4662, 0.8887, 0.5671, 0.4110, 0.4492, 0.5422, 0.5732],
[0.5737, 0.3805, 0.8622, 0.3099, 0.5229, 0.3049, 0.6988, 0.5457],
[0.6894, 0.4463, 0.8710, 0.4764, 0.4769, 0.5825, 0.5848, 0.5603],
[0.7157, 0.4586, 0.8985, 0.4550, 0.4095, 0.4748, 0.6335, 0.5365],
[0.6618, 0.4263, 0.8856, 0.5448, 0.3901, 0.4869, 0.5635, 0.5772]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6150, 0.3935, 0.8696, 0.5158, 0.4647, 0.5329, 0.6041, 0.5153],
[0.6282, 0.4092, 0.8000, 0.2183, 0.4500, 0.2383, 0.6787, 0.5364],
[0.6267, 0.4094, 0.8712, 0.3083, 0.4400, 0.2267, 0.6250, 0.5200],
[0.6226, 0.4185, 0.8850, 0.5500, 0.3800, 0.4250, 0.5625, 0.5617],
[0.6336, 0.4154, 0.8900, 0.2767, 0.4988, 0.2867, 0.7422, 0.5540],
[0.6173, 0.4013, 0.8713, 0.4640, 0.4800, 0.5700, 0.6025, 0.5600],
[0.6263, 0.4065, 0.9038, 0.4317, 0.3587, 0.4550, 0.6325, 0.5250],
[0.6222, 0.4171, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.1301426654390525
step: 72
running loss: 0.0018075370199868404
Train Steps: 72/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6263, 0.4233, 0.7924, 0.4626, 0.3788, 0.2883, 0.5573, 0.6047],
[0.6274, 0.4087, 0.8375, 0.5700, 0.4025, 0.4800, 0.5700, 0.6117],
[0.6085, 0.4005, 0.8400, 0.4317, 0.3763, 0.4750, 0.5476, 0.5058],
[0.6262, 0.4163, 0.8850, 0.5183, 0.3763, 0.4150, 0.6025, 0.5500],
[0.6198, 0.4076, 0.7945, 0.2453, 0.4475, 0.1871, 0.5897, 0.5350],
[0.6124, 0.4075, 0.7696, 0.4153, 0.3475, 0.3767, 0.5157, 0.5427],
[0.6275, 0.4008, 0.8047, 0.2484, 0.4037, 0.2777, 0.6506, 0.5212],
[0.6125, 0.4076, 0.8488, 0.3883, 0.3700, 0.3683, 0.5026, 0.5505]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6557, 0.4289, 0.8310, 0.4977, 0.4275, 0.3516, 0.5835, 0.6059],
[0.6078, 0.3892, 0.8621, 0.5863, 0.4557, 0.5347, 0.6241, 0.6111],
[0.6815, 0.4376, 0.8850, 0.4496, 0.4109, 0.5026, 0.5828, 0.5285],
[0.6125, 0.3737, 0.9020, 0.4991, 0.4120, 0.4265, 0.5849, 0.5473],
[0.7450, 0.4814, 0.8346, 0.2803, 0.4986, 0.2320, 0.6264, 0.5490],
[0.6894, 0.4417, 0.8345, 0.4276, 0.3791, 0.4259, 0.5487, 0.5544],
[0.6251, 0.3859, 0.8485, 0.2816, 0.4423, 0.3012, 0.6581, 0.5162],
[0.6389, 0.3790, 0.8842, 0.4048, 0.3998, 0.4133, 0.5169, 0.5496]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6263, 0.4232, 0.7924, 0.4626, 0.3787, 0.2883, 0.5573, 0.6047],
[0.6274, 0.4087, 0.8375, 0.5700, 0.4025, 0.4800, 0.5700, 0.6117],
[0.6084, 0.4005, 0.8400, 0.4317, 0.3762, 0.4750, 0.5476, 0.5058],
[0.6262, 0.4163, 0.8850, 0.5183, 0.3762, 0.4150, 0.6025, 0.5500],
[0.6198, 0.4076, 0.7945, 0.2453, 0.4475, 0.1871, 0.5897, 0.5350],
[0.6124, 0.4075, 0.7696, 0.4153, 0.3475, 0.3767, 0.5157, 0.5427],
[0.6275, 0.4008, 0.8047, 0.2484, 0.4037, 0.2777, 0.6506, 0.5212],
[0.6125, 0.4076, 0.8487, 0.3883, 0.3700, 0.3683, 0.5026, 0.5505]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.13164239979232661
step: 73
running loss: 0.0018033205451003646
Train Steps: 73/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6109, 0.3943, 0.8525, 0.4950, 0.4338, 0.4800, 0.5449, 0.5383],
[ nan, nan, 0.8850, 0.3000, 0.5363, 0.2250, 0.7343, 0.5771],
[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459],
[0.6260, 0.4253, 0.8938, 0.4400, 0.3675, 0.3650, 0.5675, 0.5767],
[0.6189, 0.4033, 0.8650, 0.5267, 0.4487, 0.5150, 0.5925, 0.5050],
[ nan, nan, 0.7612, 0.3250, 0.4037, 0.2533, 0.5438, 0.5767],
[0.6272, 0.4071, 0.8738, 0.5600, 0.3675, 0.3783, 0.5926, 0.4742],
[0.6264, 0.4248, 0.8938, 0.4183, 0.3875, 0.4100, 0.5400, 0.5350]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7152, 0.4496, 0.8840, 0.5291, 0.4344, 0.5146, 0.5446, 0.5550],
[0.2075, 0.1350, 0.8997, 0.3122, 0.5219, 0.2621, 0.7280, 0.5755],
[0.7042, 0.4605, 0.8933, 0.3257, 0.4916, 0.2425, 0.6603, 0.5587],
[0.7824, 0.4959, 0.8963, 0.5029, 0.3762, 0.4046, 0.5804, 0.6031],
[0.7340, 0.4657, 0.8780, 0.5537, 0.4509, 0.5468, 0.5906, 0.5369],
[0.2747, 0.1706, 0.8041, 0.3679, 0.4138, 0.2918, 0.5423, 0.6006],
[0.7430, 0.4759, 0.8953, 0.5835, 0.3869, 0.4296, 0.5988, 0.5045],
[0.7167, 0.4848, 0.8927, 0.4600, 0.3611, 0.4525, 0.5368, 0.5691]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6109, 0.3943, 0.8525, 0.4950, 0.4338, 0.4800, 0.5449, 0.5383],
[0.0000, 0.0000, 0.8850, 0.3000, 0.5362, 0.2250, 0.7343, 0.5771],
[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459],
[0.6260, 0.4253, 0.8938, 0.4400, 0.3675, 0.3650, 0.5675, 0.5767],
[0.6189, 0.4033, 0.8650, 0.5267, 0.4487, 0.5150, 0.5925, 0.5050],
[0.0000, 0.0000, 0.7613, 0.3250, 0.4038, 0.2533, 0.5437, 0.5767],
[0.6272, 0.4071, 0.8737, 0.5600, 0.3675, 0.3783, 0.5926, 0.4742],
[0.6264, 0.4248, 0.8938, 0.4183, 0.3875, 0.4100, 0.5400, 0.5350]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0047, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0047, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.13630416334490292
step: 74
running loss: 0.001841948153309499
Train Steps: 74/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.8750, 0.2467, 0.5138, 0.2617, 0.7382, 0.5552],
[0.6250, 0.4103, 0.8950, 0.4400, 0.3912, 0.5650, 0.6050, 0.5133],
[0.6223, 0.3990, 0.8037, 0.2800, 0.4000, 0.2283, 0.5864, 0.5208],
[0.6147, 0.4112, 0.7988, 0.3200, 0.3775, 0.2767, 0.5150, 0.5550],
[0.6196, 0.4068, 0.7645, 0.2234, 0.4575, 0.1737, 0.5926, 0.5284],
[0.6274, 0.4117, 0.8100, 0.5801, 0.4000, 0.4583, 0.5582, 0.6118],
[0.6109, 0.4015, 0.7668, 0.3639, 0.3513, 0.3667, 0.5200, 0.5641],
[0.6151, 0.4125, 0.8738, 0.4417, 0.3575, 0.3783, 0.5138, 0.5483]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.0903, 0.0535, 0.9101, 0.3129, 0.5345, 0.2583, 0.7578, 0.5770],
[0.6861, 0.4237, 0.9318, 0.5016, 0.4171, 0.6002, 0.6311, 0.5333],
[0.6454, 0.4002, 0.8520, 0.3570, 0.4135, 0.2628, 0.6123, 0.5308],
[0.6206, 0.4030, 0.8520, 0.3886, 0.3837, 0.2987, 0.5037, 0.5705],
[0.6418, 0.3951, 0.8160, 0.2760, 0.4705, 0.2130, 0.6188, 0.5424],
[0.6373, 0.3980, 0.8801, 0.6439, 0.4178, 0.4880, 0.5721, 0.6193],
[0.6372, 0.4049, 0.8112, 0.4223, 0.3590, 0.3866, 0.5287, 0.5580],
[0.6187, 0.3832, 0.9024, 0.5265, 0.3736, 0.4140, 0.5123, 0.5496]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.8750, 0.2467, 0.5138, 0.2617, 0.7382, 0.5552],
[0.6250, 0.4103, 0.8950, 0.4400, 0.3913, 0.5650, 0.6050, 0.5133],
[0.6223, 0.3990, 0.8037, 0.2800, 0.4000, 0.2283, 0.5864, 0.5208],
[0.6147, 0.4112, 0.7987, 0.3200, 0.3775, 0.2767, 0.5150, 0.5550],
[0.6196, 0.4068, 0.7645, 0.2234, 0.4575, 0.1737, 0.5926, 0.5284],
[0.6274, 0.4117, 0.8100, 0.5801, 0.4000, 0.4583, 0.5582, 0.6118],
[0.6109, 0.4015, 0.7668, 0.3639, 0.3512, 0.3667, 0.5200, 0.5641],
[0.6151, 0.4125, 0.8737, 0.4417, 0.3575, 0.3783, 0.5138, 0.5483]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.13764630918740295
step: 75
running loss: 0.001835284122498706
Train Steps: 75/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6266, 0.4101, 0.8350, 0.2333, 0.3950, 0.2950, 0.6264, 0.4921],
[ nan, nan, 0.8900, 0.3217, 0.5038, 0.2233, 0.6694, 0.5609],
[0.6186, 0.4013, 0.8191, 0.3188, 0.4279, 0.2060, 0.5767, 0.5411],
[0.6260, 0.4253, 0.8938, 0.4400, 0.3675, 0.3650, 0.5675, 0.5767],
[ nan, nan, 0.6688, 0.2513, 0.4113, 0.2117, 0.5193, 0.5933],
[0.6216, 0.4100, 0.7350, 0.2067, 0.4325, 0.2050, 0.5950, 0.5333],
[ nan, nan, 0.6900, 0.1917, 0.3937, 0.2367, 0.5240, 0.5246],
[0.6277, 0.4013, 0.8888, 0.4767, 0.3600, 0.3567, 0.6148, 0.4672]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6749, 0.4133, 0.8857, 0.2980, 0.4145, 0.2898, 0.6248, 0.5178],
[0.1693, 0.0882, 0.9349, 0.3785, 0.5117, 0.2394, 0.6746, 0.5773],
[0.7113, 0.4677, 0.8635, 0.3449, 0.4212, 0.2230, 0.5482, 0.5491],
[0.6812, 0.4329, 0.9257, 0.5342, 0.3713, 0.3869, 0.5587, 0.6029],
[0.1745, 0.1099, 0.7082, 0.3025, 0.4149, 0.2373, 0.5410, 0.5802],
[0.6236, 0.4131, 0.7854, 0.2501, 0.4213, 0.2076, 0.5841, 0.5242],
[0.0469, 0.0247, 0.7511, 0.2891, 0.4237, 0.2496, 0.5318, 0.5650],
[0.7042, 0.4386, 0.9340, 0.5136, 0.3466, 0.3730, 0.6089, 0.5196]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6266, 0.4101, 0.8350, 0.2333, 0.3950, 0.2950, 0.6264, 0.4921],
[0.0000, 0.0000, 0.8900, 0.3217, 0.5038, 0.2233, 0.6694, 0.5609],
[0.6186, 0.4013, 0.8191, 0.3188, 0.4279, 0.2060, 0.5767, 0.5411],
[0.6260, 0.4253, 0.8938, 0.4400, 0.3675, 0.3650, 0.5675, 0.5767],
[0.0000, 0.0000, 0.6688, 0.2513, 0.4112, 0.2117, 0.5193, 0.5933],
[0.6216, 0.4100, 0.7350, 0.2067, 0.4325, 0.2050, 0.5950, 0.5333],
[0.0000, 0.0000, 0.6900, 0.1917, 0.3938, 0.2367, 0.5240, 0.5246],
[0.6277, 0.4013, 0.8888, 0.4767, 0.3600, 0.3567, 0.6148, 0.4672]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0026, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0026, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.14028748925193213
step: 76
running loss: 0.0018458880164727912
Train Steps: 76/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6277, 0.4118, 0.8988, 0.3833, 0.3950, 0.2650, 0.6290, 0.4938],
[0.6109, 0.3943, 0.8525, 0.4950, 0.4338, 0.4800, 0.5449, 0.5383],
[0.6227, 0.4193, 0.8838, 0.4933, 0.3663, 0.3733, 0.5637, 0.5633],
[0.6109, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117],
[ nan, nan, 0.9050, 0.3500, 0.5138, 0.2300, 0.7359, 0.5702],
[0.6257, 0.4167, 0.8775, 0.3433, 0.3563, 0.4133, 0.6200, 0.5667],
[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459],
[0.6346, 0.4092, 0.7712, 0.5917, 0.4037, 0.4767, 0.7343, 0.5725]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5165, 0.3344, 0.8865, 0.3937, 0.3729, 0.2577, 0.5661, 0.4983],
[0.5008, 0.3059, 0.8650, 0.5040, 0.4121, 0.4633, 0.5061, 0.5278],
[0.5801, 0.3869, 0.8603, 0.5037, 0.3318, 0.3774, 0.5080, 0.5630],
[0.4800, 0.3126, 0.8583, 0.4781, 0.3460, 0.3829, 0.5058, 0.5076],
[0.0449, 0.0263, 0.9105, 0.3653, 0.4914, 0.2295, 0.6939, 0.5560],
[0.5305, 0.3265, 0.8573, 0.3543, 0.3323, 0.3917, 0.5863, 0.5516],
[0.5581, 0.3568, 0.8780, 0.3115, 0.4651, 0.2026, 0.6345, 0.5329],
[0.5063, 0.3323, 0.8051, 0.5204, 0.3592, 0.4526, 0.6360, 0.5617]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6277, 0.4117, 0.8988, 0.3833, 0.3950, 0.2650, 0.6290, 0.4938],
[0.6109, 0.3943, 0.8525, 0.4950, 0.4338, 0.4800, 0.5449, 0.5383],
[0.6227, 0.4193, 0.8838, 0.4933, 0.3663, 0.3733, 0.5638, 0.5633],
[0.6108, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117],
[0.0000, 0.0000, 0.9050, 0.3500, 0.5138, 0.2300, 0.7359, 0.5702],
[0.6257, 0.4167, 0.8775, 0.3433, 0.3562, 0.4133, 0.6200, 0.5667],
[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459],
[0.6346, 0.4092, 0.7713, 0.5917, 0.4038, 0.4767, 0.7343, 0.5725]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0025, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0025, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.14280669260188006
step: 77
running loss: 0.0018546323714529879
Train Steps: 77/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6224, 0.4097, 0.7438, 0.2267, 0.3850, 0.2850, 0.5988, 0.5250],
[0.6057, 0.4011, 0.8750, 0.4267, 0.4400, 0.5800, 0.5845, 0.5585],
[0.6212, 0.4033, 0.8938, 0.4167, 0.3813, 0.4267, 0.5613, 0.5583],
[0.6126, 0.4073, 0.8750, 0.5133, 0.3800, 0.4333, 0.4986, 0.5378],
[0.6361, 0.4071, 0.9100, 0.4783, 0.3738, 0.3967, 0.6670, 0.5332],
[0.6307, 0.3998, 0.8500, 0.5233, 0.3850, 0.5050, 0.7446, 0.5320],
[0.6175, 0.4091, 0.7863, 0.2800, 0.3638, 0.3583, 0.6188, 0.5433],
[0.6111, 0.4019, 0.8350, 0.3867, 0.3500, 0.4283, 0.5480, 0.5719]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5059, 0.3345, 0.7602, 0.2278, 0.3854, 0.2539, 0.6262, 0.5230],
[0.4361, 0.2765, 0.8633, 0.4468, 0.4724, 0.5165, 0.5810, 0.5478],
[0.4907, 0.3082, 0.9063, 0.4370, 0.3787, 0.3822, 0.5449, 0.5404],
[0.4585, 0.2929, 0.8790, 0.5238, 0.3940, 0.4032, 0.4904, 0.5269],
[0.4985, 0.3049, 0.9053, 0.4899, 0.3699, 0.3515, 0.6380, 0.5238],
[0.4820, 0.3069, 0.8524, 0.5386, 0.3745, 0.4547, 0.6722, 0.5328],
[0.5487, 0.3470, 0.7873, 0.2789, 0.3601, 0.3334, 0.6035, 0.5362],
[0.4773, 0.2953, 0.8434, 0.4209, 0.3548, 0.3967, 0.5461, 0.5606]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6224, 0.4097, 0.7437, 0.2267, 0.3850, 0.2850, 0.5987, 0.5250],
[0.6057, 0.4011, 0.8750, 0.4267, 0.4400, 0.5800, 0.5845, 0.5585],
[0.6212, 0.4033, 0.8938, 0.4167, 0.3812, 0.4267, 0.5612, 0.5583],
[0.6126, 0.4073, 0.8750, 0.5133, 0.3800, 0.4333, 0.4986, 0.5378],
[0.6361, 0.4071, 0.9100, 0.4783, 0.3738, 0.3967, 0.6670, 0.5332],
[0.6307, 0.3998, 0.8500, 0.5233, 0.3850, 0.5050, 0.7446, 0.5320],
[0.6175, 0.4091, 0.7862, 0.2800, 0.3638, 0.3583, 0.6187, 0.5433],
[0.6111, 0.4019, 0.8350, 0.3867, 0.3500, 0.4283, 0.5480, 0.5719]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0039, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0039, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.14673250037594698
step: 78
running loss: 0.0018811859022557305
Train Steps: 78/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6272, 0.4120, 0.9038, 0.4117, 0.3725, 0.3200, 0.6175, 0.5250],
[0.6223, 0.4171, 0.8750, 0.5500, 0.4050, 0.4817, 0.5675, 0.5600],
[0.6214, 0.4175, 0.7300, 0.2883, 0.4338, 0.2167, 0.5698, 0.5773],
[0.6357, 0.4139, 0.8450, 0.5883, 0.3775, 0.4950, 0.6488, 0.5297],
[0.6095, 0.4002, 0.8533, 0.5168, 0.5031, 0.5094, 0.5125, 0.5433],
[0.6170, 0.4102, 0.7468, 0.3695, 0.3463, 0.3767, 0.5238, 0.5823],
[0.6113, 0.4104, 0.8650, 0.4250, 0.3925, 0.5967, 0.5787, 0.5116],
[0.6266, 0.4101, 0.8350, 0.2333, 0.3950, 0.2950, 0.6264, 0.4921]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4087, 0.2881, 0.8793, 0.3682, 0.3442, 0.2797, 0.6288, 0.5055],
[0.4526, 0.2877, 0.8537, 0.5116, 0.3869, 0.4292, 0.5877, 0.5334],
[0.4888, 0.3502, 0.7298, 0.2433, 0.3949, 0.1769, 0.5642, 0.5608],
[0.4653, 0.2900, 0.8206, 0.5220, 0.3491, 0.4446, 0.6688, 0.4878],
[0.4368, 0.2940, 0.8106, 0.4830, 0.4568, 0.4552, 0.5322, 0.5297],
[0.4606, 0.2997, 0.7351, 0.3265, 0.3292, 0.3455, 0.5507, 0.5565],
[0.4449, 0.2896, 0.8538, 0.3646, 0.3796, 0.5156, 0.5988, 0.5139],
[0.4937, 0.3109, 0.8220, 0.1960, 0.3931, 0.2451, 0.6621, 0.4891]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6272, 0.4120, 0.9038, 0.4117, 0.3725, 0.3200, 0.6175, 0.5250],
[0.6223, 0.4171, 0.8750, 0.5500, 0.4050, 0.4817, 0.5675, 0.5600],
[0.6214, 0.4175, 0.7300, 0.2883, 0.4338, 0.2167, 0.5698, 0.5773],
[0.6357, 0.4139, 0.8450, 0.5883, 0.3775, 0.4950, 0.6488, 0.5297],
[0.6095, 0.4002, 0.8533, 0.5168, 0.5031, 0.5094, 0.5125, 0.5433],
[0.6170, 0.4102, 0.7468, 0.3695, 0.3462, 0.3767, 0.5238, 0.5823],
[0.6113, 0.4104, 0.8650, 0.4250, 0.3925, 0.5967, 0.5787, 0.5116],
[0.6266, 0.4101, 0.8350, 0.2333, 0.3950, 0.2950, 0.6264, 0.4921]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0059, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0059, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.15266501865698956
step: 79
running loss: 0.0019324685905948045
Train Steps: 79/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6193, 0.4050, 0.7313, 0.2433, 0.4075, 0.2117, 0.5649, 0.5656],
[0.6225, 0.4191, 0.8500, 0.4167, 0.3688, 0.3233, 0.5650, 0.5650],
[0.6200, 0.4071, 0.7338, 0.1917, 0.4200, 0.2450, 0.6150, 0.5517],
[ nan, nan, 0.8300, 0.3150, 0.3588, 0.3383, 0.5208, 0.5194],
[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837],
[0.6179, 0.3993, 0.8925, 0.4789, 0.3879, 0.4900, 0.6041, 0.5279],
[0.6275, 0.4008, 0.8047, 0.2484, 0.4037, 0.2777, 0.6506, 0.5212],
[0.6186, 0.3967, 0.7337, 0.1992, 0.4120, 0.2508, 0.6105, 0.5395]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5307, 0.3548, 0.7096, 0.2187, 0.4055, 0.2188, 0.5669, 0.5435],
[0.4671, 0.3458, 0.8251, 0.3786, 0.3618, 0.3229, 0.5673, 0.5475],
[0.4901, 0.3563, 0.7372, 0.1861, 0.4123, 0.2281, 0.6333, 0.5263],
[0.0950, 0.0853, 0.7791, 0.2953, 0.3558, 0.3173, 0.5706, 0.5129],
[0.5282, 0.3683, 0.6496, 0.2782, 0.3489, 0.2879, 0.5350, 0.5610],
[0.5229, 0.3438, 0.8743, 0.4487, 0.3905, 0.4842, 0.6071, 0.5113],
[0.4942, 0.3315, 0.7959, 0.2371, 0.3885, 0.2666, 0.6473, 0.4877],
[0.5228, 0.3476, 0.7379, 0.1952, 0.3836, 0.2282, 0.6192, 0.5012]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6193, 0.4050, 0.7312, 0.2433, 0.4075, 0.2117, 0.5649, 0.5656],
[0.6225, 0.4191, 0.8500, 0.4167, 0.3688, 0.3233, 0.5650, 0.5650],
[0.6200, 0.4071, 0.7337, 0.1917, 0.4200, 0.2450, 0.6150, 0.5517],
[0.0000, 0.0000, 0.8300, 0.3150, 0.3587, 0.3383, 0.5208, 0.5194],
[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837],
[0.6179, 0.3993, 0.8925, 0.4789, 0.3879, 0.4900, 0.6041, 0.5279],
[0.6275, 0.4008, 0.8047, 0.2484, 0.4037, 0.2777, 0.6506, 0.5212],
[0.6186, 0.3967, 0.7337, 0.1992, 0.4120, 0.2508, 0.6105, 0.5395]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0023, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0023, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.15501353502622806
step: 80
running loss: 0.0019376691878278506
Train Steps: 80/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6257, 0.4167, 0.8775, 0.3433, 0.3563, 0.4133, 0.6200, 0.5667],
[0.6212, 0.4171, 0.7875, 0.3633, 0.3813, 0.2933, 0.5675, 0.5700],
[ nan, nan, 0.7981, 0.3194, 0.3625, 0.3167, 0.5040, 0.5563],
[0.6202, 0.4054, 0.8892, 0.4428, 0.3642, 0.3249, 0.5840, 0.5426],
[0.6296, 0.4076, 0.8400, 0.5583, 0.3700, 0.4367, 0.6876, 0.5494],
[ nan, nan, 0.7425, 0.2117, 0.3937, 0.2433, 0.5438, 0.5567],
[0.6271, 0.4005, 0.8450, 0.6067, 0.3850, 0.4983, 0.6069, 0.4649],
[0.6149, 0.4054, 0.6713, 0.2333, 0.4025, 0.2017, 0.5213, 0.5695]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6282, 0.4381, 0.8355, 0.2734, 0.3580, 0.4126, 0.6383, 0.5545],
[0.6837, 0.4846, 0.7717, 0.3039, 0.3803, 0.3083, 0.5922, 0.5750],
[0.0733, 0.0855, 0.7373, 0.2484, 0.3598, 0.3237, 0.5362, 0.5699],
[0.6103, 0.4397, 0.8611, 0.3480, 0.3714, 0.3243, 0.5854, 0.5111],
[0.6272, 0.4369, 0.8275, 0.4628, 0.3831, 0.4366, 0.6994, 0.5166],
[0.0427, 0.0495, 0.7091, 0.1944, 0.4089, 0.2482, 0.5838, 0.5537],
[0.6725, 0.4609, 0.7970, 0.5225, 0.3743, 0.5087, 0.5892, 0.4707],
[0.5609, 0.4096, 0.6612, 0.1675, 0.4200, 0.2040, 0.5145, 0.5588]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6257, 0.4167, 0.8775, 0.3433, 0.3562, 0.4133, 0.6200, 0.5667],
[0.6212, 0.4171, 0.7875, 0.3633, 0.3812, 0.2933, 0.5675, 0.5700],
[0.0000, 0.0000, 0.7981, 0.3194, 0.3625, 0.3167, 0.5040, 0.5563],
[0.6202, 0.4054, 0.8892, 0.4428, 0.3642, 0.3249, 0.5840, 0.5426],
[0.6296, 0.4076, 0.8400, 0.5583, 0.3700, 0.4367, 0.6876, 0.5494],
[0.0000, 0.0000, 0.7425, 0.2117, 0.3938, 0.2433, 0.5437, 0.5567],
[0.6271, 0.4005, 0.8450, 0.6067, 0.3850, 0.4983, 0.6069, 0.4649],
[0.6149, 0.4054, 0.6712, 0.2333, 0.4025, 0.2017, 0.5213, 0.5695]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.15654646544135176
step: 81
running loss: 0.0019326724128561946
Train Steps: 81/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6250, 0.3993, 0.9138, 0.4333, 0.3763, 0.5217, 0.6995, 0.5320],
[0.6193, 0.4165, 0.8838, 0.4700, 0.4150, 0.4867, 0.5427, 0.5261],
[0.6224, 0.4097, 0.7438, 0.2267, 0.3850, 0.2850, 0.5988, 0.5250],
[0.6203, 0.4021, 0.8780, 0.5031, 0.3667, 0.3882, 0.5842, 0.5405],
[0.6203, 0.4056, 0.8942, 0.4086, 0.3643, 0.3617, 0.5917, 0.5482],
[ nan, nan, 0.7981, 0.3194, 0.3625, 0.3167, 0.5040, 0.5563],
[0.6200, 0.4086, 0.8414, 0.2974, 0.4117, 0.2274, 0.5869, 0.5391],
[0.6140, 0.4070, 0.8700, 0.5000, 0.4612, 0.4900, 0.5260, 0.5852]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6120, 0.4161, 0.8576, 0.3980, 0.3587, 0.5396, 0.7251, 0.5467],
[0.5780, 0.4041, 0.8139, 0.4110, 0.3942, 0.5006, 0.5479, 0.5276],
[0.6369, 0.4528, 0.6879, 0.1798, 0.3727, 0.2992, 0.6297, 0.5245],
[0.7181, 0.4893, 0.8373, 0.4649, 0.3389, 0.4007, 0.5916, 0.5105],
[0.6550, 0.4485, 0.8356, 0.3766, 0.3475, 0.3610, 0.6218, 0.5490],
[0.0318, 0.0481, 0.7165, 0.2537, 0.3442, 0.3365, 0.5431, 0.5739],
[0.6474, 0.4496, 0.7977, 0.2374, 0.4135, 0.2600, 0.5980, 0.5348],
[0.5745, 0.4167, 0.8119, 0.4426, 0.4552, 0.4981, 0.5370, 0.5871]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6250, 0.3993, 0.9137, 0.4333, 0.3762, 0.5217, 0.6995, 0.5320],
[0.6193, 0.4165, 0.8838, 0.4700, 0.4150, 0.4867, 0.5427, 0.5261],
[0.6224, 0.4097, 0.7437, 0.2267, 0.3850, 0.2850, 0.5987, 0.5250],
[0.6203, 0.4020, 0.8780, 0.5031, 0.3667, 0.3882, 0.5842, 0.5405],
[0.6203, 0.4056, 0.8942, 0.4086, 0.3643, 0.3617, 0.5917, 0.5482],
[0.0000, 0.0000, 0.7981, 0.3194, 0.3625, 0.3167, 0.5040, 0.5563],
[0.6199, 0.4086, 0.8414, 0.2974, 0.4117, 0.2274, 0.5869, 0.5391],
[0.6140, 0.4070, 0.8700, 0.5000, 0.4613, 0.4900, 0.5260, 0.5852]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.1579744432528969
step: 82
running loss: 0.001926517600645084
Train Steps: 82/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6249, 0.4142, 0.8350, 0.3283, 0.3613, 0.3700, 0.6188, 0.5400],
[0.6193, 0.4050, 0.7313, 0.2433, 0.4075, 0.2117, 0.5649, 0.5656],
[0.6200, 0.4071, 0.7338, 0.1917, 0.4200, 0.2450, 0.6150, 0.5517],
[ nan, nan, 0.8888, 0.3100, 0.5262, 0.2817, 0.7145, 0.6003],
[0.6250, 0.4103, 0.8950, 0.4400, 0.3912, 0.5650, 0.6050, 0.5133],
[0.6182, 0.3930, 0.8841, 0.3892, 0.3556, 0.4967, 0.6222, 0.5279],
[0.6129, 0.4069, 0.8750, 0.5067, 0.3875, 0.4233, 0.5235, 0.5881],
[0.6197, 0.4050, 0.7527, 0.2000, 0.4042, 0.2249, 0.5895, 0.4995]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6289, 0.4397, 0.7994, 0.3143, 0.3484, 0.3620, 0.6211, 0.5480],
[0.7012, 0.4679, 0.6978, 0.2448, 0.4033, 0.2456, 0.5379, 0.5728],
[0.6532, 0.4595, 0.7230, 0.2023, 0.4137, 0.2560, 0.6047, 0.5566],
[0.0559, 0.0454, 0.8784, 0.3179, 0.4937, 0.2871, 0.7252, 0.5912],
[0.7048, 0.4770, 0.8636, 0.4523, 0.3856, 0.6014, 0.5997, 0.5220],
[0.5908, 0.3908, 0.8337, 0.4236, 0.3456, 0.4994, 0.6183, 0.5246],
[0.6762, 0.4809, 0.8649, 0.5304, 0.3847, 0.4387, 0.4774, 0.5786],
[0.6734, 0.4679, 0.7195, 0.1926, 0.3988, 0.2341, 0.5801, 0.5138]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6249, 0.4142, 0.8350, 0.3283, 0.3613, 0.3700, 0.6187, 0.5400],
[0.6193, 0.4050, 0.7312, 0.2433, 0.4075, 0.2117, 0.5649, 0.5656],
[0.6200, 0.4071, 0.7337, 0.1917, 0.4200, 0.2450, 0.6150, 0.5517],
[0.0000, 0.0000, 0.8888, 0.3100, 0.5263, 0.2817, 0.7145, 0.6003],
[0.6250, 0.4103, 0.8950, 0.4400, 0.3913, 0.5650, 0.6050, 0.5133],
[0.6182, 0.3930, 0.8841, 0.3892, 0.3556, 0.4967, 0.6222, 0.5279],
[0.6129, 0.4069, 0.8750, 0.5067, 0.3875, 0.4233, 0.5235, 0.5881],
[0.6197, 0.4050, 0.7527, 0.2000, 0.4042, 0.2249, 0.5895, 0.4995]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.15900916929240339
step: 83
running loss: 0.0019157731240048602
Train Steps: 83/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6135, 0.4115, 0.8838, 0.4667, 0.4288, 0.6050, 0.5778, 0.5097],
[0.6264, 0.3972, 0.8853, 0.4771, 0.3853, 0.4511, 0.6293, 0.5334],
[0.6250, 0.4116, 0.8700, 0.4850, 0.4650, 0.5567, 0.6088, 0.5183],
[0.6199, 0.4112, 0.8475, 0.3717, 0.3550, 0.4350, 0.6063, 0.6083],
[0.6202, 0.4064, 0.7879, 0.2179, 0.4567, 0.1725, 0.5955, 0.5478],
[0.6185, 0.4079, 0.8838, 0.4617, 0.4838, 0.5650, 0.6175, 0.5850],
[0.6086, 0.4019, 0.7782, 0.4278, 0.3625, 0.4350, 0.5150, 0.5285],
[0.6167, 0.4048, 0.6831, 0.3639, 0.3763, 0.3017, 0.5700, 0.5883]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6739, 0.4526, 0.8910, 0.4254, 0.4190, 0.5681, 0.5595, 0.5604],
[0.6833, 0.4371, 0.8709, 0.4826, 0.3629, 0.4658, 0.6200, 0.5308],
[0.6546, 0.4241, 0.8739, 0.4820, 0.4487, 0.5598, 0.6135, 0.5418],
[0.6296, 0.4391, 0.8380, 0.3504, 0.3509, 0.4107, 0.5820, 0.6039],
[0.5579, 0.3854, 0.7547, 0.2289, 0.4464, 0.1491, 0.5852, 0.5591],
[0.6199, 0.3966, 0.8858, 0.4370, 0.4615, 0.5330, 0.6153, 0.5827],
[0.6631, 0.4274, 0.7721, 0.4041, 0.3427, 0.4250, 0.5122, 0.5284],
[0.5237, 0.3468, 0.7270, 0.3245, 0.3668, 0.2981, 0.5689, 0.5847]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6135, 0.4115, 0.8838, 0.4667, 0.4288, 0.6050, 0.5778, 0.5097],
[0.6264, 0.3972, 0.8853, 0.4771, 0.3853, 0.4511, 0.6293, 0.5334],
[0.6251, 0.4116, 0.8700, 0.4850, 0.4650, 0.5567, 0.6087, 0.5183],
[0.6199, 0.4112, 0.8475, 0.3717, 0.3550, 0.4350, 0.6062, 0.6083],
[0.6202, 0.4064, 0.7879, 0.2179, 0.4567, 0.1725, 0.5955, 0.5478],
[0.6184, 0.4079, 0.8838, 0.4617, 0.4837, 0.5650, 0.6175, 0.5850],
[0.6086, 0.4019, 0.7782, 0.4278, 0.3625, 0.4350, 0.5150, 0.5285],
[0.6167, 0.4048, 0.6831, 0.3639, 0.3762, 0.3017, 0.5700, 0.5883]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.15980508815846406
step: 84
running loss: 0.0019024415256960008
Train Steps: 84/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6202, 0.3983, 0.8555, 0.5429, 0.3842, 0.4370, 0.5866, 0.5398],
[0.6245, 0.4100, 0.7762, 0.2583, 0.4963, 0.1517, 0.5875, 0.5417],
[0.6300, 0.4013, 0.8938, 0.5350, 0.3675, 0.4600, 0.6456, 0.4973],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3513, 0.4050, 0.6112, 0.5500],
[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098],
[0.6124, 0.4069, 0.8314, 0.5001, 0.3738, 0.4650, 0.5167, 0.5402],
[0.6185, 0.4079, 0.8838, 0.4617, 0.4838, 0.5650, 0.6175, 0.5850]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6171, 0.3926, 0.8730, 0.5601, 0.3915, 0.4549, 0.5773, 0.5414],
[0.6341, 0.4047, 0.7808, 0.2310, 0.4821, 0.1496, 0.5899, 0.5704],
[0.7446, 0.4741, 0.8923, 0.5481, 0.3716, 0.4588, 0.5961, 0.5184],
[0.6517, 0.4116, 0.7889, 0.2948, 0.3571, 0.4012, 0.5962, 0.5773],
[0.6654, 0.4209, 0.9023, 0.4934, 0.4563, 0.5767, 0.6043, 0.5427],
[0.6486, 0.4106, 0.8826, 0.4646, 0.3893, 0.5222, 0.5684, 0.5229],
[0.7261, 0.4736, 0.8319, 0.5206, 0.3985, 0.4609, 0.5244, 0.5686],
[0.6244, 0.3855, 0.9119, 0.4555, 0.4923, 0.5583, 0.5995, 0.5956]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6202, 0.3983, 0.8555, 0.5429, 0.3842, 0.4370, 0.5866, 0.5398],
[0.6245, 0.4100, 0.7763, 0.2583, 0.4963, 0.1517, 0.5875, 0.5417],
[0.6300, 0.4013, 0.8938, 0.5350, 0.3675, 0.4600, 0.6456, 0.4973],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3512, 0.4050, 0.6112, 0.5500],
[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098],
[0.6123, 0.4069, 0.8314, 0.5001, 0.3738, 0.4650, 0.5167, 0.5402],
[0.6184, 0.4079, 0.8838, 0.4617, 0.4837, 0.5650, 0.6175, 0.5850]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.16067833415581845
step: 85
running loss: 0.0018903333430096288
Train Steps: 85/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6120, 0.4014, 0.6863, 0.2817, 0.3700, 0.2783, 0.5513, 0.5667],
[0.6215, 0.4119, 0.7688, 0.2300, 0.4200, 0.2283, 0.5925, 0.5317],
[0.6138, 0.4101, 0.8800, 0.5083, 0.4637, 0.5950, 0.5587, 0.5077],
[0.6161, 0.4040, 0.7525, 0.2133, 0.4125, 0.2067, 0.5787, 0.5117],
[0.6308, 0.3990, 0.8688, 0.5183, 0.3950, 0.4983, 0.6388, 0.5133],
[0.6142, 0.3982, 0.8650, 0.4883, 0.3912, 0.4317, 0.5315, 0.5350],
[0.6277, 0.4029, 0.8250, 0.2433, 0.4325, 0.2100, 0.6366, 0.5207],
[0.6219, 0.4097, 0.8738, 0.3400, 0.3563, 0.4117, 0.5975, 0.5683]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6802, 0.4376, 0.7374, 0.3089, 0.3743, 0.2980, 0.5208, 0.5690],
[0.4057, 0.2461, 0.7853, 0.2706, 0.4651, 0.2423, 0.5779, 0.5631],
[0.6088, 0.3779, 0.9175, 0.5766, 0.4961, 0.5800, 0.5669, 0.5666],
[0.7017, 0.4283, 0.7751, 0.2334, 0.4296, 0.2204, 0.5703, 0.5378],
[0.6362, 0.3832, 0.8968, 0.5974, 0.4216, 0.5279, 0.6449, 0.5289],
[0.6274, 0.3839, 0.9022, 0.5466, 0.4141, 0.4581, 0.5066, 0.5398],
[0.6415, 0.3878, 0.8510, 0.3102, 0.4527, 0.2484, 0.6664, 0.5180],
[0.7252, 0.4803, 0.9016, 0.4021, 0.3710, 0.4009, 0.5595, 0.5757]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6120, 0.4013, 0.6862, 0.2817, 0.3700, 0.2783, 0.5512, 0.5667],
[0.6215, 0.4119, 0.7688, 0.2300, 0.4200, 0.2283, 0.5925, 0.5317],
[0.6138, 0.4101, 0.8800, 0.5083, 0.4638, 0.5950, 0.5587, 0.5077],
[0.6161, 0.4040, 0.7525, 0.2133, 0.4125, 0.2067, 0.5788, 0.5117],
[0.6308, 0.3990, 0.8687, 0.5183, 0.3950, 0.4983, 0.6388, 0.5133],
[0.6143, 0.3982, 0.8650, 0.4883, 0.3913, 0.4317, 0.5315, 0.5350],
[0.6277, 0.4029, 0.8250, 0.2433, 0.4325, 0.2100, 0.6366, 0.5207],
[0.6219, 0.4097, 0.8737, 0.3400, 0.3562, 0.4117, 0.5975, 0.5683]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0025, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0025, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.1631579902896192
step: 86
running loss: 0.0018971859336002232
Train Steps: 86/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586],
[ nan, nan, 0.7425, 0.2117, 0.3937, 0.2433, 0.5438, 0.5567],
[0.6274, 0.4099, 0.8625, 0.3233, 0.4400, 0.1983, 0.5876, 0.4869],
[0.6125, 0.3999, 0.8750, 0.4883, 0.4750, 0.4700, 0.5533, 0.5617],
[0.6188, 0.4099, 0.7400, 0.2433, 0.3962, 0.2750, 0.6162, 0.5467],
[0.6199, 0.4102, 0.8950, 0.4417, 0.4012, 0.5367, 0.6112, 0.5967],
[ nan, nan, 0.7850, 0.2700, 0.4288, 0.1717, 0.5199, 0.4999],
[0.6250, 0.3961, 0.8672, 0.4929, 0.4199, 0.4972, 0.6312, 0.5301]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 6.5615e-01, 4.3238e-01, 8.7637e-01, 3.0122e-01, 4.6985e-01,
2.7266e-01, 6.8688e-01, 5.6284e-01],
[ 5.5656e-02, -1.0218e-04, 7.6715e-01, 2.8529e-01, 4.1903e-01,
2.4294e-01, 5.3250e-01, 5.5664e-01],
[ 7.3798e-01, 4.6379e-01, 8.9042e-01, 3.5780e-01, 4.6348e-01,
2.0265e-01, 5.6376e-01, 5.0279e-01],
[ 8.2466e-01, 5.1510e-01, 8.9817e-01, 5.4252e-01, 4.8617e-01,
4.8849e-01, 5.3407e-01, 5.4021e-01],
[ 7.7672e-01, 4.9967e-01, 7.5344e-01, 2.7726e-01, 3.9371e-01,
2.8717e-01, 6.0870e-01, 5.4520e-01],
[ 7.9712e-01, 4.9606e-01, 9.1677e-01, 5.0082e-01, 4.2626e-01,
5.5632e-01, 5.9605e-01, 5.7758e-01],
[ 6.8887e-02, 1.3605e-02, 8.0388e-01, 2.7323e-01, 4.5281e-01,
1.8833e-01, 5.1119e-01, 5.3303e-01],
[ 7.6316e-01, 4.6732e-01, 8.8208e-01, 5.5342e-01, 4.2469e-01,
5.1457e-01, 6.1878e-01, 5.2243e-01]], device='cuda:0',
grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586],
[0.0000, 0.0000, 0.7425, 0.2117, 0.3938, 0.2433, 0.5437, 0.5567],
[0.6274, 0.4099, 0.8625, 0.3233, 0.4400, 0.1983, 0.5876, 0.4869],
[0.6125, 0.3999, 0.8750, 0.4883, 0.4750, 0.4700, 0.5533, 0.5617],
[0.6188, 0.4099, 0.7400, 0.2433, 0.3963, 0.2750, 0.6162, 0.5467],
[0.6199, 0.4102, 0.8950, 0.4417, 0.4013, 0.5367, 0.6112, 0.5967],
[0.0000, 0.0000, 0.7850, 0.2700, 0.4288, 0.1717, 0.5199, 0.4999],
[0.6250, 0.3961, 0.8672, 0.4929, 0.4199, 0.4972, 0.6312, 0.5301]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0033, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0033, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.16645036087720655
step: 87
running loss: 0.001913222538818466
Train Steps: 87/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6226, 0.4125, 0.8800, 0.4900, 0.4512, 0.5600, 0.6275, 0.5517],
[0.6243, 0.4128, 0.7762, 0.2717, 0.3825, 0.3133, 0.6212, 0.5417],
[0.6339, 0.4123, 0.8638, 0.5367, 0.4075, 0.5467, 0.7517, 0.5436],
[0.6222, 0.4108, 0.8938, 0.4233, 0.3600, 0.3817, 0.5825, 0.5283],
[0.6250, 0.4236, 0.8638, 0.3767, 0.4050, 0.3150, 0.5649, 0.5799],
[0.6154, 0.4048, 0.7100, 0.2067, 0.4338, 0.1667, 0.5413, 0.5220],
[0.6201, 0.4036, 0.8596, 0.3850, 0.3492, 0.3785, 0.5978, 0.5131],
[0.6086, 0.3998, 0.8788, 0.4450, 0.4025, 0.4650, 0.5306, 0.5103]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6109, 0.3798, 0.9016, 0.5194, 0.4766, 0.5684, 0.6182, 0.5540],
[0.6222, 0.3921, 0.7879, 0.2932, 0.4149, 0.2974, 0.6207, 0.5324],
[0.5676, 0.3614, 0.8883, 0.5625, 0.4245, 0.5565, 0.7536, 0.5352],
[0.5486, 0.3695, 0.8816, 0.4359, 0.3645, 0.3880, 0.5915, 0.5291],
[0.5466, 0.3531, 0.8790, 0.4196, 0.4184, 0.3233, 0.5451, 0.5796],
[0.5856, 0.3652, 0.7095, 0.2472, 0.4402, 0.1400, 0.5354, 0.5184],
[0.6644, 0.4115, 0.8798, 0.4273, 0.3535, 0.3874, 0.6053, 0.5026],
[0.5934, 0.3878, 0.8912, 0.4718, 0.4126, 0.4666, 0.5440, 0.5000]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6226, 0.4125, 0.8800, 0.4900, 0.4512, 0.5600, 0.6275, 0.5517],
[0.6243, 0.4128, 0.7763, 0.2717, 0.3825, 0.3133, 0.6212, 0.5417],
[0.6339, 0.4123, 0.8637, 0.5367, 0.4075, 0.5467, 0.7517, 0.5436],
[0.6222, 0.4108, 0.8938, 0.4233, 0.3600, 0.3817, 0.5825, 0.5283],
[0.6250, 0.4236, 0.8637, 0.3767, 0.4050, 0.3150, 0.5649, 0.5799],
[0.6154, 0.4048, 0.7100, 0.2067, 0.4338, 0.1667, 0.5413, 0.5220],
[0.6201, 0.4036, 0.8596, 0.3850, 0.3492, 0.3785, 0.5978, 0.5131],
[0.6086, 0.3998, 0.8788, 0.4450, 0.4025, 0.4650, 0.5306, 0.5103]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.1671832787396852
step: 88
running loss: 0.0018998099856782408
Train Steps: 88/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6265, 0.4088, 0.8025, 0.1850, 0.4163, 0.2500, 0.6290, 0.4947],
[0.6268, 0.4029, 0.8500, 0.2683, 0.3937, 0.3500, 0.6860, 0.5297],
[0.6075, 0.4000, 0.8513, 0.5183, 0.4510, 0.5329, 0.5180, 0.5280],
[0.6175, 0.4013, 0.7734, 0.2783, 0.4475, 0.1786, 0.5790, 0.5351],
[0.6197, 0.4118, 0.8688, 0.5517, 0.4037, 0.5233, 0.5875, 0.5600],
[0.6267, 0.4080, 0.8438, 0.2633, 0.4763, 0.1800, 0.6259, 0.5240],
[0.6175, 0.3997, 0.6737, 0.2500, 0.4313, 0.1933, 0.5513, 0.5750],
[0.6159, 0.4085, 0.6900, 0.2283, 0.4088, 0.1950, 0.5123, 0.5397]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5255, 0.3113, 0.8251, 0.2187, 0.4319, 0.2542, 0.6413, 0.5076],
[0.6474, 0.4166, 0.8514, 0.3105, 0.3775, 0.3558, 0.6948, 0.5177],
[0.6135, 0.3969, 0.8811, 0.5613, 0.4470, 0.5547, 0.5503, 0.5267],
[0.5737, 0.3469, 0.7954, 0.2748, 0.4297, 0.2041, 0.5773, 0.5026],
[0.5767, 0.3556, 0.9012, 0.5930, 0.4184, 0.5899, 0.6142, 0.5412],
[0.5345, 0.3243, 0.8682, 0.2854, 0.4664, 0.2013, 0.6259, 0.5182],
[0.4622, 0.2721, 0.7097, 0.2735, 0.4363, 0.2165, 0.5343, 0.5638],
[0.5916, 0.3473, 0.7170, 0.2494, 0.4071, 0.2011, 0.5076, 0.5404]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6265, 0.4088, 0.8025, 0.1850, 0.4162, 0.2500, 0.6290, 0.4947],
[0.6268, 0.4029, 0.8500, 0.2683, 0.3938, 0.3500, 0.6860, 0.5297],
[0.6075, 0.4000, 0.8512, 0.5183, 0.4510, 0.5329, 0.5180, 0.5280],
[0.6175, 0.4013, 0.7734, 0.2783, 0.4475, 0.1786, 0.5790, 0.5351],
[0.6197, 0.4118, 0.8687, 0.5517, 0.4038, 0.5233, 0.5875, 0.5600],
[0.6267, 0.4080, 0.8438, 0.2633, 0.4762, 0.1800, 0.6259, 0.5240],
[0.6175, 0.3997, 0.6737, 0.2500, 0.4313, 0.1933, 0.5512, 0.5750],
[0.6159, 0.4085, 0.6900, 0.2283, 0.4087, 0.1950, 0.5123, 0.5397]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0018, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0018, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.16899637822643854
step: 89
running loss: 0.0018988357104094218
Train Steps: 89/90 Loss: 0.0019 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6118, 0.4052, 0.8463, 0.3917, 0.3538, 0.3450, 0.5053, 0.5593],
[0.6226, 0.4103, 0.8575, 0.3450, 0.4388, 0.2067, 0.5787, 0.5383],
[0.6300, 0.4013, 0.8938, 0.5350, 0.3675, 0.4600, 0.6456, 0.4973],
[ nan, nan, 0.6992, 0.2791, 0.3950, 0.2383, 0.5483, 0.5819],
[0.6082, 0.4042, 0.6975, 0.1917, 0.4100, 0.1983, 0.5502, 0.5578],
[0.6277, 0.4118, 0.8988, 0.3833, 0.3950, 0.2650, 0.6290, 0.4938],
[0.6165, 0.4106, 0.7575, 0.1733, 0.3838, 0.2650, 0.5680, 0.5116],
[0.6129, 0.4069, 0.8750, 0.5067, 0.3875, 0.4233, 0.5235, 0.5881]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4714, 0.3092, 0.8766, 0.3644, 0.3797, 0.3765, 0.5317, 0.5521],
[0.7109, 0.4638, 0.8667, 0.3510, 0.4728, 0.2814, 0.5916, 0.5561],
[0.5956, 0.3719, 0.9270, 0.5358, 0.3928, 0.4968, 0.6874, 0.4935],
[0.2441, 0.1478, 0.7006, 0.2561, 0.4080, 0.2624, 0.5646, 0.5555],
[0.6287, 0.4122, 0.7137, 0.2069, 0.4231, 0.2120, 0.5734, 0.5442],
[0.6276, 0.4006, 0.9260, 0.3551, 0.4172, 0.2875, 0.6585, 0.5085],
[0.6717, 0.4245, 0.7733, 0.1955, 0.4045, 0.2666, 0.6203, 0.5008],
[0.5436, 0.3620, 0.9240, 0.5174, 0.4223, 0.4559, 0.5638, 0.5646]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6118, 0.4052, 0.8462, 0.3917, 0.3537, 0.3450, 0.5053, 0.5593],
[0.6226, 0.4103, 0.8575, 0.3450, 0.4387, 0.2067, 0.5788, 0.5383],
[0.6300, 0.4013, 0.8938, 0.5350, 0.3675, 0.4600, 0.6456, 0.4973],
[0.0000, 0.0000, 0.6992, 0.2791, 0.3950, 0.2383, 0.5483, 0.5819],
[0.6082, 0.4042, 0.6975, 0.1917, 0.4100, 0.1983, 0.5502, 0.5578],
[0.6277, 0.4117, 0.8988, 0.3833, 0.3950, 0.2650, 0.6290, 0.4938],
[0.6165, 0.4106, 0.7575, 0.1733, 0.3837, 0.2650, 0.5680, 0.5116],
[0.6129, 0.4069, 0.8750, 0.5067, 0.3875, 0.4233, 0.5235, 0.5881]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0026, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0026, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.17162802946404554
step: 90
running loss: 0.0019069781051560615
Valid Steps: 10/10 Loss: nan 19
--------------------------------------------------
Epoch: 4 Train Loss: 0.0019 Valid Loss: nan
--------------------------------------------------
size of train loader is: 90
torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6189, 0.3911, 0.8800, 0.4917, 0.3713, 0.4800, 0.6038, 0.4833],
[ nan, nan, 0.8213, 0.2700, 0.3775, 0.2817, 0.5425, 0.5533],
[0.6353, 0.4128, 0.8488, 0.2600, 0.5525, 0.1616, 0.6694, 0.5540],
[0.6214, 0.4116, 0.7750, 0.2317, 0.4487, 0.1883, 0.6200, 0.5400],
[0.6267, 0.4065, 0.8313, 0.2467, 0.4788, 0.1733, 0.6312, 0.5133],
[0.6109, 0.4036, 0.7188, 0.1750, 0.3850, 0.2550, 0.5863, 0.5567],
[0.6222, 0.4072, 0.7164, 0.2166, 0.3738, 0.3167, 0.6100, 0.5533],
[0.6200, 0.4086, 0.8414, 0.2974, 0.4117, 0.2274, 0.5869, 0.5391]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5069, 0.3172, 0.9035, 0.4719, 0.3578, 0.5011, 0.6231, 0.4727],
[0.2427, 0.1428, 0.7823, 0.2831, 0.3590, 0.3039, 0.5319, 0.5369],
[0.4679, 0.2951, 0.8326, 0.2327, 0.5136, 0.2198, 0.6668, 0.5393],
[0.6167, 0.3997, 0.7749, 0.2314, 0.4379, 0.2040, 0.6198, 0.5140],
[0.6602, 0.4364, 0.8328, 0.2305, 0.4575, 0.1908, 0.6440, 0.5086],
[0.6117, 0.3958, 0.7204, 0.2080, 0.3732, 0.2822, 0.5813, 0.5445],
[0.6157, 0.3828, 0.7254, 0.2383, 0.3530, 0.3197, 0.6175, 0.5472],
[0.6747, 0.4466, 0.8350, 0.2806, 0.4019, 0.2544, 0.5892, 0.5197]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6189, 0.3911, 0.8800, 0.4917, 0.3713, 0.4800, 0.6037, 0.4833],
[0.0000, 0.0000, 0.8213, 0.2700, 0.3775, 0.2817, 0.5425, 0.5533],
[0.6353, 0.4128, 0.8487, 0.2600, 0.5525, 0.1616, 0.6694, 0.5540],
[0.6214, 0.4116, 0.7750, 0.2317, 0.4487, 0.1883, 0.6200, 0.5400],
[0.6266, 0.4065, 0.8313, 0.2467, 0.4787, 0.1733, 0.6313, 0.5133],
[0.6108, 0.4036, 0.7188, 0.1750, 0.3850, 0.2550, 0.5863, 0.5567],
[0.6222, 0.4072, 0.7164, 0.2166, 0.3738, 0.3167, 0.6100, 0.5533],
[0.6199, 0.4086, 0.8414, 0.2974, 0.4117, 0.2274, 0.5869, 0.5391]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0026, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0026, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.002571904333308339
step: 1
running loss: 0.002571904333308339
Train Steps: 1/90 Loss: 0.0026 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6125, 0.3983, 0.8750, 0.4867, 0.4275, 0.4783, 0.5413, 0.5717],
[0.6310, 0.4017, 0.8563, 0.5800, 0.3688, 0.4750, 0.6326, 0.5006],
[0.6042, 0.3990, 0.6831, 0.2875, 0.3500, 0.3133, 0.5143, 0.5510],
[0.6258, 0.4143, 0.8525, 0.2617, 0.4950, 0.1667, 0.6219, 0.4967],
[0.6114, 0.4018, 0.7213, 0.1967, 0.3763, 0.2700, 0.5875, 0.5533],
[0.6199, 0.3952, 0.8573, 0.5374, 0.4075, 0.4687, 0.5942, 0.5377],
[0.6223, 0.4130, 0.8100, 0.2983, 0.3525, 0.3900, 0.5694, 0.5103],
[0.6212, 0.4171, 0.7875, 0.3633, 0.3813, 0.2933, 0.5675, 0.5700]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6312, 0.4185, 0.8692, 0.4429, 0.4182, 0.4553, 0.5748, 0.5425],
[0.5685, 0.3769, 0.8712, 0.5344, 0.3641, 0.4595, 0.6565, 0.5075],
[0.4979, 0.3211, 0.7142, 0.2441, 0.3522, 0.2886, 0.5398, 0.5386],
[0.6197, 0.4256, 0.8434, 0.2249, 0.4742, 0.1780, 0.6291, 0.4914],
[0.6333, 0.4119, 0.7307, 0.1883, 0.3516, 0.2513, 0.6118, 0.5479],
[0.5472, 0.3613, 0.8589, 0.4923, 0.3900, 0.4429, 0.6165, 0.5297],
[0.6158, 0.4280, 0.8171, 0.2819, 0.3469, 0.3697, 0.5905, 0.5223],
[0.6046, 0.4057, 0.7983, 0.3157, 0.3680, 0.2756, 0.5851, 0.5720]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6125, 0.3983, 0.8750, 0.4867, 0.4275, 0.4783, 0.5412, 0.5717],
[0.6310, 0.4017, 0.8562, 0.5800, 0.3688, 0.4750, 0.6326, 0.5006],
[0.6042, 0.3990, 0.6831, 0.2875, 0.3500, 0.3133, 0.5143, 0.5510],
[0.6258, 0.4143, 0.8525, 0.2617, 0.4950, 0.1667, 0.6219, 0.4967],
[0.6114, 0.4018, 0.7212, 0.1967, 0.3762, 0.2700, 0.5875, 0.5533],
[0.6199, 0.3952, 0.8573, 0.5374, 0.4075, 0.4687, 0.5942, 0.5377],
[0.6223, 0.4130, 0.8100, 0.2983, 0.3525, 0.3900, 0.5694, 0.5103],
[0.6212, 0.4171, 0.7875, 0.3633, 0.3812, 0.2933, 0.5675, 0.5700]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.003422100911848247
step: 2
running loss: 0.0017110504559241235
Train Steps: 2/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6091, 0.3997, 0.8314, 0.4334, 0.3788, 0.4550, 0.5213, 0.5656],
[0.6128, 0.4115, 0.7934, 0.3778, 0.3450, 0.4033, 0.5337, 0.5456],
[0.6136, 0.3955, 0.8400, 0.3267, 0.3500, 0.4200, 0.5863, 0.5467],
[0.6146, 0.4124, 0.8800, 0.4867, 0.3800, 0.4500, 0.5106, 0.5524],
[0.6156, 0.4125, 0.8850, 0.4833, 0.4550, 0.5817, 0.5765, 0.5084],
[0.6200, 0.3993, 0.8639, 0.3687, 0.3658, 0.3139, 0.6002, 0.5374],
[0.6286, 0.4086, 0.8408, 0.2801, 0.4163, 0.2800, 0.6725, 0.5393],
[0.6229, 0.4198, 0.7662, 0.2700, 0.4700, 0.2133, 0.5675, 0.5783]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5767, 0.4007, 0.8143, 0.3931, 0.3484, 0.3931, 0.5638, 0.5402],
[0.5164, 0.3594, 0.7774, 0.3241, 0.3213, 0.3582, 0.5171, 0.5565],
[0.5055, 0.3489, 0.8258, 0.2838, 0.3339, 0.3657, 0.5966, 0.5359],
[0.5999, 0.4185, 0.8611, 0.4580, 0.3542, 0.3977, 0.5300, 0.5404],
[0.5769, 0.4194, 0.8771, 0.4247, 0.4371, 0.5407, 0.5959, 0.5125],
[0.5649, 0.3986, 0.8371, 0.3267, 0.3532, 0.2654, 0.6139, 0.5156],
[0.6567, 0.4417, 0.8134, 0.2386, 0.4005, 0.2341, 0.6993, 0.5478],
[0.6901, 0.4905, 0.7182, 0.2260, 0.4397, 0.1728, 0.5948, 0.5641]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6091, 0.3997, 0.8314, 0.4334, 0.3787, 0.4550, 0.5213, 0.5656],
[0.6128, 0.4115, 0.7934, 0.3778, 0.3450, 0.4033, 0.5337, 0.5456],
[0.6136, 0.3955, 0.8400, 0.3267, 0.3500, 0.4200, 0.5863, 0.5467],
[0.6146, 0.4124, 0.8800, 0.4867, 0.3800, 0.4500, 0.5106, 0.5524],
[0.6155, 0.4124, 0.8850, 0.4833, 0.4550, 0.5817, 0.5765, 0.5084],
[0.6200, 0.3993, 0.8639, 0.3687, 0.3658, 0.3139, 0.6002, 0.5374],
[0.6286, 0.4086, 0.8408, 0.2801, 0.4162, 0.2800, 0.6725, 0.5393],
[0.6229, 0.4198, 0.7663, 0.2700, 0.4700, 0.2133, 0.5675, 0.5783]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.004888763302005827
step: 3
running loss: 0.0016295877673352759
Train Steps: 3/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6239, 0.4123, 0.8313, 0.2550, 0.4500, 0.2050, 0.6175, 0.5400],
[ nan, nan, 0.7648, 0.2722, 0.3962, 0.2183, 0.5060, 0.5422],
[0.6048, 0.3928, 0.8538, 0.5433, 0.3875, 0.5117, 0.5266, 0.4719],
[0.6079, 0.3964, 0.7420, 0.2958, 0.3563, 0.2917, 0.5351, 0.4980],
[0.6179, 0.4008, 0.7505, 0.2678, 0.4368, 0.1891, 0.5831, 0.5263],
[0.6195, 0.4101, 0.8650, 0.3917, 0.3575, 0.4033, 0.5800, 0.5650],
[0.6143, 0.4034, 0.8800, 0.4833, 0.4512, 0.5367, 0.5289, 0.5097],
[0.6201, 0.4055, 0.7717, 0.1919, 0.4250, 0.2079, 0.5871, 0.5044]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6569, 0.4591, 0.8035, 0.2211, 0.4456, 0.1612, 0.6344, 0.5325],
[0.0221, 0.0467, 0.7281, 0.2313, 0.3881, 0.1999, 0.4928, 0.5521],
[0.5861, 0.4172, 0.8259, 0.5173, 0.3827, 0.4669, 0.5640, 0.5321],
[0.6071, 0.4254, 0.7368, 0.2558, 0.3392, 0.2520, 0.5336, 0.5193],
[0.6452, 0.4404, 0.7274, 0.2249, 0.4207, 0.1520, 0.5773, 0.5537],
[0.6508, 0.4609, 0.8622, 0.3731, 0.3328, 0.3513, 0.6068, 0.5783],
[0.5856, 0.4143, 0.8582, 0.4284, 0.4329, 0.4699, 0.5170, 0.5379],
[0.6478, 0.4482, 0.7278, 0.1706, 0.4110, 0.1783, 0.5851, 0.5236]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6239, 0.4123, 0.8313, 0.2550, 0.4500, 0.2050, 0.6175, 0.5400],
[0.0000, 0.0000, 0.7648, 0.2722, 0.3963, 0.2183, 0.5060, 0.5422],
[0.6048, 0.3928, 0.8537, 0.5433, 0.3875, 0.5117, 0.5266, 0.4719],
[0.6079, 0.3964, 0.7420, 0.2958, 0.3562, 0.2917, 0.5351, 0.4980],
[0.6179, 0.4008, 0.7505, 0.2678, 0.4368, 0.1891, 0.5831, 0.5263],
[0.6195, 0.4101, 0.8650, 0.3917, 0.3575, 0.4033, 0.5800, 0.5650],
[0.6143, 0.4034, 0.8800, 0.4833, 0.4512, 0.5367, 0.5289, 0.5097],
[0.6202, 0.4055, 0.7717, 0.1919, 0.4250, 0.2079, 0.5871, 0.5044]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.005824644234962761
step: 4
running loss: 0.0014561610587406904
Train Steps: 4/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.6286, 0.4055, 0.9000, 0.4717, 0.3763, 0.4683, 0.7018, 0.5494],
[0.6222, 0.4072, 0.7164, 0.2166, 0.3738, 0.3167, 0.6100, 0.5533],
[0.6058, 0.3986, 0.8324, 0.4626, 0.3838, 0.4983, 0.5147, 0.5466],
[0.6102, 0.4001, 0.7738, 0.3583, 0.3463, 0.3800, 0.5524, 0.5689],
[0.6164, 0.3956, 0.8757, 0.5088, 0.4300, 0.5320, 0.6022, 0.5202],
[0.6307, 0.4060, 0.8950, 0.5183, 0.3750, 0.3850, 0.6338, 0.4938],
[0.6151, 0.4085, 0.8750, 0.4367, 0.3887, 0.4367, 0.5066, 0.5846]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6226, 0.4463, 0.8285, 0.5319, 0.3688, 0.4619, 0.6373, 0.5457],
[0.6219, 0.4211, 0.8754, 0.4207, 0.3663, 0.4380, 0.6535, 0.5222],
[0.6355, 0.4175, 0.7015, 0.2082, 0.3690, 0.2846, 0.5753, 0.5700],
[0.5749, 0.4067, 0.8070, 0.4229, 0.3914, 0.4444, 0.5041, 0.5446],
[0.5692, 0.3908, 0.7660, 0.3264, 0.3533, 0.3449, 0.5118, 0.5689],
[0.6845, 0.4591, 0.8447, 0.4739, 0.4148, 0.4918, 0.5787, 0.5144],
[0.6625, 0.4511, 0.9037, 0.4784, 0.3745, 0.3178, 0.5695, 0.4884],
[0.5560, 0.3884, 0.8544, 0.3927, 0.4004, 0.3863, 0.4718, 0.5870]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.6286, 0.4055, 0.9000, 0.4717, 0.3762, 0.4683, 0.7018, 0.5494],
[0.6222, 0.4072, 0.7164, 0.2166, 0.3738, 0.3167, 0.6100, 0.5533],
[0.6058, 0.3986, 0.8324, 0.4626, 0.3837, 0.4983, 0.5147, 0.5466],
[0.6102, 0.4001, 0.7738, 0.3583, 0.3462, 0.3800, 0.5524, 0.5689],
[0.6164, 0.3956, 0.8757, 0.5088, 0.4300, 0.5320, 0.6022, 0.5202],
[0.6307, 0.4060, 0.8950, 0.5183, 0.3750, 0.3850, 0.6338, 0.4938],
[0.6151, 0.4085, 0.8750, 0.4367, 0.3887, 0.4367, 0.5066, 0.5846]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0068395029520615935
step: 5
running loss: 0.0013679005904123187
Train Steps: 5/90 Loss: 0.0014 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6223, 0.4028, 0.8988, 0.4200, 0.3763, 0.5733, 0.6375, 0.5167],
[0.6179, 0.3993, 0.8925, 0.4789, 0.3879, 0.4900, 0.6041, 0.5279],
[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758],
[ nan, nan, 0.6859, 0.2194, 0.4150, 0.1867, 0.5153, 0.5729],
[0.6107, 0.4050, 0.8700, 0.4850, 0.4470, 0.4848, 0.5043, 0.5431],
[0.6263, 0.4065, 0.9038, 0.4317, 0.3588, 0.4550, 0.6325, 0.5250],
[0.6308, 0.3990, 0.8688, 0.5183, 0.3950, 0.4983, 0.6388, 0.5133],
[0.6134, 0.4090, 0.6926, 0.2819, 0.3538, 0.3233, 0.5563, 0.5667]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6524, 0.4446, 0.8739, 0.4292, 0.3901, 0.5684, 0.5870, 0.5248],
[0.7536, 0.5074, 0.8733, 0.4629, 0.3983, 0.4563, 0.5661, 0.5410],
[0.6150, 0.4130, 0.8696, 0.4876, 0.4082, 0.5064, 0.6075, 0.4961],
[0.1934, 0.1508, 0.6788, 0.2390, 0.4383, 0.1802, 0.4801, 0.5844],
[0.6349, 0.4411, 0.8529, 0.4943, 0.4403, 0.4505, 0.4819, 0.5348],
[0.6732, 0.4605, 0.8986, 0.4346, 0.3841, 0.4376, 0.6269, 0.5354],
[0.6724, 0.4510, 0.8377, 0.5237, 0.4102, 0.4649, 0.6140, 0.5327],
[0.6730, 0.4634, 0.6818, 0.2965, 0.3441, 0.3061, 0.5348, 0.5776]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6223, 0.4028, 0.8988, 0.4200, 0.3762, 0.5733, 0.6375, 0.5167],
[0.6179, 0.3993, 0.8925, 0.4789, 0.3879, 0.4900, 0.6041, 0.5279],
[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758],
[0.0000, 0.0000, 0.6859, 0.2194, 0.4150, 0.1867, 0.5153, 0.5729],
[0.6107, 0.4050, 0.8700, 0.4850, 0.4470, 0.4848, 0.5043, 0.5431],
[0.6263, 0.4065, 0.9038, 0.4317, 0.3587, 0.4550, 0.6325, 0.5250],
[0.6308, 0.3990, 0.8687, 0.5183, 0.3950, 0.4983, 0.6388, 0.5133],
[0.6134, 0.4090, 0.6926, 0.2819, 0.3537, 0.3233, 0.5562, 0.5667]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0020, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0020, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.008879333385266364
step: 6
running loss: 0.001479888897544394
Train Steps: 6/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6257, 0.4024, 0.8672, 0.5422, 0.4196, 0.5198, 0.6694, 0.5204],
[0.6226, 0.4125, 0.8800, 0.4900, 0.4512, 0.5600, 0.6275, 0.5517],
[0.6169, 0.4108, 0.6821, 0.2722, 0.3825, 0.2550, 0.5550, 0.5717],
[0.6211, 0.4069, 0.8750, 0.5117, 0.4150, 0.4900, 0.5875, 0.5167],
[0.6058, 0.3986, 0.8324, 0.4626, 0.3838, 0.4983, 0.5147, 0.5466],
[0.6160, 0.4086, 0.8775, 0.3983, 0.3750, 0.3783, 0.5128, 0.4882],
[0.6268, 0.4102, 0.8938, 0.3667, 0.4025, 0.2833, 0.6275, 0.5183],
[0.6329, 0.4055, 0.9050, 0.4783, 0.3613, 0.3917, 0.6464, 0.5019]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6325, 0.4042, 0.8374, 0.5384, 0.4076, 0.5202, 0.6245, 0.5165],
[0.5927, 0.3926, 0.8575, 0.4811, 0.4553, 0.5659, 0.5778, 0.5579],
[0.5796, 0.3891, 0.6593, 0.2784, 0.3838, 0.2641, 0.5286, 0.5727],
[0.5931, 0.3895, 0.8627, 0.5164, 0.4052, 0.5231, 0.5720, 0.5328],
[0.5840, 0.3913, 0.8053, 0.4573, 0.3862, 0.4881, 0.5126, 0.5421],
[0.5666, 0.4013, 0.8484, 0.4060, 0.3668, 0.3963, 0.5045, 0.5135],
[0.5671, 0.3753, 0.8731, 0.3701, 0.4138, 0.2802, 0.5981, 0.5359],
[0.6675, 0.4155, 0.8711, 0.4727, 0.3791, 0.4025, 0.6250, 0.5075]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6257, 0.4024, 0.8672, 0.5422, 0.4196, 0.5198, 0.6694, 0.5204],
[0.6226, 0.4125, 0.8800, 0.4900, 0.4512, 0.5600, 0.6275, 0.5517],
[0.6169, 0.4108, 0.6821, 0.2722, 0.3825, 0.2550, 0.5550, 0.5717],
[0.6211, 0.4069, 0.8750, 0.5117, 0.4150, 0.4900, 0.5875, 0.5167],
[0.6058, 0.3986, 0.8324, 0.4626, 0.3837, 0.4983, 0.5147, 0.5466],
[0.6160, 0.4086, 0.8775, 0.3983, 0.3750, 0.3783, 0.5128, 0.4882],
[0.6268, 0.4102, 0.8938, 0.3667, 0.4025, 0.2833, 0.6275, 0.5183],
[0.6329, 0.4055, 0.9050, 0.4783, 0.3613, 0.3917, 0.6464, 0.5019]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.009341607365058735
step: 7
running loss: 0.0013345153378655336
Train Steps: 7/90 Loss: 0.0013 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6336, 0.4154, 0.8900, 0.2767, 0.4988, 0.2867, 0.7422, 0.5540],
[0.6185, 0.4079, 0.8838, 0.4617, 0.4838, 0.5650, 0.6175, 0.5850],
[0.6248, 0.4032, 0.7738, 0.1900, 0.4813, 0.1400, 0.5941, 0.4904],
[0.6260, 0.4106, 0.8025, 0.2583, 0.4550, 0.1867, 0.6281, 0.4869],
[0.6245, 0.4100, 0.7762, 0.2583, 0.4963, 0.1517, 0.5875, 0.5417],
[0.6206, 0.4001, 0.8900, 0.3933, 0.3588, 0.3567, 0.5837, 0.5083],
[0.6286, 0.4055, 0.9000, 0.4717, 0.3763, 0.4683, 0.7018, 0.5494],
[0.6231, 0.3973, 0.8650, 0.3950, 0.3625, 0.3183, 0.5837, 0.5167]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5499, 0.3594, 0.8369, 0.3185, 0.4948, 0.3402, 0.6740, 0.5420],
[0.5998, 0.3705, 0.8692, 0.4855, 0.4617, 0.6227, 0.5686, 0.5542],
[0.5499, 0.3415, 0.7362, 0.2629, 0.4629, 0.1953, 0.5573, 0.5133],
[0.4837, 0.2881, 0.7961, 0.2749, 0.4318, 0.2609, 0.5862, 0.5048],
[0.6002, 0.3903, 0.7413, 0.2989, 0.4616, 0.2055, 0.5607, 0.5631],
[0.5945, 0.3634, 0.8931, 0.4460, 0.3458, 0.4164, 0.5333, 0.5032],
[0.5868, 0.3631, 0.8820, 0.5066, 0.3499, 0.5411, 0.6449, 0.5156],
[0.5235, 0.3172, 0.8431, 0.4431, 0.3745, 0.3671, 0.5454, 0.5285]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6336, 0.4154, 0.8900, 0.2767, 0.4988, 0.2867, 0.7422, 0.5540],
[0.6184, 0.4079, 0.8838, 0.4617, 0.4837, 0.5650, 0.6175, 0.5850],
[0.6248, 0.4032, 0.7738, 0.1900, 0.4812, 0.1400, 0.5941, 0.4904],
[0.6260, 0.4106, 0.8025, 0.2583, 0.4550, 0.1867, 0.6281, 0.4869],
[0.6245, 0.4100, 0.7763, 0.2583, 0.4963, 0.1517, 0.5875, 0.5417],
[0.6206, 0.4001, 0.8900, 0.3933, 0.3587, 0.3567, 0.5838, 0.5083],
[0.6286, 0.4055, 0.9000, 0.4717, 0.3762, 0.4683, 0.7018, 0.5494],
[0.6231, 0.3973, 0.8650, 0.3950, 0.3625, 0.3183, 0.5838, 0.5167]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0024, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0024, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.011782382178353146
step: 8
running loss: 0.0014727977722941432
Train Steps: 8/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6209, 0.3920, 0.8650, 0.5367, 0.4400, 0.5067, 0.6025, 0.4950],
[0.6214, 0.4040, 0.8838, 0.3500, 0.3600, 0.5183, 0.6362, 0.5200],
[0.6151, 0.4125, 0.8738, 0.4417, 0.3575, 0.3783, 0.5138, 0.5483],
[0.6200, 0.3993, 0.8519, 0.4923, 0.3962, 0.4717, 0.6013, 0.5433],
[0.6267, 0.4094, 0.8712, 0.3083, 0.4400, 0.2267, 0.6250, 0.5200],
[0.6200, 0.4112, 0.8862, 0.4100, 0.3638, 0.4917, 0.6088, 0.6050],
[0.6227, 0.4049, 0.8750, 0.5367, 0.3775, 0.3667, 0.5725, 0.5317],
[0.6271, 0.4081, 0.9081, 0.4894, 0.3700, 0.4283, 0.6661, 0.5274]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6115, 0.3676, 0.8520, 0.5439, 0.4247, 0.5460, 0.5940, 0.4784],
[0.6112, 0.3801, 0.8665, 0.4029, 0.3777, 0.5389, 0.6466, 0.5161],
[0.5991, 0.3805, 0.8630, 0.4775, 0.3677, 0.4075, 0.5308, 0.5507],
[0.5744, 0.3545, 0.8599, 0.5122, 0.3941, 0.4950, 0.6332, 0.5469],
[0.5568, 0.3427, 0.8693, 0.3457, 0.4553, 0.2653, 0.6197, 0.5071],
[0.6292, 0.4066, 0.8632, 0.4395, 0.3943, 0.5198, 0.5969, 0.5634],
[0.6212, 0.3967, 0.8706, 0.5548, 0.4042, 0.3961, 0.6012, 0.5386],
[0.5783, 0.3662, 0.8935, 0.4913, 0.3843, 0.4621, 0.6692, 0.5343]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6209, 0.3920, 0.8650, 0.5367, 0.4400, 0.5067, 0.6025, 0.4950],
[0.6214, 0.4040, 0.8838, 0.3500, 0.3600, 0.5183, 0.6363, 0.5200],
[0.6151, 0.4125, 0.8737, 0.4417, 0.3575, 0.3783, 0.5138, 0.5483],
[0.6200, 0.3993, 0.8519, 0.4923, 0.3963, 0.4717, 0.6012, 0.5433],
[0.6267, 0.4094, 0.8712, 0.3083, 0.4400, 0.2267, 0.6250, 0.5200],
[0.6200, 0.4112, 0.8863, 0.4100, 0.3638, 0.4917, 0.6087, 0.6050],
[0.6227, 0.4049, 0.8750, 0.5367, 0.3775, 0.3667, 0.5725, 0.5317],
[0.6271, 0.4081, 0.9081, 0.4894, 0.3700, 0.4283, 0.6661, 0.5274]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.012471756344893947
step: 9
running loss: 0.0013857507049882163
Train Steps: 9/90 Loss: 0.0014 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6226, 0.4185, 0.8850, 0.5500, 0.3800, 0.4250, 0.5625, 0.5617],
[ nan, nan, 0.7335, 0.2569, 0.3788, 0.2667, 0.5066, 0.5578],
[0.6110, 0.4047, 0.8700, 0.4483, 0.3713, 0.3967, 0.5088, 0.5517],
[0.6086, 0.3940, 0.8712, 0.4783, 0.4025, 0.4900, 0.5498, 0.5390],
[0.6371, 0.4092, 0.8337, 0.5850, 0.3950, 0.5117, 0.6559, 0.5262],
[0.6101, 0.3977, 0.8550, 0.5667, 0.3862, 0.4417, 0.5128, 0.4869],
[0.6296, 0.4008, 0.9150, 0.4317, 0.4263, 0.3050, 0.7256, 0.5413],
[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6793, 0.4314, 0.9187, 0.5516, 0.3941, 0.4325, 0.6246, 0.5432],
[ 0.0100, -0.0118, 0.7616, 0.2766, 0.4076, 0.2870, 0.5129, 0.5589],
[ 0.6446, 0.4051, 0.9034, 0.4762, 0.3717, 0.4353, 0.5629, 0.5327],
[ 0.7062, 0.4283, 0.8897, 0.4961, 0.4185, 0.5016, 0.5951, 0.5012],
[ 0.7383, 0.4840, 0.8713, 0.5639, 0.3891, 0.5187, 0.7153, 0.5261],
[ 0.6300, 0.3864, 0.8894, 0.5457, 0.4119, 0.4570, 0.5903, 0.4735],
[ 0.6149, 0.3706, 0.9511, 0.4093, 0.4241, 0.3094, 0.7230, 0.5335],
[ 0.6544, 0.4049, 0.9248, 0.4669, 0.4432, 0.5979, 0.6524, 0.5007]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6226, 0.4185, 0.8850, 0.5500, 0.3800, 0.4250, 0.5625, 0.5617],
[0.0000, 0.0000, 0.7335, 0.2569, 0.3787, 0.2667, 0.5066, 0.5578],
[0.6110, 0.4047, 0.8700, 0.4483, 0.3713, 0.3967, 0.5088, 0.5517],
[0.6086, 0.3940, 0.8712, 0.4783, 0.4025, 0.4900, 0.5498, 0.5390],
[0.6371, 0.4092, 0.8338, 0.5850, 0.3950, 0.5117, 0.6559, 0.5262],
[0.6101, 0.3977, 0.8550, 0.5667, 0.3862, 0.4417, 0.5128, 0.4869],
[0.6296, 0.4008, 0.9150, 0.4317, 0.4263, 0.3050, 0.7256, 0.5413],
[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.013627727428684011
step: 10
running loss: 0.001362772742868401
Train Steps: 10/90 Loss: 0.0014 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383],
[0.6332, 0.4165, 0.9100, 0.3350, 0.4188, 0.3683, 0.7438, 0.5528],
[0.6086, 0.3981, 0.8700, 0.4750, 0.4512, 0.5283, 0.5324, 0.5038],
[0.6275, 0.4111, 0.8463, 0.2617, 0.4487, 0.1983, 0.6211, 0.4904],
[0.6239, 0.4107, 0.8162, 0.2763, 0.3625, 0.3600, 0.5988, 0.5700],
[0.6219, 0.4114, 0.8175, 0.2817, 0.3925, 0.2783, 0.5900, 0.5350],
[0.6026, 0.3979, 0.8550, 0.4233, 0.3613, 0.5233, 0.5582, 0.4967],
[0.6250, 0.4116, 0.8700, 0.4850, 0.4650, 0.5567, 0.6088, 0.5183]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6525, 0.4029, 0.8657, 0.3708, 0.3643, 0.3567, 0.6704, 0.5558],
[0.4966, 0.3262, 0.9405, 0.4151, 0.4271, 0.3549, 0.7339, 0.5399],
[0.6338, 0.3980, 0.8844, 0.5107, 0.4377, 0.5056, 0.5811, 0.4925],
[0.5620, 0.3533, 0.8747, 0.3214, 0.4716, 0.2212, 0.6513, 0.4920],
[0.4764, 0.3062, 0.8148, 0.3349, 0.3829, 0.3372, 0.6139, 0.5654],
[0.5407, 0.3467, 0.8335, 0.3137, 0.4079, 0.2607, 0.6321, 0.5385],
[0.6389, 0.3857, 0.9060, 0.4683, 0.3464, 0.5044, 0.6220, 0.5043],
[0.6267, 0.3907, 0.9125, 0.5158, 0.4654, 0.5760, 0.6488, 0.5189]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383],
[0.6332, 0.4165, 0.9100, 0.3350, 0.4187, 0.3683, 0.7438, 0.5528],
[0.6086, 0.3981, 0.8700, 0.4750, 0.4512, 0.5283, 0.5324, 0.5038],
[0.6275, 0.4111, 0.8462, 0.2617, 0.4487, 0.1983, 0.6211, 0.4904],
[0.6239, 0.4107, 0.8162, 0.2763, 0.3625, 0.3600, 0.5987, 0.5700],
[0.6219, 0.4114, 0.8175, 0.2817, 0.3925, 0.2783, 0.5900, 0.5350],
[0.6026, 0.3979, 0.8550, 0.4233, 0.3613, 0.5233, 0.5582, 0.4967],
[0.6251, 0.4116, 0.8700, 0.4850, 0.4650, 0.5567, 0.6087, 0.5183]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0020, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0020, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.015669901302317157
step: 11
running loss: 0.0014245364820288325
Train Steps: 11/90 Loss: 0.0014 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6212, 0.4033, 0.8938, 0.4167, 0.3813, 0.4267, 0.5613, 0.5583],
[ nan, nan, 0.8900, 0.3217, 0.5038, 0.2233, 0.6694, 0.5609],
[0.6102, 0.4020, 0.8638, 0.3717, 0.3625, 0.5017, 0.6038, 0.5500],
[0.6160, 0.4086, 0.8775, 0.3983, 0.3750, 0.3783, 0.5128, 0.4882],
[0.6147, 0.4081, 0.8538, 0.3400, 0.3663, 0.3150, 0.5142, 0.4875],
[0.6222, 0.4172, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633],
[0.6201, 0.4102, 0.7288, 0.2417, 0.4150, 0.2383, 0.6100, 0.5500],
[0.6196, 0.4094, 0.7562, 0.2817, 0.3937, 0.3183, 0.6013, 0.6183]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6875, 0.4300, 0.9321, 0.4452, 0.3982, 0.4376, 0.6041, 0.5300],
[0.1043, 0.0346, 0.9332, 0.3317, 0.5154, 0.2238, 0.6927, 0.5586],
[0.6547, 0.4155, 0.9068, 0.4049, 0.3867, 0.5096, 0.6642, 0.5283],
[0.6674, 0.4435, 0.9025, 0.4268, 0.3800, 0.3965, 0.5753, 0.4976],
[0.6864, 0.4318, 0.9109, 0.3977, 0.3846, 0.3165, 0.5818, 0.5175],
[0.7053, 0.4394, 0.9215, 0.5413, 0.3811, 0.4696, 0.6207, 0.5601],
[0.6223, 0.3908, 0.7892, 0.2697, 0.4158, 0.2622, 0.6334, 0.5526],
[0.6602, 0.4094, 0.8130, 0.3379, 0.4130, 0.3217, 0.6394, 0.6013]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6212, 0.4033, 0.8938, 0.4167, 0.3812, 0.4267, 0.5612, 0.5583],
[0.0000, 0.0000, 0.8900, 0.3217, 0.5038, 0.2233, 0.6694, 0.5609],
[0.6102, 0.4020, 0.8637, 0.3717, 0.3625, 0.5017, 0.6037, 0.5500],
[0.6160, 0.4086, 0.8775, 0.3983, 0.3750, 0.3783, 0.5128, 0.4882],
[0.6147, 0.4081, 0.8537, 0.3400, 0.3663, 0.3150, 0.5142, 0.4875],
[0.6222, 0.4171, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633],
[0.6201, 0.4102, 0.7287, 0.2417, 0.4150, 0.2383, 0.6100, 0.5500],
[0.6196, 0.4094, 0.7563, 0.2817, 0.3938, 0.3183, 0.6012, 0.6183]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.017088345863157883
step: 12
running loss: 0.0014240288219298236
Train Steps: 12/90 Loss: 0.0014 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6195, 0.4101, 0.8650, 0.3917, 0.3575, 0.4033, 0.5800, 0.5650],
[0.6069, 0.3975, 0.8625, 0.5083, 0.4388, 0.5483, 0.5650, 0.4967],
[0.6083, 0.3957, 0.8638, 0.4950, 0.4363, 0.5083, 0.5346, 0.4980],
[0.6086, 0.3998, 0.8788, 0.4450, 0.4025, 0.4650, 0.5306, 0.5103],
[0.6189, 0.4049, 0.8888, 0.4417, 0.4213, 0.5200, 0.5988, 0.5633],
[0.6180, 0.4064, 0.7200, 0.2467, 0.4275, 0.2367, 0.5963, 0.6217],
[0.6193, 0.4034, 0.7757, 0.2347, 0.3733, 0.2919, 0.5930, 0.4926],
[0.6125, 0.3974, 0.7725, 0.2517, 0.3538, 0.3317, 0.5887, 0.5500]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6531, 0.4223, 0.9179, 0.4122, 0.3533, 0.3904, 0.6084, 0.5556],
[0.6554, 0.4147, 0.8955, 0.5243, 0.4580, 0.5364, 0.5704, 0.5223],
[0.6251, 0.3943, 0.9011, 0.4907, 0.4358, 0.4927, 0.5703, 0.4922],
[0.6102, 0.3983, 0.9248, 0.4518, 0.3971, 0.4422, 0.5567, 0.5213],
[0.6523, 0.4251, 0.9362, 0.4552, 0.4239, 0.5249, 0.6157, 0.5596],
[0.6320, 0.3951, 0.7458, 0.2448, 0.4413, 0.2426, 0.6295, 0.6072],
[0.5919, 0.3868, 0.8213, 0.2366, 0.3866, 0.2564, 0.6227, 0.5115],
[0.6126, 0.3744, 0.8217, 0.2681, 0.3642, 0.3385, 0.6378, 0.5634]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6195, 0.4101, 0.8650, 0.3917, 0.3575, 0.4033, 0.5800, 0.5650],
[0.6069, 0.3975, 0.8625, 0.5083, 0.4387, 0.5483, 0.5650, 0.4967],
[0.6083, 0.3957, 0.8637, 0.4950, 0.4363, 0.5083, 0.5346, 0.4980],
[0.6086, 0.3998, 0.8788, 0.4450, 0.4025, 0.4650, 0.5306, 0.5103],
[0.6189, 0.4049, 0.8888, 0.4417, 0.4212, 0.5200, 0.5987, 0.5633],
[0.6180, 0.4064, 0.7200, 0.2467, 0.4275, 0.2367, 0.5962, 0.6217],
[0.6193, 0.4034, 0.7757, 0.2347, 0.3733, 0.2919, 0.5930, 0.4926],
[0.6125, 0.3974, 0.7725, 0.2517, 0.3537, 0.3317, 0.5888, 0.5500]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.01765251744654961
step: 13
running loss: 0.001357885957426893
Train Steps: 13/90 Loss: 0.0014 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6200, 0.4059, 0.8700, 0.4900, 0.4163, 0.5000, 0.6162, 0.5467],
[0.6101, 0.4042, 0.7775, 0.2617, 0.3713, 0.2817, 0.5440, 0.5650],
[0.6199, 0.4015, 0.8716, 0.5228, 0.3833, 0.4772, 0.5883, 0.5148],
[0.6282, 0.4092, 0.8000, 0.2183, 0.4500, 0.2383, 0.6787, 0.5364],
[0.6293, 0.4024, 0.8750, 0.5000, 0.4012, 0.5733, 0.7121, 0.5633],
[0.6246, 0.4028, 0.8738, 0.4867, 0.4088, 0.5667, 0.6362, 0.5200],
[0.6254, 0.3993, 0.8988, 0.4767, 0.3987, 0.5517, 0.6955, 0.5285],
[0.6200, 0.4118, 0.8287, 0.4017, 0.3775, 0.2833, 0.5391, 0.5799]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6367, 0.4247, 0.8898, 0.4514, 0.4261, 0.5047, 0.5741, 0.5611],
[0.5919, 0.4006, 0.8134, 0.2667, 0.3914, 0.2788, 0.5439, 0.5663],
[0.6725, 0.4472, 0.9134, 0.4913, 0.3964, 0.4697, 0.5581, 0.5180],
[0.6398, 0.4302, 0.8322, 0.2005, 0.4468, 0.2317, 0.6397, 0.5476],
[0.6671, 0.4439, 0.9001, 0.4696, 0.4171, 0.5686, 0.6304, 0.5652],
[0.7045, 0.4583, 0.8897, 0.4612, 0.4242, 0.5617, 0.5993, 0.5274],
[0.6130, 0.4137, 0.9090, 0.4562, 0.4153, 0.5455, 0.6352, 0.5445],
[0.4926, 0.3300, 0.8518, 0.3653, 0.3680, 0.2756, 0.5241, 0.5692]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6199, 0.4059, 0.8700, 0.4900, 0.4162, 0.5000, 0.6162, 0.5467],
[0.6101, 0.4042, 0.7775, 0.2617, 0.3713, 0.2817, 0.5440, 0.5650],
[0.6199, 0.4015, 0.8716, 0.5228, 0.3833, 0.4772, 0.5883, 0.5148],
[0.6282, 0.4092, 0.8000, 0.2183, 0.4500, 0.2383, 0.6787, 0.5364],
[0.6293, 0.4024, 0.8750, 0.5000, 0.4013, 0.5733, 0.7121, 0.5633],
[0.6246, 0.4028, 0.8737, 0.4867, 0.4087, 0.5667, 0.6363, 0.5200],
[0.6254, 0.3993, 0.8988, 0.4767, 0.3988, 0.5517, 0.6955, 0.5285],
[0.6200, 0.4118, 0.8288, 0.4017, 0.3775, 0.2833, 0.5391, 0.5799]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.018795535230310634
step: 14
running loss: 0.0013425382307364739
Train Steps: 14/90 Loss: 0.0013 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6226, 0.4001, 0.8438, 0.5733, 0.3862, 0.4250, 0.5750, 0.5283],
[0.6072, 0.4029, 0.7037, 0.2150, 0.3912, 0.2267, 0.5516, 0.5507],
[0.6026, 0.3979, 0.8550, 0.4233, 0.3613, 0.5233, 0.5582, 0.4967],
[0.6296, 0.4060, 0.9100, 0.3267, 0.4726, 0.3367, 0.7446, 0.5355],
[0.6275, 0.4081, 0.8063, 0.2017, 0.4825, 0.1583, 0.6156, 0.4869],
[0.6229, 0.4198, 0.7662, 0.2700, 0.4700, 0.2133, 0.5675, 0.5783],
[ nan, nan, 0.8750, 0.2467, 0.5138, 0.2617, 0.7382, 0.5552],
[0.6250, 0.4131, 0.8688, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7229, 0.4724, 0.8251, 0.5350, 0.3827, 0.4518, 0.5353, 0.5470],
[0.6008, 0.4034, 0.6870, 0.1803, 0.3881, 0.2368, 0.5260, 0.5752],
[0.6170, 0.4062, 0.8478, 0.3946, 0.3342, 0.5308, 0.5184, 0.5252],
[0.6327, 0.4191, 0.8496, 0.2966, 0.4430, 0.3363, 0.6651, 0.5467],
[0.6231, 0.4200, 0.8101, 0.1875, 0.4821, 0.1824, 0.5935, 0.4996],
[0.5662, 0.3985, 0.7558, 0.2272, 0.4465, 0.2259, 0.5278, 0.5828],
[0.0313, 0.0332, 0.8566, 0.1995, 0.4916, 0.2640, 0.6464, 0.5660],
[0.6997, 0.4572, 0.8597, 0.2787, 0.4170, 0.2444, 0.5558, 0.5374]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6226, 0.4001, 0.8438, 0.5733, 0.3862, 0.4250, 0.5750, 0.5283],
[0.6072, 0.4029, 0.7038, 0.2150, 0.3913, 0.2267, 0.5516, 0.5507],
[0.6026, 0.3979, 0.8550, 0.4233, 0.3613, 0.5233, 0.5582, 0.4967],
[0.6296, 0.4060, 0.9100, 0.3267, 0.4726, 0.3367, 0.7446, 0.5355],
[0.6275, 0.4081, 0.8062, 0.2017, 0.4825, 0.1583, 0.6156, 0.4869],
[0.6229, 0.4198, 0.7663, 0.2700, 0.4700, 0.2133, 0.5675, 0.5783],
[0.0000, 0.0000, 0.8750, 0.2467, 0.5138, 0.2617, 0.7382, 0.5552],
[0.6250, 0.4131, 0.8687, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.019952477450715378
step: 15
running loss: 0.0013301651633810252
Train Steps: 15/90 Loss: 0.0013 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.8888, 0.3100, 0.5262, 0.2817, 0.7145, 0.6003],
[0.6222, 0.4172, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633],
[0.6364, 0.4154, 0.8938, 0.3717, 0.4500, 0.2583, 0.6448, 0.5285],
[0.6286, 0.4040, 0.8696, 0.3047, 0.3924, 0.2887, 0.6300, 0.5367],
[0.6339, 0.4102, 0.9088, 0.4767, 0.3925, 0.5283, 0.7509, 0.5390],
[0.6086, 0.3981, 0.8700, 0.4750, 0.4512, 0.5283, 0.5324, 0.5038],
[0.6200, 0.4071, 0.7338, 0.1917, 0.4200, 0.2450, 0.6150, 0.5517],
[0.6282, 0.4034, 0.7830, 0.2080, 0.4532, 0.2080, 0.6404, 0.5323]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.1825, 0.1387, 0.8564, 0.2657, 0.4663, 0.2815, 0.6554, 0.5692],
[0.5838, 0.4080, 0.8435, 0.4816, 0.3514, 0.4680, 0.5071, 0.5772],
[0.6640, 0.4447, 0.8520, 0.3452, 0.4214, 0.2683, 0.5725, 0.5439],
[0.6804, 0.4549, 0.8350, 0.2710, 0.3790, 0.2731, 0.6021, 0.5237],
[0.6128, 0.4227, 0.8599, 0.4379, 0.3931, 0.5277, 0.6612, 0.5508],
[0.5641, 0.3913, 0.8124, 0.4318, 0.4103, 0.5226, 0.4824, 0.5051],
[0.6186, 0.4344, 0.7072, 0.1699, 0.4006, 0.2641, 0.5666, 0.5555],
[0.6137, 0.4181, 0.7518, 0.1825, 0.4275, 0.2110, 0.5735, 0.5496]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.8888, 0.3100, 0.5263, 0.2817, 0.7145, 0.6003],
[0.6222, 0.4171, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633],
[0.6364, 0.4154, 0.8938, 0.3717, 0.4500, 0.2583, 0.6448, 0.5285],
[0.6286, 0.4040, 0.8696, 0.3047, 0.3924, 0.2887, 0.6300, 0.5367],
[0.6339, 0.4102, 0.9087, 0.4767, 0.3925, 0.5283, 0.7509, 0.5390],
[0.6086, 0.3981, 0.8700, 0.4750, 0.4512, 0.5283, 0.5324, 0.5038],
[0.6200, 0.4071, 0.7337, 0.1917, 0.4200, 0.2450, 0.6150, 0.5517],
[0.6282, 0.4034, 0.7830, 0.2080, 0.4532, 0.2080, 0.6404, 0.5323]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0020, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0020, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.021972051385091618
step: 16
running loss: 0.001373253211568226
Train Steps: 16/90 Loss: 0.0014 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6111, 0.4019, 0.8350, 0.3867, 0.3500, 0.4283, 0.5480, 0.5719],
[0.6269, 0.4073, 0.8900, 0.4933, 0.3625, 0.4183, 0.6288, 0.5150],
[0.6274, 0.4087, 0.8375, 0.5700, 0.4025, 0.4800, 0.5700, 0.6117],
[0.6082, 0.4024, 0.8738, 0.4017, 0.3688, 0.3950, 0.5306, 0.5136],
[0.6339, 0.4102, 0.9088, 0.4767, 0.3925, 0.5283, 0.7509, 0.5390],
[0.6371, 0.4092, 0.8337, 0.5850, 0.3950, 0.5117, 0.6559, 0.5262],
[0.6203, 0.4021, 0.8780, 0.5031, 0.3667, 0.3882, 0.5842, 0.5405],
[0.6129, 0.3930, 0.8769, 0.5105, 0.4146, 0.5642, 0.6000, 0.5082]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6298, 0.4151, 0.8153, 0.3393, 0.3600, 0.4291, 0.5379, 0.5698],
[0.6456, 0.4376, 0.8645, 0.4351, 0.3727, 0.4266, 0.6316, 0.5136],
[0.5620, 0.3916, 0.8048, 0.4880, 0.3995, 0.4805, 0.5509, 0.6130],
[0.6626, 0.4515, 0.8499, 0.3342, 0.3620, 0.3796, 0.5293, 0.5116],
[0.5962, 0.3994, 0.8743, 0.4134, 0.4052, 0.5115, 0.7128, 0.5608],
[0.6262, 0.4437, 0.8169, 0.4994, 0.3806, 0.5024, 0.6557, 0.5502],
[0.6586, 0.4178, 0.8642, 0.4511, 0.3658, 0.3891, 0.5872, 0.5320],
[0.6053, 0.3949, 0.8285, 0.4581, 0.4370, 0.5583, 0.6096, 0.5243]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6111, 0.4019, 0.8350, 0.3867, 0.3500, 0.4283, 0.5480, 0.5719],
[0.6269, 0.4073, 0.8900, 0.4933, 0.3625, 0.4183, 0.6288, 0.5150],
[0.6274, 0.4087, 0.8375, 0.5700, 0.4025, 0.4800, 0.5700, 0.6117],
[0.6082, 0.4024, 0.8737, 0.4017, 0.3688, 0.3950, 0.5306, 0.5136],
[0.6339, 0.4102, 0.9087, 0.4767, 0.3925, 0.5283, 0.7509, 0.5390],
[0.6371, 0.4092, 0.8338, 0.5850, 0.3950, 0.5117, 0.6559, 0.5262],
[0.6203, 0.4020, 0.8780, 0.5031, 0.3667, 0.3882, 0.5842, 0.5405],
[0.6129, 0.3930, 0.8769, 0.5105, 0.4146, 0.5642, 0.6000, 0.5082]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.022940666152862832
step: 17
running loss: 0.001349450950168402
Train Steps: 17/90 Loss: 0.0013 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6098, 0.3991, 0.8638, 0.4717, 0.4263, 0.4967, 0.5212, 0.5650],
[0.6097, 0.4000, 0.7325, 0.2667, 0.3450, 0.3517, 0.5284, 0.5045],
[0.6182, 0.4058, 0.8738, 0.4350, 0.3563, 0.3400, 0.5290, 0.5822],
[0.6151, 0.4058, 0.7068, 0.2680, 0.3400, 0.4083, 0.5775, 0.5733],
[ nan, nan, 0.7268, 0.2333, 0.4125, 0.1933, 0.5112, 0.5383],
[ nan, nan, 0.7515, 0.2708, 0.3987, 0.2267, 0.5162, 0.5567],
[0.6193, 0.4079, 0.7288, 0.2500, 0.4250, 0.2550, 0.5989, 0.6266],
[0.6189, 0.4049, 0.8888, 0.4417, 0.4213, 0.5200, 0.5988, 0.5633]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6877, 0.4486, 0.8495, 0.5078, 0.4421, 0.4954, 0.5811, 0.5105],
[0.5926, 0.3816, 0.7462, 0.2623, 0.3489, 0.3333, 0.5847, 0.5139],
[0.7007, 0.4712, 0.8677, 0.4622, 0.3739, 0.3210, 0.5782, 0.5522],
[0.6480, 0.4357, 0.7169, 0.2784, 0.3488, 0.3984, 0.6073, 0.5504],
[0.1842, 0.1286, 0.7313, 0.2295, 0.4224, 0.1709, 0.5615, 0.5122],
[0.0856, 0.0792, 0.7627, 0.2752, 0.4135, 0.2344, 0.5505, 0.5307],
[0.7567, 0.5055, 0.7287, 0.2531, 0.4355, 0.2495, 0.6603, 0.5967],
[0.6695, 0.4580, 0.8895, 0.4715, 0.4324, 0.5336, 0.6547, 0.5361]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6098, 0.3991, 0.8637, 0.4717, 0.4263, 0.4967, 0.5213, 0.5650],
[0.6097, 0.4000, 0.7325, 0.2667, 0.3450, 0.3517, 0.5284, 0.5045],
[0.6182, 0.4058, 0.8737, 0.4350, 0.3562, 0.3400, 0.5290, 0.5822],
[0.6151, 0.4058, 0.7068, 0.2680, 0.3400, 0.4083, 0.5775, 0.5733],
[0.0000, 0.0000, 0.7268, 0.2333, 0.4125, 0.1933, 0.5113, 0.5383],
[0.0000, 0.0000, 0.7515, 0.2708, 0.3988, 0.2267, 0.5163, 0.5567],
[0.6193, 0.4078, 0.7287, 0.2500, 0.4250, 0.2550, 0.5989, 0.6266],
[0.6189, 0.4049, 0.8888, 0.4417, 0.4212, 0.5200, 0.5987, 0.5633]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0024, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0024, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.025358807033626363
step: 18
running loss: 0.0014088226129792423
Train Steps: 18/90 Loss: 0.0014 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6282, 0.4029, 0.8988, 0.3000, 0.4250, 0.4183, 0.7042, 0.5575],
[0.6151, 0.4085, 0.8750, 0.4367, 0.3887, 0.4367, 0.5066, 0.5846],
[0.6179, 0.4008, 0.7505, 0.2678, 0.4368, 0.1891, 0.5831, 0.5263],
[0.6082, 0.4024, 0.8738, 0.4017, 0.3688, 0.3950, 0.5306, 0.5136],
[0.6221, 0.4107, 0.7788, 0.3033, 0.3950, 0.2817, 0.6075, 0.5517],
[0.6212, 0.4159, 0.8675, 0.5783, 0.4088, 0.4317, 0.5613, 0.5917],
[0.6201, 0.4116, 0.8725, 0.4733, 0.3700, 0.3217, 0.5386, 0.5767],
[0.6299, 0.4008, 0.8450, 0.5350, 0.4213, 0.5000, 0.6350, 0.5100]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5624, 0.3717, 0.8425, 0.3025, 0.4063, 0.4040, 0.7155, 0.5545],
[0.5104, 0.3487, 0.8494, 0.4525, 0.3910, 0.4377, 0.5365, 0.5834],
[0.5058, 0.3339, 0.7332, 0.2560, 0.4338, 0.1844, 0.6126, 0.5182],
[0.5532, 0.3823, 0.8483, 0.4023, 0.3636, 0.3770, 0.5509, 0.4996],
[0.6263, 0.4146, 0.7884, 0.2855, 0.4145, 0.2659, 0.6401, 0.5257],
[0.5362, 0.3845, 0.8102, 0.5580, 0.4090, 0.4167, 0.5855, 0.5826],
[0.5352, 0.3609, 0.8476, 0.4723, 0.3517, 0.3063, 0.5778, 0.5627],
[0.4725, 0.3160, 0.8095, 0.5373, 0.4074, 0.4968, 0.6818, 0.5003]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6282, 0.4029, 0.8988, 0.3000, 0.4250, 0.4183, 0.7042, 0.5575],
[0.6151, 0.4085, 0.8750, 0.4367, 0.3887, 0.4367, 0.5066, 0.5846],
[0.6179, 0.4008, 0.7505, 0.2678, 0.4368, 0.1891, 0.5831, 0.5263],
[0.6082, 0.4024, 0.8737, 0.4017, 0.3688, 0.3950, 0.5306, 0.5136],
[0.6221, 0.4107, 0.7788, 0.3033, 0.3950, 0.2817, 0.6075, 0.5517],
[0.6212, 0.4159, 0.8675, 0.5783, 0.4087, 0.4317, 0.5612, 0.5917],
[0.6201, 0.4116, 0.8725, 0.4733, 0.3700, 0.3217, 0.5386, 0.5767],
[0.6299, 0.4008, 0.8450, 0.5350, 0.4212, 0.5000, 0.6350, 0.5100]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0018, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0018, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.027124431653646752
step: 19
running loss: 0.001427601665981408
Train Steps: 19/90 Loss: 0.0014 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6260, 0.4106, 0.8025, 0.2583, 0.4550, 0.1867, 0.6281, 0.4869],
[0.6199, 0.4102, 0.8950, 0.4417, 0.4012, 0.5367, 0.6112, 0.5967],
[0.6165, 0.4106, 0.7575, 0.1733, 0.3838, 0.2650, 0.5680, 0.5116],
[0.6292, 0.4010, 0.8988, 0.4800, 0.3638, 0.3817, 0.6357, 0.5051],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3788, 0.4900, 0.7121, 0.5864],
[0.6308, 0.3990, 0.8688, 0.5183, 0.3950, 0.4983, 0.6388, 0.5133],
[0.6186, 0.4013, 0.8191, 0.3188, 0.4279, 0.2060, 0.5767, 0.5411],
[0.6136, 0.3955, 0.8400, 0.3267, 0.3500, 0.4200, 0.5863, 0.5467]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5778, 0.3690, 0.8085, 0.2754, 0.4514, 0.2019, 0.6591, 0.5103],
[0.4937, 0.3214, 0.8699, 0.5001, 0.4092, 0.5391, 0.6217, 0.6006],
[0.5210, 0.3367, 0.7454, 0.2287, 0.3928, 0.2534, 0.5894, 0.5159],
[0.5524, 0.3582, 0.8768, 0.5135, 0.3693, 0.3642, 0.6268, 0.5321],
[0.5612, 0.3727, 0.8623, 0.5504, 0.3960, 0.4826, 0.7284, 0.5798],
[0.5088, 0.3190, 0.8487, 0.5750, 0.4073, 0.5123, 0.6379, 0.5277],
[0.5967, 0.3906, 0.8153, 0.3364, 0.4398, 0.2178, 0.6045, 0.5534],
[0.5869, 0.3812, 0.8239, 0.3602, 0.3586, 0.4270, 0.5885, 0.5591]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6260, 0.4106, 0.8025, 0.2583, 0.4550, 0.1867, 0.6281, 0.4869],
[0.6199, 0.4102, 0.8950, 0.4417, 0.4013, 0.5367, 0.6112, 0.5967],
[0.6165, 0.4106, 0.7575, 0.1733, 0.3837, 0.2650, 0.5680, 0.5116],
[0.6292, 0.4010, 0.8988, 0.4800, 0.3638, 0.3817, 0.6357, 0.5051],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3787, 0.4900, 0.7121, 0.5864],
[0.6308, 0.3990, 0.8687, 0.5183, 0.3950, 0.4983, 0.6388, 0.5133],
[0.6186, 0.4013, 0.8191, 0.3188, 0.4279, 0.2060, 0.5767, 0.5411],
[0.6136, 0.3955, 0.8400, 0.3267, 0.3500, 0.4200, 0.5863, 0.5467]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.028719637513859197
step: 20
running loss: 0.0014359818756929598
Train Steps: 20/90 Loss: 0.0014 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6151, 0.4125, 0.8738, 0.4417, 0.3575, 0.3783, 0.5138, 0.5483],
[0.6262, 0.4085, 0.8438, 0.3150, 0.4025, 0.2633, 0.6339, 0.4810],
[0.6124, 0.4075, 0.7696, 0.4153, 0.3475, 0.3767, 0.5157, 0.5427],
[0.6125, 0.3974, 0.7725, 0.2517, 0.3538, 0.3317, 0.5887, 0.5500],
[ nan, nan, 0.7240, 0.2722, 0.3900, 0.2567, 0.5168, 0.5933],
[0.6148, 0.4076, 0.8666, 0.4820, 0.4138, 0.5067, 0.5250, 0.5767],
[0.6276, 0.4002, 0.8800, 0.5533, 0.3575, 0.4400, 0.6132, 0.4672],
[0.6113, 0.4104, 0.8650, 0.4250, 0.3925, 0.5967, 0.5787, 0.5116]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6311, 0.3910, 0.8631, 0.4934, 0.3649, 0.3741, 0.5482, 0.5658],
[ 0.6389, 0.4029, 0.8508, 0.3148, 0.4316, 0.2565, 0.6621, 0.4937],
[ 0.6481, 0.4064, 0.8025, 0.4326, 0.3589, 0.3769, 0.5521, 0.5612],
[ 0.6320, 0.3742, 0.7733, 0.2867, 0.3728, 0.3405, 0.6450, 0.5739],
[ 0.0239, -0.0033, 0.7480, 0.3124, 0.3933, 0.2245, 0.5602, 0.5838],
[ 0.6112, 0.3836, 0.8664, 0.5335, 0.4437, 0.5030, 0.5833, 0.5835],
[ 0.6534, 0.3981, 0.8733, 0.5679, 0.3811, 0.4323, 0.6578, 0.5283],
[ 0.6353, 0.4044, 0.8751, 0.4401, 0.4185, 0.5854, 0.6248, 0.5464]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6151, 0.4125, 0.8737, 0.4417, 0.3575, 0.3783, 0.5138, 0.5483],
[0.6262, 0.4085, 0.8438, 0.3150, 0.4025, 0.2633, 0.6339, 0.4810],
[0.6124, 0.4075, 0.7696, 0.4153, 0.3475, 0.3767, 0.5157, 0.5427],
[0.6125, 0.3974, 0.7725, 0.2517, 0.3537, 0.3317, 0.5888, 0.5500],
[0.0000, 0.0000, 0.7240, 0.2722, 0.3900, 0.2567, 0.5168, 0.5933],
[0.6148, 0.4076, 0.8666, 0.4820, 0.4137, 0.5067, 0.5250, 0.5767],
[0.6276, 0.4002, 0.8800, 0.5533, 0.3575, 0.4400, 0.6132, 0.4672],
[0.6113, 0.4104, 0.8650, 0.4250, 0.3925, 0.5967, 0.5787, 0.5116]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.029402486368780956
step: 21
running loss: 0.0014001183985133789
Train Steps: 21/90 Loss: 0.0014 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6264, 0.4248, 0.8938, 0.4183, 0.3875, 0.4100, 0.5400, 0.5350],
[0.6086, 0.3981, 0.8700, 0.4750, 0.4512, 0.5283, 0.5324, 0.5038],
[0.6197, 0.3930, 0.8793, 0.4736, 0.4152, 0.5464, 0.6308, 0.5235],
[0.6113, 0.4088, 0.6859, 0.2208, 0.4363, 0.1700, 0.5188, 0.5533],
[0.6163, 0.4006, 0.8788, 0.4683, 0.3663, 0.4883, 0.5887, 0.5017],
[ nan, nan, 0.8363, 0.3317, 0.3563, 0.3367, 0.5329, 0.5142],
[0.6204, 0.4110, 0.7913, 0.2667, 0.4062, 0.2500, 0.6225, 0.5367],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3513, 0.4050, 0.6112, 0.5500]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7024, 0.4579, 0.8919, 0.4660, 0.3621, 0.3956, 0.5566, 0.5544],
[0.6047, 0.3683, 0.8764, 0.5155, 0.4330, 0.5081, 0.5417, 0.5083],
[0.5885, 0.3489, 0.9078, 0.5210, 0.4192, 0.5181, 0.6419, 0.5389],
[0.2829, 0.1731, 0.7203, 0.2559, 0.4322, 0.1594, 0.5465, 0.5538],
[0.6801, 0.4293, 0.8756, 0.5013, 0.3782, 0.4941, 0.5780, 0.5519],
[0.3500, 0.2140, 0.8230, 0.3471, 0.3318, 0.3327, 0.5382, 0.5294],
[0.6547, 0.4065, 0.8151, 0.2838, 0.4189, 0.2514, 0.6232, 0.5550],
[0.5903, 0.3585, 0.7902, 0.3010, 0.3526, 0.3983, 0.6259, 0.5612]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6264, 0.4248, 0.8938, 0.4183, 0.3875, 0.4100, 0.5400, 0.5350],
[0.6086, 0.3981, 0.8700, 0.4750, 0.4512, 0.5283, 0.5324, 0.5038],
[0.6197, 0.3930, 0.8793, 0.4736, 0.4152, 0.5464, 0.6308, 0.5235],
[0.6113, 0.4088, 0.6859, 0.2208, 0.4363, 0.1700, 0.5188, 0.5533],
[0.6163, 0.4006, 0.8788, 0.4683, 0.3663, 0.4883, 0.5888, 0.5017],
[0.0000, 0.0000, 0.8363, 0.3317, 0.3562, 0.3367, 0.5329, 0.5142],
[0.6204, 0.4110, 0.7912, 0.2667, 0.4062, 0.2500, 0.6225, 0.5367],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3512, 0.4050, 0.6112, 0.5500]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0058, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0058, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.035240815341239795
step: 22
running loss: 0.001601855242783627
Train Steps: 22/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6266, 0.4067, 0.8588, 0.2867, 0.4300, 0.2850, 0.6325, 0.5267],
[0.6124, 0.4075, 0.7696, 0.4153, 0.3475, 0.3767, 0.5157, 0.5427],
[0.6200, 0.4112, 0.8862, 0.4100, 0.3638, 0.4917, 0.6088, 0.6050],
[0.6201, 0.4050, 0.7757, 0.2234, 0.4459, 0.1798, 0.5975, 0.5426],
[0.6113, 0.4088, 0.6859, 0.2208, 0.4363, 0.1700, 0.5188, 0.5533],
[0.6299, 0.4008, 0.8450, 0.5350, 0.4213, 0.5000, 0.6350, 0.5100],
[0.6284, 0.4093, 0.8900, 0.4700, 0.3650, 0.3850, 0.6212, 0.5167],
[0.6154, 0.4112, 0.7037, 0.2317, 0.4238, 0.1833, 0.5350, 0.5600]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5260, 0.3243, 0.8976, 0.3190, 0.4337, 0.2847, 0.6278, 0.5195],
[0.5957, 0.3750, 0.8220, 0.4138, 0.3370, 0.3987, 0.4945, 0.5374],
[0.5451, 0.3495, 0.9044, 0.4324, 0.3525, 0.5072, 0.5708, 0.5915],
[0.6046, 0.3757, 0.7889, 0.2466, 0.4441, 0.2022, 0.5529, 0.5444],
[0.3285, 0.2059, 0.7271, 0.2460, 0.4224, 0.1879, 0.5087, 0.5453],
[0.5804, 0.3538, 0.8625, 0.5487, 0.4006, 0.5067, 0.6161, 0.5008],
[0.5873, 0.3687, 0.9221, 0.4838, 0.3646, 0.3840, 0.5822, 0.4999],
[0.5823, 0.3752, 0.7353, 0.2549, 0.4104, 0.2001, 0.5275, 0.5490]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6266, 0.4067, 0.8587, 0.2867, 0.4300, 0.2850, 0.6325, 0.5267],
[0.6124, 0.4075, 0.7696, 0.4153, 0.3475, 0.3767, 0.5157, 0.5427],
[0.6200, 0.4112, 0.8863, 0.4100, 0.3638, 0.4917, 0.6087, 0.6050],
[0.6201, 0.4050, 0.7757, 0.2234, 0.4459, 0.1798, 0.5975, 0.5426],
[0.6113, 0.4088, 0.6859, 0.2208, 0.4363, 0.1700, 0.5188, 0.5533],
[0.6299, 0.4008, 0.8450, 0.5350, 0.4212, 0.5000, 0.6350, 0.5100],
[0.6284, 0.4092, 0.8900, 0.4700, 0.3650, 0.3850, 0.6212, 0.5167],
[0.6154, 0.4112, 0.7038, 0.2317, 0.4238, 0.1833, 0.5350, 0.5600]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0028, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0028, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03808972876868211
step: 23
running loss: 0.0016560751638557438
Train Steps: 23/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6202, 0.4066, 0.8398, 0.2648, 0.3925, 0.2627, 0.5845, 0.5124],
[0.6203, 0.4076, 0.8611, 0.2878, 0.4050, 0.2554, 0.5907, 0.5496],
[ nan, nan, 0.6488, 0.1817, 0.4325, 0.1867, 0.5475, 0.5733],
[0.6296, 0.4008, 0.9150, 0.4317, 0.4263, 0.3050, 0.7256, 0.5413],
[0.6109, 0.4041, 0.6975, 0.3167, 0.3513, 0.3383, 0.5153, 0.5319],
[0.6332, 0.4128, 0.9200, 0.3517, 0.4400, 0.3833, 0.7461, 0.5494],
[0.6185, 0.4079, 0.8838, 0.4617, 0.4838, 0.5650, 0.6175, 0.5850],
[0.6151, 0.4058, 0.7068, 0.2680, 0.3400, 0.4083, 0.5775, 0.5733]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5628, 0.3788, 0.8062, 0.2812, 0.3902, 0.2384, 0.5447, 0.4986],
[0.5909, 0.3884, 0.8611, 0.2857, 0.3847, 0.2486, 0.5559, 0.5137],
[0.0569, 0.0567, 0.7019, 0.2182, 0.4347, 0.1737, 0.5344, 0.5591],
[0.6344, 0.4047, 0.9095, 0.4098, 0.4022, 0.2848, 0.6425, 0.5178],
[0.5850, 0.3834, 0.7315, 0.3019, 0.3443, 0.3362, 0.4449, 0.4935],
[0.6786, 0.4350, 0.8980, 0.3853, 0.4181, 0.3716, 0.6707, 0.5098],
[0.5914, 0.3821, 0.9013, 0.4644, 0.4535, 0.5465, 0.5600, 0.5473],
[0.6159, 0.4107, 0.7133, 0.2632, 0.3203, 0.3963, 0.5143, 0.5451]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6202, 0.4066, 0.8398, 0.2648, 0.3925, 0.2627, 0.5845, 0.5124],
[0.6203, 0.4076, 0.8611, 0.2878, 0.4050, 0.2554, 0.5907, 0.5496],
[0.0000, 0.0000, 0.6488, 0.1817, 0.4325, 0.1867, 0.5475, 0.5733],
[0.6296, 0.4008, 0.9150, 0.4317, 0.4263, 0.3050, 0.7256, 0.5413],
[0.6109, 0.4041, 0.6975, 0.3167, 0.3512, 0.3383, 0.5153, 0.5319],
[0.6332, 0.4128, 0.9200, 0.3517, 0.4400, 0.3833, 0.7461, 0.5494],
[0.6184, 0.4079, 0.8838, 0.4617, 0.4837, 0.5650, 0.6175, 0.5850],
[0.6151, 0.4058, 0.7068, 0.2680, 0.3400, 0.4083, 0.5775, 0.5733]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.039125452836742625
step: 24
running loss: 0.0016302272015309427
Train Steps: 24/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6185, 0.4129, 0.8900, 0.4567, 0.3937, 0.5417, 0.5734, 0.5110],
[0.6193, 0.4079, 0.7288, 0.2500, 0.4250, 0.2550, 0.5989, 0.6266],
[0.6136, 0.3955, 0.8400, 0.3267, 0.3500, 0.4200, 0.5863, 0.5467],
[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586],
[0.6286, 0.4055, 0.9000, 0.4717, 0.3763, 0.4683, 0.7018, 0.5494],
[0.6187, 0.4104, 0.7126, 0.2069, 0.3950, 0.2517, 0.5913, 0.5683],
[0.6236, 0.4081, 0.8575, 0.3000, 0.3713, 0.3033, 0.5550, 0.5633],
[0.6146, 0.4124, 0.8800, 0.4867, 0.3800, 0.4500, 0.5106, 0.5524]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5659, 0.3794, 0.9019, 0.4457, 0.3871, 0.5255, 0.5347, 0.5126],
[0.6188, 0.4026, 0.7115, 0.2296, 0.4164, 0.2545, 0.5583, 0.6091],
[0.6343, 0.3958, 0.8512, 0.3105, 0.3461, 0.4123, 0.5670, 0.5198],
[0.6368, 0.4226, 0.8449, 0.2465, 0.4428, 0.2691, 0.6653, 0.5504],
[0.5647, 0.3627, 0.8970, 0.4503, 0.3598, 0.4549, 0.6685, 0.5267],
[0.6035, 0.3871, 0.7022, 0.1994, 0.3821, 0.2455, 0.5232, 0.5336],
[0.5298, 0.3530, 0.8426, 0.3095, 0.3614, 0.3037, 0.5191, 0.5351],
[0.5681, 0.3602, 0.8807, 0.4949, 0.3830, 0.4460, 0.4697, 0.5351]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6186, 0.4129, 0.8900, 0.4567, 0.3938, 0.5417, 0.5734, 0.5110],
[0.6193, 0.4078, 0.7287, 0.2500, 0.4250, 0.2550, 0.5989, 0.6266],
[0.6136, 0.3955, 0.8400, 0.3267, 0.3500, 0.4200, 0.5863, 0.5467],
[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586],
[0.6286, 0.4055, 0.9000, 0.4717, 0.3762, 0.4683, 0.7018, 0.5494],
[0.6187, 0.4103, 0.7126, 0.2069, 0.3950, 0.2517, 0.5913, 0.5683],
[0.6236, 0.4081, 0.8575, 0.3000, 0.3713, 0.3033, 0.5550, 0.5633],
[0.6146, 0.4124, 0.8800, 0.4867, 0.3800, 0.4500, 0.5106, 0.5524]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03991389213479124
step: 25
running loss: 0.0015965556853916496
Train Steps: 25/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6230, 0.4113, 0.7213, 0.1983, 0.4325, 0.2367, 0.6262, 0.5400],
[ nan, nan, 0.9088, 0.3783, 0.4562, 0.2617, 0.6741, 0.5575],
[0.6223, 0.4130, 0.8100, 0.2983, 0.3525, 0.3900, 0.5694, 0.5103],
[0.6193, 0.4079, 0.7288, 0.2500, 0.4250, 0.2550, 0.5989, 0.6266],
[0.6304, 0.4029, 0.8413, 0.5217, 0.4125, 0.5617, 0.7089, 0.5679],
[0.6198, 0.4075, 0.8650, 0.5617, 0.4150, 0.4367, 0.5450, 0.5650],
[0.6218, 0.4185, 0.7338, 0.2650, 0.4625, 0.1950, 0.5687, 0.5800],
[0.6289, 0.4032, 0.8419, 0.5446, 0.4075, 0.5017, 0.6312, 0.5117]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5831, 0.3913, 0.7295, 0.1769, 0.4231, 0.2429, 0.5962, 0.5176],
[0.3479, 0.2480, 0.9087, 0.3481, 0.4302, 0.2771, 0.6268, 0.5512],
[0.5968, 0.4228, 0.8091, 0.2909, 0.3452, 0.4028, 0.5369, 0.5207],
[0.6655, 0.4478, 0.7199, 0.2050, 0.4058, 0.2662, 0.5594, 0.6024],
[0.6753, 0.4789, 0.8746, 0.4532, 0.3920, 0.5765, 0.6450, 0.5538],
[0.6214, 0.4176, 0.8670, 0.5141, 0.3903, 0.4475, 0.5306, 0.5421],
[0.5894, 0.4003, 0.7401, 0.1952, 0.4385, 0.2045, 0.5250, 0.5758],
[0.6596, 0.4278, 0.8682, 0.4764, 0.3848, 0.4938, 0.6082, 0.5017]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6230, 0.4113, 0.7212, 0.1983, 0.4325, 0.2367, 0.6263, 0.5400],
[0.0000, 0.0000, 0.9087, 0.3783, 0.4563, 0.2617, 0.6741, 0.5575],
[0.6223, 0.4130, 0.8100, 0.2983, 0.3525, 0.3900, 0.5694, 0.5103],
[0.6193, 0.4078, 0.7287, 0.2500, 0.4250, 0.2550, 0.5989, 0.6266],
[0.6304, 0.4029, 0.8413, 0.5217, 0.4125, 0.5617, 0.7089, 0.5679],
[0.6198, 0.4075, 0.8650, 0.5617, 0.4150, 0.4367, 0.5450, 0.5650],
[0.6218, 0.4185, 0.7337, 0.2650, 0.4625, 0.1950, 0.5688, 0.5800],
[0.6289, 0.4031, 0.8419, 0.5446, 0.4075, 0.5017, 0.6313, 0.5117]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0038, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0038, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04367428258410655
step: 26
running loss: 0.0016797800993887135
Train Steps: 26/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6128, 0.4022, 0.8738, 0.5067, 0.4983, 0.5231, 0.5364, 0.5064],
[0.6026, 0.3979, 0.8550, 0.4233, 0.3613, 0.5233, 0.5582, 0.4967],
[0.6177, 0.4086, 0.8738, 0.3950, 0.3775, 0.5600, 0.6225, 0.5700],
[0.6211, 0.4069, 0.8750, 0.5117, 0.4150, 0.4900, 0.5875, 0.5167],
[0.6199, 0.4112, 0.8475, 0.3717, 0.3550, 0.4350, 0.6063, 0.6083],
[0.6186, 0.4013, 0.8191, 0.3188, 0.4279, 0.2060, 0.5767, 0.5411],
[0.6083, 0.3957, 0.8638, 0.4950, 0.4363, 0.5083, 0.5346, 0.4980],
[0.6273, 0.4110, 0.8900, 0.3817, 0.4188, 0.2167, 0.5858, 0.4835]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6200, 0.4533, 0.8285, 0.4511, 0.4742, 0.4791, 0.5561, 0.5512],
[0.5848, 0.3958, 0.8567, 0.3728, 0.3393, 0.5062, 0.5970, 0.5217],
[0.6453, 0.4443, 0.8480, 0.3489, 0.3609, 0.5387, 0.6867, 0.5467],
[0.5991, 0.4077, 0.8601, 0.4618, 0.3996, 0.4926, 0.6376, 0.5499],
[0.6198, 0.4574, 0.8238, 0.3098, 0.3500, 0.4181, 0.6127, 0.6146],
[0.5995, 0.4142, 0.7769, 0.2683, 0.4217, 0.1999, 0.5966, 0.5539],
[0.6304, 0.4276, 0.8377, 0.4263, 0.4319, 0.5067, 0.5758, 0.5189],
[0.6700, 0.4491, 0.8450, 0.3254, 0.4215, 0.2076, 0.6212, 0.5116]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6128, 0.4022, 0.8737, 0.5067, 0.4983, 0.5231, 0.5364, 0.5064],
[0.6026, 0.3979, 0.8550, 0.4233, 0.3613, 0.5233, 0.5582, 0.4967],
[0.6177, 0.4085, 0.8737, 0.3950, 0.3775, 0.5600, 0.6225, 0.5700],
[0.6211, 0.4069, 0.8750, 0.5117, 0.4150, 0.4900, 0.5875, 0.5167],
[0.6199, 0.4112, 0.8475, 0.3717, 0.3550, 0.4350, 0.6062, 0.6083],
[0.6186, 0.4013, 0.8191, 0.3188, 0.4279, 0.2060, 0.5767, 0.5411],
[0.6083, 0.3957, 0.8637, 0.4950, 0.4363, 0.5083, 0.5346, 0.4980],
[0.6273, 0.4110, 0.8900, 0.3817, 0.4187, 0.2167, 0.5858, 0.4835]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04473406620672904
step: 27
running loss: 0.0016568172669158903
Train Steps: 27/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6299, 0.4303, 0.7963, 0.3933, 0.4850, 0.2283, 0.5480, 0.6222],
[0.6364, 0.4144, 0.8625, 0.3083, 0.4913, 0.2000, 0.6448, 0.5274],
[0.6193, 0.4050, 0.7313, 0.2433, 0.4075, 0.2117, 0.5649, 0.5656],
[0.6284, 0.4093, 0.8900, 0.4700, 0.3650, 0.3850, 0.6212, 0.5167],
[0.6263, 0.4057, 0.8800, 0.3833, 0.3650, 0.3717, 0.6375, 0.4804],
[0.6154, 0.4112, 0.7037, 0.2317, 0.4238, 0.1833, 0.5350, 0.5600],
[0.6093, 0.3990, 0.8400, 0.4333, 0.3688, 0.4633, 0.5560, 0.5656],
[0.6346, 0.4165, 0.9138, 0.3983, 0.3875, 0.4317, 0.7469, 0.5471]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6745, 0.4781, 0.7742, 0.3606, 0.4799, 0.2929, 0.5665, 0.6555],
[0.5573, 0.3864, 0.8266, 0.2973, 0.4794, 0.2549, 0.6550, 0.5509],
[0.6332, 0.4213, 0.7079, 0.2312, 0.4146, 0.2592, 0.5788, 0.5784],
[0.5261, 0.3617, 0.8744, 0.4450, 0.3764, 0.4234, 0.6246, 0.5245],
[0.6037, 0.4098, 0.8713, 0.3536, 0.3686, 0.4002, 0.6372, 0.5027],
[0.7105, 0.4971, 0.6866, 0.2331, 0.4318, 0.2278, 0.5594, 0.5842],
[0.5790, 0.3899, 0.8336, 0.3894, 0.3639, 0.5031, 0.5720, 0.5713],
[0.5605, 0.3826, 0.8994, 0.3863, 0.4046, 0.4768, 0.7165, 0.5493]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6299, 0.4303, 0.7962, 0.3933, 0.4850, 0.2283, 0.5480, 0.6222],
[0.6364, 0.4144, 0.8625, 0.3083, 0.4913, 0.2000, 0.6448, 0.5274],
[0.6193, 0.4050, 0.7312, 0.2433, 0.4075, 0.2117, 0.5649, 0.5656],
[0.6284, 0.4092, 0.8900, 0.4700, 0.3650, 0.3850, 0.6212, 0.5167],
[0.6263, 0.4057, 0.8800, 0.3833, 0.3650, 0.3717, 0.6375, 0.4804],
[0.6154, 0.4112, 0.7038, 0.2317, 0.4238, 0.1833, 0.5350, 0.5600],
[0.6093, 0.3990, 0.8400, 0.4333, 0.3688, 0.4633, 0.5560, 0.5656],
[0.6346, 0.4165, 0.9137, 0.3983, 0.3875, 0.4317, 0.7469, 0.5471]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.045994794316357
step: 28
running loss: 0.0016426712255841786
Train Steps: 28/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6086, 0.3998, 0.8788, 0.4450, 0.4025, 0.4650, 0.5306, 0.5103],
[0.6129, 0.4063, 0.8738, 0.5250, 0.4313, 0.4733, 0.5230, 0.5874],
[0.6076, 0.3958, 0.8700, 0.4667, 0.4546, 0.5046, 0.5231, 0.4960],
[0.6160, 0.4093, 0.8314, 0.4417, 0.3675, 0.4583, 0.5250, 0.5808],
[0.6286, 0.3977, 0.9038, 0.4733, 0.3900, 0.4150, 0.7074, 0.5320],
[0.6175, 0.3997, 0.6737, 0.2500, 0.4313, 0.1933, 0.5513, 0.5750],
[0.6293, 0.4024, 0.8750, 0.5000, 0.4012, 0.5733, 0.7121, 0.5633],
[ nan, nan, 0.7553, 0.2722, 0.3875, 0.2550, 0.5125, 0.5633]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6088, 0.4196, 0.8702, 0.4265, 0.4201, 0.4764, 0.5855, 0.5290],
[0.7093, 0.4789, 0.8781, 0.5137, 0.4596, 0.4663, 0.5868, 0.5960],
[0.7140, 0.4928, 0.8827, 0.4662, 0.4619, 0.4862, 0.6021, 0.5137],
[0.7183, 0.4751, 0.8284, 0.4473, 0.3919, 0.4522, 0.5970, 0.5669],
[0.6877, 0.4502, 0.8986, 0.4377, 0.3943, 0.4305, 0.7234, 0.5148],
[0.7816, 0.5401, 0.6711, 0.2598, 0.4490, 0.1916, 0.5840, 0.5908],
[0.7330, 0.4897, 0.8921, 0.4890, 0.4254, 0.5871, 0.7601, 0.5764],
[0.1528, 0.1124, 0.7438, 0.2600, 0.3938, 0.2913, 0.5318, 0.5738]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6086, 0.3998, 0.8788, 0.4450, 0.4025, 0.4650, 0.5306, 0.5103],
[0.6130, 0.4063, 0.8737, 0.5250, 0.4313, 0.4733, 0.5230, 0.5874],
[0.6076, 0.3958, 0.8700, 0.4667, 0.4546, 0.5046, 0.5231, 0.4960],
[0.6160, 0.4092, 0.8314, 0.4417, 0.3675, 0.4583, 0.5250, 0.5808],
[0.6286, 0.3977, 0.9038, 0.4733, 0.3900, 0.4150, 0.7074, 0.5320],
[0.6175, 0.3997, 0.6737, 0.2500, 0.4313, 0.1933, 0.5512, 0.5750],
[0.6293, 0.4024, 0.8750, 0.5000, 0.4013, 0.5733, 0.7121, 0.5633],
[0.0000, 0.0000, 0.7553, 0.2722, 0.3875, 0.2550, 0.5125, 0.5633]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0030, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0030, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.048961690947180614
step: 29
running loss: 0.001688334170592435
Train Steps: 29/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6196, 0.4090, 0.8450, 0.3900, 0.3575, 0.3933, 0.5975, 0.5583],
[0.6122, 0.3993, 0.8738, 0.4667, 0.4517, 0.4879, 0.5155, 0.4927],
[0.6201, 0.4004, 0.8786, 0.5043, 0.3833, 0.5138, 0.5997, 0.5092],
[0.6274, 0.4099, 0.8625, 0.3233, 0.4400, 0.1983, 0.5876, 0.4869],
[0.6263, 0.4065, 0.9038, 0.4317, 0.3588, 0.4550, 0.6325, 0.5250],
[0.6261, 0.3987, 0.9045, 0.4208, 0.3600, 0.4633, 0.6570, 0.5162],
[ nan, nan, 0.7512, 0.2117, 0.4288, 0.2000, 0.5600, 0.5617],
[0.6109, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6794, 0.4479, 0.8627, 0.3964, 0.3654, 0.3532, 0.6276, 0.5969],
[0.6532, 0.4360, 0.8675, 0.4889, 0.4654, 0.5083, 0.5451, 0.5391],
[0.6788, 0.4359, 0.8759, 0.5463, 0.4182, 0.5275, 0.6290, 0.5163],
[0.6798, 0.4425, 0.8446, 0.3496, 0.4765, 0.2144, 0.6339, 0.5350],
[0.6577, 0.4384, 0.8928, 0.4528, 0.4095, 0.4527, 0.6980, 0.5613],
[0.6829, 0.4486, 0.8871, 0.4562, 0.3815, 0.4578, 0.7193, 0.5286],
[0.3316, 0.2288, 0.7307, 0.2535, 0.4495, 0.2235, 0.5810, 0.5954],
[0.6351, 0.4448, 0.8648, 0.4567, 0.4051, 0.4139, 0.5898, 0.5463]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6196, 0.4090, 0.8450, 0.3900, 0.3575, 0.3933, 0.5975, 0.5583],
[0.6122, 0.3993, 0.8737, 0.4667, 0.4517, 0.4879, 0.5155, 0.4927],
[0.6201, 0.4004, 0.8786, 0.5043, 0.3833, 0.5138, 0.5997, 0.5092],
[0.6274, 0.4099, 0.8625, 0.3233, 0.4400, 0.1983, 0.5876, 0.4869],
[0.6263, 0.4065, 0.9038, 0.4317, 0.3587, 0.4550, 0.6325, 0.5250],
[0.6261, 0.3987, 0.9045, 0.4208, 0.3600, 0.4633, 0.6570, 0.5162],
[0.0000, 0.0000, 0.7513, 0.2117, 0.4288, 0.2000, 0.5600, 0.5617],
[0.6108, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0036, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0036, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05260280644870363
step: 30
running loss: 0.0017534268816234543
Train Steps: 30/90 Loss: 0.0018 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6200, 0.4098, 0.8237, 0.2917, 0.4012, 0.2967, 0.6000, 0.5683],
[0.6203, 0.4021, 0.8780, 0.5031, 0.3667, 0.3882, 0.5842, 0.5405],
[0.6219, 0.4097, 0.8738, 0.3400, 0.3563, 0.4117, 0.5975, 0.5683],
[0.6357, 0.4139, 0.8450, 0.5883, 0.3775, 0.4950, 0.6488, 0.5297],
[0.6275, 0.4157, 0.8337, 0.5800, 0.3763, 0.4200, 0.5547, 0.6125],
[0.6212, 0.4171, 0.7875, 0.3633, 0.3813, 0.2933, 0.5675, 0.5700],
[0.6201, 0.4029, 0.8776, 0.4602, 0.3683, 0.4203, 0.5938, 0.5450],
[0.6129, 0.3930, 0.8769, 0.5105, 0.4146, 0.5642, 0.6000, 0.5082]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5934, 0.3907, 0.8409, 0.3052, 0.4328, 0.2824, 0.6257, 0.5610],
[0.5742, 0.3419, 0.8959, 0.5044, 0.3988, 0.3896, 0.5758, 0.5160],
[0.5488, 0.3516, 0.8657, 0.3616, 0.3794, 0.3953, 0.6189, 0.5567],
[0.6236, 0.3822, 0.8468, 0.5635, 0.4088, 0.4823, 0.6499, 0.5146],
[0.7318, 0.4671, 0.8511, 0.5613, 0.4100, 0.4089, 0.5688, 0.5884],
[0.6320, 0.3917, 0.8081, 0.3804, 0.4160, 0.2909, 0.5750, 0.5517],
[0.6117, 0.3748, 0.8802, 0.4653, 0.4100, 0.4083, 0.6179, 0.5411],
[0.6195, 0.3790, 0.8797, 0.5160, 0.4637, 0.5493, 0.6130, 0.5171]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6200, 0.4098, 0.8238, 0.2917, 0.4013, 0.2967, 0.6000, 0.5683],
[0.6203, 0.4020, 0.8780, 0.5031, 0.3667, 0.3882, 0.5842, 0.5405],
[0.6219, 0.4097, 0.8737, 0.3400, 0.3562, 0.4117, 0.5975, 0.5683],
[0.6357, 0.4139, 0.8450, 0.5883, 0.3775, 0.4950, 0.6488, 0.5297],
[0.6275, 0.4157, 0.8338, 0.5800, 0.3762, 0.4200, 0.5547, 0.6125],
[0.6212, 0.4171, 0.7875, 0.3633, 0.3812, 0.2933, 0.5675, 0.5700],
[0.6201, 0.4029, 0.8776, 0.4602, 0.3683, 0.4203, 0.5938, 0.5450],
[0.6129, 0.3930, 0.8769, 0.5105, 0.4146, 0.5642, 0.6000, 0.5082]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05339707116945647
step: 31
running loss: 0.0017224861667566602
Train Steps: 31/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6350, 0.4144, 0.9250, 0.4100, 0.4125, 0.3750, 0.7129, 0.5945],
[0.6069, 0.3975, 0.8625, 0.5083, 0.4388, 0.5483, 0.5650, 0.4967],
[0.6275, 0.4071, 0.8075, 0.2100, 0.4700, 0.1533, 0.6148, 0.4834],
[0.6229, 0.4198, 0.7662, 0.2700, 0.4700, 0.2133, 0.5675, 0.5783],
[0.6129, 0.4114, 0.6950, 0.2467, 0.4050, 0.2133, 0.5363, 0.5550],
[0.6165, 0.4106, 0.7575, 0.1733, 0.3838, 0.2650, 0.5680, 0.5116],
[0.6127, 0.4119, 0.8650, 0.5300, 0.4512, 0.5250, 0.5260, 0.5461],
[0.6201, 0.4151, 0.8588, 0.5467, 0.3700, 0.3950, 0.5637, 0.5933]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4726, 0.2672, 0.9171, 0.4492, 0.4305, 0.3561, 0.7157, 0.5673],
[0.5934, 0.3507, 0.8860, 0.5450, 0.4450, 0.5328, 0.5489, 0.5182],
[0.6378, 0.3892, 0.8093, 0.2568, 0.4691, 0.1763, 0.6213, 0.4853],
[0.5002, 0.3126, 0.7706, 0.3071, 0.4582, 0.2126, 0.5596, 0.5627],
[0.6113, 0.3908, 0.7203, 0.3242, 0.4085, 0.2067, 0.5273, 0.5523],
[0.5958, 0.3624, 0.7685, 0.2393, 0.3788, 0.2428, 0.5749, 0.4980],
[0.5660, 0.3472, 0.8770, 0.5506, 0.4446, 0.4987, 0.5519, 0.5381],
[0.5380, 0.3342, 0.8785, 0.5946, 0.3659, 0.3793, 0.5535, 0.5536]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6350, 0.4144, 0.9250, 0.4100, 0.4125, 0.3750, 0.7129, 0.5945],
[0.6069, 0.3975, 0.8625, 0.5083, 0.4387, 0.5483, 0.5650, 0.4967],
[0.6275, 0.4071, 0.8075, 0.2100, 0.4700, 0.1533, 0.6148, 0.4834],
[0.6229, 0.4198, 0.7663, 0.2700, 0.4700, 0.2133, 0.5675, 0.5783],
[0.6129, 0.4114, 0.6950, 0.2467, 0.4050, 0.2133, 0.5362, 0.5550],
[0.6165, 0.4106, 0.7575, 0.1733, 0.3837, 0.2650, 0.5680, 0.5116],
[0.6127, 0.4119, 0.8650, 0.5300, 0.4512, 0.5250, 0.5260, 0.5461],
[0.6202, 0.4151, 0.8587, 0.5467, 0.3700, 0.3950, 0.5638, 0.5933]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0020, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0020, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05541980228736065
step: 32
running loss: 0.0017318688214800204
Train Steps: 32/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6087, 0.3951, 0.8387, 0.5833, 0.4188, 0.4933, 0.5146, 0.4830],
[0.6132, 0.4037, 0.6963, 0.2217, 0.4100, 0.1950, 0.5395, 0.5175],
[0.6229, 0.4066, 0.7612, 0.2967, 0.4250, 0.2167, 0.5925, 0.5350],
[0.6270, 0.4267, 0.7150, 0.3317, 0.4900, 0.1817, 0.5560, 0.6183],
[0.6198, 0.4115, 0.7762, 0.2717, 0.3713, 0.3200, 0.5837, 0.5683],
[0.6308, 0.3990, 0.8688, 0.5183, 0.3950, 0.4983, 0.6388, 0.5133],
[0.6250, 0.3993, 0.9138, 0.4333, 0.3763, 0.5217, 0.6995, 0.5320],
[ nan, nan, 0.8675, 0.2833, 0.5350, 0.1983, 0.6678, 0.5621]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6566, 0.3715, 0.8816, 0.6038, 0.4144, 0.4639, 0.4896, 0.5030],
[0.5464, 0.3426, 0.7286, 0.2806, 0.3849, 0.1901, 0.4855, 0.4883],
[0.6351, 0.3949, 0.7865, 0.3325, 0.4041, 0.2448, 0.5552, 0.5239],
[0.6059, 0.3743, 0.7327, 0.3129, 0.4484, 0.1898, 0.5123, 0.5763],
[0.5316, 0.3136, 0.8101, 0.3168, 0.3599, 0.3169, 0.5467, 0.5450],
[0.7205, 0.4120, 0.9059, 0.5588, 0.3834, 0.5009, 0.5938, 0.4897],
[0.6610, 0.3933, 0.9364, 0.4873, 0.3515, 0.5126, 0.6947, 0.5138],
[0.0570, 0.0145, 0.8727, 0.3291, 0.5222, 0.1890, 0.6622, 0.5340]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6087, 0.3951, 0.8388, 0.5833, 0.4187, 0.4933, 0.5146, 0.4830],
[0.6132, 0.4037, 0.6963, 0.2217, 0.4100, 0.1950, 0.5395, 0.5175],
[0.6229, 0.4066, 0.7613, 0.2967, 0.4250, 0.2167, 0.5925, 0.5350],
[0.6270, 0.4266, 0.7150, 0.3317, 0.4900, 0.1817, 0.5560, 0.6183],
[0.6198, 0.4115, 0.7763, 0.2717, 0.3713, 0.3200, 0.5838, 0.5683],
[0.6308, 0.3990, 0.8687, 0.5183, 0.3950, 0.4983, 0.6388, 0.5133],
[0.6250, 0.3993, 0.9137, 0.4333, 0.3762, 0.5217, 0.6995, 0.5320],
[0.0000, 0.0000, 0.8675, 0.2833, 0.5350, 0.1983, 0.6678, 0.5621]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05678630419424735
step: 33
running loss: 0.0017207970967953743
Train Steps: 33/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6198, 0.4114, 0.8263, 0.3283, 0.3550, 0.3583, 0.5813, 0.5667],
[0.6286, 0.4078, 0.8063, 0.2267, 0.4788, 0.1533, 0.5953, 0.4913],
[0.6222, 0.3937, 0.8350, 0.5617, 0.4138, 0.4600, 0.5800, 0.5233],
[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383],
[0.6124, 0.4083, 0.6954, 0.3069, 0.3650, 0.2750, 0.5163, 0.5485],
[0.6127, 0.4084, 0.8700, 0.4467, 0.3987, 0.4317, 0.5013, 0.5471],
[0.6053, 0.4035, 0.6897, 0.1916, 0.4000, 0.2117, 0.5440, 0.5168],
[0.6125, 0.3983, 0.8750, 0.4867, 0.4275, 0.4783, 0.5413, 0.5717]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5069, 0.3218, 0.8555, 0.3668, 0.3512, 0.3650, 0.5693, 0.5543],
[0.4332, 0.2523, 0.8236, 0.2801, 0.4832, 0.1434, 0.5698, 0.5128],
[0.6045, 0.3508, 0.8627, 0.6034, 0.4019, 0.4417, 0.5702, 0.5253],
[0.5790, 0.3402, 0.8591, 0.3597, 0.3533, 0.3820, 0.6203, 0.5123],
[0.5639, 0.3524, 0.7444, 0.3332, 0.3590, 0.2914, 0.5039, 0.5421],
[0.6302, 0.3901, 0.8920, 0.4865, 0.3971, 0.4280, 0.4932, 0.5448],
[0.4977, 0.3001, 0.7139, 0.2390, 0.3956, 0.1843, 0.5345, 0.5176],
[0.6276, 0.3901, 0.8870, 0.5276, 0.4145, 0.4734, 0.5482, 0.5294]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6198, 0.4114, 0.8263, 0.3283, 0.3550, 0.3583, 0.5813, 0.5667],
[0.6286, 0.4078, 0.8062, 0.2267, 0.4787, 0.1533, 0.5953, 0.4913],
[0.6222, 0.3937, 0.8350, 0.5617, 0.4137, 0.4600, 0.5800, 0.5233],
[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383],
[0.6123, 0.4083, 0.6954, 0.3069, 0.3650, 0.2750, 0.5163, 0.5485],
[0.6127, 0.4084, 0.8700, 0.4467, 0.3988, 0.4317, 0.5013, 0.5471],
[0.6054, 0.4035, 0.6897, 0.1916, 0.4000, 0.2117, 0.5440, 0.5168],
[0.6125, 0.3983, 0.8750, 0.4867, 0.4275, 0.4783, 0.5412, 0.5717]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0023, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0023, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05907099656178616
step: 34
running loss: 0.00173738225181724
Train Steps: 34/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6213, 0.4131, 0.8438, 0.3550, 0.3513, 0.4400, 0.5716, 0.5123],
[0.6144, 0.4032, 0.8563, 0.3283, 0.3525, 0.4200, 0.5775, 0.5583],
[0.6224, 0.4179, 0.8700, 0.5683, 0.4037, 0.4683, 0.5650, 0.5600],
[0.6163, 0.4114, 0.7650, 0.2017, 0.3763, 0.2867, 0.5631, 0.5071],
[0.6271, 0.4040, 0.9138, 0.3750, 0.4625, 0.2617, 0.7232, 0.5413],
[ nan, nan, 0.7625, 0.2433, 0.3713, 0.2867, 0.5235, 0.5220],
[0.6275, 0.4048, 0.8488, 0.2883, 0.4463, 0.2033, 0.6321, 0.5155],
[0.6176, 0.3911, 0.8738, 0.4217, 0.3488, 0.4033, 0.6025, 0.4817]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5963, 0.3928, 0.8422, 0.3795, 0.3410, 0.4309, 0.5365, 0.5404],
[0.6860, 0.4379, 0.8387, 0.3597, 0.3536, 0.4246, 0.5370, 0.5621],
[0.6555, 0.4334, 0.8594, 0.6063, 0.3841, 0.4639, 0.5436, 0.5663],
[0.6021, 0.3857, 0.7330, 0.2327, 0.3687, 0.2826, 0.5496, 0.5033],
[0.5491, 0.3401, 0.9177, 0.3947, 0.4646, 0.2704, 0.7094, 0.5530],
[0.0126, 0.0070, 0.7575, 0.2523, 0.3890, 0.2771, 0.4934, 0.5518],
[0.7066, 0.4475, 0.8518, 0.2999, 0.4414, 0.2243, 0.6433, 0.5179],
[0.5654, 0.3630, 0.8516, 0.4159, 0.3413, 0.4084, 0.5547, 0.5023]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6213, 0.4131, 0.8438, 0.3550, 0.3512, 0.4400, 0.5716, 0.5123],
[0.6144, 0.4032, 0.8562, 0.3283, 0.3525, 0.4200, 0.5775, 0.5583],
[0.6224, 0.4179, 0.8700, 0.5683, 0.4038, 0.4683, 0.5650, 0.5600],
[0.6163, 0.4114, 0.7650, 0.2017, 0.3762, 0.2867, 0.5631, 0.5071],
[0.6271, 0.4040, 0.9137, 0.3750, 0.4625, 0.2617, 0.7232, 0.5413],
[0.0000, 0.0000, 0.7625, 0.2433, 0.3713, 0.2867, 0.5235, 0.5220],
[0.6275, 0.4048, 0.8487, 0.2883, 0.4462, 0.2033, 0.6321, 0.5155],
[0.6176, 0.3911, 0.8737, 0.4217, 0.3487, 0.4033, 0.6025, 0.4817]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05983991172979586
step: 35
running loss: 0.001709711763708453
Train Steps: 35/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6263, 0.4057, 0.8800, 0.3833, 0.3650, 0.3717, 0.6375, 0.4804],
[0.6266, 0.4067, 0.8588, 0.2867, 0.4300, 0.2850, 0.6325, 0.5267],
[0.6198, 0.3997, 0.8582, 0.5361, 0.4117, 0.5016, 0.5942, 0.5134],
[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383],
[0.6234, 0.4179, 0.7825, 0.3450, 0.3813, 0.2867, 0.5675, 0.5617],
[0.6148, 0.4076, 0.8666, 0.4820, 0.4138, 0.5067, 0.5250, 0.5767],
[0.6097, 0.4024, 0.8488, 0.3717, 0.3875, 0.5517, 0.5836, 0.5591],
[0.6128, 0.4022, 0.8738, 0.5067, 0.4983, 0.5231, 0.5364, 0.5064]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5901, 0.4088, 0.8563, 0.3605, 0.3315, 0.3447, 0.5860, 0.4939],
[0.5359, 0.3621, 0.8485, 0.2784, 0.4185, 0.2434, 0.6223, 0.5242],
[0.5851, 0.3998, 0.8402, 0.5130, 0.3952, 0.5066, 0.5769, 0.5002],
[0.5745, 0.3787, 0.8197, 0.3058, 0.3349, 0.3723, 0.6011, 0.5366],
[0.5456, 0.3811, 0.7809, 0.3230, 0.3732, 0.2617, 0.5631, 0.5644],
[0.6271, 0.4279, 0.8482, 0.4558, 0.3857, 0.4892, 0.5296, 0.5692],
[0.5132, 0.3385, 0.8294, 0.3506, 0.3816, 0.5313, 0.5937, 0.5284],
[0.5584, 0.3972, 0.8556, 0.4872, 0.4582, 0.4736, 0.5132, 0.5291]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6263, 0.4057, 0.8800, 0.3833, 0.3650, 0.3717, 0.6375, 0.4804],
[0.6266, 0.4067, 0.8587, 0.2867, 0.4300, 0.2850, 0.6325, 0.5267],
[0.6198, 0.3997, 0.8582, 0.5361, 0.4117, 0.5016, 0.5942, 0.5134],
[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383],
[0.6234, 0.4179, 0.7825, 0.3450, 0.3812, 0.2867, 0.5675, 0.5617],
[0.6148, 0.4076, 0.8666, 0.4820, 0.4137, 0.5067, 0.5250, 0.5767],
[0.6097, 0.4024, 0.8487, 0.3717, 0.3875, 0.5517, 0.5836, 0.5591],
[0.6128, 0.4022, 0.8737, 0.5067, 0.4983, 0.5231, 0.5364, 0.5064]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.060806872352259234
step: 36
running loss: 0.0016890797875627566
Train Steps: 36/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6081, 0.3950, 0.8538, 0.4667, 0.3850, 0.4917, 0.5342, 0.4954],
[0.6182, 0.3972, 0.8552, 0.5914, 0.3683, 0.4181, 0.5688, 0.5378],
[0.6207, 0.4081, 0.7662, 0.2067, 0.3962, 0.3200, 0.6312, 0.5300],
[0.6219, 0.3934, 0.8688, 0.5267, 0.4313, 0.4967, 0.5988, 0.4983],
[0.6097, 0.4000, 0.7325, 0.2667, 0.3450, 0.3517, 0.5284, 0.5045],
[0.6159, 0.4085, 0.6900, 0.2283, 0.4088, 0.1950, 0.5123, 0.5397],
[0.6127, 0.4066, 0.8550, 0.5567, 0.4662, 0.5141, 0.5070, 0.5412],
[ nan, nan, 0.7525, 0.2291, 0.3838, 0.3017, 0.6050, 0.5667]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6335, 0.4346, 0.8782, 0.4073, 0.3632, 0.4977, 0.5222, 0.5061],
[0.6177, 0.4202, 0.8657, 0.5371, 0.3564, 0.4533, 0.5620, 0.5361],
[0.6114, 0.4360, 0.7637, 0.1912, 0.3863, 0.3127, 0.6328, 0.5387],
[0.6132, 0.4126, 0.8703, 0.4958, 0.4261, 0.4992, 0.5843, 0.4942],
[0.5834, 0.4001, 0.7386, 0.2229, 0.3346, 0.3644, 0.5495, 0.5346],
[0.6371, 0.4433, 0.6882, 0.1988, 0.3955, 0.1833, 0.5116, 0.5594],
[0.6863, 0.4815, 0.8768, 0.5128, 0.4381, 0.4661, 0.5487, 0.5464],
[0.2251, 0.1772, 0.7638, 0.1963, 0.3851, 0.3008, 0.6064, 0.5866]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6081, 0.3950, 0.8537, 0.4667, 0.3850, 0.4917, 0.5342, 0.4954],
[0.6182, 0.3972, 0.8552, 0.5914, 0.3683, 0.4181, 0.5688, 0.5378],
[0.6207, 0.4081, 0.7663, 0.2067, 0.3963, 0.3200, 0.6313, 0.5300],
[0.6219, 0.3934, 0.8687, 0.5267, 0.4313, 0.4967, 0.5987, 0.4983],
[0.6097, 0.4000, 0.7325, 0.2667, 0.3450, 0.3517, 0.5284, 0.5045],
[0.6159, 0.4085, 0.6900, 0.2283, 0.4087, 0.1950, 0.5123, 0.5397],
[0.6127, 0.4066, 0.8550, 0.5567, 0.4662, 0.5141, 0.5070, 0.5412],
[0.0000, 0.0000, 0.7525, 0.2291, 0.3837, 0.3017, 0.6050, 0.5667]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06275377355632372
step: 37
running loss: 0.0016960479339546953
Train Steps: 37/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6122, 0.4006, 0.8850, 0.4217, 0.4088, 0.5517, 0.6063, 0.5517],
[0.6223, 0.4130, 0.8100, 0.2983, 0.3525, 0.3900, 0.5694, 0.5103],
[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395],
[0.6182, 0.3930, 0.8841, 0.3892, 0.3556, 0.4967, 0.6222, 0.5279],
[0.6095, 0.4002, 0.8533, 0.5168, 0.5031, 0.5094, 0.5125, 0.5433],
[0.6275, 0.4071, 0.8075, 0.2100, 0.4700, 0.1533, 0.6148, 0.4834],
[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459],
[0.6162, 0.3949, 0.8838, 0.4517, 0.4250, 0.5183, 0.5837, 0.5500]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5923, 0.4131, 0.8545, 0.3751, 0.3961, 0.5505, 0.5932, 0.5513],
[0.6174, 0.4432, 0.7769, 0.2844, 0.3408, 0.4038, 0.5863, 0.5461],
[0.5197, 0.3747, 0.8393, 0.4754, 0.3550, 0.4011, 0.5515, 0.5350],
[0.5182, 0.3501, 0.8382, 0.3487, 0.3390, 0.4937, 0.6212, 0.5191],
[0.6206, 0.4425, 0.8216, 0.4711, 0.4638, 0.5038, 0.5184, 0.5643],
[0.6210, 0.4301, 0.7798, 0.1495, 0.4564, 0.1728, 0.6289, 0.4910],
[0.6128, 0.4325, 0.8455, 0.2361, 0.4737, 0.2206, 0.6600, 0.5483],
[0.6007, 0.4236, 0.8583, 0.4114, 0.3887, 0.5358, 0.5525, 0.5445]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6122, 0.4006, 0.8850, 0.4217, 0.4087, 0.5517, 0.6062, 0.5517],
[0.6223, 0.4130, 0.8100, 0.2983, 0.3525, 0.3900, 0.5694, 0.5103],
[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395],
[0.6182, 0.3930, 0.8841, 0.3892, 0.3556, 0.4967, 0.6222, 0.5279],
[0.6095, 0.4002, 0.8533, 0.5168, 0.5031, 0.5094, 0.5125, 0.5433],
[0.6275, 0.4071, 0.8075, 0.2100, 0.4700, 0.1533, 0.6148, 0.4834],
[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459],
[0.6162, 0.3949, 0.8838, 0.4517, 0.4250, 0.5183, 0.5838, 0.5500]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06382370277424343
step: 38
running loss: 0.001679571125637985
Train Steps: 38/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6193, 0.4034, 0.7757, 0.2347, 0.3733, 0.2919, 0.5930, 0.4926],
[0.6079, 0.3964, 0.7420, 0.2958, 0.3563, 0.2917, 0.5351, 0.4980],
[0.6216, 0.4100, 0.7350, 0.2067, 0.4325, 0.2050, 0.5950, 0.5333],
[0.6271, 0.4005, 0.8450, 0.6067, 0.3850, 0.4983, 0.6069, 0.4649],
[0.6279, 0.4008, 0.8600, 0.4883, 0.4325, 0.5283, 0.7010, 0.5378],
[0.6125, 0.4010, 0.8650, 0.4567, 0.3663, 0.3900, 0.5600, 0.5567],
[0.6230, 0.4113, 0.7213, 0.1983, 0.4325, 0.2367, 0.6262, 0.5400],
[0.6214, 0.4116, 0.7750, 0.2317, 0.4487, 0.1883, 0.6200, 0.5400]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5740, 0.4027, 0.7804, 0.2006, 0.3989, 0.3092, 0.5924, 0.5124],
[0.5530, 0.3796, 0.7529, 0.2496, 0.3690, 0.3354, 0.5114, 0.5020],
[0.6239, 0.4282, 0.7437, 0.1662, 0.4529, 0.2339, 0.5796, 0.5355],
[0.6111, 0.4053, 0.8515, 0.5777, 0.4085, 0.5404, 0.5554, 0.4905],
[0.6401, 0.4081, 0.8852, 0.4734, 0.4462, 0.5911, 0.6910, 0.5573],
[0.5619, 0.4020, 0.8669, 0.4254, 0.3718, 0.4445, 0.5490, 0.5866],
[0.6114, 0.4139, 0.7461, 0.1707, 0.4561, 0.2525, 0.6348, 0.5516],
[0.5993, 0.4027, 0.7931, 0.1914, 0.4720, 0.2240, 0.6078, 0.5352]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6193, 0.4034, 0.7757, 0.2347, 0.3733, 0.2919, 0.5930, 0.4926],
[0.6079, 0.3964, 0.7420, 0.2958, 0.3562, 0.2917, 0.5351, 0.4980],
[0.6216, 0.4100, 0.7350, 0.2067, 0.4325, 0.2050, 0.5950, 0.5333],
[0.6271, 0.4005, 0.8450, 0.6067, 0.3850, 0.4983, 0.6069, 0.4649],
[0.6279, 0.4008, 0.8600, 0.4883, 0.4325, 0.5283, 0.7010, 0.5378],
[0.6125, 0.4010, 0.8650, 0.4567, 0.3663, 0.3900, 0.5600, 0.5567],
[0.6230, 0.4113, 0.7212, 0.1983, 0.4325, 0.2367, 0.6263, 0.5400],
[0.6214, 0.4116, 0.7750, 0.2317, 0.4487, 0.1883, 0.6200, 0.5400]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06450154227786697
step: 39
running loss: 0.0016538856994324864
Train Steps: 39/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6203, 0.4072, 0.8892, 0.3523, 0.3783, 0.3017, 0.5898, 0.5478],
[0.6080, 0.4010, 0.8750, 0.4500, 0.4825, 0.5617, 0.5837, 0.5583],
[0.6250, 0.4110, 0.7238, 0.2067, 0.4263, 0.1883, 0.5625, 0.5633],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098],
[0.6262, 0.4163, 0.8850, 0.5183, 0.3763, 0.4150, 0.6025, 0.5500],
[0.6263, 0.4057, 0.8800, 0.3833, 0.3650, 0.3717, 0.6375, 0.4804],
[0.6109, 0.4015, 0.7668, 0.3639, 0.3513, 0.3667, 0.5200, 0.5641],
[0.6277, 0.4057, 0.8300, 0.2650, 0.4363, 0.1850, 0.6140, 0.4823]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5910, 0.4063, 0.8675, 0.3079, 0.3950, 0.3282, 0.6319, 0.5391],
[0.6301, 0.4437, 0.8669, 0.4167, 0.4878, 0.5472, 0.5882, 0.5389],
[0.5174, 0.3574, 0.7003, 0.1974, 0.4357, 0.2005, 0.5694, 0.5409],
[0.5996, 0.4060, 0.8421, 0.4511, 0.3845, 0.5482, 0.5982, 0.5075],
[0.5995, 0.4152, 0.8363, 0.4647, 0.3705, 0.4227, 0.5858, 0.5332],
[0.6194, 0.4364, 0.8583, 0.3602, 0.3719, 0.3915, 0.6232, 0.4786],
[0.6075, 0.4301, 0.7486, 0.3395, 0.3588, 0.4001, 0.5355, 0.5402],
[0.6480, 0.4403, 0.8199, 0.2405, 0.4479, 0.2270, 0.6470, 0.4727]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6203, 0.4072, 0.8892, 0.3523, 0.3783, 0.3017, 0.5898, 0.5478],
[0.6080, 0.4010, 0.8750, 0.4500, 0.4825, 0.5617, 0.5838, 0.5583],
[0.6250, 0.4110, 0.7237, 0.2067, 0.4263, 0.1883, 0.5625, 0.5633],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098],
[0.6262, 0.4163, 0.8850, 0.5183, 0.3762, 0.4150, 0.6025, 0.5500],
[0.6263, 0.4057, 0.8800, 0.3833, 0.3650, 0.3717, 0.6375, 0.4804],
[0.6109, 0.4015, 0.7668, 0.3639, 0.3512, 0.3667, 0.5200, 0.5641],
[0.6277, 0.4056, 0.8300, 0.2650, 0.4363, 0.1850, 0.6140, 0.4823]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06523508534883149
step: 40
running loss: 0.0016308771337207872
Train Steps: 40/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.8888, 0.3100, 0.5262, 0.2817, 0.7145, 0.6003],
[0.6147, 0.4081, 0.8538, 0.3400, 0.3663, 0.3150, 0.5142, 0.4875],
[0.6126, 0.4039, 0.8237, 0.3967, 0.3625, 0.3600, 0.5894, 0.6138],
[0.6293, 0.4097, 0.8800, 0.2517, 0.5262, 0.2600, 0.7430, 0.5378],
[0.6082, 0.4042, 0.6975, 0.1917, 0.4100, 0.1983, 0.5502, 0.5578],
[0.6255, 0.4017, 0.8688, 0.3217, 0.3638, 0.3550, 0.6344, 0.4901],
[0.6185, 0.4129, 0.8900, 0.4567, 0.3937, 0.5417, 0.5734, 0.5110],
[0.6212, 0.4171, 0.7875, 0.3633, 0.3813, 0.2933, 0.5675, 0.5700]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.0891, 0.0631, 0.8773, 0.3103, 0.5095, 0.2728, 0.7551, 0.5479],
[0.6648, 0.4404, 0.8403, 0.3713, 0.3801, 0.3216, 0.5263, 0.5005],
[0.6272, 0.4338, 0.8008, 0.4137, 0.3686, 0.3707, 0.5899, 0.5850],
[0.7378, 0.4701, 0.8775, 0.2688, 0.5286, 0.2359, 0.7385, 0.5006],
[0.5938, 0.4020, 0.6731, 0.2113, 0.4046, 0.1986, 0.5346, 0.5199],
[0.6902, 0.4420, 0.8249, 0.3392, 0.3674, 0.3924, 0.6394, 0.4805],
[0.7369, 0.4858, 0.8802, 0.4684, 0.4083, 0.5596, 0.5782, 0.5072],
[0.6505, 0.4323, 0.7702, 0.3830, 0.3922, 0.3041, 0.5700, 0.5416]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.8888, 0.3100, 0.5263, 0.2817, 0.7145, 0.6003],
[0.6147, 0.4081, 0.8537, 0.3400, 0.3663, 0.3150, 0.5142, 0.4875],
[0.6126, 0.4038, 0.8238, 0.3967, 0.3625, 0.3600, 0.5894, 0.6138],
[0.6293, 0.4097, 0.8800, 0.2517, 0.5263, 0.2600, 0.7430, 0.5378],
[0.6082, 0.4042, 0.6975, 0.1917, 0.4100, 0.1983, 0.5502, 0.5578],
[0.6255, 0.4017, 0.8687, 0.3217, 0.3638, 0.3550, 0.6344, 0.4901],
[0.6186, 0.4129, 0.8900, 0.4567, 0.3938, 0.5417, 0.5734, 0.5110],
[0.6212, 0.4171, 0.7875, 0.3633, 0.3812, 0.2933, 0.5675, 0.5700]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06645582363125868
step: 41
running loss: 0.0016208737471038702
Train Steps: 41/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6161, 0.4099, 0.8738, 0.4383, 0.3788, 0.5483, 0.5605, 0.5019],
[ nan, nan, 0.6512, 0.1717, 0.4100, 0.1983, 0.5253, 0.5240],
[0.6178, 0.4059, 0.7525, 0.2250, 0.4313, 0.1783, 0.5404, 0.5240],
[0.6139, 0.4019, 0.7137, 0.2150, 0.4375, 0.1533, 0.5293, 0.5006],
[0.6223, 0.4130, 0.8100, 0.2983, 0.3525, 0.3900, 0.5694, 0.5103],
[0.6215, 0.4119, 0.7688, 0.2300, 0.4200, 0.2283, 0.5925, 0.5317],
[0.6205, 0.4012, 0.8675, 0.3283, 0.3713, 0.3050, 0.5813, 0.5117],
[0.6361, 0.4165, 0.9038, 0.5017, 0.3750, 0.3783, 0.6448, 0.5309]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6891, 0.4599, 0.8777, 0.4752, 0.3979, 0.5489, 0.5949, 0.5166],
[0.1478, 0.0824, 0.7012, 0.2130, 0.4257, 0.1784, 0.5816, 0.5343],
[0.4423, 0.2698, 0.7500, 0.2366, 0.4303, 0.1242, 0.5547, 0.5396],
[0.6466, 0.4050, 0.7299, 0.2141, 0.4476, 0.1427, 0.5879, 0.5038],
[0.6940, 0.4596, 0.8240, 0.3588, 0.3734, 0.3761, 0.6182, 0.5333],
[0.6037, 0.3890, 0.7641, 0.2457, 0.4580, 0.2087, 0.6180, 0.5329],
[0.6408, 0.4135, 0.8916, 0.3551, 0.4042, 0.2893, 0.6089, 0.5080],
[0.6872, 0.4480, 0.9009, 0.5420, 0.4146, 0.3651, 0.6688, 0.5193]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6161, 0.4099, 0.8737, 0.4383, 0.3787, 0.5483, 0.5605, 0.5019],
[0.0000, 0.0000, 0.6513, 0.1717, 0.4100, 0.1983, 0.5253, 0.5240],
[0.6178, 0.4059, 0.7525, 0.2250, 0.4313, 0.1783, 0.5404, 0.5240],
[0.6139, 0.4019, 0.7138, 0.2150, 0.4375, 0.1533, 0.5293, 0.5006],
[0.6223, 0.4130, 0.8100, 0.2983, 0.3525, 0.3900, 0.5694, 0.5103],
[0.6215, 0.4119, 0.7688, 0.2300, 0.4200, 0.2283, 0.5925, 0.5317],
[0.6205, 0.4012, 0.8675, 0.3283, 0.3713, 0.3050, 0.5813, 0.5117],
[0.6361, 0.4165, 0.9038, 0.5017, 0.3750, 0.3783, 0.6448, 0.5309]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0021, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0021, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06857384138857014
step: 42
running loss: 0.00163271050925167
Train Steps: 42/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.8300, 0.3150, 0.3588, 0.3383, 0.5208, 0.5194],
[0.6246, 0.4090, 0.6964, 0.2027, 0.3925, 0.2683, 0.6088, 0.5583],
[0.6126, 0.3954, 0.8538, 0.4983, 0.4250, 0.4700, 0.5355, 0.5350],
[0.6304, 0.4029, 0.8413, 0.5217, 0.4125, 0.5617, 0.7089, 0.5679],
[0.6200, 0.3978, 0.8900, 0.4550, 0.3775, 0.5200, 0.6150, 0.5367],
[0.6332, 0.4165, 0.9100, 0.3350, 0.4188, 0.3683, 0.7438, 0.5528],
[0.6122, 0.4006, 0.8850, 0.4217, 0.4088, 0.5517, 0.6063, 0.5517],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3788, 0.4900, 0.7121, 0.5864]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.1296, 0.0703, 0.8199, 0.3338, 0.3646, 0.2900, 0.5425, 0.4966],
[0.7671, 0.4832, 0.7103, 0.2382, 0.3894, 0.2149, 0.5864, 0.5264],
[0.7036, 0.4180, 0.8707, 0.5230, 0.4307, 0.4502, 0.5363, 0.5218],
[0.6885, 0.4491, 0.8544, 0.5484, 0.4120, 0.5351, 0.6645, 0.5570],
[0.6785, 0.4147, 0.8790, 0.4961, 0.3750, 0.4876, 0.5926, 0.5207],
[0.6171, 0.3889, 0.9387, 0.3866, 0.4237, 0.3242, 0.7216, 0.5220],
[0.6880, 0.4228, 0.9020, 0.4466, 0.4167, 0.5017, 0.5754, 0.5190],
[0.7329, 0.4590, 0.8893, 0.5391, 0.3890, 0.4513, 0.6981, 0.5399]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.8300, 0.3150, 0.3587, 0.3383, 0.5208, 0.5194],
[0.6246, 0.4090, 0.6964, 0.2027, 0.3925, 0.2683, 0.6087, 0.5583],
[0.6126, 0.3954, 0.8537, 0.4983, 0.4250, 0.4700, 0.5355, 0.5350],
[0.6304, 0.4029, 0.8413, 0.5217, 0.4125, 0.5617, 0.7089, 0.5679],
[0.6199, 0.3978, 0.8900, 0.4550, 0.3775, 0.5200, 0.6150, 0.5367],
[0.6332, 0.4165, 0.9100, 0.3350, 0.4187, 0.3683, 0.7438, 0.5528],
[0.6122, 0.4006, 0.8850, 0.4217, 0.4087, 0.5517, 0.6062, 0.5517],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3787, 0.4900, 0.7121, 0.5864]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07046938224812038
step: 43
running loss: 0.0016388228429795439
Train Steps: 43/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6339, 0.4118, 0.7988, 0.5800, 0.3912, 0.4583, 0.7343, 0.5760],
[0.6126, 0.3954, 0.8538, 0.4983, 0.4250, 0.4700, 0.5355, 0.5350],
[0.6202, 0.4066, 0.8746, 0.3376, 0.3717, 0.3090, 0.5842, 0.5165],
[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466],
[0.6222, 0.4172, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633],
[0.6262, 0.4052, 0.8888, 0.4700, 0.3675, 0.5117, 0.6350, 0.5233],
[0.6353, 0.4128, 0.8488, 0.2600, 0.5525, 0.1616, 0.6694, 0.5540],
[0.6223, 0.4130, 0.8100, 0.2983, 0.3525, 0.3900, 0.5694, 0.5103]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6533, 0.3930, 0.8091, 0.5610, 0.3700, 0.4263, 0.6663, 0.5426],
[0.6025, 0.3455, 0.8612, 0.5094, 0.4215, 0.4670, 0.5519, 0.5381],
[0.6022, 0.3682, 0.8667, 0.3334, 0.3617, 0.2666, 0.5935, 0.5086],
[0.5780, 0.3655, 0.7793, 0.3759, 0.3514, 0.4040, 0.5146, 0.5343],
[0.6462, 0.4082, 0.9039, 0.5446, 0.3658, 0.4411, 0.5685, 0.5704],
[0.6143, 0.3738, 0.9155, 0.4762, 0.3818, 0.5059, 0.6533, 0.5145],
[0.5468, 0.3345, 0.8641, 0.2554, 0.5273, 0.1434, 0.6819, 0.5426],
[0.5857, 0.3659, 0.8191, 0.3233, 0.3502, 0.3641, 0.5801, 0.5197]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6339, 0.4118, 0.7987, 0.5800, 0.3913, 0.4583, 0.7343, 0.5760],
[0.6126, 0.3954, 0.8537, 0.4983, 0.4250, 0.4700, 0.5355, 0.5350],
[0.6202, 0.4066, 0.8746, 0.3376, 0.3717, 0.3090, 0.5842, 0.5165],
[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466],
[0.6222, 0.4171, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633],
[0.6262, 0.4052, 0.8888, 0.4700, 0.3675, 0.5117, 0.6350, 0.5233],
[0.6353, 0.4128, 0.8487, 0.2600, 0.5525, 0.1616, 0.6694, 0.5540],
[0.6223, 0.4130, 0.8100, 0.2983, 0.3525, 0.3900, 0.5694, 0.5103]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07114345880108885
step: 44
running loss: 0.0016168967909338376
Train Steps: 44/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6296, 0.4076, 0.8400, 0.5583, 0.3700, 0.4367, 0.6876, 0.5494],
[0.6250, 0.3961, 0.8672, 0.4929, 0.4199, 0.4972, 0.6312, 0.5301],
[0.6208, 0.4082, 0.8538, 0.3067, 0.3588, 0.3717, 0.6112, 0.5517],
[0.6209, 0.3920, 0.8650, 0.5367, 0.4400, 0.5067, 0.6025, 0.4950],
[ nan, nan, 0.8525, 0.2217, 0.5413, 0.2367, 0.7367, 0.5482],
[0.6231, 0.3973, 0.8650, 0.3950, 0.3625, 0.3183, 0.5837, 0.5167],
[0.6219, 0.3934, 0.8688, 0.5267, 0.4313, 0.4967, 0.5988, 0.4983],
[0.6283, 0.4283, 0.7477, 0.3542, 0.5125, 0.1917, 0.5500, 0.6167]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6648, 0.4051, 0.8547, 0.5253, 0.3593, 0.4408, 0.6620, 0.5442],
[0.5646, 0.3528, 0.8634, 0.4902, 0.3912, 0.5007, 0.6026, 0.5536],
[0.6554, 0.4185, 0.8312, 0.3112, 0.3282, 0.3703, 0.5874, 0.5649],
[0.6001, 0.3667, 0.8595, 0.5331, 0.3922, 0.5166, 0.5689, 0.5086],
[0.2252, 0.1352, 0.8452, 0.2125, 0.5094, 0.2397, 0.7010, 0.5618],
[0.6177, 0.3958, 0.8650, 0.4102, 0.3560, 0.3034, 0.5887, 0.5341],
[0.6059, 0.3636, 0.8642, 0.5232, 0.4138, 0.4863, 0.5702, 0.5012],
[0.6755, 0.4330, 0.7479, 0.3293, 0.4549, 0.1847, 0.5319, 0.6135]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6296, 0.4076, 0.8400, 0.5583, 0.3700, 0.4367, 0.6876, 0.5494],
[0.6250, 0.3961, 0.8672, 0.4929, 0.4199, 0.4972, 0.6312, 0.5301],
[0.6208, 0.4082, 0.8537, 0.3067, 0.3587, 0.3717, 0.6112, 0.5517],
[0.6209, 0.3920, 0.8650, 0.5367, 0.4400, 0.5067, 0.6025, 0.4950],
[0.0000, 0.0000, 0.8525, 0.2217, 0.5412, 0.2367, 0.7367, 0.5482],
[0.6231, 0.3973, 0.8650, 0.3950, 0.3625, 0.3183, 0.5838, 0.5167],
[0.6219, 0.3934, 0.8687, 0.5267, 0.4313, 0.4967, 0.5987, 0.4983],
[0.6283, 0.4283, 0.7477, 0.3542, 0.5125, 0.1917, 0.5500, 0.6167]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07271968291024677
step: 45
running loss: 0.0016159929535610395
Train Steps: 45/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6307, 0.4060, 0.8950, 0.5183, 0.3750, 0.3850, 0.6338, 0.4938],
[0.6068, 0.3963, 0.8650, 0.4317, 0.4037, 0.5083, 0.5253, 0.4999],
[0.6307, 0.3998, 0.8500, 0.5233, 0.3850, 0.5050, 0.7446, 0.5320],
[0.6305, 0.3983, 0.8950, 0.4833, 0.3688, 0.4683, 0.6375, 0.5117],
[0.6241, 0.4143, 0.8938, 0.4650, 0.4075, 0.5350, 0.6250, 0.5550],
[0.6350, 0.4144, 0.9250, 0.4100, 0.4125, 0.3750, 0.7129, 0.5945],
[0.6353, 0.4128, 0.9138, 0.3533, 0.4688, 0.3250, 0.7145, 0.5991],
[0.6109, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6014, 0.3906, 0.8760, 0.5141, 0.3662, 0.3807, 0.5987, 0.5159],
[0.5682, 0.3432, 0.8353, 0.4166, 0.3854, 0.5007, 0.5066, 0.5207],
[0.5977, 0.3875, 0.8380, 0.5157, 0.3754, 0.5035, 0.6486, 0.5565],
[0.6293, 0.3856, 0.8906, 0.4898, 0.3633, 0.4632, 0.6219, 0.5406],
[0.6094, 0.3830, 0.8745, 0.4607, 0.4074, 0.5207, 0.6207, 0.5795],
[0.5853, 0.3684, 0.8890, 0.4049, 0.4215, 0.3655, 0.7029, 0.5958],
[0.4055, 0.2576, 0.8998, 0.3556, 0.4626, 0.3115, 0.7230, 0.6119],
[0.6224, 0.4179, 0.8621, 0.4533, 0.3715, 0.4162, 0.5211, 0.5285]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6307, 0.4060, 0.8950, 0.5183, 0.3750, 0.3850, 0.6338, 0.4938],
[0.6068, 0.3963, 0.8650, 0.4317, 0.4038, 0.5083, 0.5253, 0.4999],
[0.6307, 0.3998, 0.8500, 0.5233, 0.3850, 0.5050, 0.7446, 0.5320],
[0.6305, 0.3983, 0.8950, 0.4833, 0.3688, 0.4683, 0.6375, 0.5117],
[0.6241, 0.4142, 0.8938, 0.4650, 0.4075, 0.5350, 0.6250, 0.5550],
[0.6350, 0.4144, 0.9250, 0.4100, 0.4125, 0.3750, 0.7129, 0.5945],
[0.6353, 0.4128, 0.9137, 0.3533, 0.4688, 0.3250, 0.7145, 0.5991],
[0.6108, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0018, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0018, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07447020555264316
step: 46
running loss: 0.0016189175120139819
Train Steps: 46/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6267, 0.4080, 0.8438, 0.2633, 0.4763, 0.1800, 0.6259, 0.5240],
[0.6118, 0.4052, 0.8463, 0.3917, 0.3538, 0.3450, 0.5053, 0.5593],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533],
[0.6102, 0.3999, 0.8750, 0.5133, 0.3825, 0.4750, 0.5637, 0.5083],
[0.6231, 0.3973, 0.8650, 0.3950, 0.3625, 0.3183, 0.5837, 0.5167],
[0.6275, 0.4013, 0.8850, 0.2833, 0.4975, 0.2233, 0.7058, 0.5343],
[0.6223, 0.3990, 0.8037, 0.2800, 0.4000, 0.2283, 0.5864, 0.5208],
[0.6204, 0.4049, 0.7975, 0.2700, 0.3937, 0.2567, 0.5700, 0.5183]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6041, 0.3938, 0.8301, 0.2768, 0.4639, 0.2062, 0.6434, 0.5514],
[0.6029, 0.4004, 0.8234, 0.3782, 0.3560, 0.3713, 0.5147, 0.5802],
[0.5090, 0.3451, 0.8887, 0.4574, 0.4401, 0.5328, 0.6144, 0.5899],
[0.5273, 0.3276, 0.8808, 0.5208, 0.3927, 0.5246, 0.5674, 0.5295],
[0.5351, 0.3431, 0.8607, 0.4114, 0.3778, 0.3320, 0.6319, 0.5436],
[0.5631, 0.3568, 0.8728, 0.2954, 0.5005, 0.2429, 0.7542, 0.5450],
[0.5440, 0.3390, 0.8046, 0.2910, 0.4050, 0.2686, 0.6255, 0.5356],
[0.4561, 0.2983, 0.7701, 0.2767, 0.3897, 0.2866, 0.5682, 0.5719]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6267, 0.4080, 0.8438, 0.2633, 0.4762, 0.1800, 0.6259, 0.5240],
[0.6118, 0.4052, 0.8462, 0.3917, 0.3537, 0.3450, 0.5053, 0.5593],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533],
[0.6102, 0.3999, 0.8750, 0.5133, 0.3825, 0.4750, 0.5638, 0.5083],
[0.6231, 0.3973, 0.8650, 0.3950, 0.3625, 0.3183, 0.5838, 0.5167],
[0.6275, 0.4013, 0.8850, 0.2833, 0.4975, 0.2233, 0.7058, 0.5343],
[0.6223, 0.3990, 0.8037, 0.2800, 0.4000, 0.2283, 0.5864, 0.5208],
[0.6204, 0.4049, 0.7975, 0.2700, 0.3938, 0.2567, 0.5700, 0.5183]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0018, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0018, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07631988901994191
step: 47
running loss: 0.0016238274259562108
Train Steps: 47/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6164, 0.4076, 0.8838, 0.4117, 0.3713, 0.5550, 0.6238, 0.5350],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3788, 0.4900, 0.7121, 0.5864],
[0.6137, 0.4038, 0.8563, 0.4050, 0.3813, 0.2550, 0.5106, 0.4954],
[0.6209, 0.3920, 0.8650, 0.5367, 0.4400, 0.5067, 0.6025, 0.4950],
[0.6201, 0.4027, 0.8029, 0.2728, 0.4042, 0.2310, 0.5980, 0.5391],
[0.6122, 0.4048, 0.7506, 0.3014, 0.3475, 0.3333, 0.5487, 0.5749],
[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383],
[0.6239, 0.4174, 0.8425, 0.5733, 0.4825, 0.4500, 0.5625, 0.5933]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5418, 0.3592, 0.8929, 0.3954, 0.3914, 0.5638, 0.6728, 0.5593],
[0.5866, 0.3958, 0.8892, 0.5073, 0.3876, 0.5094, 0.7513, 0.5850],
[0.6361, 0.4119, 0.8607, 0.3998, 0.4074, 0.2834, 0.5328, 0.5083],
[0.5712, 0.3631, 0.8827, 0.5297, 0.4291, 0.5318, 0.6194, 0.4938],
[0.5730, 0.3708, 0.8171, 0.2721, 0.4153, 0.2532, 0.6215, 0.5359],
[0.5721, 0.3738, 0.7804, 0.2966, 0.3465, 0.3352, 0.5659, 0.5552],
[0.5397, 0.3652, 0.8544, 0.3131, 0.3652, 0.3929, 0.6385, 0.5626],
[0.5920, 0.4128, 0.8771, 0.5720, 0.4985, 0.4259, 0.6170, 0.6088]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6164, 0.4076, 0.8838, 0.4117, 0.3713, 0.5550, 0.6237, 0.5350],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3787, 0.4900, 0.7121, 0.5864],
[0.6137, 0.4038, 0.8562, 0.4050, 0.3812, 0.2550, 0.5106, 0.4954],
[0.6209, 0.3920, 0.8650, 0.5367, 0.4400, 0.5067, 0.6025, 0.4950],
[0.6201, 0.4027, 0.8029, 0.2728, 0.4042, 0.2310, 0.5980, 0.5391],
[0.6122, 0.4048, 0.7506, 0.3014, 0.3475, 0.3333, 0.5487, 0.5749],
[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383],
[0.6239, 0.4174, 0.8425, 0.5733, 0.4825, 0.4500, 0.5625, 0.5933]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0770722002198454
step: 48
running loss: 0.0016056708379134459
Train Steps: 48/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6102, 0.4020, 0.8638, 0.3717, 0.3625, 0.5017, 0.6038, 0.5500],
[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395],
[0.6125, 0.3983, 0.8750, 0.4867, 0.4275, 0.4783, 0.5413, 0.5717],
[0.6095, 0.3970, 0.8688, 0.4767, 0.4860, 0.4879, 0.5191, 0.4940],
[0.6125, 0.4010, 0.8650, 0.4567, 0.3663, 0.3900, 0.5600, 0.5567],
[ nan, nan, 0.6488, 0.1817, 0.4325, 0.1867, 0.5475, 0.5733],
[0.6262, 0.4163, 0.8850, 0.5183, 0.3763, 0.4150, 0.6025, 0.5500],
[0.6223, 0.3990, 0.8037, 0.2800, 0.4000, 0.2283, 0.5864, 0.5208]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6116, 0.4067, 0.8828, 0.3820, 0.3839, 0.5019, 0.6557, 0.5338],
[0.7061, 0.4629, 0.8807, 0.5306, 0.3652, 0.3922, 0.5974, 0.5166],
[0.6063, 0.4012, 0.8859, 0.4928, 0.4343, 0.4867, 0.5892, 0.5541],
[0.5990, 0.3772, 0.9000, 0.4734, 0.4776, 0.4876, 0.5473, 0.5143],
[0.6460, 0.4354, 0.8652, 0.4529, 0.3676, 0.4091, 0.5995, 0.5648],
[0.0335, 0.0334, 0.7170, 0.1800, 0.4606, 0.2172, 0.5830, 0.5723],
[0.6761, 0.4458, 0.8849, 0.4941, 0.3624, 0.4209, 0.6187, 0.5309],
[0.6916, 0.4472, 0.8236, 0.2844, 0.4038, 0.2530, 0.6177, 0.5026]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6102, 0.4020, 0.8637, 0.3717, 0.3625, 0.5017, 0.6037, 0.5500],
[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395],
[0.6125, 0.3983, 0.8750, 0.4867, 0.4275, 0.4783, 0.5412, 0.5717],
[0.6095, 0.3970, 0.8687, 0.4767, 0.4860, 0.4879, 0.5191, 0.4940],
[0.6125, 0.4010, 0.8650, 0.4567, 0.3663, 0.3900, 0.5600, 0.5567],
[0.0000, 0.0000, 0.6488, 0.1817, 0.4325, 0.1867, 0.5475, 0.5733],
[0.6262, 0.4163, 0.8850, 0.5183, 0.3762, 0.4150, 0.6025, 0.5500],
[0.6223, 0.3990, 0.8037, 0.2800, 0.4000, 0.2283, 0.5864, 0.5208]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07790248477249406
step: 49
running loss: 0.001589846628010083
Train Steps: 49/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6038, 0.3946, 0.8413, 0.4883, 0.3563, 0.4550, 0.5266, 0.4693],
[0.6200, 0.3993, 0.8639, 0.3687, 0.3658, 0.3139, 0.6002, 0.5374],
[0.6117, 0.4018, 0.6562, 0.1967, 0.3738, 0.2550, 0.5280, 0.5103],
[0.6203, 0.4073, 0.8189, 0.2398, 0.4400, 0.2054, 0.5929, 0.5501],
[0.6260, 0.4214, 0.8538, 0.5500, 0.3663, 0.3767, 0.5587, 0.5983],
[ nan, nan, 0.8900, 0.3217, 0.5038, 0.2233, 0.6694, 0.5609],
[0.6168, 0.4029, 0.8523, 0.3417, 0.3588, 0.5000, 0.6125, 0.5400],
[0.6160, 0.4086, 0.8775, 0.3983, 0.3750, 0.3783, 0.5128, 0.4882]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.5667, 0.3969, 0.8627, 0.5026, 0.3836, 0.4889, 0.5366, 0.5161],
[ 0.7085, 0.4804, 0.8648, 0.3856, 0.3830, 0.3395, 0.6228, 0.5103],
[ 0.6474, 0.4425, 0.6780, 0.2258, 0.3905, 0.2618, 0.5197, 0.4995],
[ 0.7389, 0.5162, 0.8219, 0.2639, 0.4505, 0.2242, 0.6105, 0.5333],
[ 0.7038, 0.4682, 0.8615, 0.5522, 0.3831, 0.4068, 0.6023, 0.5929],
[-0.0587, -0.0297, 0.9008, 0.3119, 0.5381, 0.2447, 0.6911, 0.5574],
[ 0.6270, 0.4166, 0.8636, 0.3521, 0.3723, 0.5205, 0.6568, 0.5517],
[ 0.6500, 0.4548, 0.8787, 0.3977, 0.3747, 0.4232, 0.5579, 0.4989]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6038, 0.3946, 0.8413, 0.4883, 0.3562, 0.4550, 0.5266, 0.4693],
[0.6200, 0.3993, 0.8639, 0.3687, 0.3658, 0.3139, 0.6002, 0.5374],
[0.6116, 0.4018, 0.6562, 0.1967, 0.3738, 0.2550, 0.5280, 0.5103],
[0.6203, 0.4073, 0.8189, 0.2398, 0.4400, 0.2054, 0.5929, 0.5501],
[0.6260, 0.4214, 0.8537, 0.5500, 0.3663, 0.3767, 0.5587, 0.5983],
[0.0000, 0.0000, 0.8900, 0.3217, 0.5038, 0.2233, 0.6694, 0.5609],
[0.6168, 0.4029, 0.8523, 0.3417, 0.3587, 0.5000, 0.6125, 0.5400],
[0.6160, 0.4086, 0.8775, 0.3983, 0.3750, 0.3783, 0.5128, 0.4882]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07921916476334445
step: 50
running loss: 0.001584383295266889
Train Steps: 50/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6283, 0.4283, 0.7477, 0.3542, 0.5125, 0.1917, 0.5500, 0.6167],
[0.6265, 0.4091, 0.8950, 0.3533, 0.3600, 0.3967, 0.6295, 0.4901],
[0.6087, 0.3951, 0.8387, 0.5833, 0.4188, 0.4933, 0.5146, 0.4830],
[0.6118, 0.4052, 0.8463, 0.3917, 0.3538, 0.3450, 0.5053, 0.5593],
[0.6250, 0.4146, 0.8838, 0.3933, 0.3588, 0.4283, 0.6162, 0.5367],
[0.6350, 0.4144, 0.9250, 0.4100, 0.4125, 0.3750, 0.7129, 0.5945],
[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.6218, 0.4098, 0.7238, 0.1850, 0.4238, 0.2517, 0.6288, 0.5350]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5915, 0.4134, 0.7551, 0.3165, 0.4903, 0.1958, 0.5103, 0.5853],
[0.5764, 0.3818, 0.9127, 0.3342, 0.3573, 0.3764, 0.6141, 0.4978],
[0.5345, 0.3572, 0.8517, 0.5715, 0.4077, 0.4864, 0.5188, 0.4861],
[0.5781, 0.4059, 0.8441, 0.3646, 0.3541, 0.3400, 0.4695, 0.5328],
[0.5979, 0.4039, 0.8465, 0.3703, 0.3558, 0.4157, 0.5717, 0.5015],
[0.5912, 0.4007, 0.9070, 0.3955, 0.4255, 0.3726, 0.6829, 0.5573],
[0.5950, 0.4042, 0.8472, 0.5555, 0.3779, 0.4802, 0.6432, 0.5175],
[0.6436, 0.4484, 0.7460, 0.2079, 0.4379, 0.2331, 0.5944, 0.5265]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6283, 0.4283, 0.7477, 0.3542, 0.5125, 0.1917, 0.5500, 0.6167],
[0.6265, 0.4091, 0.8950, 0.3533, 0.3600, 0.3967, 0.6295, 0.4901],
[0.6087, 0.3951, 0.8388, 0.5833, 0.4187, 0.4933, 0.5146, 0.4830],
[0.6118, 0.4052, 0.8462, 0.3917, 0.3537, 0.3450, 0.5053, 0.5593],
[0.6250, 0.4146, 0.8838, 0.3933, 0.3587, 0.4283, 0.6162, 0.5367],
[0.6350, 0.4144, 0.9250, 0.4100, 0.4125, 0.3750, 0.7129, 0.5945],
[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.6218, 0.4098, 0.7237, 0.1850, 0.4238, 0.2517, 0.6288, 0.5350]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07985461122007109
step: 51
running loss: 0.0015657766905896292
Train Steps: 51/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6268, 0.4061, 0.8350, 0.2433, 0.4575, 0.2283, 0.6350, 0.5300],
[0.6230, 0.4113, 0.7213, 0.1983, 0.4325, 0.2367, 0.6262, 0.5400],
[0.6076, 0.3958, 0.8700, 0.4667, 0.4546, 0.5046, 0.5231, 0.4960],
[0.6128, 0.4115, 0.7934, 0.3778, 0.3450, 0.4033, 0.5337, 0.5456],
[0.6215, 0.4119, 0.7688, 0.2300, 0.4200, 0.2283, 0.5925, 0.5317],
[0.6218, 0.4098, 0.7238, 0.1850, 0.4238, 0.2517, 0.6288, 0.5350],
[0.6154, 0.4112, 0.7037, 0.2317, 0.4238, 0.1833, 0.5350, 0.5600],
[0.6268, 0.4029, 0.8500, 0.2683, 0.3937, 0.3500, 0.6860, 0.5297]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5507, 0.3677, 0.8739, 0.2727, 0.4537, 0.1950, 0.5911, 0.5079],
[0.6034, 0.4039, 0.7401, 0.2273, 0.4371, 0.2180, 0.5913, 0.5303],
[0.5627, 0.3646, 0.9055, 0.5243, 0.4412, 0.4729, 0.5209, 0.4831],
[0.6226, 0.3989, 0.8272, 0.4100, 0.3243, 0.4034, 0.5167, 0.5258],
[0.5484, 0.3707, 0.7738, 0.2498, 0.4351, 0.2388, 0.5541, 0.5149],
[0.6328, 0.4251, 0.7578, 0.2479, 0.4367, 0.2240, 0.5967, 0.5330],
[0.5407, 0.3771, 0.7163, 0.2564, 0.4186, 0.1785, 0.4994, 0.5358],
[0.5917, 0.3917, 0.8435, 0.3103, 0.3848, 0.3313, 0.6699, 0.5156]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6268, 0.4060, 0.8350, 0.2433, 0.4575, 0.2283, 0.6350, 0.5300],
[0.6230, 0.4113, 0.7212, 0.1983, 0.4325, 0.2367, 0.6263, 0.5400],
[0.6076, 0.3958, 0.8700, 0.4667, 0.4546, 0.5046, 0.5231, 0.4960],
[0.6128, 0.4115, 0.7934, 0.3778, 0.3450, 0.4033, 0.5337, 0.5456],
[0.6215, 0.4119, 0.7688, 0.2300, 0.4200, 0.2283, 0.5925, 0.5317],
[0.6218, 0.4098, 0.7237, 0.1850, 0.4238, 0.2517, 0.6288, 0.5350],
[0.6154, 0.4112, 0.7038, 0.2317, 0.4238, 0.1833, 0.5350, 0.5600],
[0.6268, 0.4029, 0.8500, 0.2683, 0.3938, 0.3500, 0.6860, 0.5297]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.08078289640252478
step: 52
running loss: 0.001553517238510092
Train Steps: 52/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.7612, 0.3250, 0.4037, 0.2533, 0.5438, 0.5767],
[0.6111, 0.3995, 0.8788, 0.4567, 0.3813, 0.4833, 0.5450, 0.5700],
[ nan, nan, 0.8037, 0.2483, 0.3975, 0.2517, 0.5575, 0.5600],
[0.6202, 0.4053, 0.8638, 0.5283, 0.4546, 0.5108, 0.5900, 0.5133],
[0.6128, 0.4116, 0.8450, 0.4583, 0.3675, 0.4867, 0.5337, 0.5446],
[0.6268, 0.4102, 0.8938, 0.3667, 0.4025, 0.2833, 0.6275, 0.5183],
[0.6218, 0.4185, 0.7338, 0.2650, 0.4625, 0.1950, 0.5687, 0.5800],
[0.6273, 0.4100, 0.7137, 0.2133, 0.4000, 0.2650, 0.6075, 0.5633]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.1549, 0.0988, 0.7728, 0.2984, 0.3965, 0.2483, 0.5293, 0.5679],
[0.7679, 0.4968, 0.8719, 0.4534, 0.3593, 0.4609, 0.5512, 0.5227],
[0.2748, 0.1950, 0.7612, 0.2568, 0.3874, 0.2569, 0.5394, 0.5318],
[0.7197, 0.4644, 0.8651, 0.5402, 0.4529, 0.4879, 0.6104, 0.5005],
[0.6871, 0.4434, 0.8564, 0.4625, 0.3680, 0.4583, 0.5583, 0.5248],
[0.7213, 0.4817, 0.8850, 0.3534, 0.3950, 0.2741, 0.6116, 0.5200],
[0.7321, 0.4945, 0.7385, 0.2308, 0.4484, 0.1679, 0.5341, 0.5670],
[0.6125, 0.3907, 0.7119, 0.1921, 0.3792, 0.2419, 0.5768, 0.5231]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.7613, 0.3250, 0.4038, 0.2533, 0.5437, 0.5767],
[0.6111, 0.3995, 0.8788, 0.4567, 0.3812, 0.4833, 0.5450, 0.5700],
[0.0000, 0.0000, 0.8037, 0.2483, 0.3975, 0.2517, 0.5575, 0.5600],
[0.6202, 0.4053, 0.8637, 0.5283, 0.4546, 0.5108, 0.5900, 0.5133],
[0.6128, 0.4116, 0.8450, 0.4583, 0.3675, 0.4867, 0.5337, 0.5446],
[0.6268, 0.4102, 0.8938, 0.3667, 0.4025, 0.2833, 0.6275, 0.5183],
[0.6218, 0.4185, 0.7337, 0.2650, 0.4625, 0.1950, 0.5688, 0.5800],
[0.6273, 0.4099, 0.7138, 0.2133, 0.4000, 0.2650, 0.6075, 0.5633]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0040, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0040, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.08473318166215904
step: 53
running loss: 0.00159873927664451
Train Steps: 53/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6131, 0.4064, 0.8638, 0.5200, 0.4788, 0.4783, 0.5258, 0.5867],
[0.6195, 0.4101, 0.8650, 0.3917, 0.3575, 0.4033, 0.5800, 0.5650],
[0.6233, 0.4091, 0.8100, 0.2950, 0.3563, 0.3883, 0.6013, 0.5200],
[0.6099, 0.4030, 0.8638, 0.5117, 0.4983, 0.4965, 0.5086, 0.5388],
[0.6282, 0.4029, 0.8988, 0.3000, 0.4250, 0.4183, 0.7042, 0.5575],
[0.6250, 0.4110, 0.7238, 0.2067, 0.4263, 0.1883, 0.5625, 0.5633],
[0.6304, 0.4024, 0.8925, 0.4800, 0.3937, 0.4817, 0.7485, 0.5297],
[ nan, nan, 0.9088, 0.3783, 0.4562, 0.2617, 0.6741, 0.5575]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6802, 0.4430, 0.8318, 0.5072, 0.4398, 0.4642, 0.5124, 0.5521],
[0.6704, 0.4308, 0.8398, 0.3959, 0.3240, 0.3879, 0.5255, 0.5485],
[0.6728, 0.4352, 0.7903, 0.2926, 0.3243, 0.3784, 0.5523, 0.5330],
[0.6356, 0.4171, 0.8449, 0.5169, 0.4777, 0.4851, 0.4889, 0.5001],
[0.7161, 0.4596, 0.8432, 0.2972, 0.3887, 0.3969, 0.6283, 0.5522],
[0.6475, 0.4336, 0.6810, 0.2289, 0.3940, 0.1639, 0.4837, 0.5542],
[0.7142, 0.4602, 0.8448, 0.4690, 0.3557, 0.4662, 0.6634, 0.5211],
[0.1883, 0.1220, 0.8808, 0.3820, 0.4354, 0.2764, 0.6137, 0.5517]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6132, 0.4063, 0.8637, 0.5200, 0.4787, 0.4783, 0.5258, 0.5867],
[0.6195, 0.4101, 0.8650, 0.3917, 0.3575, 0.4033, 0.5800, 0.5650],
[0.6233, 0.4091, 0.8100, 0.2950, 0.3562, 0.3883, 0.6012, 0.5200],
[0.6098, 0.4030, 0.8637, 0.5117, 0.4983, 0.4965, 0.5086, 0.5388],
[0.6282, 0.4029, 0.8988, 0.3000, 0.4250, 0.4183, 0.7042, 0.5575],
[0.6250, 0.4110, 0.7237, 0.2067, 0.4263, 0.1883, 0.5625, 0.5633],
[0.6304, 0.4024, 0.8925, 0.4800, 0.3938, 0.4817, 0.7485, 0.5297],
[0.0000, 0.0000, 0.9087, 0.3783, 0.4563, 0.2617, 0.6741, 0.5575]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0022, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0022, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0869114036031533
step: 54
running loss: 0.0016094704370954315
Train Steps: 54/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6182, 0.4099, 0.7812, 0.3000, 0.3937, 0.2367, 0.5325, 0.5750],
[0.6350, 0.4144, 0.9250, 0.4100, 0.4125, 0.3750, 0.7129, 0.5945],
[0.6200, 0.4086, 0.8414, 0.2974, 0.4117, 0.2274, 0.5869, 0.5391],
[0.6203, 0.4072, 0.8892, 0.3523, 0.3783, 0.3017, 0.5898, 0.5478],
[0.6196, 0.4090, 0.8450, 0.3900, 0.3575, 0.3933, 0.5975, 0.5583],
[0.6186, 0.4154, 0.6825, 0.2633, 0.4150, 0.2300, 0.5713, 0.5517],
[0.6127, 0.4066, 0.8550, 0.5567, 0.4662, 0.5141, 0.5070, 0.5412],
[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4948, 0.3271, 0.7504, 0.2717, 0.3895, 0.2462, 0.5128, 0.5725],
[0.6211, 0.3864, 0.8843, 0.3831, 0.4266, 0.3624, 0.7101, 0.5913],
[0.5479, 0.3498, 0.8209, 0.2813, 0.4246, 0.2453, 0.5822, 0.5351],
[0.5730, 0.3568, 0.8808, 0.3202, 0.3858, 0.3009, 0.5986, 0.5536],
[0.6147, 0.3810, 0.8437, 0.3561, 0.3642, 0.3641, 0.5878, 0.5957],
[0.5775, 0.3750, 0.6776, 0.2280, 0.4179, 0.2321, 0.5617, 0.5697],
[0.5753, 0.3730, 0.8436, 0.5263, 0.4640, 0.4712, 0.5426, 0.5266],
[0.5807, 0.3767, 0.7651, 0.3495, 0.3590, 0.4238, 0.5293, 0.5445]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6182, 0.4099, 0.7812, 0.3000, 0.3938, 0.2367, 0.5325, 0.5750],
[0.6350, 0.4144, 0.9250, 0.4100, 0.4125, 0.3750, 0.7129, 0.5945],
[0.6199, 0.4086, 0.8414, 0.2974, 0.4117, 0.2274, 0.5869, 0.5391],
[0.6203, 0.4072, 0.8892, 0.3523, 0.3783, 0.3017, 0.5898, 0.5478],
[0.6196, 0.4090, 0.8450, 0.3900, 0.3575, 0.3933, 0.5975, 0.5583],
[0.6186, 0.4154, 0.6825, 0.2633, 0.4150, 0.2300, 0.5713, 0.5517],
[0.6127, 0.4066, 0.8550, 0.5567, 0.4662, 0.5141, 0.5070, 0.5412],
[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.08789730866556056
step: 55
running loss: 0.0015981328848283737
Train Steps: 55/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6115, 0.4005, 0.8838, 0.3867, 0.3763, 0.4700, 0.5800, 0.5550],
[0.6068, 0.3963, 0.8650, 0.4317, 0.4037, 0.5083, 0.5253, 0.4999],
[ nan, nan, 0.9088, 0.3783, 0.4562, 0.2617, 0.6741, 0.5575],
[0.6270, 0.4267, 0.7150, 0.3317, 0.4900, 0.1817, 0.5560, 0.6183],
[0.6275, 0.4081, 0.8063, 0.2017, 0.4825, 0.1583, 0.6156, 0.4869],
[0.6203, 0.4096, 0.8862, 0.4267, 0.3538, 0.4117, 0.6025, 0.5650],
[0.6188, 0.4099, 0.7400, 0.2433, 0.3962, 0.2750, 0.6162, 0.5467],
[0.6127, 0.4118, 0.8650, 0.5083, 0.4088, 0.5367, 0.5300, 0.5456]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6512, 0.4229, 0.8618, 0.3790, 0.3667, 0.4765, 0.5779, 0.5789],
[0.6838, 0.4149, 0.8431, 0.4274, 0.3979, 0.5157, 0.5459, 0.5217],
[0.1031, 0.0614, 0.8903, 0.3869, 0.4564, 0.2801, 0.6815, 0.5916],
[0.5853, 0.3887, 0.6898, 0.2776, 0.4559, 0.1826, 0.5637, 0.6347],
[0.6206, 0.3911, 0.7994, 0.2031, 0.4864, 0.1657, 0.6258, 0.5273],
[0.6177, 0.4136, 0.8885, 0.4072, 0.3660, 0.4113, 0.6229, 0.6092],
[0.6280, 0.4210, 0.7120, 0.2187, 0.3850, 0.2793, 0.6336, 0.5902],
[0.6331, 0.4122, 0.8470, 0.4942, 0.4314, 0.5270, 0.5640, 0.5644]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6115, 0.4005, 0.8838, 0.3867, 0.3762, 0.4700, 0.5800, 0.5550],
[0.6068, 0.3963, 0.8650, 0.4317, 0.4038, 0.5083, 0.5253, 0.4999],
[0.0000, 0.0000, 0.9087, 0.3783, 0.4563, 0.2617, 0.6741, 0.5575],
[0.6270, 0.4266, 0.7150, 0.3317, 0.4900, 0.1817, 0.5560, 0.6183],
[0.6275, 0.4081, 0.8062, 0.2017, 0.4825, 0.1583, 0.6156, 0.4869],
[0.6203, 0.4096, 0.8863, 0.4267, 0.3537, 0.4117, 0.6025, 0.5650],
[0.6188, 0.4099, 0.7400, 0.2433, 0.3963, 0.2750, 0.6162, 0.5467],
[0.6127, 0.4118, 0.8650, 0.5083, 0.4087, 0.5367, 0.5300, 0.5456]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.08864424467901699
step: 56
running loss: 0.001582932940696732
Train Steps: 56/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6346, 0.4144, 0.9088, 0.4667, 0.3850, 0.4333, 0.7121, 0.5899],
[ nan, nan, 0.8938, 0.2850, 0.4662, 0.3117, 0.7406, 0.5528],
[0.6229, 0.4066, 0.8513, 0.5717, 0.4500, 0.5050, 0.6025, 0.5350],
[0.6227, 0.4049, 0.8750, 0.5367, 0.3775, 0.3667, 0.5725, 0.5317],
[0.6200, 0.4055, 0.8011, 0.2988, 0.3842, 0.2798, 0.5949, 0.5183],
[0.6304, 0.4029, 0.8413, 0.5217, 0.4125, 0.5617, 0.7089, 0.5679],
[0.6132, 0.4066, 0.7259, 0.2402, 0.3588, 0.3300, 0.6000, 0.5600],
[0.6192, 0.4128, 0.8513, 0.5617, 0.4200, 0.5267, 0.5850, 0.5633]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6746, 0.4382, 0.8947, 0.4301, 0.4024, 0.4315, 0.6823, 0.5842],
[0.0795, 0.0425, 0.8813, 0.2713, 0.4756, 0.3016, 0.7231, 0.5805],
[0.6175, 0.3949, 0.8288, 0.5494, 0.4417, 0.4728, 0.5768, 0.5437],
[0.5646, 0.3568, 0.8741, 0.5262, 0.3934, 0.3711, 0.5676, 0.5532],
[0.6259, 0.4015, 0.7931, 0.2748, 0.3971, 0.2923, 0.5981, 0.5459],
[0.6373, 0.4096, 0.8234, 0.4940, 0.4075, 0.5483, 0.6636, 0.5948],
[0.6988, 0.4403, 0.7122, 0.2193, 0.3589, 0.3156, 0.5807, 0.5981],
[0.6013, 0.3702, 0.8606, 0.5430, 0.4338, 0.4950, 0.5684, 0.5725]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6346, 0.4144, 0.9087, 0.4667, 0.3850, 0.4333, 0.7121, 0.5899],
[0.0000, 0.0000, 0.8938, 0.2850, 0.4663, 0.3117, 0.7406, 0.5528],
[0.6229, 0.4066, 0.8512, 0.5717, 0.4500, 0.5050, 0.6025, 0.5350],
[0.6227, 0.4049, 0.8750, 0.5367, 0.3775, 0.3667, 0.5725, 0.5317],
[0.6201, 0.4055, 0.8011, 0.2988, 0.3842, 0.2798, 0.5949, 0.5183],
[0.6304, 0.4029, 0.8413, 0.5217, 0.4125, 0.5617, 0.7089, 0.5679],
[0.6132, 0.4066, 0.7259, 0.2402, 0.3587, 0.3300, 0.6000, 0.5600],
[0.6192, 0.4128, 0.8512, 0.5617, 0.4200, 0.5267, 0.5850, 0.5633]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.08935375869623385
step: 57
running loss: 0.0015676098016883131
Train Steps: 57/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6280, 0.4055, 0.8600, 0.5317, 0.3800, 0.4700, 0.6275, 0.5133],
[0.6263, 0.4233, 0.7924, 0.4626, 0.3788, 0.2883, 0.5573, 0.6047],
[0.6090, 0.4045, 0.7250, 0.2100, 0.4075, 0.2300, 0.5476, 0.5663],
[0.6258, 0.4038, 0.8750, 0.4883, 0.3900, 0.5500, 0.6375, 0.5217],
[0.6109, 0.4041, 0.6975, 0.3167, 0.3513, 0.3383, 0.5153, 0.5319],
[0.6226, 0.4185, 0.8850, 0.5500, 0.3800, 0.4250, 0.5625, 0.5617],
[0.6203, 0.4076, 0.8611, 0.2878, 0.4050, 0.2554, 0.5907, 0.5496],
[0.6201, 0.4116, 0.8725, 0.4733, 0.3700, 0.3217, 0.5386, 0.5767]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5957, 0.3914, 0.8953, 0.5222, 0.4134, 0.4844, 0.6682, 0.5365],
[0.5112, 0.3648, 0.8072, 0.4491, 0.4238, 0.3225, 0.6067, 0.6391],
[0.4843, 0.3409, 0.7270, 0.2297, 0.4249, 0.2574, 0.5738, 0.5921],
[0.5497, 0.3573, 0.8853, 0.4831, 0.4449, 0.5554, 0.6904, 0.5349],
[0.5592, 0.3758, 0.7483, 0.2906, 0.3913, 0.3537, 0.5571, 0.5424],
[0.5409, 0.3602, 0.9018, 0.5374, 0.4245, 0.4396, 0.6098, 0.5927],
[0.5360, 0.3595, 0.8909, 0.2613, 0.4279, 0.2904, 0.6356, 0.5659],
[0.4802, 0.3276, 0.8787, 0.4517, 0.3916, 0.3253, 0.5922, 0.6089]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6280, 0.4055, 0.8600, 0.5317, 0.3800, 0.4700, 0.6275, 0.5133],
[0.6263, 0.4232, 0.7924, 0.4626, 0.3787, 0.2883, 0.5573, 0.6047],
[0.6090, 0.4045, 0.7250, 0.2100, 0.4075, 0.2300, 0.5476, 0.5663],
[0.6258, 0.4038, 0.8750, 0.4883, 0.3900, 0.5500, 0.6375, 0.5217],
[0.6109, 0.4041, 0.6975, 0.3167, 0.3512, 0.3383, 0.5153, 0.5319],
[0.6226, 0.4185, 0.8850, 0.5500, 0.3800, 0.4250, 0.5625, 0.5617],
[0.6203, 0.4076, 0.8611, 0.2878, 0.4050, 0.2554, 0.5907, 0.5496],
[0.6201, 0.4116, 0.8725, 0.4733, 0.3700, 0.3217, 0.5386, 0.5767]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0022, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0022, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.09153115292428993
step: 58
running loss: 0.001578123326280861
Train Steps: 58/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6112, 0.4029, 0.8638, 0.4800, 0.4875, 0.5083, 0.5763, 0.5567],
[0.6339, 0.4081, 0.8425, 0.5417, 0.3850, 0.4833, 0.7335, 0.5760],
[0.6125, 0.3999, 0.8750, 0.4883, 0.4750, 0.4700, 0.5533, 0.5617],
[0.6300, 0.4013, 0.8938, 0.5350, 0.3675, 0.4600, 0.6456, 0.4973],
[ nan, nan, 0.9050, 0.3500, 0.5138, 0.2300, 0.7359, 0.5702],
[ nan, nan, 0.7515, 0.2708, 0.3987, 0.2267, 0.5162, 0.5567],
[0.6129, 0.3925, 0.8720, 0.5246, 0.4534, 0.5515, 0.6026, 0.5114],
[0.6151, 0.4125, 0.8738, 0.4417, 0.3575, 0.3783, 0.5138, 0.5483]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6248, 0.4224, 0.8997, 0.4786, 0.4800, 0.4956, 0.6026, 0.5643],
[0.7256, 0.4915, 0.8637, 0.5552, 0.3857, 0.5023, 0.7066, 0.5893],
[0.6146, 0.4201, 0.8895, 0.4822, 0.4621, 0.5014, 0.5588, 0.5500],
[0.7021, 0.4626, 0.8826, 0.5517, 0.3648, 0.4587, 0.6539, 0.4981],
[0.0649, 0.0642, 0.9014, 0.3397, 0.4924, 0.2533, 0.7295, 0.5833],
[0.0735, 0.0730, 0.7442, 0.2641, 0.3869, 0.2435, 0.5210, 0.5732],
[0.6739, 0.4641, 0.8749, 0.5194, 0.4548, 0.5321, 0.6159, 0.5258],
[0.6096, 0.4239, 0.8694, 0.4396, 0.3547, 0.3754, 0.5269, 0.5667]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6112, 0.4029, 0.8637, 0.4800, 0.4875, 0.5083, 0.5763, 0.5567],
[0.6339, 0.4081, 0.8425, 0.5417, 0.3850, 0.4833, 0.7335, 0.5760],
[0.6125, 0.3999, 0.8750, 0.4883, 0.4750, 0.4700, 0.5533, 0.5617],
[0.6300, 0.4013, 0.8938, 0.5350, 0.3675, 0.4600, 0.6456, 0.4973],
[0.0000, 0.0000, 0.9050, 0.3500, 0.5138, 0.2300, 0.7359, 0.5702],
[0.0000, 0.0000, 0.7515, 0.2708, 0.3988, 0.2267, 0.5163, 0.5567],
[0.6129, 0.3925, 0.8720, 0.5246, 0.4534, 0.5515, 0.6026, 0.5114],
[0.6151, 0.4125, 0.8737, 0.4417, 0.3575, 0.3783, 0.5138, 0.5483]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.09251674797269516
step: 59
running loss: 0.0015680804741134773
Train Steps: 59/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6086, 0.3981, 0.8700, 0.4750, 0.4512, 0.5283, 0.5324, 0.5038],
[0.6126, 0.4067, 0.8638, 0.5383, 0.4188, 0.4850, 0.5016, 0.5392],
[0.6222, 0.4108, 0.8938, 0.4233, 0.3600, 0.3817, 0.5825, 0.5283],
[0.6200, 0.4039, 0.8880, 0.4799, 0.3625, 0.4285, 0.5866, 0.5148],
[0.6300, 0.4133, 0.8538, 0.2167, 0.5587, 0.2250, 0.7390, 0.5413],
[0.6260, 0.4153, 0.9000, 0.4533, 0.4025, 0.2633, 0.6223, 0.4967],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5413, 0.5683],
[0.6199, 0.4093, 0.7913, 0.2533, 0.4288, 0.2467, 0.5975, 0.5700]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5696, 0.3680, 0.8549, 0.4859, 0.4327, 0.5179, 0.5572, 0.4864],
[0.5494, 0.3816, 0.8490, 0.5808, 0.4114, 0.5042, 0.5461, 0.5231],
[0.5412, 0.3755, 0.8835, 0.4247, 0.3414, 0.3799, 0.6158, 0.5338],
[0.5183, 0.3418, 0.8871, 0.4990, 0.3579, 0.4325, 0.6339, 0.5204],
[0.4538, 0.3013, 0.8366, 0.2473, 0.5292, 0.2839, 0.7284, 0.5587],
[0.5399, 0.3747, 0.9038, 0.4655, 0.3930, 0.3018, 0.6449, 0.5132],
[0.5060, 0.3411, 0.8525, 0.5727, 0.3688, 0.3681, 0.5648, 0.5554],
[0.5151, 0.3688, 0.7626, 0.2425, 0.4081, 0.2603, 0.6358, 0.5804]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6086, 0.3981, 0.8700, 0.4750, 0.4512, 0.5283, 0.5324, 0.5038],
[0.6126, 0.4067, 0.8637, 0.5383, 0.4187, 0.4850, 0.5016, 0.5392],
[0.6222, 0.4108, 0.8938, 0.4233, 0.3600, 0.3817, 0.5825, 0.5283],
[0.6201, 0.4039, 0.8880, 0.4799, 0.3625, 0.4285, 0.5866, 0.5148],
[0.6300, 0.4133, 0.8537, 0.2167, 0.5587, 0.2250, 0.7390, 0.5413],
[0.6260, 0.4153, 0.9000, 0.4533, 0.4025, 0.2633, 0.6223, 0.4967],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5412, 0.5683],
[0.6198, 0.4093, 0.7912, 0.2533, 0.4288, 0.2467, 0.5975, 0.5700]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0022, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0022, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.09467396742547862
step: 60
running loss: 0.0015778994570913103
Train Steps: 60/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6277, 0.4057, 0.8300, 0.2650, 0.4363, 0.1850, 0.6140, 0.4823],
[0.6236, 0.3977, 0.8985, 0.4806, 0.3835, 0.5216, 0.6613, 0.5166],
[0.6202, 0.4079, 0.8025, 0.2500, 0.3763, 0.3217, 0.6125, 0.5533],
[0.6311, 0.3998, 0.7975, 0.5767, 0.3838, 0.4850, 0.7327, 0.5343],
[0.6185, 0.4129, 0.8900, 0.4567, 0.3937, 0.5417, 0.5734, 0.5110],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3513, 0.4050, 0.6112, 0.5500],
[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383],
[0.6149, 0.4054, 0.6713, 0.2333, 0.4025, 0.2017, 0.5213, 0.5695]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5558, 0.3568, 0.8592, 0.3219, 0.4439, 0.2026, 0.6285, 0.4938],
[0.5836, 0.3509, 0.9035, 0.5453, 0.4080, 0.5315, 0.6395, 0.5006],
[0.6229, 0.4163, 0.8235, 0.3249, 0.3960, 0.3336, 0.6160, 0.5354],
[0.5874, 0.3863, 0.8409, 0.5990, 0.4015, 0.4852, 0.6877, 0.5168],
[0.4982, 0.3207, 0.9290, 0.5280, 0.4096, 0.5368, 0.5549, 0.4946],
[0.5610, 0.3600, 0.8111, 0.3305, 0.3712, 0.4111, 0.6245, 0.5420],
[0.5940, 0.3892, 0.8602, 0.3784, 0.3739, 0.3779, 0.6145, 0.5378],
[0.5522, 0.3593, 0.7109, 0.2939, 0.4385, 0.2026, 0.5390, 0.5488]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6277, 0.4056, 0.8300, 0.2650, 0.4363, 0.1850, 0.6140, 0.4823],
[0.6236, 0.3977, 0.8985, 0.4806, 0.3835, 0.5216, 0.6613, 0.5166],
[0.6202, 0.4079, 0.8025, 0.2500, 0.3762, 0.3217, 0.6125, 0.5533],
[0.6311, 0.3998, 0.7975, 0.5767, 0.3837, 0.4850, 0.7327, 0.5343],
[0.6186, 0.4129, 0.8900, 0.4567, 0.3938, 0.5417, 0.5734, 0.5110],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3512, 0.4050, 0.6112, 0.5500],
[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383],
[0.6149, 0.4054, 0.6712, 0.2333, 0.4025, 0.2017, 0.5213, 0.5695]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.09618941575172357
step: 61
running loss: 0.0015768756680610422
Train Steps: 61/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6178, 0.4059, 0.7525, 0.2250, 0.4313, 0.1783, 0.5404, 0.5240],
[0.6189, 0.4029, 0.8375, 0.5767, 0.4745, 0.4829, 0.5551, 0.5598],
[0.6150, 0.4097, 0.7468, 0.3194, 0.3825, 0.2633, 0.5463, 0.5800],
[0.6255, 0.4017, 0.8688, 0.3217, 0.3638, 0.3550, 0.6344, 0.4901],
[0.6262, 0.4163, 0.8850, 0.5183, 0.3763, 0.4150, 0.6025, 0.5500],
[0.6225, 0.4116, 0.8662, 0.3517, 0.3663, 0.3233, 0.5837, 0.5317],
[ nan, nan, 0.7240, 0.2722, 0.3900, 0.2567, 0.5168, 0.5933],
[0.6213, 0.4131, 0.8438, 0.3550, 0.3513, 0.4400, 0.5716, 0.5123]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6293, 0.3999, 0.7578, 0.2511, 0.4518, 0.1490, 0.5578, 0.5300],
[0.6185, 0.4012, 0.8560, 0.5950, 0.4820, 0.4643, 0.5926, 0.5478],
[0.5366, 0.3654, 0.7644, 0.3100, 0.3725, 0.2572, 0.5464, 0.5521],
[0.5998, 0.3699, 0.8737, 0.3380, 0.3826, 0.3640, 0.6650, 0.4941],
[0.5691, 0.3774, 0.9011, 0.5399, 0.3759, 0.4019, 0.6141, 0.5238],
[0.6344, 0.4208, 0.8663, 0.3617, 0.3727, 0.3084, 0.6055, 0.5220],
[0.0288, 0.0073, 0.7313, 0.2803, 0.4008, 0.2289, 0.5316, 0.5480],
[0.6353, 0.4239, 0.8864, 0.3825, 0.3525, 0.4215, 0.5744, 0.4790]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6178, 0.4059, 0.7525, 0.2250, 0.4313, 0.1783, 0.5404, 0.5240],
[0.6189, 0.4029, 0.8375, 0.5767, 0.4745, 0.4829, 0.5551, 0.5598],
[0.6150, 0.4097, 0.7468, 0.3194, 0.3825, 0.2633, 0.5462, 0.5800],
[0.6255, 0.4017, 0.8687, 0.3217, 0.3638, 0.3550, 0.6344, 0.4901],
[0.6262, 0.4163, 0.8850, 0.5183, 0.3762, 0.4150, 0.6025, 0.5500],
[0.6225, 0.4116, 0.8662, 0.3517, 0.3663, 0.3233, 0.5838, 0.5317],
[0.0000, 0.0000, 0.7240, 0.2722, 0.3900, 0.2567, 0.5168, 0.5933],
[0.6213, 0.4131, 0.8438, 0.3550, 0.3512, 0.4400, 0.5716, 0.5123]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.09672151939594187
step: 62
running loss: 0.0015600245063861593
Train Steps: 62/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6149, 0.4054, 0.6713, 0.2333, 0.4025, 0.2017, 0.5213, 0.5695],
[0.6068, 0.3963, 0.8650, 0.4317, 0.4037, 0.5083, 0.5253, 0.4999],
[0.6214, 0.3982, 0.8938, 0.4517, 0.3663, 0.4083, 0.5863, 0.5050],
[0.6277, 0.4083, 0.8350, 0.2717, 0.4562, 0.1800, 0.5918, 0.4878],
[0.6117, 0.4018, 0.6562, 0.1967, 0.3738, 0.2550, 0.5280, 0.5103],
[0.6207, 0.4081, 0.7662, 0.2067, 0.3962, 0.3200, 0.6312, 0.5300],
[0.6213, 0.4001, 0.7712, 0.2117, 0.4338, 0.1800, 0.5850, 0.5183],
[0.6125, 0.4076, 0.8488, 0.3883, 0.3700, 0.3683, 0.5026, 0.5505]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5845, 0.3731, 0.7125, 0.2705, 0.4301, 0.1965, 0.5510, 0.5530],
[0.5448, 0.3305, 0.8915, 0.4691, 0.3918, 0.5389, 0.5213, 0.4772],
[0.5425, 0.3449, 0.9177, 0.5062, 0.3573, 0.4249, 0.5814, 0.4759],
[0.6598, 0.4127, 0.8657, 0.3145, 0.4771, 0.2235, 0.6076, 0.4885],
[0.5708, 0.3631, 0.7040, 0.2629, 0.3926, 0.2395, 0.5489, 0.5093],
[0.5866, 0.3729, 0.7770, 0.2500, 0.3852, 0.3128, 0.6369, 0.5207],
[0.6762, 0.4158, 0.7889, 0.2567, 0.4456, 0.1642, 0.6077, 0.5199],
[0.5105, 0.3045, 0.8920, 0.4341, 0.3555, 0.3648, 0.4901, 0.5239]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6149, 0.4054, 0.6712, 0.2333, 0.4025, 0.2017, 0.5213, 0.5695],
[0.6068, 0.3963, 0.8650, 0.4317, 0.4038, 0.5083, 0.5253, 0.4999],
[0.6214, 0.3982, 0.8938, 0.4517, 0.3663, 0.4083, 0.5863, 0.5050],
[0.6277, 0.4083, 0.8350, 0.2717, 0.4563, 0.1800, 0.5918, 0.4878],
[0.6116, 0.4018, 0.6562, 0.1967, 0.3738, 0.2550, 0.5280, 0.5103],
[0.6207, 0.4081, 0.7663, 0.2067, 0.3963, 0.3200, 0.6313, 0.5300],
[0.6213, 0.4001, 0.7713, 0.2117, 0.4338, 0.1800, 0.5850, 0.5183],
[0.6125, 0.4076, 0.8487, 0.3883, 0.3700, 0.3683, 0.5026, 0.5505]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0980854112713132
step: 63
running loss: 0.0015569112900208446
Train Steps: 63/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6136, 0.4085, 0.6688, 0.2317, 0.3862, 0.2367, 0.5517, 0.5783],
[0.6222, 0.3937, 0.8350, 0.5617, 0.4138, 0.4600, 0.5800, 0.5233],
[0.6272, 0.4045, 0.8538, 0.5900, 0.3750, 0.4417, 0.5989, 0.4649],
[0.6082, 0.4024, 0.8738, 0.4017, 0.3688, 0.3950, 0.5306, 0.5136],
[0.6183, 0.4076, 0.8838, 0.4517, 0.3813, 0.4483, 0.5775, 0.5633],
[0.6202, 0.4066, 0.8746, 0.3376, 0.3717, 0.3090, 0.5842, 0.5165],
[0.6361, 0.4071, 0.9100, 0.4783, 0.3738, 0.3967, 0.6670, 0.5332],
[0.6279, 0.4050, 0.8025, 0.2200, 0.4313, 0.2733, 0.6820, 0.5320]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6443, 0.4123, 0.6926, 0.2116, 0.3916, 0.2383, 0.5444, 0.5459],
[0.5970, 0.3596, 0.8289, 0.5472, 0.4022, 0.4737, 0.5319, 0.5218],
[0.6078, 0.3907, 0.8406, 0.5781, 0.3599, 0.4388, 0.5628, 0.4617],
[0.5568, 0.3553, 0.8705, 0.3905, 0.3469, 0.3844, 0.4892, 0.4773],
[0.7234, 0.4420, 0.8791, 0.4286, 0.3780, 0.4776, 0.5646, 0.5362],
[0.6287, 0.4008, 0.8808, 0.3129, 0.3524, 0.3089, 0.5696, 0.4900],
[0.7104, 0.4353, 0.9023, 0.4677, 0.3627, 0.4362, 0.6397, 0.5030],
[0.6305, 0.4165, 0.8075, 0.1914, 0.4149, 0.2623, 0.6327, 0.5142]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6136, 0.4085, 0.6687, 0.2317, 0.3862, 0.2367, 0.5517, 0.5783],
[0.6222, 0.3937, 0.8350, 0.5617, 0.4137, 0.4600, 0.5800, 0.5233],
[0.6271, 0.4045, 0.8537, 0.5900, 0.3750, 0.4417, 0.5989, 0.4649],
[0.6082, 0.4024, 0.8737, 0.4017, 0.3688, 0.3950, 0.5306, 0.5136],
[0.6183, 0.4076, 0.8838, 0.4517, 0.3812, 0.4483, 0.5775, 0.5633],
[0.6202, 0.4066, 0.8746, 0.3376, 0.3717, 0.3090, 0.5842, 0.5165],
[0.6361, 0.4071, 0.9100, 0.4783, 0.3738, 0.3967, 0.6670, 0.5332],
[0.6279, 0.4050, 0.8025, 0.2200, 0.4313, 0.2733, 0.6820, 0.5320]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.09885636498802342
step: 64
running loss: 0.0015446307029378659
Train Steps: 64/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.6124, 0.4030, 0.8650, 0.4867, 0.4999, 0.5106, 0.5137, 0.5773],
[0.6101, 0.4042, 0.7775, 0.2617, 0.3713, 0.2817, 0.5440, 0.5650],
[ nan, nan, 0.9088, 0.3783, 0.4562, 0.2617, 0.6741, 0.5575],
[0.6224, 0.4179, 0.8700, 0.5683, 0.4037, 0.4683, 0.5650, 0.5600],
[ nan, nan, 0.8525, 0.2217, 0.5413, 0.2367, 0.7367, 0.5482],
[0.6250, 0.4131, 0.8688, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367],
[0.6148, 0.4053, 0.8750, 0.4550, 0.4850, 0.5218, 0.5863, 0.5567]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7994, 0.5367, 0.7996, 0.5162, 0.3479, 0.4840, 0.5989, 0.5018],
[0.7304, 0.4841, 0.8247, 0.4373, 0.4467, 0.4928, 0.4858, 0.4879],
[0.6837, 0.4597, 0.7335, 0.2450, 0.3503, 0.2686, 0.5322, 0.5364],
[0.0720, 0.0430, 0.8790, 0.3516, 0.4122, 0.2363, 0.6346, 0.5353],
[0.7726, 0.5192, 0.8251, 0.5377, 0.3656, 0.4561, 0.5352, 0.5271],
[0.1233, 0.0741, 0.8074, 0.1840, 0.4907, 0.2171, 0.6621, 0.5080],
[0.6856, 0.4354, 0.8384, 0.2577, 0.4017, 0.2215, 0.5753, 0.5097],
[0.8259, 0.5425, 0.8471, 0.4142, 0.4311, 0.4802, 0.5386, 0.5119]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.6124, 0.4030, 0.8650, 0.4867, 0.4999, 0.5106, 0.5137, 0.5773],
[0.6101, 0.4042, 0.7775, 0.2617, 0.3713, 0.2817, 0.5440, 0.5650],
[0.0000, 0.0000, 0.9087, 0.3783, 0.4563, 0.2617, 0.6741, 0.5575],
[0.6224, 0.4179, 0.8700, 0.5683, 0.4038, 0.4683, 0.5650, 0.5600],
[0.0000, 0.0000, 0.8525, 0.2217, 0.5412, 0.2367, 0.7367, 0.5482],
[0.6250, 0.4131, 0.8687, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367],
[0.6148, 0.4053, 0.8750, 0.4550, 0.4850, 0.5218, 0.5863, 0.5567]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0043, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0043, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.10314330333494581
step: 65
running loss: 0.0015868200513068586
Train Steps: 65/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6176, 0.4017, 0.8788, 0.5100, 0.4075, 0.5250, 0.5913, 0.5033],
[0.6350, 0.4043, 0.8738, 0.5650, 0.3850, 0.4750, 0.6401, 0.4950],
[0.6130, 0.4072, 0.8550, 0.4567, 0.3638, 0.3667, 0.5290, 0.5892],
[0.6276, 0.4120, 0.8738, 0.3133, 0.4225, 0.2217, 0.6203, 0.4892],
[0.6182, 0.4099, 0.7812, 0.3000, 0.3937, 0.2367, 0.5325, 0.5750],
[0.6224, 0.4061, 0.8988, 0.4300, 0.3838, 0.4750, 0.6112, 0.5483],
[0.6147, 0.4026, 0.6600, 0.2467, 0.4088, 0.2150, 0.5489, 0.5773],
[0.6122, 0.4006, 0.8850, 0.4217, 0.4088, 0.5517, 0.6063, 0.5517]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6405, 0.4135, 0.8524, 0.4461, 0.4034, 0.5525, 0.5545, 0.5209],
[0.6956, 0.4378, 0.8569, 0.5324, 0.3790, 0.4938, 0.6071, 0.5266],
[0.5868, 0.3892, 0.8500, 0.4279, 0.3564, 0.3593, 0.5179, 0.5958],
[0.6459, 0.4150, 0.8801, 0.3083, 0.4352, 0.2120, 0.6126, 0.5217],
[0.6575, 0.4345, 0.7819, 0.2809, 0.3977, 0.2372, 0.5261, 0.5703],
[0.6123, 0.4102, 0.8703, 0.3776, 0.3593, 0.4997, 0.5979, 0.5484],
[0.6556, 0.4435, 0.7015, 0.2308, 0.4147, 0.2139, 0.5435, 0.6041],
[0.5834, 0.3792, 0.8637, 0.3678, 0.4143, 0.5444, 0.5634, 0.5441]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6176, 0.4017, 0.8788, 0.5100, 0.4075, 0.5250, 0.5913, 0.5033],
[0.6350, 0.4043, 0.8737, 0.5650, 0.3850, 0.4750, 0.6401, 0.4950],
[0.6130, 0.4072, 0.8550, 0.4567, 0.3638, 0.3667, 0.5290, 0.5892],
[0.6276, 0.4120, 0.8737, 0.3133, 0.4225, 0.2217, 0.6203, 0.4892],
[0.6182, 0.4099, 0.7812, 0.3000, 0.3938, 0.2367, 0.5325, 0.5750],
[0.6224, 0.4061, 0.8988, 0.4300, 0.3837, 0.4750, 0.6112, 0.5483],
[0.6147, 0.4026, 0.6600, 0.2467, 0.4087, 0.2150, 0.5489, 0.5773],
[0.6122, 0.4006, 0.8850, 0.4217, 0.4087, 0.5517, 0.6062, 0.5517]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.1037804797233548
step: 66
running loss: 0.0015724315109599213
Train Steps: 66/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6276, 0.4095, 0.8237, 0.2250, 0.4662, 0.1783, 0.6171, 0.4869],
[0.6255, 0.4017, 0.8688, 0.3217, 0.3638, 0.3550, 0.6344, 0.4901],
[0.6254, 0.3993, 0.8988, 0.4767, 0.3987, 0.5517, 0.6955, 0.5285],
[0.6111, 0.3995, 0.8788, 0.4567, 0.3813, 0.4833, 0.5450, 0.5700],
[0.6300, 0.4102, 0.9088, 0.4433, 0.4088, 0.3067, 0.6820, 0.5540],
[0.6148, 0.4053, 0.8750, 0.4550, 0.4850, 0.5218, 0.5863, 0.5567],
[0.6277, 0.4013, 0.8888, 0.4767, 0.3600, 0.3567, 0.6148, 0.4672],
[ nan, nan, 0.7625, 0.2433, 0.3713, 0.2867, 0.5235, 0.5220]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6785, 0.4481, 0.8139, 0.2020, 0.4749, 0.1850, 0.6138, 0.5308],
[0.6331, 0.4025, 0.8234, 0.2862, 0.3667, 0.3415, 0.6191, 0.5370],
[0.6745, 0.4569, 0.8635, 0.4377, 0.4150, 0.5758, 0.6779, 0.5648],
[0.7044, 0.4675, 0.8349, 0.4179, 0.3905, 0.4767, 0.5015, 0.5859],
[0.6103, 0.4076, 0.8960, 0.4278, 0.4193, 0.3025, 0.6647, 0.5860],
[0.7442, 0.4936, 0.8570, 0.4359, 0.4789, 0.4910, 0.5747, 0.5813],
[0.7321, 0.5025, 0.8436, 0.4162, 0.3645, 0.3410, 0.6136, 0.5306],
[0.0770, 0.0437, 0.7523, 0.2256, 0.3834, 0.2551, 0.5500, 0.5512]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6276, 0.4095, 0.8238, 0.2250, 0.4663, 0.1783, 0.6171, 0.4869],
[0.6255, 0.4017, 0.8687, 0.3217, 0.3638, 0.3550, 0.6344, 0.4901],
[0.6254, 0.3993, 0.8988, 0.4767, 0.3988, 0.5517, 0.6955, 0.5285],
[0.6111, 0.3995, 0.8788, 0.4567, 0.3812, 0.4833, 0.5450, 0.5700],
[0.6300, 0.4102, 0.9087, 0.4433, 0.4087, 0.3067, 0.6820, 0.5540],
[0.6148, 0.4053, 0.8750, 0.4550, 0.4850, 0.5218, 0.5863, 0.5567],
[0.6277, 0.4013, 0.8888, 0.4767, 0.3600, 0.3567, 0.6148, 0.4672],
[0.0000, 0.0000, 0.7625, 0.2433, 0.3713, 0.2867, 0.5235, 0.5220]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0018, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0018, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.10556276931311004
step: 67
running loss: 0.0015755637210911947
Train Steps: 67/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6068, 0.3963, 0.8650, 0.4317, 0.4037, 0.5083, 0.5253, 0.4999],
[0.6157, 0.3956, 0.8323, 0.4138, 0.3479, 0.4431, 0.5914, 0.5131],
[0.6332, 0.4128, 0.9200, 0.3517, 0.4400, 0.3833, 0.7461, 0.5494],
[0.6137, 0.4035, 0.8850, 0.4417, 0.3900, 0.4283, 0.5449, 0.5617],
[0.6225, 0.4116, 0.8662, 0.3517, 0.3663, 0.3233, 0.5837, 0.5317],
[0.6216, 0.4167, 0.8588, 0.5583, 0.3975, 0.5167, 0.5775, 0.5667],
[0.6273, 0.4105, 0.8988, 0.4517, 0.3912, 0.2550, 0.5894, 0.4811],
[0.6128, 0.4022, 0.8738, 0.5067, 0.4983, 0.5231, 0.5364, 0.5064]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5519, 0.3711, 0.8373, 0.3983, 0.3957, 0.4941, 0.5430, 0.5392],
[0.5763, 0.3926, 0.8314, 0.3637, 0.3484, 0.4117, 0.5856, 0.5564],
[0.5165, 0.3468, 0.8993, 0.3403, 0.4354, 0.3505, 0.7177, 0.5684],
[0.6442, 0.4390, 0.8608, 0.4409, 0.3806, 0.4275, 0.5905, 0.5781],
[0.6688, 0.4501, 0.8287, 0.3181, 0.3599, 0.2964, 0.6153, 0.5782],
[0.6583, 0.4522, 0.8290, 0.5357, 0.4189, 0.5248, 0.6321, 0.5842],
[0.6497, 0.4241, 0.8771, 0.4061, 0.4136, 0.2432, 0.6155, 0.5340],
[0.6057, 0.4289, 0.8389, 0.4843, 0.4893, 0.4952, 0.5470, 0.5456]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6068, 0.3963, 0.8650, 0.4317, 0.4038, 0.5083, 0.5253, 0.4999],
[0.6157, 0.3956, 0.8323, 0.4138, 0.3479, 0.4431, 0.5914, 0.5131],
[0.6332, 0.4128, 0.9200, 0.3517, 0.4400, 0.3833, 0.7461, 0.5494],
[0.6137, 0.4035, 0.8850, 0.4417, 0.3900, 0.4283, 0.5449, 0.5617],
[0.6225, 0.4116, 0.8662, 0.3517, 0.3663, 0.3233, 0.5838, 0.5317],
[0.6216, 0.4167, 0.8587, 0.5583, 0.3975, 0.5167, 0.5775, 0.5667],
[0.6273, 0.4105, 0.8988, 0.4517, 0.3913, 0.2550, 0.5894, 0.4811],
[0.6128, 0.4022, 0.8737, 0.5067, 0.4983, 0.5231, 0.5364, 0.5064]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.10667031232151203
step: 68
running loss: 0.0015686810635516474
Train Steps: 68/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6185, 0.4129, 0.8900, 0.4567, 0.3937, 0.5417, 0.5734, 0.5110],
[0.6098, 0.3991, 0.8638, 0.4717, 0.4263, 0.4967, 0.5212, 0.5650],
[0.6332, 0.4118, 0.9238, 0.4267, 0.4012, 0.4733, 0.7525, 0.5436],
[0.6182, 0.4058, 0.8738, 0.4350, 0.3563, 0.3400, 0.5290, 0.5822],
[0.6186, 0.4013, 0.8191, 0.3188, 0.4279, 0.2060, 0.5767, 0.5411],
[0.6127, 0.4119, 0.8650, 0.5300, 0.4512, 0.5250, 0.5260, 0.5461],
[0.6037, 0.4020, 0.8300, 0.4033, 0.3575, 0.4883, 0.5647, 0.5631],
[0.6310, 0.4017, 0.8563, 0.5800, 0.3688, 0.4750, 0.6326, 0.5006]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6513, 0.4373, 0.8968, 0.4452, 0.4122, 0.5273, 0.6020, 0.5217],
[0.6055, 0.3957, 0.8620, 0.4681, 0.4406, 0.4793, 0.5524, 0.5462],
[0.5849, 0.3926, 0.9103, 0.4227, 0.4073, 0.4678, 0.7246, 0.5526],
[0.6474, 0.4221, 0.8637, 0.4193, 0.3624, 0.3218, 0.5677, 0.5930],
[0.5914, 0.3841, 0.8379, 0.3149, 0.4315, 0.1825, 0.6207, 0.5486],
[0.5509, 0.3660, 0.8650, 0.5164, 0.4588, 0.5093, 0.5628, 0.5499],
[0.5631, 0.3833, 0.8470, 0.3880, 0.3613, 0.4727, 0.5943, 0.5614],
[0.6208, 0.4106, 0.8653, 0.5627, 0.3887, 0.4721, 0.6646, 0.5145]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6186, 0.4129, 0.8900, 0.4567, 0.3938, 0.5417, 0.5734, 0.5110],
[0.6098, 0.3991, 0.8637, 0.4717, 0.4263, 0.4967, 0.5213, 0.5650],
[0.6332, 0.4118, 0.9237, 0.4267, 0.4013, 0.4733, 0.7525, 0.5436],
[0.6182, 0.4058, 0.8737, 0.4350, 0.3562, 0.3400, 0.5290, 0.5822],
[0.6186, 0.4013, 0.8191, 0.3188, 0.4279, 0.2060, 0.5767, 0.5411],
[0.6127, 0.4119, 0.8650, 0.5300, 0.4512, 0.5250, 0.5260, 0.5461],
[0.6037, 0.4020, 0.8300, 0.4033, 0.3575, 0.4883, 0.5647, 0.5631],
[0.6310, 0.4017, 0.8562, 0.5800, 0.3688, 0.4750, 0.6326, 0.5006]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.10714027981157415
step: 69
running loss: 0.001552757678428611
Train Steps: 69/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6197, 0.4118, 0.8688, 0.5517, 0.4037, 0.5233, 0.5875, 0.5600],
[0.6168, 0.4029, 0.8523, 0.3417, 0.3588, 0.5000, 0.6125, 0.5400],
[0.6161, 0.4076, 0.8900, 0.4667, 0.4125, 0.5917, 0.6262, 0.5367],
[0.6261, 0.4066, 0.8325, 0.2150, 0.4763, 0.2667, 0.7002, 0.5633],
[ nan, nan, 0.7425, 0.2117, 0.3937, 0.2433, 0.5438, 0.5567],
[0.6222, 0.4172, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633],
[0.6357, 0.4139, 0.8450, 0.5883, 0.3775, 0.4950, 0.6488, 0.5297],
[0.6136, 0.4029, 0.8263, 0.3350, 0.3625, 0.3067, 0.5675, 0.5167]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6797, 0.4425, 0.8824, 0.5833, 0.4246, 0.5367, 0.5965, 0.5615],
[0.5917, 0.3821, 0.8896, 0.3713, 0.3764, 0.4707, 0.6431, 0.5447],
[0.6304, 0.4132, 0.9070, 0.4863, 0.4543, 0.5783, 0.6085, 0.5383],
[0.6103, 0.3874, 0.8507, 0.2457, 0.4849, 0.2317, 0.7062, 0.5364],
[0.1297, 0.0855, 0.7537, 0.2486, 0.4253, 0.2378, 0.5901, 0.5524],
[0.6390, 0.4320, 0.9092, 0.5563, 0.3869, 0.4732, 0.5894, 0.5641],
[0.6987, 0.4476, 0.8577, 0.6106, 0.3919, 0.5049, 0.6735, 0.5354],
[0.6582, 0.4399, 0.8386, 0.3634, 0.4016, 0.2942, 0.5853, 0.5336]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6197, 0.4118, 0.8687, 0.5517, 0.4038, 0.5233, 0.5875, 0.5600],
[0.6168, 0.4029, 0.8523, 0.3417, 0.3587, 0.5000, 0.6125, 0.5400],
[0.6161, 0.4076, 0.8900, 0.4667, 0.4125, 0.5917, 0.6263, 0.5367],
[0.6261, 0.4066, 0.8325, 0.2150, 0.4762, 0.2667, 0.7002, 0.5633],
[0.0000, 0.0000, 0.7425, 0.2117, 0.3938, 0.2433, 0.5437, 0.5567],
[0.6222, 0.4171, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633],
[0.6357, 0.4139, 0.8450, 0.5883, 0.3775, 0.4950, 0.6488, 0.5297],
[0.6136, 0.4029, 0.8263, 0.3350, 0.3625, 0.3067, 0.5675, 0.5167]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.10814244553330354
step: 70
running loss: 0.0015448920790471935
Train Steps: 70/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6068, 0.3963, 0.8650, 0.4317, 0.4037, 0.5083, 0.5253, 0.4999],
[0.6098, 0.3991, 0.8638, 0.4717, 0.4263, 0.4967, 0.5212, 0.5650],
[0.6198, 0.3997, 0.8582, 0.5361, 0.4117, 0.5016, 0.5942, 0.5134],
[0.6300, 0.4133, 0.8538, 0.2167, 0.5587, 0.2250, 0.7390, 0.5413],
[0.6257, 0.4034, 0.8287, 0.2333, 0.3925, 0.2717, 0.6330, 0.4901],
[0.6276, 0.4095, 0.8237, 0.2250, 0.4662, 0.1783, 0.6171, 0.4869],
[0.6200, 0.3961, 0.8461, 0.5497, 0.4142, 0.4577, 0.5892, 0.5402],
[0.6193, 0.4050, 0.7313, 0.2433, 0.4075, 0.2117, 0.5649, 0.5656]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5551, 0.3648, 0.8834, 0.4773, 0.3928, 0.5299, 0.5418, 0.5109],
[0.5776, 0.3809, 0.8719, 0.5290, 0.4246, 0.5201, 0.5414, 0.5491],
[0.5532, 0.3692, 0.8817, 0.5963, 0.4139, 0.5325, 0.6002, 0.5089],
[0.5847, 0.3793, 0.8621, 0.2714, 0.5321, 0.2797, 0.7289, 0.5481],
[0.5375, 0.3378, 0.8474, 0.2894, 0.3923, 0.2840, 0.6445, 0.4855],
[0.5882, 0.3816, 0.8420, 0.2702, 0.4611, 0.2218, 0.6174, 0.4954],
[0.5419, 0.3502, 0.8819, 0.5863, 0.3925, 0.4763, 0.6229, 0.5348],
[0.5298, 0.3446, 0.7433, 0.2817, 0.4003, 0.2351, 0.5706, 0.5667]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6068, 0.3963, 0.8650, 0.4317, 0.4038, 0.5083, 0.5253, 0.4999],
[0.6098, 0.3991, 0.8637, 0.4717, 0.4263, 0.4967, 0.5213, 0.5650],
[0.6198, 0.3997, 0.8582, 0.5361, 0.4117, 0.5016, 0.5942, 0.5134],
[0.6300, 0.4133, 0.8537, 0.2167, 0.5587, 0.2250, 0.7390, 0.5413],
[0.6257, 0.4034, 0.8288, 0.2333, 0.3925, 0.2717, 0.6330, 0.4901],
[0.6276, 0.4095, 0.8238, 0.2250, 0.4663, 0.1783, 0.6171, 0.4869],
[0.6200, 0.3961, 0.8461, 0.5497, 0.4142, 0.4577, 0.5892, 0.5402],
[0.6193, 0.4050, 0.7312, 0.2433, 0.4075, 0.2117, 0.5649, 0.5656]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.10943879742990248
step: 71
running loss: 0.001541391513097218
Train Steps: 71/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.7097, 0.2346, 0.4250, 0.1850, 0.5175, 0.5583],
[0.6202, 0.3983, 0.8555, 0.5429, 0.3842, 0.4370, 0.5866, 0.5398],
[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150],
[0.6226, 0.4001, 0.8438, 0.5733, 0.3862, 0.4250, 0.5750, 0.5283],
[ nan, nan, 0.7425, 0.2117, 0.3937, 0.2433, 0.5438, 0.5567],
[0.6201, 0.4050, 0.7757, 0.2234, 0.4459, 0.1798, 0.5975, 0.5426],
[0.6274, 0.4087, 0.8375, 0.5700, 0.4025, 0.4800, 0.5700, 0.6117],
[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.1746, 0.1223, 0.7293, 0.2208, 0.4302, 0.2071, 0.5374, 0.5330],
[0.6888, 0.4421, 0.9003, 0.5702, 0.3797, 0.4544, 0.6007, 0.5144],
[0.6518, 0.4239, 0.9269, 0.5022, 0.4492, 0.5962, 0.6580, 0.5112],
[0.6560, 0.4232, 0.8784, 0.5940, 0.3866, 0.4556, 0.6057, 0.5096],
[0.0818, 0.0514, 0.7669, 0.2419, 0.4034, 0.2672, 0.5743, 0.5333],
[0.6324, 0.4228, 0.7939, 0.2588, 0.4446, 0.2049, 0.5882, 0.5233],
[0.7643, 0.4976, 0.8812, 0.6012, 0.3931, 0.5022, 0.5749, 0.5795],
[0.5979, 0.3965, 0.9247, 0.4614, 0.4477, 0.5889, 0.6334, 0.5222]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.7097, 0.2346, 0.4250, 0.1850, 0.5175, 0.5583],
[0.6202, 0.3983, 0.8555, 0.5429, 0.3842, 0.4370, 0.5866, 0.5398],
[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150],
[0.6226, 0.4001, 0.8438, 0.5733, 0.3862, 0.4250, 0.5750, 0.5283],
[0.0000, 0.0000, 0.7425, 0.2117, 0.3938, 0.2433, 0.5437, 0.5567],
[0.6201, 0.4050, 0.7757, 0.2234, 0.4459, 0.1798, 0.5975, 0.5426],
[0.6274, 0.4087, 0.8375, 0.5700, 0.4025, 0.4800, 0.5700, 0.6117],
[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.11130989887169562
step: 72
running loss: 0.0015459708176624393
Train Steps: 72/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6114, 0.4018, 0.7213, 0.1967, 0.3763, 0.2700, 0.5875, 0.5533],
[0.6161, 0.4040, 0.7525, 0.2133, 0.4125, 0.2067, 0.5787, 0.5117],
[0.6057, 0.4011, 0.8750, 0.4267, 0.4400, 0.5800, 0.5845, 0.5585],
[0.6357, 0.4159, 0.8788, 0.5583, 0.3638, 0.4433, 0.6488, 0.5297],
[0.6106, 0.4022, 0.7125, 0.2650, 0.3713, 0.2700, 0.5431, 0.5123],
[0.6185, 0.4079, 0.8838, 0.4617, 0.4838, 0.5650, 0.6175, 0.5850],
[0.6250, 0.4236, 0.8638, 0.3767, 0.4050, 0.3150, 0.5649, 0.5799],
[0.6078, 0.4033, 0.8019, 0.3055, 0.3450, 0.4200, 0.6025, 0.5550]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5244, 0.3230, 0.7322, 0.2232, 0.3741, 0.2648, 0.5930, 0.5196],
[0.5423, 0.3285, 0.7587, 0.2411, 0.4187, 0.2186, 0.5792, 0.4869],
[0.5157, 0.3403, 0.8917, 0.4692, 0.4561, 0.5478, 0.5834, 0.5112],
[0.5739, 0.3679, 0.8928, 0.5662, 0.3678, 0.4318, 0.6299, 0.5162],
[0.5439, 0.3567, 0.7502, 0.2889, 0.3702, 0.2684, 0.5522, 0.4780],
[0.5751, 0.3509, 0.9098, 0.4848, 0.4810, 0.5481, 0.6122, 0.5371],
[0.5244, 0.3461, 0.8728, 0.4333, 0.3907, 0.3227, 0.5516, 0.5536],
[0.5542, 0.3530, 0.8331, 0.3390, 0.3716, 0.4300, 0.6096, 0.5287]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6114, 0.4018, 0.7212, 0.1967, 0.3762, 0.2700, 0.5875, 0.5533],
[0.6161, 0.4040, 0.7525, 0.2133, 0.4125, 0.2067, 0.5788, 0.5117],
[0.6057, 0.4011, 0.8750, 0.4267, 0.4400, 0.5800, 0.5845, 0.5585],
[0.6357, 0.4159, 0.8788, 0.5583, 0.3638, 0.4433, 0.6488, 0.5297],
[0.6106, 0.4022, 0.7125, 0.2650, 0.3713, 0.2700, 0.5431, 0.5123],
[0.6184, 0.4079, 0.8838, 0.4617, 0.4837, 0.5650, 0.6175, 0.5850],
[0.6250, 0.4236, 0.8637, 0.3767, 0.4050, 0.3150, 0.5649, 0.5799],
[0.6078, 0.4033, 0.8019, 0.3055, 0.3450, 0.4200, 0.6025, 0.5550]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.11289354818291031
step: 73
running loss: 0.0015464869614097302
Train Steps: 73/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6099, 0.4030, 0.8638, 0.5117, 0.4983, 0.4965, 0.5086, 0.5388],
[0.6300, 0.4133, 0.8538, 0.2167, 0.5587, 0.2250, 0.7390, 0.5413],
[0.6178, 0.4012, 0.8900, 0.4495, 0.3891, 0.5617, 0.5972, 0.4879],
[0.6198, 0.4101, 0.8838, 0.5283, 0.3763, 0.5267, 0.5913, 0.5567],
[0.6325, 0.4165, 0.9000, 0.4617, 0.3813, 0.4900, 0.7485, 0.5447],
[0.6283, 0.4283, 0.7477, 0.3542, 0.5125, 0.1917, 0.5500, 0.6167],
[0.6179, 0.4008, 0.7505, 0.2678, 0.4368, 0.1891, 0.5831, 0.5263],
[0.6275, 0.4048, 0.8488, 0.2883, 0.4463, 0.2033, 0.6321, 0.5155]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5338, 0.3522, 0.8780, 0.5271, 0.4792, 0.5190, 0.4882, 0.5306],
[0.5412, 0.3423, 0.8516, 0.2336, 0.5212, 0.2795, 0.6972, 0.5319],
[0.5630, 0.3671, 0.8744, 0.4487, 0.3698, 0.5784, 0.5697, 0.4878],
[0.5473, 0.3473, 0.8602, 0.5516, 0.3654, 0.5584, 0.5371, 0.5472],
[0.5457, 0.3635, 0.9200, 0.4802, 0.3689, 0.5329, 0.6613, 0.5378],
[0.5589, 0.3510, 0.7413, 0.3505, 0.4733, 0.2244, 0.5237, 0.6045],
[0.5656, 0.3641, 0.7410, 0.2551, 0.4121, 0.2023, 0.5469, 0.5126],
[0.5246, 0.3155, 0.8481, 0.2755, 0.4280, 0.2449, 0.6312, 0.5021]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6098, 0.4030, 0.8637, 0.5117, 0.4983, 0.4965, 0.5086, 0.5388],
[0.6300, 0.4133, 0.8537, 0.2167, 0.5587, 0.2250, 0.7390, 0.5413],
[0.6178, 0.4012, 0.8900, 0.4495, 0.3891, 0.5617, 0.5972, 0.4879],
[0.6198, 0.4101, 0.8838, 0.5283, 0.3762, 0.5267, 0.5913, 0.5567],
[0.6325, 0.4165, 0.9000, 0.4617, 0.3812, 0.4900, 0.7485, 0.5447],
[0.6283, 0.4283, 0.7477, 0.3542, 0.5125, 0.1917, 0.5500, 0.6167],
[0.6179, 0.4008, 0.7505, 0.2678, 0.4368, 0.1891, 0.5831, 0.5263],
[0.6275, 0.4048, 0.8487, 0.2883, 0.4462, 0.2033, 0.6321, 0.5155]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0018, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0018, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.11465108217089437
step: 74
running loss: 0.0015493389482553292
Train Steps: 74/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6275, 0.4111, 0.8463, 0.2617, 0.4487, 0.1983, 0.6211, 0.4904],
[0.6329, 0.4055, 0.9050, 0.4783, 0.3613, 0.3917, 0.6464, 0.5019],
[0.6250, 0.4054, 0.8770, 0.4723, 0.4662, 0.5367, 0.6162, 0.5433],
[0.6164, 0.4076, 0.8838, 0.4117, 0.3713, 0.5550, 0.6238, 0.5350],
[0.6307, 0.3998, 0.8500, 0.5233, 0.3850, 0.5050, 0.7446, 0.5320],
[0.6277, 0.4013, 0.8888, 0.4767, 0.3600, 0.3567, 0.6148, 0.4672],
[0.6200, 0.4039, 0.8880, 0.4799, 0.3625, 0.4285, 0.5866, 0.5148],
[0.6282, 0.4092, 0.8000, 0.2183, 0.4500, 0.2383, 0.6787, 0.5364]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5727, 0.3657, 0.8181, 0.2616, 0.4693, 0.2311, 0.5641, 0.5257],
[0.6030, 0.3700, 0.8953, 0.4802, 0.3780, 0.4110, 0.6093, 0.5120],
[0.5460, 0.3730, 0.8862, 0.4525, 0.4609, 0.5342, 0.5684, 0.5456],
[0.6147, 0.4029, 0.8721, 0.3928, 0.3868, 0.5654, 0.5933, 0.5465],
[0.5614, 0.3649, 0.8514, 0.5074, 0.3873, 0.5299, 0.6509, 0.5383],
[0.6059, 0.3993, 0.8745, 0.4442, 0.3633, 0.3604, 0.5813, 0.5028],
[0.5465, 0.3564, 0.8698, 0.4750, 0.3883, 0.4464, 0.5409, 0.5462],
[0.5784, 0.3736, 0.7716, 0.2147, 0.4488, 0.2392, 0.6080, 0.5363]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6275, 0.4111, 0.8462, 0.2617, 0.4487, 0.1983, 0.6211, 0.4904],
[0.6329, 0.4055, 0.9050, 0.4783, 0.3613, 0.3917, 0.6464, 0.5019],
[0.6250, 0.4054, 0.8770, 0.4723, 0.4663, 0.5367, 0.6162, 0.5433],
[0.6164, 0.4076, 0.8838, 0.4117, 0.3713, 0.5550, 0.6237, 0.5350],
[0.6307, 0.3998, 0.8500, 0.5233, 0.3850, 0.5050, 0.7446, 0.5320],
[0.6277, 0.4013, 0.8888, 0.4767, 0.3600, 0.3567, 0.6148, 0.4672],
[0.6201, 0.4039, 0.8880, 0.4799, 0.3625, 0.4285, 0.5866, 0.5148],
[0.6282, 0.4092, 0.8000, 0.2183, 0.4500, 0.2383, 0.6787, 0.5364]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.1157409083971288
step: 75
running loss: 0.0015432121119617174
Train Steps: 75/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6111, 0.3995, 0.8788, 0.4567, 0.3813, 0.4833, 0.5450, 0.5700],
[ nan, nan, 0.7625, 0.2433, 0.3713, 0.2867, 0.5235, 0.5220],
[0.6166, 0.4008, 0.8563, 0.5667, 0.4388, 0.4933, 0.5575, 0.5567],
[0.6286, 0.4034, 0.8191, 0.2414, 0.4262, 0.2393, 0.6365, 0.5356],
[0.6101, 0.3977, 0.8550, 0.5667, 0.3862, 0.4417, 0.5128, 0.4869],
[0.6198, 0.4130, 0.8762, 0.4117, 0.3650, 0.4900, 0.5707, 0.5103],
[0.6262, 0.4085, 0.8438, 0.3150, 0.4025, 0.2633, 0.6339, 0.4810],
[0.6113, 0.4104, 0.8650, 0.4250, 0.3925, 0.5967, 0.5787, 0.5116]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.7047, 0.4521, 0.8542, 0.4457, 0.3852, 0.4534, 0.5695, 0.5806],
[-0.0310, -0.0268, 0.7352, 0.2170, 0.3854, 0.2452, 0.5475, 0.5456],
[ 0.6074, 0.3916, 0.8318, 0.5185, 0.4381, 0.4620, 0.5896, 0.5820],
[ 0.6495, 0.4064, 0.7906, 0.2347, 0.4436, 0.2241, 0.6480, 0.5400],
[ 0.6545, 0.4307, 0.8227, 0.5311, 0.4055, 0.4264, 0.5485, 0.5173],
[ 0.6268, 0.4137, 0.8465, 0.3939, 0.3636, 0.4709, 0.5830, 0.5404],
[ 0.6327, 0.4152, 0.8263, 0.2706, 0.4183, 0.2436, 0.6445, 0.5048],
[ 0.6758, 0.4513, 0.8386, 0.3769, 0.4227, 0.5609, 0.6045, 0.5502]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6111, 0.3995, 0.8788, 0.4567, 0.3812, 0.4833, 0.5450, 0.5700],
[0.0000, 0.0000, 0.7625, 0.2433, 0.3713, 0.2867, 0.5235, 0.5220],
[0.6166, 0.4008, 0.8562, 0.5667, 0.4387, 0.4933, 0.5575, 0.5567],
[0.6286, 0.4034, 0.8191, 0.2414, 0.4262, 0.2393, 0.6365, 0.5356],
[0.6101, 0.3977, 0.8550, 0.5667, 0.3862, 0.4417, 0.5128, 0.4869],
[0.6198, 0.4130, 0.8763, 0.4117, 0.3650, 0.4900, 0.5707, 0.5103],
[0.6262, 0.4085, 0.8438, 0.3150, 0.4025, 0.2633, 0.6339, 0.4810],
[0.6113, 0.4104, 0.8650, 0.4250, 0.3925, 0.5967, 0.5787, 0.5116]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.11660776424105279
step: 76
running loss: 0.0015343126873822736
Train Steps: 76/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6148, 0.4076, 0.8666, 0.4820, 0.4138, 0.5067, 0.5250, 0.5767],
[0.6300, 0.4102, 0.9088, 0.4433, 0.4088, 0.3067, 0.6820, 0.5540],
[0.6361, 0.4076, 0.8862, 0.5350, 0.3713, 0.4650, 0.6654, 0.5297],
[0.6265, 0.4251, 0.7113, 0.3550, 0.4375, 0.2117, 0.5587, 0.6118],
[0.6147, 0.4026, 0.6600, 0.2467, 0.4088, 0.2150, 0.5489, 0.5773],
[0.6214, 0.4112, 0.7838, 0.2117, 0.3650, 0.3133, 0.5675, 0.5083],
[0.6296, 0.3989, 0.9000, 0.4150, 0.3613, 0.3867, 0.6400, 0.5100],
[0.6272, 0.4071, 0.8738, 0.5600, 0.3675, 0.3783, 0.5926, 0.4742]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5444, 0.3557, 0.8830, 0.4480, 0.4301, 0.5141, 0.5388, 0.5729],
[0.6076, 0.3915, 0.9206, 0.4102, 0.4174, 0.3018, 0.6659, 0.5342],
[0.6002, 0.3981, 0.8804, 0.5211, 0.3667, 0.4781, 0.6635, 0.5433],
[0.6297, 0.4335, 0.7276, 0.2955, 0.4258, 0.2230, 0.5619, 0.6147],
[0.5596, 0.3659, 0.6780, 0.1973, 0.4080, 0.2274, 0.5393, 0.5786],
[0.5413, 0.3425, 0.7714, 0.1700, 0.3657, 0.2916, 0.5894, 0.5097],
[0.6796, 0.4358, 0.8973, 0.3880, 0.3720, 0.3797, 0.6493, 0.5082],
[0.6840, 0.4333, 0.8701, 0.5319, 0.3848, 0.3931, 0.6216, 0.4820]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6148, 0.4076, 0.8666, 0.4820, 0.4137, 0.5067, 0.5250, 0.5767],
[0.6300, 0.4102, 0.9087, 0.4433, 0.4087, 0.3067, 0.6820, 0.5540],
[0.6361, 0.4076, 0.8863, 0.5350, 0.3713, 0.4650, 0.6654, 0.5297],
[0.6265, 0.4251, 0.7113, 0.3550, 0.4375, 0.2117, 0.5587, 0.6118],
[0.6147, 0.4026, 0.6600, 0.2467, 0.4087, 0.2150, 0.5489, 0.5773],
[0.6214, 0.4112, 0.7837, 0.2117, 0.3650, 0.3133, 0.5675, 0.5083],
[0.6296, 0.3989, 0.9000, 0.4150, 0.3613, 0.3867, 0.6400, 0.5100],
[0.6272, 0.4071, 0.8737, 0.5600, 0.3675, 0.3783, 0.5926, 0.4742]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.11740422362345271
step: 77
running loss: 0.0015247301769279573
Train Steps: 77/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6339, 0.4159, 0.8400, 0.5617, 0.3825, 0.4150, 0.7343, 0.5748],
[0.6200, 0.3993, 0.8519, 0.4923, 0.3962, 0.4717, 0.6013, 0.5433],
[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395],
[0.6168, 0.4055, 0.7575, 0.2950, 0.4050, 0.2717, 0.5938, 0.6167],
[0.6140, 0.4070, 0.8700, 0.5000, 0.4612, 0.4900, 0.5260, 0.5852],
[ nan, nan, 0.7850, 0.2700, 0.4288, 0.1717, 0.5199, 0.4999],
[0.6143, 0.4034, 0.8800, 0.4833, 0.4512, 0.5367, 0.5289, 0.5097],
[0.6180, 0.4064, 0.7200, 0.2467, 0.4275, 0.2367, 0.5963, 0.6217]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6762, 0.4645, 0.8378, 0.5068, 0.3814, 0.3885, 0.6824, 0.5250],
[0.6535, 0.4385, 0.8755, 0.4775, 0.3767, 0.4595, 0.6373, 0.5371],
[0.6861, 0.4507, 0.8526, 0.5125, 0.3286, 0.3462, 0.5766, 0.5065],
[0.6160, 0.4223, 0.7629, 0.2434, 0.3948, 0.2627, 0.6210, 0.6043],
[0.6554, 0.4457, 0.8855, 0.4622, 0.4515, 0.4659, 0.5474, 0.5615],
[0.1650, 0.1163, 0.7443, 0.1991, 0.4005, 0.1677, 0.5614, 0.4940],
[0.6359, 0.4271, 0.8692, 0.4393, 0.4413, 0.5079, 0.5420, 0.4931],
[0.7311, 0.4831, 0.6914, 0.1935, 0.4226, 0.2248, 0.6182, 0.5892]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6339, 0.4159, 0.8400, 0.5617, 0.3825, 0.4150, 0.7343, 0.5748],
[0.6200, 0.3993, 0.8519, 0.4923, 0.3963, 0.4717, 0.6012, 0.5433],
[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395],
[0.6168, 0.4055, 0.7575, 0.2950, 0.4050, 0.2717, 0.5938, 0.6167],
[0.6140, 0.4070, 0.8700, 0.5000, 0.4613, 0.4900, 0.5260, 0.5852],
[0.0000, 0.0000, 0.7850, 0.2700, 0.4288, 0.1717, 0.5199, 0.4999],
[0.6143, 0.4034, 0.8800, 0.4833, 0.4512, 0.5367, 0.5289, 0.5097],
[0.6180, 0.4064, 0.7200, 0.2467, 0.4275, 0.2367, 0.5962, 0.6217]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.11927059848676436
step: 78
running loss: 0.0015291102370097993
Train Steps: 78/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6321, 0.4048, 0.8738, 0.5617, 0.3875, 0.4417, 0.6361, 0.4927],
[0.6087, 0.3951, 0.8387, 0.5833, 0.4188, 0.4933, 0.5146, 0.4830],
[0.6125, 0.3983, 0.8750, 0.4867, 0.4275, 0.4783, 0.5413, 0.5717],
[0.6286, 0.4040, 0.8696, 0.3047, 0.3924, 0.2887, 0.6300, 0.5367],
[0.6127, 0.4119, 0.8650, 0.5300, 0.4512, 0.5250, 0.5260, 0.5461],
[0.6259, 0.4156, 0.8812, 0.3183, 0.4775, 0.1867, 0.6219, 0.4960],
[0.6271, 0.4040, 0.9138, 0.3750, 0.4625, 0.2617, 0.7232, 0.5413],
[0.6127, 0.4115, 0.7163, 0.2883, 0.3625, 0.2950, 0.5327, 0.5495]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6987, 0.4584, 0.8383, 0.5464, 0.3512, 0.4217, 0.6277, 0.4938],
[0.5863, 0.3896, 0.8132, 0.5523, 0.3801, 0.4898, 0.5403, 0.5217],
[0.5919, 0.4097, 0.8451, 0.4679, 0.4123, 0.4491, 0.5641, 0.5819],
[0.6159, 0.4131, 0.8378, 0.2951, 0.3678, 0.2500, 0.6546, 0.5304],
[0.5996, 0.4130, 0.8316, 0.5114, 0.4123, 0.5076, 0.5484, 0.5542],
[0.5672, 0.3895, 0.8641, 0.2796, 0.4345, 0.1819, 0.6205, 0.5191],
[0.6335, 0.4170, 0.9235, 0.3661, 0.4421, 0.2307, 0.7317, 0.5447],
[0.5672, 0.3924, 0.7009, 0.2516, 0.3476, 0.2907, 0.5554, 0.5630]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6321, 0.4048, 0.8737, 0.5617, 0.3875, 0.4417, 0.6361, 0.4927],
[0.6087, 0.3951, 0.8388, 0.5833, 0.4187, 0.4933, 0.5146, 0.4830],
[0.6125, 0.3983, 0.8750, 0.4867, 0.4275, 0.4783, 0.5412, 0.5717],
[0.6286, 0.4040, 0.8696, 0.3047, 0.3924, 0.2887, 0.6300, 0.5367],
[0.6127, 0.4119, 0.8650, 0.5300, 0.4512, 0.5250, 0.5260, 0.5461],
[0.6259, 0.4156, 0.8813, 0.3183, 0.4775, 0.1867, 0.6219, 0.4960],
[0.6271, 0.4040, 0.9137, 0.3750, 0.4625, 0.2617, 0.7232, 0.5413],
[0.6127, 0.4114, 0.7163, 0.2883, 0.3625, 0.2950, 0.5327, 0.5495]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.11994522050372325
step: 79
running loss: 0.0015182939304268766
Train Steps: 79/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.6859, 0.2194, 0.4150, 0.1867, 0.5153, 0.5729],
[0.6167, 0.4048, 0.6831, 0.3639, 0.3763, 0.3017, 0.5700, 0.5883],
[0.6229, 0.4086, 0.7538, 0.2600, 0.4775, 0.1617, 0.5900, 0.5383],
[0.6299, 0.4008, 0.8450, 0.5350, 0.4213, 0.5000, 0.6350, 0.5100],
[0.6225, 0.4191, 0.8500, 0.4167, 0.3688, 0.3233, 0.5650, 0.5650],
[0.6280, 0.4055, 0.8600, 0.5317, 0.3800, 0.4700, 0.6275, 0.5133],
[0.6211, 0.3993, 0.7650, 0.1933, 0.4575, 0.1550, 0.5965, 0.4895],
[0.6286, 0.4097, 0.8107, 0.2414, 0.4425, 0.2483, 0.6745, 0.5385]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.1057, 0.0799, 0.6776, 0.2266, 0.4075, 0.1826, 0.5185, 0.5593],
[0.5822, 0.4002, 0.7446, 0.3650, 0.3553, 0.3069, 0.5613, 0.5871],
[0.7067, 0.4896, 0.7654, 0.2641, 0.4527, 0.1474, 0.6178, 0.5330],
[0.6936, 0.4618, 0.8660, 0.5623, 0.4117, 0.5137, 0.6381, 0.5277],
[0.6334, 0.4676, 0.8516, 0.4369, 0.3563, 0.3323, 0.5630, 0.5715],
[0.7058, 0.4797, 0.8861, 0.5675, 0.3770, 0.4973, 0.6390, 0.5419],
[0.6569, 0.4481, 0.7611, 0.2014, 0.4641, 0.1767, 0.6098, 0.5115],
[0.6362, 0.4427, 0.8369, 0.2680, 0.4433, 0.2233, 0.7059, 0.5670]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.6859, 0.2194, 0.4150, 0.1867, 0.5153, 0.5729],
[0.6167, 0.4048, 0.6831, 0.3639, 0.3762, 0.3017, 0.5700, 0.5883],
[0.6229, 0.4086, 0.7538, 0.2600, 0.4775, 0.1617, 0.5900, 0.5383],
[0.6299, 0.4008, 0.8450, 0.5350, 0.4212, 0.5000, 0.6350, 0.5100],
[0.6225, 0.4191, 0.8500, 0.4167, 0.3688, 0.3233, 0.5650, 0.5650],
[0.6280, 0.4055, 0.8600, 0.5317, 0.3800, 0.4700, 0.6275, 0.5133],
[0.6211, 0.3993, 0.7650, 0.1933, 0.4575, 0.1550, 0.5965, 0.4895],
[0.6286, 0.4097, 0.8107, 0.2414, 0.4425, 0.2483, 0.6745, 0.5385]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.121143347438192
step: 80
running loss: 0.0015142918429774
Train Steps: 80/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6201, 0.4055, 0.7717, 0.1919, 0.4250, 0.2079, 0.5871, 0.5044],
[0.6111, 0.3995, 0.8788, 0.4567, 0.3813, 0.4833, 0.5450, 0.5700],
[0.6198, 0.4130, 0.8762, 0.4117, 0.3650, 0.4900, 0.5707, 0.5103],
[0.6185, 0.4080, 0.8625, 0.3483, 0.3788, 0.2650, 0.5320, 0.5272],
[0.6193, 0.4108, 0.7438, 0.2700, 0.3650, 0.3683, 0.6238, 0.5717],
[0.6197, 0.4091, 0.8800, 0.4783, 0.3538, 0.4767, 0.5950, 0.5550],
[0.6185, 0.4129, 0.8900, 0.4567, 0.3937, 0.5417, 0.5734, 0.5110],
[0.6197, 0.3930, 0.8793, 0.4736, 0.4152, 0.5464, 0.6308, 0.5235]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5598, 0.3661, 0.7617, 0.2352, 0.4312, 0.1759, 0.5951, 0.5085],
[0.6472, 0.4201, 0.8735, 0.5111, 0.3916, 0.4521, 0.5697, 0.5639],
[0.6271, 0.4169, 0.8698, 0.4614, 0.3704, 0.4657, 0.5780, 0.5201],
[0.5978, 0.3887, 0.8416, 0.4152, 0.4066, 0.2550, 0.5161, 0.5368],
[0.6568, 0.4365, 0.7498, 0.3367, 0.3714, 0.3466, 0.6398, 0.5593],
[0.6814, 0.4443, 0.8768, 0.5257, 0.3883, 0.4427, 0.6180, 0.5738],
[0.5511, 0.3807, 0.8901, 0.5058, 0.4081, 0.5096, 0.5988, 0.5190],
[0.7312, 0.4653, 0.8871, 0.5383, 0.4363, 0.5173, 0.6679, 0.5432]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6202, 0.4055, 0.7717, 0.1919, 0.4250, 0.2079, 0.5871, 0.5044],
[0.6111, 0.3995, 0.8788, 0.4567, 0.3812, 0.4833, 0.5450, 0.5700],
[0.6198, 0.4130, 0.8763, 0.4117, 0.3650, 0.4900, 0.5707, 0.5103],
[0.6186, 0.4080, 0.8625, 0.3483, 0.3787, 0.2650, 0.5320, 0.5272],
[0.6193, 0.4108, 0.7437, 0.2700, 0.3650, 0.3683, 0.6237, 0.5717],
[0.6197, 0.4091, 0.8800, 0.4783, 0.3537, 0.4767, 0.5950, 0.5550],
[0.6186, 0.4129, 0.8900, 0.4567, 0.3938, 0.5417, 0.5734, 0.5110],
[0.6197, 0.3930, 0.8793, 0.4736, 0.4152, 0.5464, 0.6308, 0.5235]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.12236118371947668
step: 81
running loss: 0.001510631897771317
Train Steps: 81/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6145, 0.4007, 0.8775, 0.4533, 0.4562, 0.5533, 0.6088, 0.5533],
[0.6275, 0.4024, 0.8500, 0.5383, 0.3912, 0.4883, 0.6288, 0.5100],
[0.6224, 0.3964, 0.8225, 0.5717, 0.4150, 0.4617, 0.5775, 0.5267],
[0.6286, 0.4097, 0.8107, 0.2414, 0.4425, 0.2483, 0.6745, 0.5385],
[0.6246, 0.4126, 0.8850, 0.4833, 0.4200, 0.5350, 0.6112, 0.5250],
[0.6200, 0.4059, 0.8700, 0.4900, 0.4163, 0.5000, 0.6162, 0.5467],
[0.6364, 0.4165, 0.9088, 0.4367, 0.4075, 0.3150, 0.6448, 0.5297],
[0.6198, 0.4101, 0.8838, 0.5283, 0.3763, 0.5267, 0.5913, 0.5567]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6552, 0.4201, 0.8652, 0.4655, 0.4552, 0.5254, 0.5912, 0.5429],
[0.6301, 0.3977, 0.8483, 0.5500, 0.4006, 0.4668, 0.6007, 0.4875],
[0.6143, 0.4100, 0.8121, 0.5916, 0.3956, 0.4262, 0.5624, 0.5386],
[0.6091, 0.4006, 0.8325, 0.2715, 0.4438, 0.2067, 0.6716, 0.5364],
[0.6086, 0.3938, 0.8833, 0.4870, 0.4127, 0.5155, 0.5829, 0.5079],
[0.5988, 0.3928, 0.8847, 0.5002, 0.4260, 0.4873, 0.5860, 0.5524],
[0.6430, 0.4311, 0.9103, 0.4571, 0.4090, 0.2978, 0.6228, 0.5287],
[0.6248, 0.3931, 0.8567, 0.5376, 0.3810, 0.5050, 0.5612, 0.5507]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6145, 0.4007, 0.8775, 0.4533, 0.4563, 0.5533, 0.6087, 0.5533],
[0.6275, 0.4024, 0.8500, 0.5383, 0.3913, 0.4883, 0.6288, 0.5100],
[0.6224, 0.3964, 0.8225, 0.5717, 0.4150, 0.4617, 0.5775, 0.5267],
[0.6286, 0.4097, 0.8107, 0.2414, 0.4425, 0.2483, 0.6745, 0.5385],
[0.6246, 0.4126, 0.8850, 0.4833, 0.4200, 0.5350, 0.6112, 0.5250],
[0.6199, 0.4059, 0.8700, 0.4900, 0.4162, 0.5000, 0.6162, 0.5467],
[0.6364, 0.4165, 0.9087, 0.4367, 0.4075, 0.3150, 0.6448, 0.5297],
[0.6198, 0.4101, 0.8838, 0.5283, 0.3762, 0.5267, 0.5913, 0.5567]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.12267718787188642
step: 82
running loss: 0.0014960632667303222
Train Steps: 82/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6090, 0.4045, 0.7250, 0.2100, 0.4075, 0.2300, 0.5476, 0.5663],
[0.6043, 0.4022, 0.6887, 0.1983, 0.3775, 0.2483, 0.5480, 0.5136],
[0.6198, 0.3997, 0.8582, 0.5361, 0.4117, 0.5016, 0.5942, 0.5134],
[0.6223, 0.4130, 0.8100, 0.2983, 0.3525, 0.3900, 0.5694, 0.5103],
[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459],
[0.6271, 0.4005, 0.8450, 0.6067, 0.3850, 0.4983, 0.6069, 0.4649],
[0.6076, 0.3953, 0.8125, 0.3917, 0.3525, 0.4083, 0.5346, 0.4954],
[0.6267, 0.4065, 0.8313, 0.2467, 0.4788, 0.1733, 0.6312, 0.5133]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5914, 0.3665, 0.7146, 0.2745, 0.4171, 0.2598, 0.5285, 0.5583],
[0.6297, 0.3911, 0.7009, 0.2508, 0.3974, 0.2863, 0.5636, 0.5424],
[0.5483, 0.3389, 0.8805, 0.5764, 0.4454, 0.5368, 0.5776, 0.5156],
[0.6216, 0.3915, 0.8177, 0.3364, 0.3854, 0.4146, 0.5627, 0.5295],
[0.6665, 0.4182, 0.8659, 0.3129, 0.5133, 0.2287, 0.6636, 0.5608],
[0.5599, 0.3312, 0.8511, 0.6297, 0.4080, 0.5062, 0.5952, 0.4846],
[0.6774, 0.4302, 0.8439, 0.4182, 0.3562, 0.4139, 0.5344, 0.5245],
[0.6530, 0.4147, 0.8346, 0.2688, 0.4997, 0.1857, 0.6275, 0.5368]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6090, 0.4045, 0.7250, 0.2100, 0.4075, 0.2300, 0.5476, 0.5663],
[0.6043, 0.4022, 0.6888, 0.1983, 0.3775, 0.2483, 0.5480, 0.5136],
[0.6198, 0.3997, 0.8582, 0.5361, 0.4117, 0.5016, 0.5942, 0.5134],
[0.6223, 0.4130, 0.8100, 0.2983, 0.3525, 0.3900, 0.5694, 0.5103],
[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459],
[0.6271, 0.4005, 0.8450, 0.6067, 0.3850, 0.4983, 0.6069, 0.4649],
[0.6076, 0.3952, 0.8125, 0.3917, 0.3525, 0.4083, 0.5346, 0.4954],
[0.6266, 0.4065, 0.8313, 0.2467, 0.4787, 0.1733, 0.6313, 0.5133]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.12356227377313189
step: 83
running loss: 0.0014887020936521914
Train Steps: 83/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6104, 0.4029, 0.8738, 0.4900, 0.4088, 0.4533, 0.5070, 0.5510],
[0.6236, 0.3977, 0.8985, 0.4806, 0.3835, 0.5216, 0.6613, 0.5166],
[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837],
[0.6212, 0.4159, 0.8675, 0.5783, 0.4088, 0.4317, 0.5613, 0.5917],
[0.6185, 0.4079, 0.8838, 0.4617, 0.4838, 0.5650, 0.6175, 0.5850],
[0.6175, 0.3957, 0.8700, 0.4817, 0.4662, 0.5133, 0.5800, 0.5517],
[0.6264, 0.4049, 0.8988, 0.4633, 0.3813, 0.4983, 0.6326, 0.4843],
[0.6246, 0.4090, 0.6964, 0.2027, 0.3925, 0.2683, 0.6088, 0.5583]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6121, 0.3956, 0.8771, 0.5035, 0.4204, 0.4715, 0.4994, 0.5032],
[0.6205, 0.3745, 0.9002, 0.5052, 0.3913, 0.5386, 0.6705, 0.4973],
[0.6060, 0.3819, 0.7070, 0.3297, 0.3670, 0.3024, 0.5258, 0.5516],
[0.6212, 0.4016, 0.8674, 0.5632, 0.4227, 0.4285, 0.5475, 0.5770],
[0.6462, 0.4000, 0.9094, 0.4689, 0.4834, 0.5711, 0.6178, 0.5542],
[0.5842, 0.3633, 0.8862, 0.4659, 0.4760, 0.5078, 0.5525, 0.5156],
[0.6476, 0.3985, 0.9158, 0.4879, 0.3884, 0.5060, 0.6152, 0.4727],
[0.6824, 0.4276, 0.7175, 0.2365, 0.3930, 0.2785, 0.5990, 0.5228]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6104, 0.4029, 0.8737, 0.4900, 0.4087, 0.4533, 0.5070, 0.5510],
[0.6236, 0.3977, 0.8985, 0.4806, 0.3835, 0.5216, 0.6613, 0.5166],
[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837],
[0.6212, 0.4159, 0.8675, 0.5783, 0.4087, 0.4317, 0.5612, 0.5917],
[0.6184, 0.4079, 0.8838, 0.4617, 0.4837, 0.5650, 0.6175, 0.5850],
[0.6175, 0.3957, 0.8700, 0.4817, 0.4663, 0.5133, 0.5800, 0.5517],
[0.6264, 0.4049, 0.8988, 0.4633, 0.3812, 0.4983, 0.6326, 0.4843],
[0.6246, 0.4090, 0.6964, 0.2027, 0.3925, 0.2683, 0.6087, 0.5583]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.12402151894639246
step: 84
running loss: 0.0014764466541237198
Train Steps: 84/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6225, 0.4196, 0.8788, 0.3467, 0.3750, 0.3400, 0.5413, 0.5433],
[0.6109, 0.4015, 0.7668, 0.3639, 0.3513, 0.3667, 0.5200, 0.5641],
[0.6205, 0.4012, 0.8675, 0.3283, 0.3713, 0.3050, 0.5813, 0.5117],
[0.6101, 0.4042, 0.7775, 0.2617, 0.3713, 0.2817, 0.5440, 0.5650],
[0.6277, 0.4083, 0.8350, 0.2717, 0.4562, 0.1800, 0.5918, 0.4878],
[0.6223, 0.4130, 0.8100, 0.2983, 0.3525, 0.3900, 0.5694, 0.5103],
[0.6206, 0.4123, 0.7175, 0.2400, 0.3887, 0.2933, 0.6225, 0.5750],
[0.6277, 0.4036, 0.8688, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5706, 0.3611, 0.8415, 0.3558, 0.3894, 0.3482, 0.5369, 0.5443],
[0.6374, 0.4090, 0.7719, 0.3737, 0.3650, 0.3895, 0.5323, 0.5581],
[0.5539, 0.3452, 0.8682, 0.3352, 0.3994, 0.3267, 0.5938, 0.5154],
[0.6228, 0.4052, 0.7520, 0.2746, 0.4052, 0.2969, 0.5474, 0.5626],
[0.5389, 0.3360, 0.8147, 0.2744, 0.4840, 0.2404, 0.5875, 0.4859],
[0.5996, 0.3857, 0.8043, 0.3106, 0.3818, 0.4226, 0.5740, 0.5148],
[0.6152, 0.3860, 0.7280, 0.2786, 0.4149, 0.3206, 0.6044, 0.5611],
[0.6196, 0.3619, 0.8757, 0.3720, 0.4327, 0.2936, 0.6399, 0.4696]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6225, 0.4196, 0.8788, 0.3467, 0.3750, 0.3400, 0.5412, 0.5433],
[0.6109, 0.4015, 0.7668, 0.3639, 0.3512, 0.3667, 0.5200, 0.5641],
[0.6205, 0.4012, 0.8675, 0.3283, 0.3713, 0.3050, 0.5813, 0.5117],
[0.6101, 0.4042, 0.7775, 0.2617, 0.3713, 0.2817, 0.5440, 0.5650],
[0.6277, 0.4083, 0.8350, 0.2717, 0.4563, 0.1800, 0.5918, 0.4878],
[0.6223, 0.4130, 0.8100, 0.2983, 0.3525, 0.3900, 0.5694, 0.5103],
[0.6206, 0.4123, 0.7175, 0.2400, 0.3887, 0.2933, 0.6225, 0.5750],
[0.6277, 0.4036, 0.8687, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.1248362893529702
step: 85
running loss: 0.0014686622276820023
Train Steps: 85/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6233, 0.4091, 0.8100, 0.2950, 0.3563, 0.3883, 0.6013, 0.5200],
[0.6185, 0.4067, 0.8838, 0.4450, 0.4037, 0.4733, 0.5213, 0.5142],
[0.6236, 0.4081, 0.8575, 0.3000, 0.3713, 0.3033, 0.5550, 0.5633],
[0.6277, 0.4029, 0.8250, 0.2433, 0.4325, 0.2100, 0.6366, 0.5207],
[0.6126, 0.4067, 0.8638, 0.5383, 0.4188, 0.4850, 0.5016, 0.5392],
[0.6200, 0.4055, 0.8011, 0.2988, 0.3842, 0.2798, 0.5949, 0.5183],
[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383],
[0.6129, 0.4114, 0.6950, 0.2467, 0.4050, 0.2133, 0.5363, 0.5550]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6439, 0.4169, 0.7913, 0.2965, 0.3638, 0.4242, 0.6197, 0.5277],
[0.6116, 0.3866, 0.8863, 0.4314, 0.4029, 0.4827, 0.5048, 0.5232],
[0.6431, 0.4087, 0.8547, 0.3027, 0.3808, 0.3170, 0.5720, 0.5248],
[0.6157, 0.3800, 0.8009, 0.2299, 0.4458, 0.2494, 0.6712, 0.5019],
[0.6382, 0.4040, 0.8611, 0.5433, 0.4226, 0.5305, 0.5289, 0.5456],
[0.6433, 0.3967, 0.7910, 0.2740, 0.4048, 0.3044, 0.6042, 0.5222],
[0.6362, 0.4055, 0.8299, 0.3050, 0.3622, 0.4071, 0.6183, 0.5390],
[0.6083, 0.3849, 0.6878, 0.2513, 0.4030, 0.2424, 0.5473, 0.5537]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6233, 0.4091, 0.8100, 0.2950, 0.3562, 0.3883, 0.6012, 0.5200],
[0.6185, 0.4067, 0.8838, 0.4450, 0.4038, 0.4733, 0.5213, 0.5142],
[0.6236, 0.4081, 0.8575, 0.3000, 0.3713, 0.3033, 0.5550, 0.5633],
[0.6277, 0.4029, 0.8250, 0.2433, 0.4325, 0.2100, 0.6366, 0.5207],
[0.6126, 0.4067, 0.8637, 0.5383, 0.4187, 0.4850, 0.5016, 0.5392],
[0.6201, 0.4055, 0.8011, 0.2988, 0.3842, 0.2798, 0.5949, 0.5183],
[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383],
[0.6129, 0.4114, 0.6950, 0.2467, 0.4050, 0.2133, 0.5362, 0.5550]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.12514446672867052
step: 86
running loss: 0.0014551682177752386
Train Steps: 86/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6339, 0.4081, 0.8425, 0.5417, 0.3850, 0.4833, 0.7335, 0.5760],
[0.6179, 0.3998, 0.8396, 0.3505, 0.3552, 0.3768, 0.6064, 0.5329],
[0.6108, 0.4011, 0.8037, 0.3400, 0.3700, 0.2933, 0.5658, 0.5617],
[0.6198, 0.4075, 0.8650, 0.5617, 0.4150, 0.4367, 0.5450, 0.5650],
[0.6199, 0.4015, 0.8716, 0.5228, 0.3833, 0.4772, 0.5883, 0.5148],
[0.6087, 0.3976, 0.8337, 0.3867, 0.3713, 0.3117, 0.5938, 0.5300],
[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586],
[ nan, nan, 0.6412, 0.1900, 0.4238, 0.1883, 0.5487, 0.5700]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5966, 0.3957, 0.8675, 0.5086, 0.3638, 0.5120, 0.6810, 0.5625],
[0.7951, 0.5214, 0.8327, 0.3075, 0.3375, 0.3722, 0.5612, 0.5145],
[0.6586, 0.4217, 0.8096, 0.3004, 0.3758, 0.3178, 0.5457, 0.5269],
[0.6461, 0.4297, 0.8695, 0.5199, 0.3957, 0.4628, 0.5302, 0.5536],
[0.6294, 0.4333, 0.8799, 0.4842, 0.3766, 0.5092, 0.5607, 0.4978],
[0.6841, 0.4662, 0.8497, 0.3571, 0.3594, 0.3482, 0.5710, 0.5243],
[0.6373, 0.4358, 0.8713, 0.2233, 0.4394, 0.2694, 0.6967, 0.5514],
[0.2011, 0.1628, 0.6991, 0.1745, 0.4166, 0.2143, 0.5079, 0.5705]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6339, 0.4081, 0.8425, 0.5417, 0.3850, 0.4833, 0.7335, 0.5760],
[0.6179, 0.3998, 0.8396, 0.3505, 0.3552, 0.3768, 0.6064, 0.5329],
[0.6108, 0.4011, 0.8037, 0.3400, 0.3700, 0.2933, 0.5658, 0.5617],
[0.6198, 0.4075, 0.8650, 0.5617, 0.4150, 0.4367, 0.5450, 0.5650],
[0.6199, 0.4015, 0.8716, 0.5228, 0.3833, 0.4772, 0.5883, 0.5148],
[0.6087, 0.3976, 0.8338, 0.3867, 0.3713, 0.3117, 0.5938, 0.5300],
[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586],
[0.0000, 0.0000, 0.6413, 0.1900, 0.4238, 0.1883, 0.5487, 0.5700]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0026, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0026, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.12772876137751155
step: 87
running loss: 0.0014681466825001326
Train Steps: 87/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6339, 0.4081, 0.8425, 0.5417, 0.3850, 0.4833, 0.7335, 0.5760],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3788, 0.4900, 0.7121, 0.5864],
[0.6079, 0.3964, 0.7420, 0.2958, 0.3563, 0.2917, 0.5351, 0.4980],
[0.6150, 0.3949, 0.8800, 0.4033, 0.3825, 0.4900, 0.5875, 0.5483],
[0.6143, 0.4055, 0.8150, 0.2767, 0.3825, 0.2567, 0.5173, 0.4901],
[0.6236, 0.3966, 0.8850, 0.4967, 0.3638, 0.4017, 0.5850, 0.5183],
[0.6357, 0.4118, 0.8400, 0.2500, 0.5413, 0.1633, 0.6725, 0.5586],
[0.6225, 0.4191, 0.8500, 0.4167, 0.3688, 0.3233, 0.5650, 0.5650]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5803, 0.3842, 0.8580, 0.5116, 0.3559, 0.4980, 0.6933, 0.5874],
[0.6300, 0.4038, 0.8794, 0.4717, 0.3554, 0.5003, 0.7029, 0.5902],
[0.6064, 0.4055, 0.7442, 0.2507, 0.3430, 0.2914, 0.5109, 0.5141],
[0.5785, 0.3940, 0.8552, 0.3603, 0.3619, 0.5005, 0.5622, 0.5352],
[0.5799, 0.3884, 0.7843, 0.2502, 0.3571, 0.2743, 0.5150, 0.5242],
[0.5797, 0.3719, 0.8946, 0.4518, 0.3488, 0.4259, 0.5736, 0.5385],
[0.5465, 0.3934, 0.8544, 0.2093, 0.5169, 0.1659, 0.6492, 0.5658],
[0.6566, 0.4615, 0.8477, 0.3786, 0.3487, 0.3242, 0.5568, 0.5618]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6339, 0.4081, 0.8425, 0.5417, 0.3850, 0.4833, 0.7335, 0.5760],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3787, 0.4900, 0.7121, 0.5864],
[0.6079, 0.3964, 0.7420, 0.2958, 0.3562, 0.2917, 0.5351, 0.4980],
[0.6150, 0.3949, 0.8800, 0.4033, 0.3825, 0.4900, 0.5875, 0.5483],
[0.6143, 0.4055, 0.8150, 0.2767, 0.3825, 0.2567, 0.5173, 0.4901],
[0.6236, 0.3965, 0.8850, 0.4967, 0.3638, 0.4017, 0.5850, 0.5183],
[0.6357, 0.4118, 0.8400, 0.2500, 0.5412, 0.1633, 0.6725, 0.5586],
[0.6225, 0.4191, 0.8500, 0.4167, 0.3688, 0.3233, 0.5650, 0.5650]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.12843954053823836
step: 88
running loss: 0.0014595402333890722
Train Steps: 88/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6068, 0.3963, 0.8650, 0.4317, 0.4037, 0.5083, 0.5253, 0.4999],
[0.6161, 0.4040, 0.7525, 0.2133, 0.4125, 0.2067, 0.5787, 0.5117],
[0.6170, 0.4102, 0.7468, 0.3695, 0.3463, 0.3767, 0.5238, 0.5823],
[0.6154, 0.4112, 0.7037, 0.2317, 0.4238, 0.1833, 0.5350, 0.5600],
[0.6275, 0.4008, 0.8047, 0.2484, 0.4037, 0.2777, 0.6506, 0.5212],
[0.6161, 0.4099, 0.8738, 0.4383, 0.3788, 0.5483, 0.5605, 0.5019],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4012, 0.4633, 0.5338, 0.5767],
[0.6131, 0.4037, 0.6907, 0.2819, 0.3688, 0.2700, 0.5217, 0.5680]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6554, 0.4362, 0.8934, 0.4392, 0.3842, 0.4940, 0.5825, 0.5158],
[0.6204, 0.4117, 0.7705, 0.1987, 0.3993, 0.1871, 0.6053, 0.5255],
[0.5925, 0.3959, 0.7826, 0.3638, 0.3346, 0.3605, 0.5689, 0.5980],
[0.5463, 0.3805, 0.7074, 0.2054, 0.4121, 0.1620, 0.5610, 0.5656],
[0.6076, 0.4064, 0.8212, 0.2460, 0.3942, 0.2600, 0.6509, 0.5222],
[0.6327, 0.4301, 0.8894, 0.4261, 0.3661, 0.5427, 0.6239, 0.5256],
[0.5979, 0.3990, 0.9151, 0.5030, 0.3897, 0.4423, 0.5752, 0.5977],
[0.6053, 0.3951, 0.7183, 0.2489, 0.3607, 0.2643, 0.5485, 0.5817]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6068, 0.3963, 0.8650, 0.4317, 0.4038, 0.5083, 0.5253, 0.4999],
[0.6161, 0.4040, 0.7525, 0.2133, 0.4125, 0.2067, 0.5788, 0.5117],
[0.6170, 0.4102, 0.7468, 0.3695, 0.3462, 0.3767, 0.5238, 0.5823],
[0.6154, 0.4112, 0.7038, 0.2317, 0.4238, 0.1833, 0.5350, 0.5600],
[0.6275, 0.4008, 0.8047, 0.2484, 0.4037, 0.2777, 0.6506, 0.5212],
[0.6161, 0.4099, 0.8737, 0.4383, 0.3787, 0.5483, 0.5605, 0.5019],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4013, 0.4633, 0.5337, 0.5767],
[0.6131, 0.4036, 0.6907, 0.2819, 0.3688, 0.2700, 0.5217, 0.5680]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.12903116384404711
step: 89
running loss: 0.0014497883577982821
Train Steps: 89/90 Loss: 0.0014 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6148, 0.4076, 0.8666, 0.4820, 0.4138, 0.5067, 0.5250, 0.5767],
[0.6204, 0.4110, 0.7913, 0.2667, 0.4062, 0.2500, 0.6225, 0.5367],
[0.6216, 0.4099, 0.7225, 0.2033, 0.4188, 0.2217, 0.5975, 0.5283],
[0.6108, 0.4011, 0.8037, 0.3400, 0.3700, 0.2933, 0.5658, 0.5617],
[0.6196, 0.4088, 0.8888, 0.4583, 0.4500, 0.5683, 0.6138, 0.5883],
[0.6164, 0.4066, 0.6625, 0.3033, 0.3775, 0.2967, 0.5725, 0.5833],
[0.6126, 0.3954, 0.8538, 0.4983, 0.4250, 0.4700, 0.5355, 0.5350],
[0.6198, 0.4115, 0.7762, 0.2717, 0.3713, 0.3200, 0.5837, 0.5683]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6364, 0.4298, 0.8848, 0.4947, 0.3976, 0.4907, 0.5543, 0.5624],
[0.5528, 0.3813, 0.7996, 0.2573, 0.3886, 0.2307, 0.6113, 0.5471],
[0.6042, 0.4352, 0.7250, 0.2135, 0.3953, 0.1917, 0.5677, 0.5342],
[0.6216, 0.3989, 0.8161, 0.3435, 0.3605, 0.2686, 0.5757, 0.5322],
[0.5356, 0.3706, 0.9046, 0.4557, 0.4116, 0.5370, 0.6324, 0.5777],
[0.4950, 0.3409, 0.7071, 0.2959, 0.3453, 0.2621, 0.5593, 0.5702],
[0.6456, 0.4085, 0.8733, 0.4935, 0.3967, 0.4418, 0.5593, 0.5491],
[0.6524, 0.4392, 0.7946, 0.2740, 0.3508, 0.2938, 0.5992, 0.5466]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6148, 0.4076, 0.8666, 0.4820, 0.4137, 0.5067, 0.5250, 0.5767],
[0.6204, 0.4110, 0.7912, 0.2667, 0.4062, 0.2500, 0.6225, 0.5367],
[0.6216, 0.4099, 0.7225, 0.2033, 0.4187, 0.2217, 0.5975, 0.5283],
[0.6108, 0.4011, 0.8037, 0.3400, 0.3700, 0.2933, 0.5658, 0.5617],
[0.6196, 0.4088, 0.8888, 0.4583, 0.4500, 0.5683, 0.6137, 0.5883],
[0.6164, 0.4066, 0.6625, 0.3033, 0.3775, 0.2967, 0.5725, 0.5833],
[0.6126, 0.3954, 0.8537, 0.4983, 0.4250, 0.4700, 0.5355, 0.5350],
[0.6198, 0.4115, 0.7763, 0.2717, 0.3713, 0.3200, 0.5838, 0.5683]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.12994244889705442
step: 90
running loss: 0.001443804987745049
Valid Steps: 10/10 Loss: nan 3.3351
--------------------------------------------------
Epoch: 5 Train Loss: 0.0014 Valid Loss: nan
--------------------------------------------------
size of train loader is: 90
torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6271, 0.4040, 0.9138, 0.3750, 0.4625, 0.2617, 0.7232, 0.5413],
[ nan, nan, 0.8850, 0.3000, 0.5363, 0.2250, 0.7343, 0.5771],
[0.6086, 0.3940, 0.8712, 0.4783, 0.4025, 0.4900, 0.5498, 0.5390],
[0.6117, 0.4019, 0.8538, 0.4067, 0.3513, 0.3583, 0.5663, 0.5133],
[0.6267, 0.4094, 0.8712, 0.3083, 0.4400, 0.2267, 0.6250, 0.5200],
[0.6243, 0.4128, 0.7762, 0.2717, 0.3825, 0.3133, 0.6212, 0.5417],
[0.6339, 0.4159, 0.8400, 0.5617, 0.3825, 0.4150, 0.7343, 0.5748],
[0.6248, 0.4032, 0.7738, 0.1900, 0.4813, 0.1400, 0.5941, 0.4904]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6332, 0.4250, 0.8920, 0.3640, 0.4325, 0.2550, 0.6897, 0.5502],
[-0.0614, -0.0035, 0.8266, 0.2532, 0.4840, 0.2003, 0.6934, 0.5828],
[ 0.5656, 0.3930, 0.8296, 0.4740, 0.3736, 0.4827, 0.5273, 0.5308],
[ 0.6408, 0.4271, 0.8211, 0.3995, 0.3206, 0.3348, 0.5158, 0.5318],
[ 0.6423, 0.4379, 0.8163, 0.2955, 0.4129, 0.2113, 0.5810, 0.5201],
[ 0.6365, 0.4531, 0.7563, 0.2654, 0.3638, 0.2782, 0.5941, 0.5576],
[ 0.5648, 0.4057, 0.7927, 0.5257, 0.3614, 0.3913, 0.6561, 0.5536],
[ 0.5543, 0.3796, 0.7082, 0.1927, 0.4567, 0.1175, 0.5567, 0.5030]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6271, 0.4040, 0.9137, 0.3750, 0.4625, 0.2617, 0.7232, 0.5413],
[0.0000, 0.0000, 0.8850, 0.3000, 0.5362, 0.2250, 0.7343, 0.5771],
[0.6086, 0.3940, 0.8712, 0.4783, 0.4025, 0.4900, 0.5498, 0.5390],
[0.6116, 0.4019, 0.8537, 0.4067, 0.3512, 0.3583, 0.5663, 0.5133],
[0.6267, 0.4094, 0.8712, 0.3083, 0.4400, 0.2267, 0.6250, 0.5200],
[0.6243, 0.4128, 0.7763, 0.2717, 0.3825, 0.3133, 0.6212, 0.5417],
[0.6339, 0.4159, 0.8400, 0.5617, 0.3825, 0.4150, 0.7343, 0.5748],
[0.6248, 0.4032, 0.7738, 0.1900, 0.4812, 0.1400, 0.5941, 0.4904]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0010950572323054075
step: 1
running loss: 0.0010950572323054075
Train Steps: 1/90 Loss: 0.0011 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6178, 0.4059, 0.7525, 0.2250, 0.4313, 0.1783, 0.5404, 0.5240],
[0.6271, 0.4040, 0.9000, 0.3250, 0.4938, 0.2300, 0.7192, 0.5413],
[ nan, nan, 0.7515, 0.2708, 0.3987, 0.2267, 0.5162, 0.5567],
[0.6364, 0.4165, 0.9088, 0.4367, 0.4075, 0.3150, 0.6448, 0.5297],
[0.6197, 0.4118, 0.8688, 0.5517, 0.4037, 0.5233, 0.5875, 0.5600],
[0.6250, 0.4146, 0.8838, 0.3933, 0.3588, 0.4283, 0.6162, 0.5367],
[0.6150, 0.4097, 0.7468, 0.3194, 0.3825, 0.2633, 0.5463, 0.5800],
[0.6106, 0.4022, 0.7125, 0.2650, 0.3713, 0.2700, 0.5431, 0.5123]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4767, 0.3139, 0.7132, 0.2130, 0.4388, 0.1563, 0.5310, 0.5519],
[0.5141, 0.3293, 0.8923, 0.3159, 0.5079, 0.2378, 0.7557, 0.5437],
[0.0024, 0.0341, 0.7160, 0.2549, 0.4101, 0.2055, 0.5066, 0.5869],
[0.6908, 0.4591, 0.9057, 0.4473, 0.4126, 0.2974, 0.6531, 0.5544],
[0.7181, 0.4650, 0.8476, 0.5692, 0.3929, 0.5315, 0.6112, 0.5648],
[0.6992, 0.4510, 0.8456, 0.4030, 0.3658, 0.4038, 0.6252, 0.5446],
[0.5817, 0.4095, 0.7255, 0.2901, 0.3826, 0.2522, 0.5198, 0.5925],
[0.5966, 0.4142, 0.7107, 0.2639, 0.3920, 0.2604, 0.5655, 0.5287]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6178, 0.4059, 0.7525, 0.2250, 0.4313, 0.1783, 0.5404, 0.5240],
[0.6271, 0.4040, 0.9000, 0.3250, 0.4938, 0.2300, 0.7192, 0.5413],
[0.0000, 0.0000, 0.7515, 0.2708, 0.3988, 0.2267, 0.5163, 0.5567],
[0.6364, 0.4165, 0.9087, 0.4367, 0.4075, 0.3150, 0.6448, 0.5297],
[0.6197, 0.4118, 0.8687, 0.5517, 0.4038, 0.5233, 0.5875, 0.5600],
[0.6250, 0.4146, 0.8838, 0.3933, 0.3587, 0.4283, 0.6162, 0.5367],
[0.6150, 0.4097, 0.7468, 0.3194, 0.3825, 0.2633, 0.5462, 0.5800],
[0.6106, 0.4022, 0.7125, 0.2650, 0.3713, 0.2700, 0.5431, 0.5123]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.002500983187928796
step: 2
running loss: 0.001250491593964398
Train Steps: 2/90 Loss: 0.0013 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6260, 0.4214, 0.8538, 0.5500, 0.3663, 0.3767, 0.5587, 0.5983],
[0.6266, 0.4067, 0.8588, 0.2867, 0.4300, 0.2850, 0.6325, 0.5267],
[0.6149, 0.4054, 0.6713, 0.2333, 0.4025, 0.2017, 0.5213, 0.5695],
[0.6307, 0.4029, 0.8650, 0.5200, 0.3763, 0.4017, 0.7311, 0.5366],
[0.6202, 0.4066, 0.8746, 0.3376, 0.3717, 0.3090, 0.5842, 0.5165],
[ nan, nan, 0.7515, 0.2708, 0.3987, 0.2267, 0.5162, 0.5567],
[0.6171, 0.4127, 0.8900, 0.4800, 0.4325, 0.5783, 0.5769, 0.5090],
[0.6218, 0.4137, 0.7263, 0.2233, 0.4075, 0.2650, 0.6212, 0.5783]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5942, 0.3765, 0.8441, 0.5555, 0.3895, 0.3756, 0.5572, 0.5978],
[0.6839, 0.4461, 0.8516, 0.2989, 0.4596, 0.2601, 0.6697, 0.5343],
[0.5452, 0.3702, 0.6386, 0.2365, 0.4353, 0.1893, 0.5224, 0.5777],
[0.6697, 0.4203, 0.8474, 0.5115, 0.4019, 0.3696, 0.7155, 0.5159],
[0.6741, 0.4410, 0.8573, 0.3529, 0.3951, 0.2907, 0.6152, 0.5146],
[0.0102, 0.0326, 0.7223, 0.2657, 0.4187, 0.2061, 0.5159, 0.5756],
[0.6716, 0.4447, 0.9013, 0.4962, 0.4554, 0.5630, 0.6017, 0.5144],
[0.6185, 0.3953, 0.7324, 0.2696, 0.4223, 0.2574, 0.6101, 0.5704]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6260, 0.4214, 0.8537, 0.5500, 0.3663, 0.3767, 0.5587, 0.5983],
[0.6266, 0.4067, 0.8587, 0.2867, 0.4300, 0.2850, 0.6325, 0.5267],
[0.6149, 0.4054, 0.6712, 0.2333, 0.4025, 0.2017, 0.5213, 0.5695],
[0.6307, 0.4029, 0.8650, 0.5200, 0.3762, 0.4017, 0.7311, 0.5366],
[0.6202, 0.4066, 0.8746, 0.3376, 0.3717, 0.3090, 0.5842, 0.5165],
[0.0000, 0.0000, 0.7515, 0.2708, 0.3988, 0.2267, 0.5163, 0.5567],
[0.6171, 0.4127, 0.8900, 0.4800, 0.4325, 0.5783, 0.5769, 0.5090],
[0.6218, 0.4137, 0.7262, 0.2233, 0.4075, 0.2650, 0.6212, 0.5783]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0031757151591591537
step: 3
running loss: 0.001058571719719718
Train Steps: 3/90 Loss: 0.0011 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6176, 0.4017, 0.8788, 0.5100, 0.4075, 0.5250, 0.5913, 0.5033],
[0.6040, 0.4002, 0.7338, 0.2267, 0.3975, 0.2100, 0.5231, 0.4778],
[0.6133, 0.4094, 0.8495, 0.4028, 0.3588, 0.3200, 0.5003, 0.5407],
[0.6144, 0.4032, 0.8563, 0.3283, 0.3525, 0.4200, 0.5775, 0.5583],
[0.6339, 0.4112, 0.8838, 0.5067, 0.4000, 0.5433, 0.7549, 0.5378],
[0.6311, 0.3998, 0.7975, 0.5767, 0.3838, 0.4850, 0.7327, 0.5343],
[0.6271, 0.4040, 0.9000, 0.3250, 0.4938, 0.2300, 0.7192, 0.5413],
[0.6241, 0.4143, 0.8938, 0.4650, 0.4075, 0.5350, 0.6250, 0.5550]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5998, 0.3881, 0.8489, 0.5266, 0.4269, 0.5364, 0.5653, 0.5266],
[0.6322, 0.4066, 0.7096, 0.2361, 0.4164, 0.1925, 0.5609, 0.5039],
[0.6330, 0.4206, 0.8351, 0.4194, 0.3907, 0.3015, 0.5033, 0.5504],
[0.6071, 0.3998, 0.8333, 0.3566, 0.3592, 0.4133, 0.5639, 0.5432],
[0.6248, 0.3960, 0.8594, 0.5358, 0.4098, 0.5365, 0.6945, 0.5580],
[0.5699, 0.3728, 0.7798, 0.5499, 0.4036, 0.4531, 0.6909, 0.5258],
[0.5120, 0.3214, 0.8967, 0.3325, 0.5200, 0.2344, 0.7362, 0.5293],
[0.6220, 0.4074, 0.8722, 0.4873, 0.4371, 0.5165, 0.6189, 0.5546]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6176, 0.4017, 0.8788, 0.5100, 0.4075, 0.5250, 0.5913, 0.5033],
[0.6040, 0.4002, 0.7337, 0.2267, 0.3975, 0.2100, 0.5231, 0.4778],
[0.6133, 0.4094, 0.8495, 0.4028, 0.3587, 0.3200, 0.5003, 0.5407],
[0.6144, 0.4032, 0.8562, 0.3283, 0.3525, 0.4200, 0.5775, 0.5583],
[0.6339, 0.4112, 0.8838, 0.5067, 0.4000, 0.5433, 0.7549, 0.5378],
[0.6311, 0.3998, 0.7975, 0.5767, 0.3837, 0.4850, 0.7327, 0.5343],
[0.6271, 0.4040, 0.9000, 0.3250, 0.4938, 0.2300, 0.7192, 0.5413],
[0.6241, 0.4142, 0.8938, 0.4650, 0.4075, 0.5350, 0.6250, 0.5550]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.003960852511227131
step: 4
running loss: 0.0009902131278067827
Train Steps: 4/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6125, 0.4076, 0.8488, 0.3883, 0.3700, 0.3683, 0.5026, 0.5505],
[0.6141, 0.4038, 0.8650, 0.4833, 0.4839, 0.5176, 0.5787, 0.5600],
[0.6286, 0.4040, 0.8696, 0.3047, 0.3924, 0.2887, 0.6300, 0.5367],
[0.6265, 0.4088, 0.8025, 0.1850, 0.4163, 0.2500, 0.6290, 0.4947],
[ nan, nan, 0.6900, 0.1917, 0.3937, 0.2367, 0.5240, 0.5246],
[0.6205, 0.4004, 0.8938, 0.4883, 0.3663, 0.5000, 0.6357, 0.4947],
[0.6203, 0.4072, 0.8892, 0.3523, 0.3783, 0.3017, 0.5898, 0.5478],
[0.6282, 0.4034, 0.7830, 0.2080, 0.4532, 0.2080, 0.6404, 0.5323]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6783, 0.4287, 0.8345, 0.4148, 0.3889, 0.3670, 0.5106, 0.5487],
[0.6346, 0.3948, 0.8567, 0.5327, 0.4835, 0.5207, 0.6150, 0.5423],
[0.6474, 0.3986, 0.8573, 0.3465, 0.4161, 0.2739, 0.6702, 0.5225],
[0.6479, 0.4147, 0.7972, 0.2488, 0.4486, 0.2405, 0.6617, 0.5058],
[0.0196, 0.0039, 0.7029, 0.2429, 0.4289, 0.2278, 0.5220, 0.5362],
[0.5678, 0.3465, 0.8812, 0.5202, 0.3915, 0.5057, 0.6697, 0.4872],
[0.6323, 0.3935, 0.8804, 0.3828, 0.3995, 0.3069, 0.6250, 0.5382],
[0.6513, 0.4062, 0.7634, 0.2697, 0.4707, 0.2048, 0.6481, 0.5327]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6125, 0.4076, 0.8487, 0.3883, 0.3700, 0.3683, 0.5026, 0.5505],
[0.6141, 0.4038, 0.8650, 0.4833, 0.4839, 0.5176, 0.5788, 0.5600],
[0.6286, 0.4040, 0.8696, 0.3047, 0.3924, 0.2887, 0.6300, 0.5367],
[0.6265, 0.4088, 0.8025, 0.1850, 0.4162, 0.2500, 0.6290, 0.4947],
[0.0000, 0.0000, 0.6900, 0.1917, 0.3938, 0.2367, 0.5240, 0.5246],
[0.6205, 0.4004, 0.8938, 0.4883, 0.3663, 0.5000, 0.6357, 0.4947],
[0.6203, 0.4072, 0.8892, 0.3523, 0.3783, 0.3017, 0.5898, 0.5478],
[0.6282, 0.4034, 0.7830, 0.2080, 0.4532, 0.2080, 0.6404, 0.5323]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.00465098989661783
step: 5
running loss: 0.0009301979793235659
Train Steps: 5/90 Loss: 0.0009 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6271, 0.4081, 0.9081, 0.4894, 0.3700, 0.4283, 0.6661, 0.5274],
[0.6300, 0.4102, 0.9088, 0.4433, 0.4088, 0.3067, 0.6820, 0.5540],
[0.6161, 0.4099, 0.8738, 0.4383, 0.3788, 0.5483, 0.5605, 0.5019],
[0.6201, 0.4004, 0.8786, 0.5043, 0.3833, 0.5138, 0.5997, 0.5092],
[0.6222, 0.4108, 0.8938, 0.4233, 0.3600, 0.3817, 0.5825, 0.5283],
[0.6307, 0.4060, 0.8950, 0.5183, 0.3750, 0.3850, 0.6338, 0.4938],
[0.6182, 0.4058, 0.8738, 0.4350, 0.3563, 0.3400, 0.5290, 0.5822],
[0.6296, 0.3989, 0.9000, 0.4150, 0.3613, 0.3867, 0.6400, 0.5100]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6552, 0.4114, 0.8774, 0.4658, 0.3782, 0.4515, 0.6856, 0.5181],
[0.6604, 0.4108, 0.9086, 0.4488, 0.4350, 0.3231, 0.7029, 0.5382],
[0.5866, 0.3753, 0.8584, 0.4249, 0.4075, 0.5679, 0.5804, 0.5033],
[0.6180, 0.3723, 0.8611, 0.5224, 0.4083, 0.5331, 0.5848, 0.5022],
[0.6441, 0.4107, 0.8707, 0.4167, 0.3678, 0.4041, 0.6107, 0.5390],
[0.5974, 0.3602, 0.8996, 0.5247, 0.3950, 0.3934, 0.6271, 0.4822],
[0.6110, 0.3776, 0.8502, 0.4215, 0.3777, 0.3466, 0.5408, 0.5714],
[0.5673, 0.3445, 0.8787, 0.4207, 0.3819, 0.3933, 0.6621, 0.5070]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6271, 0.4081, 0.9081, 0.4894, 0.3700, 0.4283, 0.6661, 0.5274],
[0.6300, 0.4102, 0.9087, 0.4433, 0.4087, 0.3067, 0.6820, 0.5540],
[0.6161, 0.4099, 0.8737, 0.4383, 0.3787, 0.5483, 0.5605, 0.5019],
[0.6201, 0.4004, 0.8786, 0.5043, 0.3833, 0.5138, 0.5997, 0.5092],
[0.6222, 0.4108, 0.8938, 0.4233, 0.3600, 0.3817, 0.5825, 0.5283],
[0.6307, 0.4060, 0.8950, 0.5183, 0.3750, 0.3850, 0.6338, 0.4938],
[0.6182, 0.4058, 0.8737, 0.4350, 0.3562, 0.3400, 0.5290, 0.5822],
[0.6296, 0.3989, 0.9000, 0.4150, 0.3613, 0.3867, 0.6400, 0.5100]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.00511719353380613
step: 6
running loss: 0.0008528655889676884
Train Steps: 6/90 Loss: 0.0009 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6266, 0.4070, 0.8712, 0.5600, 0.3713, 0.4783, 0.5775, 0.6100],
[ nan, nan, 0.7268, 0.2333, 0.4125, 0.1933, 0.5112, 0.5383],
[0.6161, 0.4040, 0.7525, 0.2133, 0.4125, 0.2067, 0.5787, 0.5117],
[0.6201, 0.4055, 0.7717, 0.1919, 0.4250, 0.2079, 0.5871, 0.5044],
[0.6286, 0.4274, 0.8500, 0.4500, 0.4525, 0.2583, 0.5440, 0.6209],
[0.6226, 0.4001, 0.8438, 0.5733, 0.3862, 0.4250, 0.5750, 0.5283],
[0.6293, 0.3982, 0.8700, 0.5300, 0.3763, 0.4717, 0.7050, 0.5297],
[0.6127, 0.4119, 0.8650, 0.5300, 0.4512, 0.5250, 0.5260, 0.5461]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6628, 0.4258, 0.8829, 0.5384, 0.3582, 0.5162, 0.6053, 0.5552],
[0.1885, 0.1040, 0.7453, 0.2245, 0.3961, 0.2227, 0.5406, 0.5308],
[0.6685, 0.4067, 0.7905, 0.2101, 0.4101, 0.2576, 0.5969, 0.4991],
[0.6771, 0.4192, 0.8103, 0.2036, 0.4245, 0.2512, 0.6132, 0.4906],
[0.6017, 0.3746, 0.8931, 0.4406, 0.4620, 0.3175, 0.5585, 0.5956],
[0.6587, 0.4070, 0.8789, 0.5625, 0.3910, 0.4548, 0.6079, 0.5264],
[0.6750, 0.4058, 0.8986, 0.5292, 0.3593, 0.5000, 0.6943, 0.5169],
[0.6772, 0.4275, 0.8966, 0.5189, 0.4330, 0.5449, 0.5616, 0.5367]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6266, 0.4070, 0.8712, 0.5600, 0.3713, 0.4783, 0.5775, 0.6100],
[0.0000, 0.0000, 0.7268, 0.2333, 0.4125, 0.1933, 0.5113, 0.5383],
[0.6161, 0.4040, 0.7525, 0.2133, 0.4125, 0.2067, 0.5788, 0.5117],
[0.6202, 0.4055, 0.7717, 0.1919, 0.4250, 0.2079, 0.5871, 0.5044],
[0.6286, 0.4274, 0.8500, 0.4500, 0.4525, 0.2583, 0.5440, 0.6209],
[0.6226, 0.4001, 0.8438, 0.5733, 0.3862, 0.4250, 0.5750, 0.5283],
[0.6293, 0.3982, 0.8700, 0.5300, 0.3762, 0.4717, 0.7050, 0.5297],
[0.6127, 0.4119, 0.8650, 0.5300, 0.4512, 0.5250, 0.5260, 0.5461]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.006649552000453696
step: 7
running loss: 0.0009499360000648137
Train Steps: 7/90 Loss: 0.0009 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6261, 0.3987, 0.9045, 0.4208, 0.3600, 0.4633, 0.6570, 0.5162],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533],
[0.6200, 0.4071, 0.7338, 0.1917, 0.4200, 0.2450, 0.6150, 0.5517],
[0.6126, 0.4039, 0.8237, 0.3967, 0.3625, 0.3600, 0.5894, 0.6138],
[0.6115, 0.4005, 0.8838, 0.3867, 0.3763, 0.4700, 0.5800, 0.5550],
[0.6314, 0.4050, 0.8227, 0.5431, 0.4150, 0.5517, 0.7121, 0.5690],
[0.6264, 0.4035, 0.8888, 0.4883, 0.4050, 0.5217, 0.6361, 0.4791],
[0.6248, 0.4185, 0.8500, 0.5767, 0.4463, 0.4550, 0.5613, 0.5917]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5887, 0.3806, 0.9167, 0.4414, 0.3467, 0.4701, 0.6545, 0.4994],
[0.6237, 0.4254, 0.9156, 0.4351, 0.4059, 0.5172, 0.5768, 0.5177],
[0.6543, 0.4100, 0.7849, 0.2122, 0.3987, 0.2520, 0.6252, 0.5278],
[0.6230, 0.3921, 0.8515, 0.4160, 0.3300, 0.3534, 0.6035, 0.5913],
[0.6065, 0.3897, 0.8989, 0.3883, 0.3638, 0.4858, 0.5655, 0.5183],
[0.6534, 0.4116, 0.8756, 0.5226, 0.3947, 0.5489, 0.7233, 0.5426],
[0.6262, 0.3883, 0.9243, 0.4744, 0.3783, 0.5022, 0.6143, 0.4519],
[0.6220, 0.3931, 0.8964, 0.5730, 0.4454, 0.4293, 0.5510, 0.5697]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6261, 0.3987, 0.9045, 0.4208, 0.3600, 0.4633, 0.6570, 0.5162],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533],
[0.6200, 0.4071, 0.7337, 0.1917, 0.4200, 0.2450, 0.6150, 0.5517],
[0.6126, 0.4038, 0.8238, 0.3967, 0.3625, 0.3600, 0.5894, 0.6138],
[0.6115, 0.4005, 0.8838, 0.3867, 0.3762, 0.4700, 0.5800, 0.5550],
[0.6314, 0.4050, 0.8227, 0.5431, 0.4150, 0.5517, 0.7121, 0.5690],
[0.6264, 0.4035, 0.8888, 0.4883, 0.4050, 0.5217, 0.6361, 0.4791],
[0.6248, 0.4185, 0.8500, 0.5767, 0.4462, 0.4550, 0.5612, 0.5917]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.007122047507436946
step: 8
running loss: 0.0008902559384296183
Train Steps: 8/90 Loss: 0.0009 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6275, 0.4008, 0.8047, 0.2484, 0.4037, 0.2777, 0.6506, 0.5212],
[0.6273, 0.4110, 0.8900, 0.3817, 0.4188, 0.2167, 0.5858, 0.4835],
[0.6214, 0.4040, 0.8838, 0.3500, 0.3600, 0.5183, 0.6362, 0.5200],
[ nan, nan, 0.6512, 0.1717, 0.4100, 0.1983, 0.5253, 0.5240],
[0.6189, 0.3911, 0.8800, 0.4917, 0.3713, 0.4800, 0.6038, 0.4833],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4012, 0.4633, 0.5338, 0.5767],
[0.6198, 0.4105, 0.7950, 0.3267, 0.3675, 0.3767, 0.6038, 0.6167],
[0.6246, 0.4126, 0.8850, 0.4833, 0.4200, 0.5350, 0.6112, 0.5250]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6781, 0.4366, 0.8292, 0.2767, 0.3947, 0.3024, 0.6299, 0.5228],
[0.6502, 0.4163, 0.9356, 0.3927, 0.4165, 0.2404, 0.6043, 0.5037],
[0.6243, 0.4212, 0.8959, 0.3969, 0.3492, 0.5258, 0.6535, 0.5265],
[0.0754, 0.0272, 0.7135, 0.2025, 0.3964, 0.2239, 0.5353, 0.5389],
[0.7175, 0.4695, 0.9051, 0.5078, 0.3554, 0.4924, 0.5934, 0.5303],
[0.6314, 0.4253, 0.9020, 0.5113, 0.4033, 0.4586, 0.5315, 0.6031],
[0.6845, 0.4592, 0.8323, 0.3439, 0.3670, 0.4061, 0.5821, 0.6231],
[0.6510, 0.4404, 0.9164, 0.4900, 0.4029, 0.5442, 0.6044, 0.5414]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6275, 0.4008, 0.8047, 0.2484, 0.4037, 0.2777, 0.6506, 0.5212],
[0.6273, 0.4110, 0.8900, 0.3817, 0.4187, 0.2167, 0.5858, 0.4835],
[0.6214, 0.4040, 0.8838, 0.3500, 0.3600, 0.5183, 0.6363, 0.5200],
[0.0000, 0.0000, 0.6513, 0.1717, 0.4100, 0.1983, 0.5253, 0.5240],
[0.6189, 0.3911, 0.8800, 0.4917, 0.3713, 0.4800, 0.6037, 0.4833],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4013, 0.4633, 0.5337, 0.5767],
[0.6198, 0.4105, 0.7950, 0.3267, 0.3675, 0.3767, 0.6037, 0.6167],
[0.6246, 0.4126, 0.8850, 0.4833, 0.4200, 0.5350, 0.6112, 0.5250]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.008067115588346496
step: 9
running loss: 0.000896346176482944
Train Steps: 9/90 Loss: 0.0009 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6250, 0.4131, 0.8688, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367],
[0.6353, 0.4128, 0.9138, 0.3533, 0.4688, 0.3250, 0.7145, 0.5991],
[ nan, nan, 0.7512, 0.2117, 0.4288, 0.2000, 0.5600, 0.5617],
[0.6275, 0.4157, 0.8337, 0.5800, 0.3763, 0.4200, 0.5547, 0.6125],
[0.6204, 0.4055, 0.8438, 0.5733, 0.4574, 0.4801, 0.5487, 0.5617],
[0.6265, 0.4088, 0.8025, 0.1850, 0.4163, 0.2500, 0.6290, 0.4947],
[0.6339, 0.4102, 0.9088, 0.4767, 0.3925, 0.5283, 0.7509, 0.5390],
[0.6273, 0.4100, 0.7137, 0.2133, 0.4000, 0.2650, 0.6075, 0.5633]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6229, 0.4118, 0.8863, 0.2859, 0.4184, 0.2557, 0.5658, 0.5340],
[0.6148, 0.4197, 0.9315, 0.3354, 0.4334, 0.3215, 0.6852, 0.5903],
[0.0754, 0.0627, 0.7600, 0.2218, 0.3954, 0.2259, 0.5242, 0.5600],
[0.5883, 0.4249, 0.8646, 0.5609, 0.3616, 0.4497, 0.5613, 0.6069],
[0.5997, 0.4042, 0.8556, 0.5515, 0.4356, 0.4546, 0.4996, 0.5693],
[0.6244, 0.4190, 0.8221, 0.1943, 0.4030, 0.2628, 0.5984, 0.5144],
[0.6360, 0.4487, 0.9374, 0.4746, 0.3753, 0.5383, 0.7273, 0.5499],
[0.5903, 0.3867, 0.7336, 0.2222, 0.3727, 0.2676, 0.5683, 0.5639]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6250, 0.4131, 0.8687, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367],
[0.6353, 0.4128, 0.9137, 0.3533, 0.4688, 0.3250, 0.7145, 0.5991],
[0.0000, 0.0000, 0.7513, 0.2117, 0.4288, 0.2000, 0.5600, 0.5617],
[0.6275, 0.4157, 0.8338, 0.5800, 0.3762, 0.4200, 0.5547, 0.6125],
[0.6204, 0.4055, 0.8438, 0.5733, 0.4574, 0.4801, 0.5487, 0.5617],
[0.6265, 0.4088, 0.8025, 0.1850, 0.4162, 0.2500, 0.6290, 0.4947],
[0.6339, 0.4102, 0.9087, 0.4767, 0.3925, 0.5283, 0.7509, 0.5390],
[0.6273, 0.4099, 0.7138, 0.2133, 0.4000, 0.2650, 0.6075, 0.5633]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.008671639865497127
step: 10
running loss: 0.0008671639865497127
Train Steps: 10/90 Loss: 0.0009 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6332, 0.4165, 0.9100, 0.3350, 0.4188, 0.3683, 0.7438, 0.5528],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4012, 0.4633, 0.5338, 0.5767],
[0.6086, 0.3998, 0.8788, 0.4450, 0.4025, 0.4650, 0.5306, 0.5103],
[0.6289, 0.4081, 0.8720, 0.3487, 0.3900, 0.3183, 0.6703, 0.5376],
[0.6279, 0.4008, 0.8600, 0.4883, 0.4325, 0.5283, 0.7010, 0.5378],
[0.6086, 0.4019, 0.7782, 0.4278, 0.3625, 0.4350, 0.5150, 0.5285],
[0.6182, 0.4058, 0.8738, 0.4350, 0.3563, 0.3400, 0.5290, 0.5822],
[0.6175, 0.4093, 0.8800, 0.4433, 0.4075, 0.4367, 0.5128, 0.4901]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5651, 0.3872, 0.9091, 0.3589, 0.4060, 0.3687, 0.7129, 0.5629],
[0.5442, 0.3813, 0.8742, 0.4722, 0.4190, 0.4401, 0.5225, 0.5954],
[0.5596, 0.3881, 0.8712, 0.4179, 0.3868, 0.4584, 0.5164, 0.5327],
[0.5353, 0.3653, 0.8768, 0.3212, 0.3934, 0.3146, 0.6572, 0.5564],
[0.5771, 0.3766, 0.8791, 0.4666, 0.4206, 0.5151, 0.6954, 0.5690],
[0.5786, 0.3886, 0.7983, 0.4074, 0.3795, 0.4221, 0.5060, 0.5502],
[0.5158, 0.3602, 0.8586, 0.4000, 0.3567, 0.3225, 0.5129, 0.5861],
[0.6043, 0.4215, 0.8886, 0.4290, 0.4082, 0.4468, 0.5101, 0.5186]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6332, 0.4165, 0.9100, 0.3350, 0.4187, 0.3683, 0.7438, 0.5528],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4013, 0.4633, 0.5337, 0.5767],
[0.6086, 0.3998, 0.8788, 0.4450, 0.4025, 0.4650, 0.5306, 0.5103],
[0.6289, 0.4081, 0.8720, 0.3487, 0.3900, 0.3183, 0.6703, 0.5376],
[0.6279, 0.4008, 0.8600, 0.4883, 0.4325, 0.5283, 0.7010, 0.5378],
[0.6086, 0.4019, 0.7782, 0.4278, 0.3625, 0.4350, 0.5150, 0.5285],
[0.6182, 0.4058, 0.8737, 0.4350, 0.3562, 0.3400, 0.5290, 0.5822],
[0.6175, 0.4093, 0.8800, 0.4433, 0.4075, 0.4367, 0.5128, 0.4901]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.00954322874895297
step: 11
running loss: 0.0008675662499048154
Train Steps: 11/90 Loss: 0.0009 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6164, 0.3956, 0.8757, 0.5088, 0.4300, 0.5320, 0.6022, 0.5202],
[0.6048, 0.3928, 0.8538, 0.5433, 0.3875, 0.5117, 0.5266, 0.4719],
[0.6243, 0.4128, 0.7762, 0.2717, 0.3825, 0.3133, 0.6212, 0.5417],
[0.6361, 0.4076, 0.8862, 0.5350, 0.3713, 0.4650, 0.6654, 0.5297],
[0.6203, 0.4021, 0.8780, 0.5031, 0.3667, 0.3882, 0.5842, 0.5405],
[0.6273, 0.4100, 0.7137, 0.2133, 0.4000, 0.2650, 0.6075, 0.5633],
[0.6070, 0.3979, 0.8575, 0.5083, 0.4350, 0.5400, 0.5180, 0.5466],
[0.6175, 0.3957, 0.8700, 0.4817, 0.4662, 0.5133, 0.5800, 0.5517]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5483, 0.3622, 0.8770, 0.4779, 0.3990, 0.5093, 0.6017, 0.5437],
[0.5784, 0.3904, 0.8539, 0.5166, 0.3958, 0.4806, 0.5558, 0.5333],
[0.5637, 0.3742, 0.7941, 0.2559, 0.3872, 0.3076, 0.6280, 0.5515],
[0.5998, 0.4185, 0.8796, 0.5261, 0.3549, 0.4438, 0.6606, 0.5561],
[0.6237, 0.4060, 0.8862, 0.4990, 0.3595, 0.3872, 0.5895, 0.5282],
[0.5888, 0.3756, 0.7120, 0.2081, 0.3834, 0.2500, 0.6050, 0.5684],
[0.5443, 0.3876, 0.8513, 0.4988, 0.4388, 0.5221, 0.5204, 0.5598],
[0.5425, 0.3668, 0.8625, 0.4351, 0.4530, 0.4921, 0.5606, 0.5558]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6164, 0.3956, 0.8757, 0.5088, 0.4300, 0.5320, 0.6022, 0.5202],
[0.6048, 0.3928, 0.8537, 0.5433, 0.3875, 0.5117, 0.5266, 0.4719],
[0.6243, 0.4128, 0.7763, 0.2717, 0.3825, 0.3133, 0.6212, 0.5417],
[0.6361, 0.4076, 0.8863, 0.5350, 0.3713, 0.4650, 0.6654, 0.5297],
[0.6203, 0.4020, 0.8780, 0.5031, 0.3667, 0.3882, 0.5842, 0.5405],
[0.6273, 0.4099, 0.7138, 0.2133, 0.4000, 0.2650, 0.6075, 0.5633],
[0.6070, 0.3979, 0.8575, 0.5083, 0.4350, 0.5400, 0.5180, 0.5466],
[0.6175, 0.3957, 0.8700, 0.4817, 0.4663, 0.5133, 0.5800, 0.5517]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.010210297914454713
step: 12
running loss: 0.0008508581595378928
Train Steps: 12/90 Loss: 0.0009 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6190, 0.4135, 0.8000, 0.4883, 0.3566, 0.3647, 0.5613, 0.5900],
[0.6173, 0.4114, 0.7325, 0.2500, 0.4213, 0.1917, 0.5338, 0.5700],
[ nan, nan, 0.7225, 0.2167, 0.3987, 0.2283, 0.5427, 0.5181],
[0.6246, 0.4090, 0.6964, 0.2027, 0.3925, 0.2683, 0.6088, 0.5583],
[0.6262, 0.4163, 0.8850, 0.5183, 0.3763, 0.4150, 0.6025, 0.5500],
[0.6266, 0.4070, 0.8712, 0.5600, 0.3713, 0.4783, 0.5775, 0.6100],
[ nan, nan, 0.8525, 0.2217, 0.5413, 0.2367, 0.7367, 0.5482],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3788, 0.4900, 0.7121, 0.5864]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6665, 0.4454, 0.8174, 0.4735, 0.3770, 0.3649, 0.5131, 0.5624],
[0.5387, 0.3739, 0.7161, 0.2188, 0.4464, 0.2063, 0.5391, 0.5532],
[0.2135, 0.1407, 0.6820, 0.1918, 0.4179, 0.2471, 0.5318, 0.5153],
[0.6443, 0.4274, 0.6857, 0.2046, 0.4088, 0.2694, 0.6036, 0.5470],
[0.6675, 0.4486, 0.8739, 0.4873, 0.3920, 0.4055, 0.5779, 0.5486],
[0.6897, 0.4687, 0.8466, 0.5476, 0.3902, 0.4891, 0.5805, 0.5826],
[0.2292, 0.1626, 0.8446, 0.2121, 0.5398, 0.2417, 0.7055, 0.5412],
[0.6525, 0.4344, 0.8758, 0.5061, 0.3929, 0.4984, 0.7030, 0.5711]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6190, 0.4135, 0.8000, 0.4883, 0.3566, 0.3647, 0.5612, 0.5900],
[0.6173, 0.4114, 0.7325, 0.2500, 0.4212, 0.1917, 0.5337, 0.5700],
[0.0000, 0.0000, 0.7225, 0.2167, 0.3988, 0.2283, 0.5427, 0.5181],
[0.6246, 0.4090, 0.6964, 0.2027, 0.3925, 0.2683, 0.6087, 0.5583],
[0.6262, 0.4163, 0.8850, 0.5183, 0.3762, 0.4150, 0.6025, 0.5500],
[0.6266, 0.4070, 0.8712, 0.5600, 0.3713, 0.4783, 0.5775, 0.6100],
[0.0000, 0.0000, 0.8525, 0.2217, 0.5412, 0.2367, 0.7367, 0.5482],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3787, 0.4900, 0.7121, 0.5864]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0029, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0029, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.013074482005322352
step: 13
running loss: 0.0010057293850247962
Train Steps: 13/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6277, 0.4057, 0.8300, 0.2650, 0.4363, 0.1850, 0.6140, 0.4823],
[0.6087, 0.3951, 0.8387, 0.5833, 0.4188, 0.4933, 0.5146, 0.4830],
[0.6034, 0.4011, 0.7350, 0.2533, 0.3438, 0.3367, 0.5516, 0.5084],
[0.6272, 0.4071, 0.8738, 0.5600, 0.3675, 0.3783, 0.5926, 0.4742],
[0.6260, 0.4133, 0.8800, 0.5117, 0.3713, 0.3283, 0.6223, 0.4967],
[0.6275, 0.4003, 0.9100, 0.3783, 0.4388, 0.3133, 0.7058, 0.5343],
[0.6292, 0.4010, 0.8988, 0.4800, 0.3638, 0.3817, 0.6357, 0.5051],
[0.6260, 0.4120, 0.8013, 0.2350, 0.4888, 0.1533, 0.6281, 0.4895]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6209, 0.3946, 0.7829, 0.2354, 0.4578, 0.2138, 0.5985, 0.5199],
[0.5912, 0.3801, 0.8002, 0.5580, 0.4329, 0.5129, 0.5151, 0.5371],
[0.5538, 0.3627, 0.6871, 0.2188, 0.3659, 0.3580, 0.5647, 0.5449],
[0.5544, 0.3579, 0.8420, 0.5472, 0.3969, 0.4023, 0.6108, 0.4973],
[0.5533, 0.3713, 0.8420, 0.4789, 0.3996, 0.3498, 0.6161, 0.5338],
[0.5912, 0.3869, 0.8465, 0.3534, 0.4348, 0.3184, 0.6907, 0.5468],
[0.6274, 0.3913, 0.8715, 0.4603, 0.3700, 0.3854, 0.6073, 0.5570],
[0.5417, 0.3396, 0.7500, 0.1926, 0.4977, 0.1744, 0.6412, 0.5392]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6277, 0.4056, 0.8300, 0.2650, 0.4363, 0.1850, 0.6140, 0.4823],
[0.6087, 0.3951, 0.8388, 0.5833, 0.4187, 0.4933, 0.5146, 0.4830],
[0.6033, 0.4011, 0.7350, 0.2533, 0.3438, 0.3367, 0.5516, 0.5084],
[0.6272, 0.4071, 0.8737, 0.5600, 0.3675, 0.3783, 0.5926, 0.4742],
[0.6260, 0.4133, 0.8800, 0.5117, 0.3713, 0.3283, 0.6223, 0.4967],
[0.6275, 0.4003, 0.9100, 0.3783, 0.4387, 0.3133, 0.7058, 0.5343],
[0.6292, 0.4010, 0.8988, 0.4800, 0.3638, 0.3817, 0.6357, 0.5051],
[0.6259, 0.4120, 0.8012, 0.2350, 0.4888, 0.1533, 0.6281, 0.4895]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.014277539594331756
step: 14
running loss: 0.0010198242567379826
Train Steps: 14/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6082, 0.4042, 0.6975, 0.1917, 0.4100, 0.1983, 0.5502, 0.5578],
[0.6083, 0.3957, 0.8638, 0.4950, 0.4363, 0.5083, 0.5346, 0.4980],
[0.6200, 0.4071, 0.7338, 0.1917, 0.4200, 0.2450, 0.6150, 0.5517],
[0.6160, 0.4086, 0.8775, 0.3983, 0.3750, 0.3783, 0.5128, 0.4882],
[0.6357, 0.4139, 0.8450, 0.5883, 0.3775, 0.4950, 0.6488, 0.5297],
[0.6201, 0.4017, 0.8871, 0.4621, 0.3517, 0.4675, 0.5999, 0.5106],
[0.6202, 0.4054, 0.8892, 0.4428, 0.3642, 0.3249, 0.5840, 0.5426],
[0.6271, 0.4081, 0.9081, 0.4894, 0.3700, 0.4283, 0.6661, 0.5274]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5333, 0.3506, 0.6552, 0.2076, 0.4242, 0.1751, 0.5727, 0.5451],
[0.4893, 0.3109, 0.8448, 0.5058, 0.4601, 0.5073, 0.5673, 0.4904],
[0.5904, 0.3878, 0.7141, 0.1966, 0.4354, 0.2181, 0.6287, 0.5480],
[0.5772, 0.3840, 0.8524, 0.4117, 0.3834, 0.3702, 0.5531, 0.5023],
[0.6300, 0.4052, 0.8221, 0.5879, 0.3911, 0.4689, 0.6662, 0.5207],
[0.6077, 0.3779, 0.8499, 0.4657, 0.3675, 0.4600, 0.6185, 0.5338],
[0.6065, 0.3866, 0.8750, 0.4366, 0.3635, 0.3120, 0.6016, 0.5102],
[0.5697, 0.3748, 0.8739, 0.4813, 0.3705, 0.4117, 0.6781, 0.5255]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6082, 0.4042, 0.6975, 0.1917, 0.4100, 0.1983, 0.5502, 0.5578],
[0.6083, 0.3957, 0.8637, 0.4950, 0.4363, 0.5083, 0.5346, 0.4980],
[0.6200, 0.4071, 0.7337, 0.1917, 0.4200, 0.2450, 0.6150, 0.5517],
[0.6160, 0.4086, 0.8775, 0.3983, 0.3750, 0.3783, 0.5128, 0.4882],
[0.6357, 0.4139, 0.8450, 0.5883, 0.3775, 0.4950, 0.6488, 0.5297],
[0.6201, 0.4017, 0.8871, 0.4621, 0.3517, 0.4675, 0.5999, 0.5106],
[0.6202, 0.4054, 0.8892, 0.4428, 0.3642, 0.3249, 0.5840, 0.5426],
[0.6271, 0.4081, 0.9081, 0.4894, 0.3700, 0.4283, 0.6661, 0.5274]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.015163687261519954
step: 15
running loss: 0.0010109124841013303
Train Steps: 15/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6157, 0.4102, 0.8513, 0.3817, 0.3613, 0.3667, 0.5096, 0.5890],
[0.6146, 0.4124, 0.8800, 0.4867, 0.3800, 0.4500, 0.5106, 0.5524],
[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150],
[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395],
[0.6205, 0.4012, 0.8675, 0.3283, 0.3713, 0.3050, 0.5813, 0.5117],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533],
[0.6201, 0.4116, 0.8725, 0.4733, 0.3700, 0.3217, 0.5386, 0.5767],
[0.6085, 0.4005, 0.8400, 0.4317, 0.3763, 0.4750, 0.5476, 0.5058]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5410, 0.3491, 0.8061, 0.3897, 0.3737, 0.3296, 0.5710, 0.5361],
[0.5908, 0.3836, 0.8486, 0.5070, 0.3837, 0.4084, 0.5487, 0.5290],
[0.5794, 0.3698, 0.8578, 0.4783, 0.4464, 0.5413, 0.6610, 0.5036],
[0.5673, 0.3616, 0.8306, 0.5433, 0.3512, 0.3234, 0.6101, 0.5062],
[0.5835, 0.3757, 0.8322, 0.3436, 0.3784, 0.2795, 0.6196, 0.4811],
[0.5601, 0.3804, 0.8507, 0.4410, 0.4294, 0.4775, 0.6118, 0.5142],
[0.6267, 0.4019, 0.8304, 0.4744, 0.3647, 0.2856, 0.5849, 0.5461],
[0.6285, 0.4035, 0.8221, 0.4240, 0.3711, 0.4418, 0.5872, 0.4826]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6157, 0.4102, 0.8512, 0.3817, 0.3613, 0.3667, 0.5096, 0.5890],
[0.6146, 0.4124, 0.8800, 0.4867, 0.3800, 0.4500, 0.5106, 0.5524],
[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150],
[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395],
[0.6205, 0.4012, 0.8675, 0.3283, 0.3713, 0.3050, 0.5813, 0.5117],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533],
[0.6201, 0.4116, 0.8725, 0.4733, 0.3700, 0.3217, 0.5386, 0.5767],
[0.6084, 0.4005, 0.8400, 0.4317, 0.3762, 0.4750, 0.5476, 0.5058]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.016262349992757663
step: 16
running loss: 0.001016396874547354
Train Steps: 16/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6214, 0.3982, 0.8938, 0.4517, 0.3663, 0.4083, 0.5863, 0.5050],
[0.6109, 0.4003, 0.8650, 0.4883, 0.4775, 0.4867, 0.5175, 0.5683],
[0.6200, 0.4039, 0.8880, 0.4799, 0.3625, 0.4285, 0.5866, 0.5148],
[0.6273, 0.4105, 0.8988, 0.4517, 0.3912, 0.2550, 0.5894, 0.4811],
[ nan, nan, 0.6412, 0.1900, 0.4238, 0.1883, 0.5487, 0.5700],
[0.6336, 0.4191, 0.8938, 0.5167, 0.3937, 0.3517, 0.7343, 0.5748],
[0.6138, 0.4101, 0.8800, 0.5083, 0.4637, 0.5950, 0.5587, 0.5077],
[0.6109, 0.4041, 0.6975, 0.3167, 0.3513, 0.3383, 0.5153, 0.5319]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6855, 0.4411, 0.8811, 0.4829, 0.3468, 0.4056, 0.5976, 0.4854],
[0.6003, 0.3924, 0.8620, 0.5050, 0.4516, 0.4777, 0.5454, 0.5403],
[0.7025, 0.4502, 0.8847, 0.4959, 0.3405, 0.4132, 0.5959, 0.4986],
[0.6217, 0.3892, 0.8945, 0.4343, 0.3822, 0.2371, 0.5838, 0.4497],
[0.0274, 0.0246, 0.6846, 0.2371, 0.3901, 0.1621, 0.5692, 0.5287],
[0.6936, 0.4408, 0.8705, 0.5191, 0.3849, 0.3495, 0.7009, 0.5208],
[0.6504, 0.4256, 0.8840, 0.5347, 0.4355, 0.5537, 0.5773, 0.5028],
[0.6316, 0.4177, 0.7242, 0.3255, 0.3338, 0.3280, 0.5260, 0.4997]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6214, 0.3982, 0.8938, 0.4517, 0.3663, 0.4083, 0.5863, 0.5050],
[0.6109, 0.4003, 0.8650, 0.4883, 0.4775, 0.4867, 0.5175, 0.5683],
[0.6201, 0.4039, 0.8880, 0.4799, 0.3625, 0.4285, 0.5866, 0.5148],
[0.6273, 0.4105, 0.8988, 0.4517, 0.3913, 0.2550, 0.5894, 0.4811],
[0.0000, 0.0000, 0.6413, 0.1900, 0.4238, 0.1883, 0.5487, 0.5700],
[0.6336, 0.4191, 0.8938, 0.5167, 0.3938, 0.3517, 0.7343, 0.5748],
[0.6138, 0.4101, 0.8800, 0.5083, 0.4638, 0.5950, 0.5587, 0.5077],
[0.6109, 0.4041, 0.6975, 0.3167, 0.3512, 0.3383, 0.5153, 0.5319]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0170363754441496
step: 17
running loss: 0.0010021397320088
Train Steps: 17/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6120, 0.4014, 0.6863, 0.2817, 0.3700, 0.2783, 0.5513, 0.5667],
[0.6343, 0.4097, 0.9287, 0.4367, 0.4313, 0.3600, 0.7248, 0.5841],
[0.6093, 0.3990, 0.8400, 0.4333, 0.3688, 0.4633, 0.5560, 0.5656],
[0.6276, 0.4095, 0.8237, 0.2250, 0.4662, 0.1783, 0.6171, 0.4869],
[ nan, nan, 0.8213, 0.2700, 0.3775, 0.2817, 0.5425, 0.5533],
[0.6129, 0.3925, 0.8720, 0.5246, 0.4534, 0.5515, 0.6026, 0.5114],
[0.6211, 0.3993, 0.7650, 0.1933, 0.4575, 0.1550, 0.5965, 0.4895],
[0.6164, 0.4066, 0.6625, 0.3033, 0.3775, 0.2967, 0.5725, 0.5833]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6260, 0.4011, 0.7258, 0.3199, 0.3612, 0.2915, 0.5442, 0.5361],
[0.7346, 0.4767, 0.9288, 0.5064, 0.4090, 0.3807, 0.7193, 0.5532],
[0.6979, 0.4502, 0.8781, 0.4688, 0.3707, 0.4679, 0.5312, 0.5525],
[0.6071, 0.3951, 0.8454, 0.2538, 0.4587, 0.1876, 0.6201, 0.4572],
[0.0940, 0.0501, 0.8083, 0.3363, 0.3641, 0.2925, 0.5379, 0.5242],
[0.6665, 0.4243, 0.8967, 0.5811, 0.4485, 0.5496, 0.5898, 0.5064],
[0.6506, 0.4104, 0.7844, 0.2195, 0.4589, 0.1643, 0.5733, 0.4783],
[0.6472, 0.4191, 0.7120, 0.3332, 0.3684, 0.2936, 0.5573, 0.5656]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6120, 0.4013, 0.6862, 0.2817, 0.3700, 0.2783, 0.5512, 0.5667],
[0.6343, 0.4097, 0.9287, 0.4367, 0.4313, 0.3600, 0.7248, 0.5841],
[0.6093, 0.3990, 0.8400, 0.4333, 0.3688, 0.4633, 0.5560, 0.5656],
[0.6276, 0.4095, 0.8238, 0.2250, 0.4663, 0.1783, 0.6171, 0.4869],
[0.0000, 0.0000, 0.8213, 0.2700, 0.3775, 0.2817, 0.5425, 0.5533],
[0.6129, 0.3925, 0.8720, 0.5246, 0.4534, 0.5515, 0.6026, 0.5114],
[0.6211, 0.3993, 0.7650, 0.1933, 0.4575, 0.1550, 0.5965, 0.4895],
[0.6164, 0.4066, 0.6625, 0.3033, 0.3775, 0.2967, 0.5725, 0.5833]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.018217981763882563
step: 18
running loss: 0.0010121100979934756
Train Steps: 18/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6173, 0.4114, 0.7325, 0.2500, 0.4213, 0.1917, 0.5338, 0.5700],
[0.6141, 0.4038, 0.8650, 0.4833, 0.4839, 0.5176, 0.5787, 0.5600],
[0.6170, 0.4102, 0.7468, 0.3695, 0.3463, 0.3767, 0.5238, 0.5823],
[0.6031, 0.3986, 0.7462, 0.2833, 0.3638, 0.2717, 0.5253, 0.4726],
[0.6154, 0.4112, 0.7037, 0.2317, 0.4238, 0.1833, 0.5350, 0.5600],
[0.6086, 0.3981, 0.8700, 0.4750, 0.4512, 0.5283, 0.5324, 0.5038],
[0.6136, 0.4060, 0.8025, 0.3217, 0.3650, 0.3000, 0.5060, 0.5646],
[0.6201, 0.4064, 0.8688, 0.5050, 0.4225, 0.5100, 0.6138, 0.5500]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5512, 0.3725, 0.7604, 0.2443, 0.4207, 0.1884, 0.5394, 0.5562],
[0.6294, 0.3869, 0.9030, 0.5222, 0.4701, 0.5182, 0.5802, 0.5584],
[0.5952, 0.3779, 0.7930, 0.3845, 0.3451, 0.3834, 0.5343, 0.5833],
[0.6804, 0.4306, 0.8026, 0.3019, 0.3634, 0.2921, 0.5605, 0.4898],
[0.6347, 0.4243, 0.7262, 0.2597, 0.4223, 0.1819, 0.5501, 0.5555],
[0.5753, 0.3615, 0.9085, 0.5114, 0.4387, 0.5237, 0.5442, 0.5066],
[0.5027, 0.3365, 0.8310, 0.3479, 0.3453, 0.2930, 0.5062, 0.5514],
[0.6423, 0.4073, 0.9061, 0.5245, 0.4004, 0.5121, 0.5782, 0.5466]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6173, 0.4114, 0.7325, 0.2500, 0.4212, 0.1917, 0.5337, 0.5700],
[0.6141, 0.4038, 0.8650, 0.4833, 0.4839, 0.5176, 0.5788, 0.5600],
[0.6170, 0.4102, 0.7468, 0.3695, 0.3462, 0.3767, 0.5238, 0.5823],
[0.6031, 0.3986, 0.7462, 0.2833, 0.3638, 0.2717, 0.5253, 0.4726],
[0.6154, 0.4112, 0.7038, 0.2317, 0.4238, 0.1833, 0.5350, 0.5600],
[0.6086, 0.3981, 0.8700, 0.4750, 0.4512, 0.5283, 0.5324, 0.5038],
[0.6136, 0.4060, 0.8025, 0.3217, 0.3650, 0.3000, 0.5060, 0.5646],
[0.6201, 0.4064, 0.8687, 0.5050, 0.4225, 0.5100, 0.6137, 0.5500]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.019125032442389056
step: 19
running loss: 0.0010065806548625819
Train Steps: 19/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6201, 0.4082, 0.8827, 0.3715, 0.3825, 0.2712, 0.5845, 0.5412],
[0.6182, 0.4058, 0.8738, 0.4350, 0.3563, 0.3400, 0.5290, 0.5822],
[0.6200, 0.3913, 0.8788, 0.5217, 0.4075, 0.5100, 0.6060, 0.4913],
[0.6179, 0.4040, 0.7412, 0.1850, 0.3825, 0.2783, 0.5837, 0.5600],
[0.6208, 0.4082, 0.8538, 0.3067, 0.3588, 0.3717, 0.6112, 0.5517],
[0.6179, 0.3998, 0.8396, 0.3505, 0.3552, 0.3768, 0.6064, 0.5329],
[0.6216, 0.4100, 0.7350, 0.2067, 0.4325, 0.2050, 0.5950, 0.5333],
[0.6068, 0.3963, 0.8650, 0.4317, 0.4037, 0.5083, 0.5253, 0.4999]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6359, 0.4048, 0.9052, 0.3762, 0.3995, 0.2797, 0.5899, 0.5466],
[0.6064, 0.3951, 0.8949, 0.4519, 0.3761, 0.3334, 0.5104, 0.6051],
[0.6164, 0.3700, 0.8848, 0.5386, 0.4169, 0.5256, 0.5715, 0.5245],
[0.6481, 0.4276, 0.7565, 0.2404, 0.3964, 0.2855, 0.5759, 0.5843],
[0.6212, 0.4118, 0.8703, 0.3438, 0.3663, 0.3934, 0.5951, 0.5677],
[0.6131, 0.3926, 0.8612, 0.3559, 0.3660, 0.3619, 0.5658, 0.5549],
[0.5858, 0.3855, 0.7570, 0.2178, 0.4388, 0.2146, 0.5812, 0.5519],
[0.5676, 0.3535, 0.8760, 0.4405, 0.4186, 0.5101, 0.5055, 0.5193]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6201, 0.4082, 0.8827, 0.3715, 0.3825, 0.2712, 0.5845, 0.5412],
[0.6182, 0.4058, 0.8737, 0.4350, 0.3562, 0.3400, 0.5290, 0.5822],
[0.6199, 0.3913, 0.8788, 0.5217, 0.4075, 0.5100, 0.6060, 0.4913],
[0.6179, 0.4040, 0.7412, 0.1850, 0.3825, 0.2783, 0.5838, 0.5600],
[0.6208, 0.4082, 0.8537, 0.3067, 0.3587, 0.3717, 0.6112, 0.5517],
[0.6179, 0.3998, 0.8396, 0.3505, 0.3552, 0.3768, 0.6064, 0.5329],
[0.6216, 0.4100, 0.7350, 0.2067, 0.4325, 0.2050, 0.5950, 0.5333],
[0.6068, 0.3963, 0.8650, 0.4317, 0.4038, 0.5083, 0.5253, 0.4999]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.01953231156221591
step: 20
running loss: 0.0009766155781107955
Train Steps: 20/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6206, 0.4001, 0.8900, 0.3933, 0.3588, 0.3567, 0.5837, 0.5083],
[0.6227, 0.4049, 0.8750, 0.5367, 0.3775, 0.3667, 0.5725, 0.5317],
[ nan, nan, 0.8037, 0.2483, 0.3975, 0.2517, 0.5575, 0.5600],
[0.6128, 0.4022, 0.8738, 0.5067, 0.4983, 0.5231, 0.5364, 0.5064],
[0.6108, 0.4011, 0.8037, 0.3400, 0.3700, 0.2933, 0.5658, 0.5617],
[ nan, nan, 0.7850, 0.2700, 0.4288, 0.1717, 0.5199, 0.4999],
[0.6205, 0.4004, 0.8938, 0.4883, 0.3663, 0.5000, 0.6357, 0.4947],
[0.6070, 0.3979, 0.8575, 0.5083, 0.4350, 0.5400, 0.5180, 0.5466]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7210, 0.4565, 0.9084, 0.3731, 0.3526, 0.3772, 0.5655, 0.5376],
[0.8087, 0.5395, 0.8758, 0.5171, 0.3853, 0.3925, 0.5778, 0.5738],
[0.1119, 0.0785, 0.7751, 0.2568, 0.4144, 0.2698, 0.5499, 0.5953],
[0.6822, 0.4636, 0.8693, 0.4949, 0.4949, 0.5419, 0.5108, 0.5413],
[0.7736, 0.5026, 0.8111, 0.3225, 0.3772, 0.3114, 0.5589, 0.5785],
[0.0275, 0.0309, 0.7832, 0.2323, 0.4275, 0.1838, 0.5191, 0.5356],
[0.7302, 0.4657, 0.9031, 0.4539, 0.3850, 0.5179, 0.6317, 0.5228],
[0.6900, 0.4722, 0.8493, 0.4946, 0.4511, 0.5650, 0.5092, 0.5610]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6206, 0.4001, 0.8900, 0.3933, 0.3587, 0.3567, 0.5838, 0.5083],
[0.6227, 0.4049, 0.8750, 0.5367, 0.3775, 0.3667, 0.5725, 0.5317],
[0.0000, 0.0000, 0.8037, 0.2483, 0.3975, 0.2517, 0.5575, 0.5600],
[0.6128, 0.4022, 0.8737, 0.5067, 0.4983, 0.5231, 0.5364, 0.5064],
[0.6108, 0.4011, 0.8037, 0.3400, 0.3700, 0.2933, 0.5658, 0.5617],
[0.0000, 0.0000, 0.7850, 0.2700, 0.4288, 0.1717, 0.5199, 0.4999],
[0.6205, 0.4004, 0.8938, 0.4883, 0.3663, 0.5000, 0.6357, 0.4947],
[0.6070, 0.3979, 0.8575, 0.5083, 0.4350, 0.5400, 0.5180, 0.5466]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0028, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0028, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.022330504696583375
step: 21
running loss: 0.0010633573665039702
Train Steps: 21/90 Loss: 0.0011 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6199, 0.3952, 0.8573, 0.5374, 0.4075, 0.4687, 0.5942, 0.5377],
[0.6111, 0.4019, 0.8350, 0.3867, 0.3500, 0.4283, 0.5480, 0.5719],
[0.6127, 0.4084, 0.8700, 0.4467, 0.3987, 0.4317, 0.5013, 0.5471],
[0.6108, 0.4011, 0.8037, 0.3400, 0.3700, 0.2933, 0.5658, 0.5617],
[0.6275, 0.4013, 0.8850, 0.2833, 0.4975, 0.2233, 0.7058, 0.5343],
[ nan, nan, 0.8888, 0.3100, 0.5262, 0.2817, 0.7145, 0.6003],
[0.6150, 0.4097, 0.7468, 0.3194, 0.3825, 0.2633, 0.5463, 0.5800],
[0.6126, 0.4039, 0.8237, 0.3967, 0.3625, 0.3600, 0.5894, 0.6138]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6185, 0.3869, 0.8579, 0.5263, 0.4154, 0.5089, 0.5843, 0.5349],
[0.6103, 0.4033, 0.8438, 0.3815, 0.3781, 0.4424, 0.5075, 0.5624],
[0.6637, 0.4565, 0.8744, 0.4178, 0.4033, 0.4657, 0.4512, 0.5411],
[0.6865, 0.4526, 0.8055, 0.3225, 0.3858, 0.3246, 0.5445, 0.5547],
[0.6587, 0.4332, 0.8624, 0.2587, 0.5050, 0.2517, 0.6967, 0.5345],
[0.1376, 0.0907, 0.8921, 0.2710, 0.5097, 0.2876, 0.7036, 0.5853],
[0.6178, 0.4209, 0.7452, 0.2694, 0.3747, 0.3018, 0.5023, 0.5806],
[0.6423, 0.4236, 0.8180, 0.3788, 0.3601, 0.3860, 0.5589, 0.6233]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6199, 0.3952, 0.8573, 0.5374, 0.4075, 0.4687, 0.5942, 0.5377],
[0.6111, 0.4019, 0.8350, 0.3867, 0.3500, 0.4283, 0.5480, 0.5719],
[0.6127, 0.4084, 0.8700, 0.4467, 0.3988, 0.4317, 0.5013, 0.5471],
[0.6108, 0.4011, 0.8037, 0.3400, 0.3700, 0.2933, 0.5658, 0.5617],
[0.6275, 0.4013, 0.8850, 0.2833, 0.4975, 0.2233, 0.7058, 0.5343],
[0.0000, 0.0000, 0.8888, 0.3100, 0.5263, 0.2817, 0.7145, 0.6003],
[0.6150, 0.4097, 0.7468, 0.3194, 0.3825, 0.2633, 0.5462, 0.5800],
[0.6126, 0.4038, 0.8238, 0.3967, 0.3625, 0.3600, 0.5894, 0.6138]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.023386229382595047
step: 22
running loss: 0.001063010426481593
Train Steps: 22/90 Loss: 0.0011 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6048, 0.3928, 0.8538, 0.5433, 0.3875, 0.5117, 0.5266, 0.4719],
[0.6275, 0.4024, 0.8600, 0.2283, 0.5350, 0.1800, 0.7074, 0.5413],
[0.6149, 0.4054, 0.6713, 0.2333, 0.4025, 0.2017, 0.5213, 0.5695],
[0.6259, 0.4156, 0.8812, 0.3183, 0.4775, 0.1867, 0.6219, 0.4960],
[0.6223, 0.3990, 0.8037, 0.2800, 0.4000, 0.2283, 0.5864, 0.5208],
[0.6250, 0.4008, 0.8950, 0.4183, 0.3550, 0.4383, 0.6361, 0.4927],
[0.6196, 0.4094, 0.7562, 0.2817, 0.3937, 0.3183, 0.6013, 0.6183],
[0.6234, 0.4179, 0.7825, 0.3450, 0.3813, 0.2867, 0.5675, 0.5617]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5246, 0.3330, 0.8417, 0.5379, 0.3996, 0.5314, 0.5079, 0.5074],
[0.5499, 0.3492, 0.8426, 0.2148, 0.5311, 0.2304, 0.6864, 0.5399],
[0.5512, 0.3678, 0.6624, 0.2023, 0.4101, 0.2173, 0.4776, 0.5696],
[0.5862, 0.3871, 0.8917, 0.2849, 0.4597, 0.2297, 0.5993, 0.5250],
[0.5173, 0.3275, 0.7987, 0.2612, 0.3914, 0.2580, 0.5748, 0.5194],
[0.5717, 0.3551, 0.8947, 0.4054, 0.3440, 0.4823, 0.6041, 0.5235],
[0.5840, 0.3897, 0.7675, 0.2568, 0.3996, 0.3258, 0.5925, 0.6365],
[0.5287, 0.3531, 0.7851, 0.3243, 0.3914, 0.2944, 0.5629, 0.5665]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6048, 0.3928, 0.8537, 0.5433, 0.3875, 0.5117, 0.5266, 0.4719],
[0.6275, 0.4024, 0.8600, 0.2283, 0.5350, 0.1800, 0.7074, 0.5413],
[0.6149, 0.4054, 0.6712, 0.2333, 0.4025, 0.2017, 0.5213, 0.5695],
[0.6259, 0.4156, 0.8813, 0.3183, 0.4775, 0.1867, 0.6219, 0.4960],
[0.6223, 0.3990, 0.8037, 0.2800, 0.4000, 0.2283, 0.5864, 0.5208],
[0.6250, 0.4008, 0.8950, 0.4183, 0.3550, 0.4383, 0.6361, 0.4927],
[0.6196, 0.4094, 0.7563, 0.2817, 0.3938, 0.3183, 0.6012, 0.6183],
[0.6234, 0.4179, 0.7825, 0.3450, 0.3812, 0.2867, 0.5675, 0.5617]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.024698010383872315
step: 23
running loss: 0.001073826538429231
Train Steps: 23/90 Loss: 0.0011 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6248, 0.4185, 0.8500, 0.5767, 0.4463, 0.4550, 0.5613, 0.5917],
[0.6132, 0.4066, 0.7259, 0.2402, 0.3588, 0.3300, 0.6000, 0.5600],
[0.6203, 0.4078, 0.8800, 0.5083, 0.3900, 0.5000, 0.6100, 0.5583],
[0.6254, 0.4076, 0.8700, 0.3267, 0.4150, 0.3083, 0.7050, 0.5609],
[0.6357, 0.4118, 0.8400, 0.2500, 0.5413, 0.1633, 0.6725, 0.5586],
[0.6157, 0.4102, 0.8513, 0.3817, 0.3613, 0.3667, 0.5096, 0.5890],
[0.6075, 0.4000, 0.8513, 0.5183, 0.4510, 0.5329, 0.5180, 0.5280],
[0.6175, 0.4013, 0.7734, 0.2783, 0.4475, 0.1786, 0.5790, 0.5351]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5903, 0.3847, 0.8431, 0.5428, 0.4399, 0.4542, 0.5502, 0.5792],
[0.5266, 0.3435, 0.7182, 0.2179, 0.3495, 0.3179, 0.5764, 0.5612],
[0.5280, 0.3317, 0.8819, 0.4689, 0.3673, 0.4914, 0.5831, 0.5414],
[0.6012, 0.3880, 0.8877, 0.2876, 0.4039, 0.2774, 0.6887, 0.5500],
[0.5292, 0.3549, 0.8352, 0.2285, 0.5218, 0.1683, 0.6503, 0.5430],
[0.5647, 0.3668, 0.8404, 0.3564, 0.3523, 0.3591, 0.5268, 0.5653],
[0.5416, 0.3683, 0.8392, 0.5033, 0.4493, 0.5229, 0.5332, 0.5184],
[0.4986, 0.3387, 0.7712, 0.2292, 0.4214, 0.1707, 0.5749, 0.5097]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6248, 0.4185, 0.8500, 0.5767, 0.4462, 0.4550, 0.5612, 0.5917],
[0.6132, 0.4066, 0.7259, 0.2402, 0.3587, 0.3300, 0.6000, 0.5600],
[0.6203, 0.4078, 0.8800, 0.5083, 0.3900, 0.5000, 0.6100, 0.5583],
[0.6254, 0.4076, 0.8700, 0.3267, 0.4150, 0.3083, 0.7050, 0.5609],
[0.6357, 0.4118, 0.8400, 0.2500, 0.5412, 0.1633, 0.6725, 0.5586],
[0.6157, 0.4102, 0.8512, 0.3817, 0.3613, 0.3667, 0.5096, 0.5890],
[0.6075, 0.4000, 0.8512, 0.5183, 0.4510, 0.5329, 0.5180, 0.5280],
[0.6175, 0.4013, 0.7734, 0.2783, 0.4475, 0.1786, 0.5790, 0.5351]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.02608701281133108
step: 24
running loss: 0.0010869588671387949
Train Steps: 24/90 Loss: 0.0011 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6339, 0.4112, 0.8838, 0.5067, 0.4000, 0.5433, 0.7549, 0.5378],
[ nan, nan, 0.8900, 0.3217, 0.5038, 0.2233, 0.6694, 0.5609],
[0.6092, 0.4001, 0.8638, 0.4867, 0.4288, 0.5367, 0.5484, 0.5064],
[0.6185, 0.4067, 0.8838, 0.4450, 0.4037, 0.4733, 0.5213, 0.5142],
[0.6282, 0.4029, 0.8988, 0.3000, 0.4250, 0.4183, 0.7042, 0.5575],
[ nan, nan, 0.7268, 0.2333, 0.4125, 0.1933, 0.5112, 0.5383],
[0.6332, 0.4165, 0.9100, 0.3350, 0.4188, 0.3683, 0.7438, 0.5528],
[ nan, nan, 0.8363, 0.3317, 0.3563, 0.3367, 0.5329, 0.5142]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7749, 0.5050, 0.8667, 0.5227, 0.4023, 0.5295, 0.7262, 0.5520],
[0.1078, 0.0715, 0.8621, 0.3088, 0.5078, 0.1750, 0.6640, 0.5756],
[0.7126, 0.4748, 0.8329, 0.4779, 0.4340, 0.5367, 0.5249, 0.5027],
[0.7413, 0.5045, 0.8681, 0.4425, 0.4100, 0.4426, 0.5186, 0.5116],
[0.7770, 0.5188, 0.8618, 0.3211, 0.4173, 0.4002, 0.6991, 0.5632],
[0.0340, 0.0423, 0.6935, 0.2104, 0.4144, 0.1369, 0.5162, 0.5456],
[0.7058, 0.4849, 0.8911, 0.3628, 0.4073, 0.3391, 0.7341, 0.5740],
[0.1683, 0.1309, 0.7931, 0.3116, 0.3325, 0.3041, 0.5446, 0.5366]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6339, 0.4112, 0.8838, 0.5067, 0.4000, 0.5433, 0.7549, 0.5378],
[0.0000, 0.0000, 0.8900, 0.3217, 0.5038, 0.2233, 0.6694, 0.5609],
[0.6092, 0.4001, 0.8637, 0.4867, 0.4288, 0.5367, 0.5484, 0.5064],
[0.6185, 0.4067, 0.8838, 0.4450, 0.4038, 0.4733, 0.5213, 0.5142],
[0.6282, 0.4029, 0.8988, 0.3000, 0.4250, 0.4183, 0.7042, 0.5575],
[0.0000, 0.0000, 0.7268, 0.2333, 0.4125, 0.1933, 0.5113, 0.5383],
[0.6332, 0.4165, 0.9100, 0.3350, 0.4187, 0.3683, 0.7438, 0.5528],
[0.0000, 0.0000, 0.8363, 0.3317, 0.3562, 0.3367, 0.5329, 0.5142]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0032, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0032, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.02925560690346174
step: 25
running loss: 0.0011702242761384696
Train Steps: 25/90 Loss: 0.0012 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6185, 0.4080, 0.8625, 0.3483, 0.3788, 0.2650, 0.5320, 0.5272],
[0.6250, 0.4008, 0.8950, 0.4183, 0.3550, 0.4383, 0.6361, 0.4927],
[0.6192, 0.4128, 0.8513, 0.5617, 0.4200, 0.5267, 0.5850, 0.5633],
[0.6229, 0.4066, 0.7612, 0.2967, 0.4250, 0.2167, 0.5925, 0.5350],
[0.6201, 0.4036, 0.8596, 0.3850, 0.3492, 0.3785, 0.5978, 0.5131],
[0.6201, 0.4064, 0.8688, 0.5050, 0.4225, 0.5100, 0.6138, 0.5500],
[0.6109, 0.4041, 0.6975, 0.3167, 0.3513, 0.3383, 0.5153, 0.5319],
[0.6182, 0.3972, 0.8552, 0.5914, 0.3683, 0.4181, 0.5688, 0.5378]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5933, 0.3969, 0.8577, 0.3590, 0.4118, 0.2590, 0.5607, 0.5364],
[0.5607, 0.3531, 0.8947, 0.4054, 0.3543, 0.4176, 0.6658, 0.5124],
[0.5784, 0.3753, 0.8585, 0.5589, 0.4376, 0.4992, 0.6307, 0.5515],
[0.5546, 0.3648, 0.7714, 0.2658, 0.4262, 0.2079, 0.6115, 0.5436],
[0.4776, 0.3190, 0.8711, 0.3610, 0.3545, 0.3455, 0.6230, 0.5217],
[0.5311, 0.3501, 0.8663, 0.4774, 0.4244, 0.4933, 0.6378, 0.5392],
[0.5744, 0.3876, 0.7364, 0.2986, 0.3520, 0.3252, 0.5476, 0.5329],
[0.6285, 0.4031, 0.8640, 0.5768, 0.3735, 0.3970, 0.6315, 0.5407]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6186, 0.4080, 0.8625, 0.3483, 0.3787, 0.2650, 0.5320, 0.5272],
[0.6250, 0.4008, 0.8950, 0.4183, 0.3550, 0.4383, 0.6361, 0.4927],
[0.6192, 0.4128, 0.8512, 0.5617, 0.4200, 0.5267, 0.5850, 0.5633],
[0.6229, 0.4066, 0.7613, 0.2967, 0.4250, 0.2167, 0.5925, 0.5350],
[0.6201, 0.4036, 0.8596, 0.3850, 0.3492, 0.3785, 0.5978, 0.5131],
[0.6201, 0.4064, 0.8687, 0.5050, 0.4225, 0.5100, 0.6137, 0.5500],
[0.6109, 0.4041, 0.6975, 0.3167, 0.3512, 0.3383, 0.5153, 0.5319],
[0.6182, 0.3972, 0.8552, 0.5914, 0.3683, 0.4181, 0.5688, 0.5378]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03047404598328285
step: 26
running loss: 0.001172078691664725
Train Steps: 26/90 Loss: 0.0012 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6211, 0.4069, 0.8750, 0.5117, 0.4150, 0.4900, 0.5875, 0.5167],
[ nan, nan, 0.8675, 0.2833, 0.5350, 0.1983, 0.6678, 0.5621],
[0.6124, 0.4030, 0.8650, 0.4867, 0.4999, 0.5106, 0.5137, 0.5773],
[0.6307, 0.4060, 0.8950, 0.5183, 0.3750, 0.3850, 0.6338, 0.4938],
[0.6173, 0.4013, 0.8713, 0.4640, 0.4800, 0.5700, 0.6025, 0.5600],
[0.6222, 0.4172, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633],
[0.6364, 0.4154, 0.8938, 0.3717, 0.4500, 0.2583, 0.6448, 0.5285],
[0.6280, 0.4101, 0.9050, 0.4533, 0.3775, 0.3217, 0.6338, 0.4915]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.5571, 0.3781, 0.8592, 0.4977, 0.3940, 0.5043, 0.6304, 0.5167],
[-0.0641, -0.0320, 0.8451, 0.2732, 0.5266, 0.1686, 0.6831, 0.5694],
[ 0.5501, 0.3686, 0.8577, 0.4885, 0.4755, 0.5070, 0.5333, 0.5305],
[ 0.6006, 0.4094, 0.8789, 0.5209, 0.3491, 0.3783, 0.6467, 0.4951],
[ 0.5343, 0.3618, 0.8626, 0.4401, 0.4468, 0.5363, 0.6245, 0.5325],
[ 0.5859, 0.4038, 0.8746, 0.5054, 0.3550, 0.4501, 0.6062, 0.5472],
[ 0.5593, 0.3798, 0.8754, 0.3642, 0.4343, 0.2383, 0.6505, 0.5330],
[ 0.6434, 0.4352, 0.8833, 0.4716, 0.3494, 0.3238, 0.6562, 0.5142]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6211, 0.4069, 0.8750, 0.5117, 0.4150, 0.4900, 0.5875, 0.5167],
[0.0000, 0.0000, 0.8675, 0.2833, 0.5350, 0.1983, 0.6678, 0.5621],
[0.6124, 0.4030, 0.8650, 0.4867, 0.4999, 0.5106, 0.5137, 0.5773],
[0.6307, 0.4060, 0.8950, 0.5183, 0.3750, 0.3850, 0.6338, 0.4938],
[0.6173, 0.4013, 0.8713, 0.4640, 0.4800, 0.5700, 0.6025, 0.5600],
[0.6222, 0.4171, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633],
[0.6364, 0.4154, 0.8938, 0.3717, 0.4500, 0.2583, 0.6448, 0.5285],
[0.6280, 0.4101, 0.9050, 0.4533, 0.3775, 0.3217, 0.6338, 0.4915]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03130909425090067
step: 27
running loss: 0.0011595960833666915
Train Steps: 27/90 Loss: 0.0012 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6203, 0.4078, 0.8800, 0.5083, 0.3900, 0.5000, 0.6100, 0.5583],
[0.6153, 0.4117, 0.8688, 0.5167, 0.4895, 0.5647, 0.5524, 0.5136],
[0.6225, 0.4116, 0.8662, 0.3517, 0.3663, 0.3233, 0.5837, 0.5317],
[0.6179, 0.3998, 0.8396, 0.3505, 0.3552, 0.3768, 0.6064, 0.5329],
[0.6270, 0.4267, 0.7150, 0.3317, 0.4900, 0.1817, 0.5560, 0.6183],
[ nan, nan, 0.8525, 0.2217, 0.5413, 0.2367, 0.7367, 0.5482],
[0.6151, 0.4125, 0.8738, 0.4417, 0.3575, 0.3783, 0.5138, 0.5483],
[ nan, nan, 0.6469, 0.1943, 0.4025, 0.2000, 0.5125, 0.5533]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6480, 0.4196, 0.8940, 0.5324, 0.3837, 0.5083, 0.6373, 0.5335],
[ 0.6795, 0.4661, 0.8864, 0.5449, 0.4735, 0.5319, 0.6194, 0.5147],
[ 0.5716, 0.3851, 0.8499, 0.3645, 0.3668, 0.3217, 0.6308, 0.5389],
[ 0.6398, 0.4191, 0.8459, 0.3649, 0.3495, 0.3682, 0.6308, 0.5194],
[ 0.6781, 0.4620, 0.7139, 0.3219, 0.4760, 0.1850, 0.5917, 0.5935],
[-0.0955, -0.0567, 0.8607, 0.2603, 0.5467, 0.2307, 0.7484, 0.5299],
[ 0.6616, 0.4385, 0.8714, 0.4713, 0.3620, 0.3759, 0.5641, 0.5374],
[ 0.1023, 0.0534, 0.6864, 0.2369, 0.4190, 0.1628, 0.5558, 0.5566]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6203, 0.4078, 0.8800, 0.5083, 0.3900, 0.5000, 0.6100, 0.5583],
[0.6154, 0.4117, 0.8687, 0.5167, 0.4895, 0.5647, 0.5524, 0.5136],
[0.6225, 0.4116, 0.8662, 0.3517, 0.3663, 0.3233, 0.5838, 0.5317],
[0.6179, 0.3998, 0.8396, 0.3505, 0.3552, 0.3768, 0.6064, 0.5329],
[0.6270, 0.4266, 0.7150, 0.3317, 0.4900, 0.1817, 0.5560, 0.6183],
[0.0000, 0.0000, 0.8525, 0.2217, 0.5412, 0.2367, 0.7367, 0.5482],
[0.6151, 0.4125, 0.8737, 0.4417, 0.3575, 0.3783, 0.5138, 0.5483],
[0.0000, 0.0000, 0.6469, 0.1943, 0.4025, 0.2000, 0.5125, 0.5533]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03243761681369506
step: 28
running loss: 0.0011584863147748234
Train Steps: 28/90 Loss: 0.0012 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6274, 0.4117, 0.8100, 0.5801, 0.4000, 0.4583, 0.5582, 0.6118],
[0.6208, 0.4082, 0.8538, 0.3067, 0.3588, 0.3717, 0.6112, 0.5517],
[0.6076, 0.3953, 0.8125, 0.3917, 0.3525, 0.4083, 0.5346, 0.4954],
[0.6332, 0.4118, 0.9238, 0.4267, 0.4012, 0.4733, 0.7525, 0.5436],
[0.6272, 0.4071, 0.8738, 0.5600, 0.3675, 0.3783, 0.5926, 0.4742],
[0.6296, 0.4076, 0.8400, 0.5583, 0.3700, 0.4367, 0.6876, 0.5494],
[0.6093, 0.3990, 0.8400, 0.4333, 0.3688, 0.4633, 0.5560, 0.5656],
[0.6260, 0.4253, 0.8938, 0.4400, 0.3675, 0.3650, 0.5675, 0.5767]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5333, 0.3519, 0.8224, 0.5819, 0.4291, 0.4459, 0.5833, 0.5994],
[0.5432, 0.3570, 0.8515, 0.3269, 0.3724, 0.3711, 0.6106, 0.5296],
[0.5232, 0.3436, 0.8307, 0.3767, 0.3578, 0.3805, 0.5443, 0.4934],
[0.6259, 0.4124, 0.9127, 0.4304, 0.4193, 0.4777, 0.7340, 0.5407],
[0.5638, 0.3596, 0.8785, 0.5704, 0.3951, 0.3730, 0.6073, 0.4628],
[0.5675, 0.3640, 0.8701, 0.5401, 0.4035, 0.4203, 0.6903, 0.5244],
[0.5548, 0.3612, 0.8543, 0.4221, 0.3882, 0.4384, 0.5354, 0.5408],
[0.5765, 0.3649, 0.8960, 0.4664, 0.4072, 0.3573, 0.5822, 0.5698]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6274, 0.4117, 0.8100, 0.5801, 0.4000, 0.4583, 0.5582, 0.6118],
[0.6208, 0.4082, 0.8537, 0.3067, 0.3587, 0.3717, 0.6112, 0.5517],
[0.6076, 0.3952, 0.8125, 0.3917, 0.3525, 0.4083, 0.5346, 0.4954],
[0.6332, 0.4118, 0.9237, 0.4267, 0.4013, 0.4733, 0.7525, 0.5436],
[0.6272, 0.4071, 0.8737, 0.5600, 0.3675, 0.3783, 0.5926, 0.4742],
[0.6296, 0.4076, 0.8400, 0.5583, 0.3700, 0.4367, 0.6876, 0.5494],
[0.6093, 0.3990, 0.8400, 0.4333, 0.3688, 0.4633, 0.5560, 0.5656],
[0.6260, 0.4253, 0.8938, 0.4400, 0.3675, 0.3650, 0.5675, 0.5767]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03350451713777147
step: 29
running loss: 0.0011553281771645334
Train Steps: 29/90 Loss: 0.0012 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6198, 0.4105, 0.7950, 0.3267, 0.3675, 0.3767, 0.6038, 0.6167],
[0.6317, 0.4038, 0.8287, 0.5900, 0.3800, 0.4717, 0.6295, 0.4986],
[0.6200, 0.4055, 0.8011, 0.2988, 0.3842, 0.2798, 0.5949, 0.5183],
[0.6261, 0.4029, 0.8720, 0.3364, 0.3665, 0.3753, 0.6531, 0.5183],
[0.6182, 0.3987, 0.7878, 0.2889, 0.3699, 0.3260, 0.6086, 0.5367],
[0.6097, 0.4000, 0.7325, 0.2667, 0.3450, 0.3517, 0.5284, 0.5045],
[0.6219, 0.4114, 0.8175, 0.2817, 0.3925, 0.2783, 0.5900, 0.5350],
[0.6106, 0.4022, 0.7125, 0.2650, 0.3713, 0.2700, 0.5431, 0.5123]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5300, 0.3320, 0.8162, 0.3578, 0.3960, 0.3841, 0.5884, 0.6032],
[0.5531, 0.3594, 0.8705, 0.6327, 0.3978, 0.4552, 0.6268, 0.5013],
[0.6140, 0.3880, 0.8141, 0.3311, 0.4078, 0.2734, 0.5962, 0.5032],
[0.5975, 0.3754, 0.8768, 0.3859, 0.3943, 0.3580, 0.6395, 0.5108],
[0.5600, 0.3510, 0.8141, 0.3194, 0.3890, 0.3210, 0.6084, 0.5404],
[0.5502, 0.3410, 0.7539, 0.3059, 0.3619, 0.3273, 0.5426, 0.5130],
[0.5694, 0.3608, 0.8149, 0.3133, 0.4233, 0.2520, 0.5978, 0.5442],
[0.5955, 0.3840, 0.7417, 0.2904, 0.3905, 0.2555, 0.5303, 0.5149]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6198, 0.4105, 0.7950, 0.3267, 0.3675, 0.3767, 0.6037, 0.6167],
[0.6317, 0.4038, 0.8288, 0.5900, 0.3800, 0.4717, 0.6295, 0.4986],
[0.6201, 0.4055, 0.8011, 0.2988, 0.3842, 0.2798, 0.5949, 0.5183],
[0.6261, 0.4029, 0.8720, 0.3364, 0.3665, 0.3753, 0.6531, 0.5183],
[0.6182, 0.3987, 0.7878, 0.2889, 0.3699, 0.3260, 0.6086, 0.5367],
[0.6097, 0.4000, 0.7325, 0.2667, 0.3450, 0.3517, 0.5284, 0.5045],
[0.6219, 0.4114, 0.8175, 0.2817, 0.3925, 0.2783, 0.5900, 0.5350],
[0.6106, 0.4022, 0.7125, 0.2650, 0.3713, 0.2700, 0.5431, 0.5123]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03453243928379379
step: 30
running loss: 0.001151081309459793
Train Steps: 30/90 Loss: 0.0012 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6271, 0.4020, 0.8375, 0.6083, 0.3925, 0.4867, 0.6037, 0.4626],
[0.6222, 0.4172, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633],
[0.6064, 0.3953, 0.8738, 0.4417, 0.3663, 0.4683, 0.5511, 0.5416],
[0.6272, 0.4045, 0.8538, 0.5900, 0.3750, 0.4417, 0.5989, 0.4649],
[ nan, nan, 0.8850, 0.2817, 0.5112, 0.2183, 0.7184, 0.5436],
[0.6357, 0.4097, 0.9038, 0.3883, 0.4213, 0.2950, 0.6686, 0.5390],
[0.6236, 0.3966, 0.8850, 0.4967, 0.3638, 0.4017, 0.5850, 0.5183],
[0.6080, 0.4010, 0.8750, 0.4500, 0.4825, 0.5617, 0.5837, 0.5583]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6427, 0.4202, 0.8314, 0.6064, 0.3901, 0.5030, 0.5913, 0.4913],
[0.6279, 0.4157, 0.8776, 0.5284, 0.3637, 0.4915, 0.5434, 0.5713],
[0.6431, 0.4021, 0.8803, 0.4585, 0.3645, 0.4955, 0.5290, 0.5244],
[0.6660, 0.4271, 0.8366, 0.5968, 0.3659, 0.4531, 0.5882, 0.4971],
[0.2643, 0.1526, 0.8646, 0.2992, 0.5143, 0.2550, 0.6820, 0.5459],
[0.6371, 0.4096, 0.8860, 0.3984, 0.3991, 0.3012, 0.6437, 0.5549],
[0.6351, 0.4026, 0.8868, 0.4923, 0.3529, 0.4365, 0.5662, 0.5320],
[0.6200, 0.4089, 0.8712, 0.4522, 0.4741, 0.5675, 0.5527, 0.5659]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6271, 0.4020, 0.8375, 0.6083, 0.3925, 0.4867, 0.6037, 0.4626],
[0.6222, 0.4171, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633],
[0.6064, 0.3952, 0.8737, 0.4417, 0.3663, 0.4683, 0.5511, 0.5416],
[0.6271, 0.4045, 0.8537, 0.5900, 0.3750, 0.4417, 0.5989, 0.4649],
[0.0000, 0.0000, 0.8850, 0.2817, 0.5113, 0.2183, 0.7184, 0.5436],
[0.6357, 0.4097, 0.9038, 0.3883, 0.4212, 0.2950, 0.6686, 0.5390],
[0.6236, 0.3965, 0.8850, 0.4967, 0.3638, 0.4017, 0.5850, 0.5183],
[0.6080, 0.4010, 0.8750, 0.4500, 0.4825, 0.5617, 0.5838, 0.5583]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0018, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0018, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03629230541992001
step: 31
running loss: 0.0011707195296748391
Train Steps: 31/90 Loss: 0.0012 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586],
[0.6127, 0.4066, 0.8550, 0.5567, 0.4662, 0.5141, 0.5070, 0.5412],
[0.6211, 0.4069, 0.8750, 0.5117, 0.4150, 0.4900, 0.5875, 0.5167],
[0.6201, 0.4036, 0.8596, 0.3850, 0.3492, 0.3785, 0.5978, 0.5131],
[0.6159, 0.4085, 0.6900, 0.2283, 0.4088, 0.1950, 0.5123, 0.5397],
[0.6182, 0.3998, 0.8793, 0.4191, 0.3552, 0.4285, 0.6038, 0.5312],
[0.6055, 0.4015, 0.7425, 0.2033, 0.4113, 0.1883, 0.5217, 0.4823],
[0.6110, 0.4047, 0.8700, 0.4483, 0.3713, 0.3967, 0.5088, 0.5517]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6312, 0.4087, 0.8552, 0.2854, 0.4418, 0.2874, 0.6899, 0.5743],
[0.6343, 0.4257, 0.8424, 0.5669, 0.4541, 0.5228, 0.5158, 0.5439],
[0.5952, 0.3849, 0.8683, 0.5273, 0.4134, 0.5349, 0.5800, 0.5326],
[0.6040, 0.3875, 0.8703, 0.3866, 0.3464, 0.3959, 0.5834, 0.5296],
[0.5615, 0.3480, 0.6886, 0.2595, 0.4079, 0.2172, 0.4974, 0.5599],
[0.6166, 0.3884, 0.8692, 0.4099, 0.3551, 0.4637, 0.5817, 0.5406],
[0.5760, 0.3547, 0.7143, 0.2348, 0.3887, 0.2061, 0.5262, 0.5102],
[0.5566, 0.3679, 0.8671, 0.4734, 0.3623, 0.4301, 0.5038, 0.5463]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586],
[0.6127, 0.4066, 0.8550, 0.5567, 0.4662, 0.5141, 0.5070, 0.5412],
[0.6211, 0.4069, 0.8750, 0.5117, 0.4150, 0.4900, 0.5875, 0.5167],
[0.6201, 0.4036, 0.8596, 0.3850, 0.3492, 0.3785, 0.5978, 0.5131],
[0.6159, 0.4085, 0.6900, 0.2283, 0.4087, 0.1950, 0.5123, 0.5397],
[0.6182, 0.3998, 0.8793, 0.4191, 0.3552, 0.4285, 0.6038, 0.5312],
[0.6055, 0.4015, 0.7425, 0.2033, 0.4112, 0.1883, 0.5217, 0.4823],
[0.6110, 0.4047, 0.8700, 0.4483, 0.3713, 0.3967, 0.5088, 0.5517]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03677627723664045
step: 32
running loss: 0.0011492586636450142
Train Steps: 32/90 Loss: 0.0011 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6125, 0.3999, 0.8750, 0.4883, 0.4750, 0.4700, 0.5533, 0.5617],
[0.6196, 0.4094, 0.7562, 0.2817, 0.3937, 0.3183, 0.6013, 0.6183],
[0.6169, 0.4108, 0.6821, 0.2722, 0.3825, 0.2550, 0.5550, 0.5717],
[0.6273, 0.4110, 0.8900, 0.3817, 0.4188, 0.2167, 0.5858, 0.4835],
[0.6068, 0.3963, 0.8650, 0.4317, 0.4037, 0.5083, 0.5253, 0.4999],
[0.6122, 0.4006, 0.8850, 0.4217, 0.4088, 0.5517, 0.6063, 0.5517],
[ nan, nan, 0.6992, 0.2791, 0.3950, 0.2383, 0.5483, 0.5819],
[0.6043, 0.4022, 0.6887, 0.1983, 0.3775, 0.2483, 0.5480, 0.5136]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6957, 0.4481, 0.8929, 0.5009, 0.4728, 0.5124, 0.5399, 0.5542],
[0.6731, 0.4449, 0.7781, 0.3020, 0.3991, 0.3333, 0.6170, 0.6263],
[0.6312, 0.4144, 0.6878, 0.2701, 0.3600, 0.2677, 0.5420, 0.5699],
[0.6798, 0.4307, 0.9188, 0.4046, 0.4165, 0.2358, 0.5908, 0.4885],
[0.6334, 0.4017, 0.8684, 0.4303, 0.3911, 0.5226, 0.5477, 0.4909],
[0.6938, 0.4446, 0.8939, 0.4294, 0.4075, 0.5651, 0.5999, 0.5187],
[0.1302, 0.0652, 0.6944, 0.2737, 0.3742, 0.2653, 0.5407, 0.5516],
[0.6296, 0.4025, 0.6964, 0.2256, 0.3679, 0.2693, 0.5542, 0.5215]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6125, 0.3999, 0.8750, 0.4883, 0.4750, 0.4700, 0.5533, 0.5617],
[0.6196, 0.4094, 0.7563, 0.2817, 0.3938, 0.3183, 0.6012, 0.6183],
[0.6169, 0.4108, 0.6821, 0.2722, 0.3825, 0.2550, 0.5550, 0.5717],
[0.6273, 0.4110, 0.8900, 0.3817, 0.4187, 0.2167, 0.5858, 0.4835],
[0.6068, 0.3963, 0.8650, 0.4317, 0.4038, 0.5083, 0.5253, 0.4999],
[0.6122, 0.4006, 0.8850, 0.4217, 0.4087, 0.5517, 0.6062, 0.5517],
[0.0000, 0.0000, 0.6992, 0.2791, 0.3950, 0.2383, 0.5483, 0.5819],
[0.6043, 0.4022, 0.6888, 0.1983, 0.3775, 0.2483, 0.5480, 0.5136]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.037722738285083324
step: 33
running loss: 0.0011431132813661613
Train Steps: 33/90 Loss: 0.0011 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6273, 0.4100, 0.7137, 0.2133, 0.4000, 0.2650, 0.6075, 0.5633],
[0.6212, 0.4033, 0.8938, 0.4167, 0.3813, 0.4267, 0.5613, 0.5583],
[0.6085, 0.4008, 0.8588, 0.5200, 0.4959, 0.4977, 0.5175, 0.5283],
[0.6137, 0.4035, 0.8850, 0.4417, 0.3900, 0.4283, 0.5449, 0.5617],
[0.6222, 0.4072, 0.7164, 0.2166, 0.3738, 0.3167, 0.6100, 0.5533],
[0.6053, 0.4035, 0.6897, 0.1916, 0.4000, 0.2117, 0.5440, 0.5168],
[0.6200, 0.4071, 0.7338, 0.1917, 0.4200, 0.2450, 0.6150, 0.5517],
[0.6346, 0.4086, 0.7938, 0.5500, 0.3962, 0.4867, 0.7343, 0.5702]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6207, 0.4087, 0.7299, 0.2346, 0.3832, 0.2794, 0.5773, 0.5598],
[0.6340, 0.4120, 0.9302, 0.4444, 0.3620, 0.4391, 0.5457, 0.5405],
[0.6096, 0.4085, 0.8734, 0.5473, 0.5027, 0.5276, 0.4847, 0.5311],
[0.6392, 0.4208, 0.9139, 0.4806, 0.3919, 0.4799, 0.5381, 0.5347],
[0.6476, 0.4382, 0.7389, 0.2453, 0.3673, 0.3284, 0.5825, 0.5613],
[0.5024, 0.3274, 0.6944, 0.2168, 0.3967, 0.2365, 0.5230, 0.5248],
[0.5912, 0.4161, 0.7449, 0.2064, 0.4182, 0.2596, 0.5937, 0.5524],
[0.6630, 0.4463, 0.8269, 0.5501, 0.3866, 0.5200, 0.6644, 0.5626]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6273, 0.4099, 0.7138, 0.2133, 0.4000, 0.2650, 0.6075, 0.5633],
[0.6212, 0.4033, 0.8938, 0.4167, 0.3812, 0.4267, 0.5612, 0.5583],
[0.6084, 0.4008, 0.8587, 0.5200, 0.4959, 0.4977, 0.5175, 0.5283],
[0.6137, 0.4035, 0.8850, 0.4417, 0.3900, 0.4283, 0.5449, 0.5617],
[0.6222, 0.4072, 0.7164, 0.2166, 0.3738, 0.3167, 0.6100, 0.5533],
[0.6054, 0.4035, 0.6897, 0.1916, 0.4000, 0.2117, 0.5440, 0.5168],
[0.6200, 0.4071, 0.7337, 0.1917, 0.4200, 0.2450, 0.6150, 0.5517],
[0.6346, 0.4086, 0.7937, 0.5500, 0.3963, 0.4867, 0.7343, 0.5702]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03848643408855423
step: 34
running loss: 0.001131953943781007
Train Steps: 34/90 Loss: 0.0011 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6128, 0.4084, 0.8738, 0.4683, 0.3613, 0.3700, 0.4960, 0.5397],
[0.6251, 0.4163, 0.8662, 0.4467, 0.3625, 0.3567, 0.6038, 0.5533],
[0.6222, 0.3957, 0.8838, 0.5017, 0.3937, 0.4600, 0.5900, 0.5017],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3513, 0.4050, 0.6112, 0.5500],
[0.6224, 0.4097, 0.7438, 0.2267, 0.3850, 0.2850, 0.5988, 0.5250],
[0.6200, 0.4039, 0.8880, 0.4799, 0.3625, 0.4285, 0.5866, 0.5148],
[0.6030, 0.3969, 0.7988, 0.3917, 0.3450, 0.3667, 0.5266, 0.4700],
[0.6275, 0.4048, 0.8488, 0.2883, 0.4463, 0.2033, 0.6321, 0.5155]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6183, 0.4021, 0.8597, 0.4573, 0.3796, 0.3890, 0.5009, 0.5528],
[0.6546, 0.4281, 0.8510, 0.4200, 0.3696, 0.3607, 0.5795, 0.5611],
[0.6465, 0.4086, 0.8639, 0.4932, 0.3910, 0.4767, 0.5734, 0.5107],
[0.6153, 0.4060, 0.7664, 0.2453, 0.3581, 0.4111, 0.6184, 0.5636],
[0.6052, 0.4063, 0.7235, 0.2073, 0.3895, 0.3052, 0.5874, 0.5488],
[0.6432, 0.4107, 0.8695, 0.4533, 0.3793, 0.4444, 0.5860, 0.5381],
[0.6142, 0.4123, 0.8144, 0.3713, 0.3490, 0.3675, 0.5293, 0.5152],
[0.7097, 0.4605, 0.8296, 0.2603, 0.4559, 0.2119, 0.6177, 0.5250]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6127, 0.4084, 0.8737, 0.4683, 0.3613, 0.3700, 0.4960, 0.5397],
[0.6252, 0.4162, 0.8662, 0.4467, 0.3625, 0.3567, 0.6037, 0.5533],
[0.6222, 0.3957, 0.8838, 0.5017, 0.3938, 0.4600, 0.5900, 0.5017],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3512, 0.4050, 0.6112, 0.5500],
[0.6224, 0.4097, 0.7437, 0.2267, 0.3850, 0.2850, 0.5987, 0.5250],
[0.6201, 0.4039, 0.8880, 0.4799, 0.3625, 0.4285, 0.5866, 0.5148],
[0.6030, 0.3969, 0.7987, 0.3917, 0.3450, 0.3667, 0.5266, 0.4700],
[0.6275, 0.4048, 0.8487, 0.2883, 0.4462, 0.2033, 0.6321, 0.5155]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03889687912305817
step: 35
running loss: 0.0011113394035159477
Train Steps: 35/90 Loss: 0.0011 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6268, 0.4102, 0.8938, 0.3667, 0.4025, 0.2833, 0.6275, 0.5183],
[0.6186, 0.4060, 0.8750, 0.5050, 0.3538, 0.4367, 0.5813, 0.6083],
[0.6138, 0.4054, 0.8750, 0.4750, 0.4363, 0.5017, 0.5086, 0.5822],
[0.6147, 0.4081, 0.8538, 0.3400, 0.3663, 0.3150, 0.5142, 0.4875],
[0.6150, 0.3949, 0.8800, 0.4033, 0.3825, 0.4900, 0.5875, 0.5483],
[0.6053, 0.4035, 0.6897, 0.1916, 0.4000, 0.2117, 0.5440, 0.5168],
[0.6214, 0.4175, 0.7300, 0.2883, 0.4338, 0.2167, 0.5698, 0.5773],
[0.6339, 0.4102, 0.8588, 0.3133, 0.4425, 0.2117, 0.6417, 0.5089]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6272, 0.4205, 0.8835, 0.3393, 0.3981, 0.2917, 0.6411, 0.5323],
[0.5420, 0.3742, 0.8473, 0.4490, 0.3551, 0.4554, 0.6004, 0.5777],
[0.6386, 0.4225, 0.8350, 0.4646, 0.4252, 0.4898, 0.5376, 0.5558],
[0.6313, 0.4140, 0.8614, 0.3493, 0.3677, 0.3204, 0.5472, 0.5091],
[0.5479, 0.3567, 0.8535, 0.3825, 0.3773, 0.4866, 0.6150, 0.5179],
[0.5576, 0.3567, 0.6646, 0.1769, 0.3972, 0.2270, 0.5550, 0.5160],
[0.6751, 0.4624, 0.7140, 0.2613, 0.4381, 0.2245, 0.5698, 0.5634],
[0.6748, 0.4515, 0.8537, 0.2882, 0.4649, 0.2031, 0.6719, 0.5120]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6268, 0.4102, 0.8938, 0.3667, 0.4025, 0.2833, 0.6275, 0.5183],
[0.6186, 0.4060, 0.8750, 0.5050, 0.3537, 0.4367, 0.5813, 0.6083],
[0.6138, 0.4054, 0.8750, 0.4750, 0.4363, 0.5017, 0.5086, 0.5822],
[0.6147, 0.4081, 0.8537, 0.3400, 0.3663, 0.3150, 0.5142, 0.4875],
[0.6150, 0.3949, 0.8800, 0.4033, 0.3825, 0.4900, 0.5875, 0.5483],
[0.6054, 0.4035, 0.6897, 0.1916, 0.4000, 0.2117, 0.5440, 0.5168],
[0.6214, 0.4175, 0.7300, 0.2883, 0.4338, 0.2167, 0.5698, 0.5773],
[0.6339, 0.4102, 0.8587, 0.3133, 0.4425, 0.2117, 0.6417, 0.5089]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03962359408615157
step: 36
running loss: 0.001100655391281988
Train Steps: 36/90 Loss: 0.0011 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6150, 0.4097, 0.7468, 0.3194, 0.3825, 0.2633, 0.5463, 0.5800],
[0.6128, 0.4084, 0.8738, 0.4683, 0.3613, 0.3700, 0.4960, 0.5397],
[0.6268, 0.4094, 0.9038, 0.4300, 0.3700, 0.3483, 0.6262, 0.5167],
[0.6271, 0.4081, 0.9081, 0.4894, 0.3700, 0.4283, 0.6661, 0.5274],
[0.6200, 0.4118, 0.8287, 0.4017, 0.3775, 0.2833, 0.5391, 0.5799],
[0.6202, 0.4079, 0.8025, 0.2500, 0.3763, 0.3217, 0.6125, 0.5533],
[0.6154, 0.4048, 0.7100, 0.2067, 0.4338, 0.1667, 0.5413, 0.5220],
[0.6184, 0.4079, 0.8350, 0.3700, 0.3675, 0.2883, 0.5312, 0.5783]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6731, 0.4660, 0.7442, 0.2541, 0.3794, 0.2471, 0.5337, 0.5815],
[0.5771, 0.3816, 0.8796, 0.4264, 0.3821, 0.3529, 0.5279, 0.5435],
[0.5705, 0.3869, 0.9043, 0.3565, 0.3812, 0.3285, 0.6388, 0.5319],
[0.5005, 0.3500, 0.8975, 0.4178, 0.3760, 0.4214, 0.6897, 0.5422],
[0.5129, 0.3521, 0.8153, 0.3398, 0.3702, 0.2708, 0.5315, 0.5734],
[0.5919, 0.4103, 0.7996, 0.1988, 0.3947, 0.3031, 0.6229, 0.5450],
[0.6546, 0.4317, 0.6917, 0.1848, 0.4577, 0.1434, 0.5603, 0.5350],
[0.6887, 0.4524, 0.8398, 0.3022, 0.3768, 0.2874, 0.5113, 0.5499]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6150, 0.4097, 0.7468, 0.3194, 0.3825, 0.2633, 0.5462, 0.5800],
[0.6127, 0.4084, 0.8737, 0.4683, 0.3613, 0.3700, 0.4960, 0.5397],
[0.6268, 0.4094, 0.9038, 0.4300, 0.3700, 0.3483, 0.6263, 0.5167],
[0.6271, 0.4081, 0.9081, 0.4894, 0.3700, 0.4283, 0.6661, 0.5274],
[0.6200, 0.4118, 0.8288, 0.4017, 0.3775, 0.2833, 0.5391, 0.5799],
[0.6202, 0.4079, 0.8025, 0.2500, 0.3762, 0.3217, 0.6125, 0.5533],
[0.6154, 0.4048, 0.7100, 0.2067, 0.4338, 0.1667, 0.5413, 0.5220],
[0.6184, 0.4079, 0.8350, 0.3700, 0.3675, 0.2883, 0.5312, 0.5783]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04108484456082806
step: 37
running loss: 0.0011104012043467043
Train Steps: 37/90 Loss: 0.0011 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6132, 0.4037, 0.6963, 0.2217, 0.4100, 0.1950, 0.5395, 0.5175],
[0.6205, 0.4012, 0.8675, 0.3283, 0.3713, 0.3050, 0.5813, 0.5117],
[0.6350, 0.4144, 0.9250, 0.4100, 0.4125, 0.3750, 0.7129, 0.5945],
[0.6243, 0.4128, 0.7762, 0.2717, 0.3825, 0.3133, 0.6212, 0.5417],
[0.6293, 0.4024, 0.8750, 0.5000, 0.4012, 0.5733, 0.7121, 0.5633],
[0.6277, 0.4013, 0.8888, 0.4767, 0.3600, 0.3567, 0.6148, 0.4672],
[0.6109, 0.4041, 0.6975, 0.3167, 0.3513, 0.3383, 0.5153, 0.5319],
[0.6251, 0.4163, 0.8662, 0.4467, 0.3625, 0.3567, 0.6038, 0.5533]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7004, 0.4781, 0.6918, 0.2217, 0.4056, 0.1450, 0.5147, 0.5004],
[0.6227, 0.4156, 0.8690, 0.3062, 0.3745, 0.2790, 0.5618, 0.5130],
[0.5683, 0.3657, 0.9082, 0.3851, 0.4262, 0.3278, 0.6973, 0.5923],
[0.6048, 0.4049, 0.7707, 0.2541, 0.3962, 0.2739, 0.6194, 0.5442],
[0.5766, 0.3658, 0.8741, 0.4772, 0.4067, 0.5390, 0.6700, 0.5635],
[0.6280, 0.4125, 0.8869, 0.4231, 0.3597, 0.2912, 0.6195, 0.4975],
[0.5745, 0.3832, 0.7137, 0.2926, 0.3510, 0.3062, 0.5140, 0.5181],
[0.6141, 0.4022, 0.8545, 0.4257, 0.3587, 0.3034, 0.5714, 0.5359]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6132, 0.4037, 0.6963, 0.2217, 0.4100, 0.1950, 0.5395, 0.5175],
[0.6205, 0.4012, 0.8675, 0.3283, 0.3713, 0.3050, 0.5813, 0.5117],
[0.6350, 0.4144, 0.9250, 0.4100, 0.4125, 0.3750, 0.7129, 0.5945],
[0.6243, 0.4128, 0.7763, 0.2717, 0.3825, 0.3133, 0.6212, 0.5417],
[0.6293, 0.4024, 0.8750, 0.5000, 0.4013, 0.5733, 0.7121, 0.5633],
[0.6277, 0.4013, 0.8888, 0.4767, 0.3600, 0.3567, 0.6148, 0.4672],
[0.6109, 0.4041, 0.6975, 0.3167, 0.3512, 0.3383, 0.5153, 0.5319],
[0.6252, 0.4162, 0.8662, 0.4467, 0.3625, 0.3567, 0.6037, 0.5533]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04196064005373046
step: 38
running loss: 0.001104227369835012
Train Steps: 38/90 Loss: 0.0011 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6364, 0.4144, 0.8625, 0.3083, 0.4913, 0.2000, 0.6448, 0.5274],
[0.6059, 0.4002, 0.7562, 0.2767, 0.3538, 0.3033, 0.5529, 0.5455],
[0.6279, 0.4008, 0.8600, 0.4883, 0.4325, 0.5283, 0.7010, 0.5378],
[0.6196, 0.4088, 0.8888, 0.4583, 0.4500, 0.5683, 0.6138, 0.5883],
[0.6082, 0.4042, 0.6975, 0.1917, 0.4100, 0.1983, 0.5502, 0.5578],
[0.6138, 0.4054, 0.8750, 0.4750, 0.4363, 0.5017, 0.5086, 0.5822],
[0.6199, 0.4112, 0.8475, 0.3717, 0.3550, 0.4350, 0.6063, 0.6083],
[0.6189, 0.4029, 0.8375, 0.5767, 0.4745, 0.4829, 0.5551, 0.5598]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6322, 0.4343, 0.8624, 0.3162, 0.4473, 0.1855, 0.6437, 0.4917],
[0.6319, 0.4302, 0.7483, 0.2713, 0.3327, 0.2648, 0.5815, 0.5005],
[0.6248, 0.3952, 0.8612, 0.4800, 0.4064, 0.4749, 0.7014, 0.5224],
[0.6160, 0.4161, 0.8835, 0.4645, 0.4237, 0.5160, 0.5874, 0.5665],
[0.6446, 0.4308, 0.6868, 0.2093, 0.3712, 0.1665, 0.5641, 0.5247],
[0.6253, 0.4151, 0.8410, 0.4777, 0.4036, 0.4330, 0.5291, 0.5450],
[0.5632, 0.3792, 0.8631, 0.3644, 0.3287, 0.3986, 0.6136, 0.5751],
[0.6078, 0.4056, 0.8220, 0.5465, 0.4432, 0.4151, 0.5733, 0.5377]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6364, 0.4144, 0.8625, 0.3083, 0.4913, 0.2000, 0.6448, 0.5274],
[0.6059, 0.4002, 0.7563, 0.2767, 0.3537, 0.3033, 0.5529, 0.5455],
[0.6279, 0.4008, 0.8600, 0.4883, 0.4325, 0.5283, 0.7010, 0.5378],
[0.6196, 0.4088, 0.8888, 0.4583, 0.4500, 0.5683, 0.6137, 0.5883],
[0.6082, 0.4042, 0.6975, 0.1917, 0.4100, 0.1983, 0.5502, 0.5578],
[0.6138, 0.4054, 0.8750, 0.4750, 0.4363, 0.5017, 0.5086, 0.5822],
[0.6199, 0.4112, 0.8475, 0.3717, 0.3550, 0.4350, 0.6062, 0.6083],
[0.6189, 0.4029, 0.8375, 0.5767, 0.4745, 0.4829, 0.5551, 0.5598]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.042734951653983444
step: 39
running loss: 0.0010957679911277806
Train Steps: 39/90 Loss: 0.0011 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6289, 0.4019, 0.8113, 0.5467, 0.3875, 0.5017, 0.7367, 0.5332],
[0.6086, 0.4019, 0.7782, 0.4278, 0.3625, 0.4350, 0.5150, 0.5285],
[0.6150, 0.4097, 0.7468, 0.3194, 0.3825, 0.2633, 0.5463, 0.5800],
[0.6161, 0.4024, 0.8838, 0.4583, 0.3688, 0.3733, 0.5311, 0.5344],
[0.6305, 0.3983, 0.8950, 0.4833, 0.3688, 0.4683, 0.6375, 0.5117],
[0.6085, 0.4005, 0.8400, 0.4317, 0.3763, 0.4750, 0.5476, 0.5058],
[0.6261, 0.4131, 0.8938, 0.3550, 0.4000, 0.2683, 0.6188, 0.5283],
[0.6307, 0.4029, 0.8988, 0.4817, 0.3937, 0.3500, 0.7311, 0.5378]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6414, 0.4290, 0.8107, 0.5311, 0.3755, 0.4731, 0.6912, 0.5280],
[0.6003, 0.3886, 0.7825, 0.4177, 0.3560, 0.4139, 0.5226, 0.5284],
[0.6446, 0.4353, 0.7344, 0.3098, 0.3624, 0.2710, 0.5068, 0.5727],
[0.5883, 0.3823, 0.8884, 0.4842, 0.3630, 0.3670, 0.5167, 0.5230],
[0.6610, 0.4082, 0.8864, 0.4826, 0.3667, 0.4435, 0.6328, 0.5101],
[0.6120, 0.3974, 0.8367, 0.4157, 0.3598, 0.4524, 0.5596, 0.4991],
[0.7246, 0.4780, 0.9052, 0.3613, 0.3900, 0.2460, 0.6239, 0.5306],
[0.6220, 0.4103, 0.8976, 0.4861, 0.3990, 0.3335, 0.7187, 0.5409]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6289, 0.4019, 0.8112, 0.5467, 0.3875, 0.5017, 0.7367, 0.5332],
[0.6086, 0.4019, 0.7782, 0.4278, 0.3625, 0.4350, 0.5150, 0.5285],
[0.6150, 0.4097, 0.7468, 0.3194, 0.3825, 0.2633, 0.5462, 0.5800],
[0.6161, 0.4024, 0.8838, 0.4583, 0.3688, 0.3733, 0.5311, 0.5344],
[0.6305, 0.3983, 0.8950, 0.4833, 0.3688, 0.4683, 0.6375, 0.5117],
[0.6084, 0.4005, 0.8400, 0.4317, 0.3762, 0.4750, 0.5476, 0.5058],
[0.6261, 0.4131, 0.8938, 0.3550, 0.4000, 0.2683, 0.6187, 0.5283],
[0.6307, 0.4029, 0.8988, 0.4817, 0.3938, 0.3500, 0.7311, 0.5378]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0431966645992361
step: 40
running loss: 0.0010799166149809026
Train Steps: 40/90 Loss: 0.0011 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6196, 0.4090, 0.8450, 0.3900, 0.3575, 0.3933, 0.5975, 0.5583],
[0.6225, 0.4116, 0.8662, 0.3517, 0.3663, 0.3233, 0.5837, 0.5317],
[0.6182, 0.3987, 0.7878, 0.2889, 0.3699, 0.3260, 0.6086, 0.5367],
[0.6229, 0.4066, 0.8513, 0.5717, 0.4500, 0.5050, 0.6025, 0.5350],
[0.6321, 0.4048, 0.8738, 0.5617, 0.3875, 0.4417, 0.6361, 0.4927],
[0.6128, 0.4116, 0.8450, 0.4583, 0.3675, 0.4867, 0.5337, 0.5446],
[0.6255, 0.4017, 0.8688, 0.3217, 0.3638, 0.3550, 0.6344, 0.4901],
[0.6204, 0.4091, 0.8950, 0.4783, 0.3613, 0.4617, 0.6063, 0.5617]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6134, 0.3949, 0.8595, 0.3987, 0.3494, 0.3724, 0.5910, 0.5731],
[0.6684, 0.4354, 0.8558, 0.3522, 0.3534, 0.3221, 0.6058, 0.5432],
[0.6412, 0.4086, 0.8021, 0.3002, 0.3626, 0.3407, 0.6261, 0.5365],
[0.6907, 0.4500, 0.8277, 0.5763, 0.4382, 0.4893, 0.5934, 0.5552],
[0.6440, 0.4196, 0.8511, 0.5767, 0.3726, 0.4335, 0.6587, 0.4990],
[0.6427, 0.4119, 0.8444, 0.4761, 0.3769, 0.4700, 0.5662, 0.5726],
[0.6348, 0.3972, 0.8611, 0.3470, 0.3555, 0.3311, 0.6533, 0.5098],
[0.6770, 0.4490, 0.8951, 0.5009, 0.3560, 0.4613, 0.6049, 0.5530]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6196, 0.4090, 0.8450, 0.3900, 0.3575, 0.3933, 0.5975, 0.5583],
[0.6225, 0.4116, 0.8662, 0.3517, 0.3663, 0.3233, 0.5838, 0.5317],
[0.6182, 0.3987, 0.7878, 0.2889, 0.3699, 0.3260, 0.6086, 0.5367],
[0.6229, 0.4066, 0.8512, 0.5717, 0.4500, 0.5050, 0.6025, 0.5350],
[0.6321, 0.4048, 0.8737, 0.5617, 0.3875, 0.4417, 0.6361, 0.4927],
[0.6128, 0.4116, 0.8450, 0.4583, 0.3675, 0.4867, 0.5337, 0.5446],
[0.6255, 0.4017, 0.8687, 0.3217, 0.3638, 0.3550, 0.6344, 0.4901],
[0.6204, 0.4091, 0.8950, 0.4783, 0.3613, 0.4617, 0.6062, 0.5617]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04362316819606349
step: 41
running loss: 0.0010639797120991095
Train Steps: 41/90 Loss: 0.0011 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6164, 0.4119, 0.7913, 0.2650, 0.3538, 0.3500, 0.5614, 0.5038],
[0.6192, 0.4128, 0.8513, 0.5617, 0.4200, 0.5267, 0.5850, 0.5633],
[0.6274, 0.4099, 0.8625, 0.3233, 0.4400, 0.1983, 0.5876, 0.4869],
[0.6198, 0.4115, 0.7762, 0.2717, 0.3713, 0.3200, 0.5837, 0.5683],
[0.6275, 0.4024, 0.7722, 0.2080, 0.4392, 0.2234, 0.6435, 0.5290],
[0.6128, 0.4084, 0.8738, 0.4683, 0.3613, 0.3700, 0.4960, 0.5397],
[0.6203, 0.4021, 0.8780, 0.5031, 0.3667, 0.3882, 0.5842, 0.5405],
[0.6222, 0.4169, 0.8638, 0.5650, 0.4313, 0.4783, 0.5637, 0.5633]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5952, 0.3894, 0.7800, 0.2822, 0.3461, 0.3827, 0.6112, 0.5220],
[0.6692, 0.4349, 0.8421, 0.5854, 0.4277, 0.5497, 0.5884, 0.5794],
[0.7066, 0.4452, 0.8616, 0.3625, 0.4512, 0.2253, 0.6105, 0.5051],
[0.6223, 0.3899, 0.7771, 0.2893, 0.3718, 0.3561, 0.5877, 0.5753],
[0.5444, 0.3587, 0.7548, 0.2279, 0.4270, 0.2348, 0.6474, 0.5424],
[0.6348, 0.4049, 0.8640, 0.4997, 0.3731, 0.3949, 0.5174, 0.5608],
[0.6215, 0.3988, 0.8642, 0.5334, 0.3727, 0.4115, 0.6142, 0.5432],
[0.6647, 0.4366, 0.8561, 0.5870, 0.4228, 0.4839, 0.5994, 0.5959]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6164, 0.4119, 0.7912, 0.2650, 0.3537, 0.3500, 0.5614, 0.5038],
[0.6192, 0.4128, 0.8512, 0.5617, 0.4200, 0.5267, 0.5850, 0.5633],
[0.6274, 0.4099, 0.8625, 0.3233, 0.4400, 0.1983, 0.5876, 0.4869],
[0.6198, 0.4115, 0.7763, 0.2717, 0.3713, 0.3200, 0.5838, 0.5683],
[0.6275, 0.4024, 0.7722, 0.2080, 0.4392, 0.2234, 0.6435, 0.5290],
[0.6127, 0.4084, 0.8737, 0.4683, 0.3613, 0.3700, 0.4960, 0.5397],
[0.6203, 0.4020, 0.8780, 0.5031, 0.3667, 0.3882, 0.5842, 0.5405],
[0.6222, 0.4169, 0.8637, 0.5650, 0.4313, 0.4783, 0.5638, 0.5633]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04430640529608354
step: 42
running loss: 0.001054914411811513
Train Steps: 42/90 Loss: 0.0011 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6314, 0.4050, 0.8227, 0.5431, 0.4150, 0.5517, 0.7121, 0.5690],
[0.6225, 0.4196, 0.8788, 0.3467, 0.3750, 0.3400, 0.5413, 0.5433],
[0.6204, 0.4091, 0.8950, 0.4783, 0.3613, 0.4617, 0.6063, 0.5617],
[0.6168, 0.4081, 0.8438, 0.3367, 0.3500, 0.4667, 0.6212, 0.5400],
[0.6227, 0.4193, 0.8838, 0.4933, 0.3663, 0.3733, 0.5637, 0.5633],
[0.6087, 0.3976, 0.8337, 0.3867, 0.3713, 0.3117, 0.5938, 0.5300],
[0.6200, 0.3993, 0.8639, 0.3687, 0.3658, 0.3139, 0.6002, 0.5374],
[0.6271, 0.4040, 0.9138, 0.3750, 0.4625, 0.2617, 0.7232, 0.5413]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6467, 0.4283, 0.8193, 0.5591, 0.4115, 0.5895, 0.7145, 0.5837],
[0.6037, 0.3921, 0.8437, 0.3812, 0.3790, 0.3736, 0.5460, 0.5361],
[0.6682, 0.4433, 0.8867, 0.5180, 0.3720, 0.4951, 0.5859, 0.5464],
[0.6078, 0.4041, 0.8402, 0.3575, 0.3668, 0.4851, 0.6394, 0.5646],
[0.6845, 0.4671, 0.8428, 0.5293, 0.3853, 0.4209, 0.5545, 0.5740],
[0.6057, 0.3982, 0.8355, 0.4236, 0.3830, 0.3535, 0.5858, 0.5416],
[0.5911, 0.3794, 0.8517, 0.4044, 0.3831, 0.3585, 0.5884, 0.5192],
[0.6004, 0.3727, 0.9194, 0.3995, 0.4778, 0.3034, 0.7175, 0.5427]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6314, 0.4050, 0.8227, 0.5431, 0.4150, 0.5517, 0.7121, 0.5690],
[0.6225, 0.4196, 0.8788, 0.3467, 0.3750, 0.3400, 0.5412, 0.5433],
[0.6204, 0.4091, 0.8950, 0.4783, 0.3613, 0.4617, 0.6062, 0.5617],
[0.6168, 0.4081, 0.8438, 0.3367, 0.3500, 0.4667, 0.6212, 0.5400],
[0.6227, 0.4193, 0.8838, 0.4933, 0.3663, 0.3733, 0.5638, 0.5633],
[0.6087, 0.3976, 0.8338, 0.3867, 0.3713, 0.3117, 0.5938, 0.5300],
[0.6200, 0.3993, 0.8639, 0.3687, 0.3658, 0.3139, 0.6002, 0.5374],
[0.6271, 0.4040, 0.9137, 0.3750, 0.4625, 0.2617, 0.7232, 0.5413]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.044957086036447436
step: 43
running loss: 0.0010455136287545914
Train Steps: 43/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6201, 0.4151, 0.8588, 0.5467, 0.3700, 0.3950, 0.5637, 0.5933],
[0.6182, 0.3982, 0.7541, 0.2379, 0.3959, 0.2792, 0.6079, 0.5389],
[0.6250, 0.4054, 0.8770, 0.4723, 0.4662, 0.5367, 0.6162, 0.5433],
[0.6124, 0.4075, 0.7696, 0.4153, 0.3475, 0.3767, 0.5157, 0.5427],
[0.6164, 0.3956, 0.8757, 0.5088, 0.4300, 0.5320, 0.6022, 0.5202],
[0.6263, 0.4233, 0.7924, 0.4626, 0.3788, 0.2883, 0.5573, 0.6047],
[0.6204, 0.4110, 0.7913, 0.2667, 0.4062, 0.2500, 0.6225, 0.5367],
[0.6102, 0.4020, 0.8638, 0.3717, 0.3625, 0.5017, 0.6038, 0.5500]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6396, 0.4144, 0.8675, 0.5608, 0.3827, 0.4323, 0.5664, 0.5795],
[0.5833, 0.3797, 0.8016, 0.2433, 0.3960, 0.2990, 0.6173, 0.5316],
[0.6888, 0.4475, 0.8880, 0.4995, 0.4760, 0.5530, 0.6200, 0.5388],
[0.6149, 0.3904, 0.8058, 0.4255, 0.3589, 0.4215, 0.5320, 0.5407],
[0.6182, 0.4064, 0.8864, 0.5289, 0.4396, 0.5638, 0.6034, 0.5243],
[0.6576, 0.4455, 0.8199, 0.5035, 0.4000, 0.3319, 0.5725, 0.6120],
[0.5834, 0.3808, 0.8157, 0.2679, 0.4248, 0.2818, 0.6214, 0.5289],
[0.6289, 0.4154, 0.8847, 0.3929, 0.3923, 0.5196, 0.6435, 0.5359]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6202, 0.4151, 0.8587, 0.5467, 0.3700, 0.3950, 0.5638, 0.5933],
[0.6182, 0.3982, 0.7541, 0.2379, 0.3959, 0.2792, 0.6079, 0.5389],
[0.6250, 0.4054, 0.8770, 0.4723, 0.4663, 0.5367, 0.6162, 0.5433],
[0.6124, 0.4075, 0.7696, 0.4153, 0.3475, 0.3767, 0.5157, 0.5427],
[0.6164, 0.3956, 0.8757, 0.5088, 0.4300, 0.5320, 0.6022, 0.5202],
[0.6263, 0.4232, 0.7924, 0.4626, 0.3787, 0.2883, 0.5573, 0.6047],
[0.6204, 0.4110, 0.7912, 0.2667, 0.4062, 0.2500, 0.6225, 0.5367],
[0.6102, 0.4020, 0.8637, 0.3717, 0.3625, 0.5017, 0.6037, 0.5500]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04550424014450982
step: 44
running loss: 0.0010341872760115868
Train Steps: 44/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6268, 0.4094, 0.9038, 0.4300, 0.3700, 0.3483, 0.6262, 0.5167],
[ nan, nan, 0.7725, 0.2611, 0.3675, 0.2733, 0.5413, 0.5167],
[0.6127, 0.4115, 0.7163, 0.2883, 0.3625, 0.2950, 0.5327, 0.5495],
[0.6048, 0.3928, 0.8538, 0.5433, 0.3875, 0.5117, 0.5266, 0.4719],
[0.6275, 0.4157, 0.8337, 0.5800, 0.3763, 0.4200, 0.5547, 0.6125],
[0.6357, 0.4139, 0.8450, 0.5883, 0.3775, 0.4950, 0.6488, 0.5297],
[0.6314, 0.4050, 0.8227, 0.5431, 0.4150, 0.5517, 0.7121, 0.5690],
[0.6087, 0.3976, 0.8337, 0.3867, 0.3713, 0.3117, 0.5938, 0.5300]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6898, 0.4383, 0.9413, 0.4102, 0.4053, 0.3490, 0.6271, 0.5214],
[0.0654, 0.0371, 0.8057, 0.2584, 0.3954, 0.3384, 0.5145, 0.5398],
[0.5854, 0.3809, 0.7735, 0.2698, 0.3950, 0.3140, 0.5210, 0.5573],
[0.7269, 0.4606, 0.8708, 0.5288, 0.4172, 0.5184, 0.5386, 0.5147],
[0.7218, 0.4794, 0.8484, 0.5600, 0.4143, 0.4491, 0.5731, 0.6127],
[0.6632, 0.4350, 0.8738, 0.5665, 0.3998, 0.5053, 0.6562, 0.5334],
[0.6927, 0.4557, 0.8649, 0.5187, 0.4277, 0.5654, 0.7123, 0.5794],
[0.6533, 0.4278, 0.8803, 0.3830, 0.3984, 0.3294, 0.5873, 0.5378]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6268, 0.4094, 0.9038, 0.4300, 0.3700, 0.3483, 0.6263, 0.5167],
[0.0000, 0.0000, 0.7725, 0.2611, 0.3675, 0.2733, 0.5412, 0.5167],
[0.6127, 0.4114, 0.7163, 0.2883, 0.3625, 0.2950, 0.5327, 0.5495],
[0.6048, 0.3928, 0.8537, 0.5433, 0.3875, 0.5117, 0.5266, 0.4719],
[0.6275, 0.4157, 0.8338, 0.5800, 0.3762, 0.4200, 0.5547, 0.6125],
[0.6357, 0.4139, 0.8450, 0.5883, 0.3775, 0.4950, 0.6488, 0.5297],
[0.6314, 0.4050, 0.8227, 0.5431, 0.4150, 0.5517, 0.7121, 0.5690],
[0.6087, 0.3976, 0.8338, 0.3867, 0.3713, 0.3117, 0.5938, 0.5300]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04684005380840972
step: 45
running loss: 0.0010408900846313272
Train Steps: 45/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.6992, 0.2791, 0.3950, 0.2383, 0.5483, 0.5819],
[0.6211, 0.3993, 0.7650, 0.1933, 0.4575, 0.1550, 0.5965, 0.4895],
[0.6162, 0.4134, 0.6700, 0.2467, 0.3962, 0.2533, 0.5737, 0.5467],
[0.6222, 0.3957, 0.8838, 0.5017, 0.3937, 0.4600, 0.5900, 0.5017],
[0.6182, 0.3987, 0.7878, 0.2889, 0.3699, 0.3260, 0.6086, 0.5367],
[0.6199, 0.4071, 0.7600, 0.2117, 0.4037, 0.2767, 0.6138, 0.5550],
[0.6129, 0.4114, 0.6950, 0.2467, 0.4050, 0.2133, 0.5363, 0.5550],
[0.6165, 0.4106, 0.7575, 0.1733, 0.3838, 0.2650, 0.5680, 0.5116]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.0948, 0.0649, 0.7369, 0.2828, 0.4063, 0.2761, 0.5456, 0.5900],
[0.6272, 0.3999, 0.7922, 0.2179, 0.4729, 0.1858, 0.5854, 0.5116],
[0.6376, 0.4229, 0.7174, 0.2835, 0.3986, 0.2754, 0.5660, 0.5660],
[0.6890, 0.4232, 0.9184, 0.5697, 0.4056, 0.4773, 0.5971, 0.5330],
[0.6022, 0.3880, 0.8296, 0.3167, 0.3761, 0.3408, 0.6021, 0.5541],
[0.6351, 0.4145, 0.8118, 0.2516, 0.4369, 0.2929, 0.6219, 0.5716],
[0.5690, 0.3789, 0.7400, 0.2806, 0.4204, 0.2384, 0.5463, 0.5773],
[0.6463, 0.4115, 0.7827, 0.2099, 0.3979, 0.2565, 0.5745, 0.5275]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.6992, 0.2791, 0.3950, 0.2383, 0.5483, 0.5819],
[0.6211, 0.3993, 0.7650, 0.1933, 0.4575, 0.1550, 0.5965, 0.4895],
[0.6162, 0.4134, 0.6700, 0.2467, 0.3963, 0.2533, 0.5738, 0.5467],
[0.6222, 0.3957, 0.8838, 0.5017, 0.3938, 0.4600, 0.5900, 0.5017],
[0.6182, 0.3987, 0.7878, 0.2889, 0.3699, 0.3260, 0.6086, 0.5367],
[0.6199, 0.4071, 0.7600, 0.2117, 0.4038, 0.2767, 0.6137, 0.5550],
[0.6129, 0.4114, 0.6950, 0.2467, 0.4050, 0.2133, 0.5362, 0.5550],
[0.6165, 0.4106, 0.7575, 0.1733, 0.3837, 0.2650, 0.5680, 0.5116]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04774374206317589
step: 46
running loss: 0.0010379074361559976
Train Steps: 46/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6200, 0.3961, 0.8461, 0.5497, 0.4142, 0.4577, 0.5892, 0.5402],
[0.6201, 0.4004, 0.8786, 0.5043, 0.3833, 0.5138, 0.5997, 0.5092],
[0.6274, 0.4087, 0.8375, 0.5700, 0.4025, 0.4800, 0.5700, 0.6117],
[0.6263, 0.4039, 0.9000, 0.4400, 0.3625, 0.4667, 0.6424, 0.4804],
[0.6157, 0.4102, 0.8513, 0.3817, 0.3613, 0.3667, 0.5096, 0.5890],
[0.6193, 0.4034, 0.7757, 0.2347, 0.3733, 0.2919, 0.5930, 0.4926],
[0.6325, 0.4165, 0.9000, 0.4617, 0.3813, 0.4900, 0.7485, 0.5447],
[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6132, 0.3930, 0.8448, 0.5366, 0.3979, 0.4417, 0.5856, 0.5404],
[0.6065, 0.3869, 0.8564, 0.5038, 0.3883, 0.5033, 0.5811, 0.4995],
[0.6180, 0.4011, 0.8389, 0.5640, 0.3996, 0.4710, 0.5505, 0.6195],
[0.5635, 0.3521, 0.8894, 0.4405, 0.3446, 0.4432, 0.5997, 0.4692],
[0.5423, 0.3544, 0.8496, 0.3760, 0.3585, 0.3441, 0.4819, 0.5728],
[0.5672, 0.3738, 0.7683, 0.2288, 0.3706, 0.2683, 0.5741, 0.4807],
[0.5929, 0.3905, 0.9018, 0.4519, 0.3811, 0.4729, 0.7004, 0.5482],
[0.5863, 0.3843, 0.8827, 0.4588, 0.4425, 0.5560, 0.6066, 0.5455]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6200, 0.3961, 0.8461, 0.5497, 0.4142, 0.4577, 0.5892, 0.5402],
[0.6201, 0.4004, 0.8786, 0.5043, 0.3833, 0.5138, 0.5997, 0.5092],
[0.6274, 0.4087, 0.8375, 0.5700, 0.4025, 0.4800, 0.5700, 0.6117],
[0.6263, 0.4038, 0.9000, 0.4400, 0.3625, 0.4667, 0.6424, 0.4804],
[0.6157, 0.4102, 0.8512, 0.3817, 0.3613, 0.3667, 0.5096, 0.5890],
[0.6193, 0.4034, 0.7757, 0.2347, 0.3733, 0.2919, 0.5930, 0.4926],
[0.6325, 0.4165, 0.9000, 0.4617, 0.3812, 0.4900, 0.7485, 0.5447],
[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04828619211912155
step: 47
running loss: 0.0010273657897685437
Train Steps: 47/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6264, 0.4069, 0.7900, 0.1650, 0.4275, 0.2267, 0.6290, 0.4947],
[0.6332, 0.4128, 0.9200, 0.3517, 0.4400, 0.3833, 0.7461, 0.5494],
[0.6161, 0.4024, 0.8662, 0.4683, 0.4935, 0.5364, 0.6063, 0.5567],
[0.6343, 0.4097, 0.9287, 0.4367, 0.4313, 0.3600, 0.7248, 0.5841],
[0.6219, 0.4089, 0.8938, 0.4800, 0.3825, 0.4450, 0.5850, 0.5200],
[0.6204, 0.4049, 0.7975, 0.2700, 0.3937, 0.2567, 0.5700, 0.5183],
[0.6272, 0.4071, 0.8738, 0.5600, 0.3675, 0.3783, 0.5926, 0.4742],
[0.6222, 0.3937, 0.8350, 0.5617, 0.4138, 0.4600, 0.5800, 0.5233]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5316, 0.3312, 0.7556, 0.1395, 0.4007, 0.2116, 0.6300, 0.4945],
[0.5704, 0.3699, 0.8897, 0.3588, 0.4087, 0.3668, 0.6990, 0.5320],
[0.5642, 0.3640, 0.8545, 0.4413, 0.4406, 0.5011, 0.5789, 0.5432],
[0.5409, 0.3582, 0.8844, 0.4137, 0.3971, 0.3509, 0.6847, 0.5424],
[0.5854, 0.3841, 0.8754, 0.4690, 0.3467, 0.4304, 0.5603, 0.5154],
[0.5621, 0.3721, 0.7616, 0.2443, 0.3572, 0.2442, 0.5230, 0.5137],
[0.5795, 0.3681, 0.8496, 0.5353, 0.3407, 0.3531, 0.5610, 0.4714],
[0.5794, 0.3526, 0.7994, 0.5492, 0.3817, 0.4437, 0.5184, 0.5368]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6264, 0.4069, 0.7900, 0.1650, 0.4275, 0.2267, 0.6290, 0.4947],
[0.6332, 0.4128, 0.9200, 0.3517, 0.4400, 0.3833, 0.7461, 0.5494],
[0.6161, 0.4024, 0.8662, 0.4683, 0.4935, 0.5364, 0.6062, 0.5567],
[0.6343, 0.4097, 0.9287, 0.4367, 0.4313, 0.3600, 0.7248, 0.5841],
[0.6219, 0.4089, 0.8938, 0.4800, 0.3825, 0.4450, 0.5850, 0.5200],
[0.6204, 0.4049, 0.7975, 0.2700, 0.3938, 0.2567, 0.5700, 0.5183],
[0.6272, 0.4071, 0.8737, 0.5600, 0.3675, 0.3783, 0.5926, 0.4742],
[0.6222, 0.3937, 0.8350, 0.5617, 0.4137, 0.4600, 0.5800, 0.5233]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04967287927865982
step: 48
running loss: 0.0010348516516387463
Train Steps: 48/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6163, 0.4114, 0.7650, 0.2017, 0.3763, 0.2867, 0.5631, 0.5071],
[0.6135, 0.4115, 0.8838, 0.4667, 0.4288, 0.6050, 0.5778, 0.5097],
[0.6201, 0.4027, 0.8029, 0.2728, 0.4042, 0.2310, 0.5980, 0.5391],
[0.6161, 0.4040, 0.7525, 0.2133, 0.4125, 0.2067, 0.5787, 0.5117],
[0.6132, 0.4118, 0.8200, 0.3633, 0.3563, 0.5400, 0.5787, 0.5136],
[0.6129, 0.3925, 0.8720, 0.5246, 0.4534, 0.5515, 0.6026, 0.5114],
[0.6161, 0.4076, 0.8900, 0.4667, 0.4125, 0.5917, 0.6262, 0.5367],
[0.6212, 0.4159, 0.8675, 0.5783, 0.4088, 0.4317, 0.5613, 0.5917]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5932, 0.3752, 0.7299, 0.1961, 0.3496, 0.2364, 0.5796, 0.4742],
[0.5746, 0.3886, 0.8618, 0.4477, 0.4209, 0.5416, 0.5816, 0.5256],
[0.5612, 0.3511, 0.7895, 0.2552, 0.3983, 0.1881, 0.5990, 0.5168],
[0.5476, 0.3570, 0.7310, 0.1807, 0.3870, 0.1791, 0.5720, 0.4853],
[0.5533, 0.3635, 0.7871, 0.3705, 0.3497, 0.4683, 0.5949, 0.5131],
[0.5736, 0.3728, 0.8460, 0.5015, 0.4372, 0.4897, 0.6130, 0.5065],
[0.5700, 0.3722, 0.8619, 0.4676, 0.4099, 0.5433, 0.6251, 0.5171],
[0.5712, 0.3966, 0.8282, 0.5571, 0.3881, 0.3772, 0.5808, 0.5863]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6163, 0.4114, 0.7650, 0.2017, 0.3762, 0.2867, 0.5631, 0.5071],
[0.6135, 0.4115, 0.8838, 0.4667, 0.4288, 0.6050, 0.5778, 0.5097],
[0.6201, 0.4027, 0.8029, 0.2728, 0.4042, 0.2310, 0.5980, 0.5391],
[0.6161, 0.4040, 0.7525, 0.2133, 0.4125, 0.2067, 0.5788, 0.5117],
[0.6132, 0.4118, 0.8200, 0.3633, 0.3562, 0.5400, 0.5787, 0.5136],
[0.6129, 0.3925, 0.8720, 0.5246, 0.4534, 0.5515, 0.6026, 0.5114],
[0.6161, 0.4076, 0.8900, 0.4667, 0.4125, 0.5917, 0.6263, 0.5367],
[0.6212, 0.4159, 0.8675, 0.5783, 0.4087, 0.4317, 0.5612, 0.5917]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05076544382609427
step: 49
running loss: 0.0010360294658386586
Train Steps: 49/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6058, 0.3986, 0.8324, 0.4626, 0.3838, 0.4983, 0.5147, 0.5466],
[0.6270, 0.4267, 0.7150, 0.3317, 0.4900, 0.1817, 0.5560, 0.6183],
[0.6040, 0.4002, 0.7338, 0.2267, 0.3975, 0.2100, 0.5231, 0.4778],
[0.6182, 0.4099, 0.7812, 0.3000, 0.3937, 0.2367, 0.5325, 0.5750],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533],
[0.6353, 0.4128, 0.8488, 0.2600, 0.5525, 0.1616, 0.6694, 0.5540],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098],
[0.6201, 0.4065, 0.7300, 0.1933, 0.4075, 0.2533, 0.6162, 0.5483]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5817, 0.3841, 0.8039, 0.4701, 0.3774, 0.5051, 0.5660, 0.5194],
[0.4629, 0.3292, 0.7094, 0.2834, 0.4573, 0.1952, 0.5821, 0.5922],
[0.5646, 0.3773, 0.7173, 0.1904, 0.3819, 0.2052, 0.5569, 0.4717],
[0.5157, 0.3567, 0.7806, 0.2952, 0.3890, 0.2561, 0.5382, 0.5372],
[0.6007, 0.4074, 0.8742, 0.4553, 0.4202, 0.5225, 0.6016, 0.5305],
[0.4842, 0.3445, 0.8362, 0.2285, 0.5071, 0.1936, 0.6952, 0.5239],
[0.5824, 0.3880, 0.8562, 0.4701, 0.3626, 0.5318, 0.6304, 0.4917],
[0.5742, 0.3909, 0.7183, 0.1900, 0.3832, 0.2580, 0.6323, 0.5240]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6058, 0.3986, 0.8324, 0.4626, 0.3837, 0.4983, 0.5147, 0.5466],
[0.6270, 0.4266, 0.7150, 0.3317, 0.4900, 0.1817, 0.5560, 0.6183],
[0.6040, 0.4002, 0.7337, 0.2267, 0.3975, 0.2100, 0.5231, 0.4778],
[0.6182, 0.4099, 0.7812, 0.3000, 0.3938, 0.2367, 0.5325, 0.5750],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533],
[0.6353, 0.4128, 0.8487, 0.2600, 0.5525, 0.1616, 0.6694, 0.5540],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098],
[0.6201, 0.4065, 0.7300, 0.1933, 0.4075, 0.2533, 0.6162, 0.5483]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05246755573898554
step: 50
running loss: 0.0010493511147797107
Train Steps: 50/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6107, 0.4013, 0.8700, 0.4650, 0.5049, 0.5176, 0.5850, 0.5550],
[0.6245, 0.4100, 0.7762, 0.2583, 0.4963, 0.1517, 0.5875, 0.5417],
[0.6055, 0.4015, 0.7425, 0.2033, 0.4113, 0.1883, 0.5217, 0.4823],
[0.6145, 0.4008, 0.8750, 0.5383, 0.3975, 0.4650, 0.5563, 0.5533],
[ nan, nan, 0.6935, 0.1930, 0.4150, 0.2250, 0.5450, 0.5650],
[0.6224, 0.4061, 0.8988, 0.4300, 0.3838, 0.4750, 0.6112, 0.5483],
[ nan, nan, 0.7525, 0.2291, 0.3838, 0.3017, 0.6050, 0.5667],
[0.6226, 0.4125, 0.8800, 0.4900, 0.4512, 0.5600, 0.6275, 0.5517]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6535, 0.4426, 0.8615, 0.4605, 0.4753, 0.5020, 0.6464, 0.5205],
[0.6618, 0.4507, 0.7415, 0.2485, 0.4715, 0.1504, 0.6295, 0.5336],
[0.6118, 0.4104, 0.7157, 0.1890, 0.3934, 0.1675, 0.5420, 0.4826],
[0.6650, 0.4469, 0.8542, 0.5318, 0.3817, 0.4565, 0.5792, 0.5371],
[0.0827, 0.0845, 0.7178, 0.2095, 0.4269, 0.2542, 0.5514, 0.5404],
[0.7079, 0.4768, 0.8986, 0.4412, 0.3717, 0.4759, 0.6466, 0.5368],
[0.1929, 0.1621, 0.7625, 0.2185, 0.3761, 0.2935, 0.6065, 0.5570],
[0.7233, 0.4964, 0.8791, 0.4836, 0.4390, 0.5540, 0.6191, 0.5469]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6107, 0.4013, 0.8700, 0.4650, 0.5049, 0.5176, 0.5850, 0.5550],
[0.6245, 0.4100, 0.7763, 0.2583, 0.4963, 0.1517, 0.5875, 0.5417],
[0.6055, 0.4015, 0.7425, 0.2033, 0.4112, 0.1883, 0.5217, 0.4823],
[0.6145, 0.4008, 0.8750, 0.5383, 0.3975, 0.4650, 0.5562, 0.5533],
[0.0000, 0.0000, 0.6935, 0.1930, 0.4150, 0.2250, 0.5450, 0.5650],
[0.6224, 0.4061, 0.8988, 0.4300, 0.3837, 0.4750, 0.6112, 0.5483],
[0.0000, 0.0000, 0.7525, 0.2291, 0.3837, 0.3017, 0.6050, 0.5667],
[0.6226, 0.4125, 0.8800, 0.4900, 0.4512, 0.5600, 0.6275, 0.5517]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0021, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0021, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05460604024119675
step: 51
running loss: 0.0010707066713960148
Train Steps: 51/90 Loss: 0.0011 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6087, 0.3951, 0.8387, 0.5833, 0.4188, 0.4933, 0.5146, 0.4830],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5413, 0.5683],
[0.6296, 0.3989, 0.9000, 0.4150, 0.3613, 0.3867, 0.6400, 0.5100],
[0.6262, 0.4085, 0.8438, 0.3150, 0.4025, 0.2633, 0.6339, 0.4810],
[0.6124, 0.4030, 0.8650, 0.4867, 0.4999, 0.5106, 0.5137, 0.5773],
[0.6214, 0.4175, 0.7300, 0.2883, 0.4338, 0.2167, 0.5698, 0.5773],
[0.6251, 0.4163, 0.8662, 0.4467, 0.3625, 0.3567, 0.6038, 0.5533],
[0.6239, 0.4206, 0.8750, 0.5400, 0.3688, 0.4850, 0.5737, 0.5700]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5814, 0.3786, 0.8285, 0.5403, 0.4182, 0.5051, 0.5368, 0.5026],
[0.6062, 0.3988, 0.8697, 0.4950, 0.3917, 0.3794, 0.5435, 0.5671],
[0.6641, 0.4272, 0.8921, 0.3767, 0.3677, 0.3942, 0.6647, 0.4933],
[0.6181, 0.4069, 0.8375, 0.2639, 0.4191, 0.2653, 0.6480, 0.4718],
[0.5773, 0.3799, 0.8746, 0.4581, 0.5086, 0.5067, 0.5284, 0.5730],
[0.5787, 0.4009, 0.7336, 0.2481, 0.4412, 0.2274, 0.5866, 0.5746],
[0.5987, 0.4005, 0.8599, 0.4030, 0.3679, 0.3575, 0.6200, 0.5459],
[0.6027, 0.3978, 0.8663, 0.5080, 0.4044, 0.5205, 0.6093, 0.5446]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6087, 0.3951, 0.8388, 0.5833, 0.4187, 0.4933, 0.5146, 0.4830],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5412, 0.5683],
[0.6296, 0.3989, 0.9000, 0.4150, 0.3613, 0.3867, 0.6400, 0.5100],
[0.6262, 0.4085, 0.8438, 0.3150, 0.4025, 0.2633, 0.6339, 0.4810],
[0.6124, 0.4030, 0.8650, 0.4867, 0.4999, 0.5106, 0.5137, 0.5773],
[0.6214, 0.4175, 0.7300, 0.2883, 0.4338, 0.2167, 0.5698, 0.5773],
[0.6252, 0.4162, 0.8662, 0.4467, 0.3625, 0.3567, 0.6037, 0.5533],
[0.6239, 0.4206, 0.8750, 0.5400, 0.3688, 0.4850, 0.5738, 0.5700]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0550856547197327
step: 52
running loss: 0.0010593395138410134
Train Steps: 52/90 Loss: 0.0011 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6128, 0.4022, 0.8738, 0.5067, 0.4983, 0.5231, 0.5364, 0.5064],
[ nan, nan, 0.9050, 0.3500, 0.5138, 0.2300, 0.7359, 0.5702],
[0.6115, 0.4005, 0.8838, 0.3867, 0.3763, 0.4700, 0.5800, 0.5550],
[0.6219, 0.4097, 0.8738, 0.3400, 0.3563, 0.4117, 0.5975, 0.5683],
[0.6260, 0.4153, 0.9000, 0.4533, 0.4025, 0.2633, 0.6223, 0.4967],
[0.6227, 0.4083, 0.8938, 0.4800, 0.3800, 0.2950, 0.5737, 0.5350],
[0.6199, 0.4093, 0.7913, 0.2533, 0.4288, 0.2467, 0.5975, 0.5700],
[0.6085, 0.4005, 0.8400, 0.4317, 0.3763, 0.4750, 0.5476, 0.5058]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6195, 0.4219, 0.8560, 0.4903, 0.5090, 0.5246, 0.5346, 0.5340],
[0.0739, 0.0713, 0.8875, 0.3262, 0.5059, 0.2328, 0.6973, 0.5713],
[0.6520, 0.4337, 0.8578, 0.3723, 0.4002, 0.4738, 0.5595, 0.5606],
[0.6410, 0.4396, 0.8600, 0.3413, 0.3624, 0.3962, 0.5996, 0.5702],
[0.6282, 0.4127, 0.8733, 0.4211, 0.4223, 0.2760, 0.6183, 0.5145],
[0.6489, 0.4297, 0.8637, 0.4640, 0.4111, 0.3077, 0.5486, 0.5505],
[0.6476, 0.4493, 0.7594, 0.2379, 0.4411, 0.2562, 0.5998, 0.5810],
[0.6860, 0.4447, 0.8223, 0.4055, 0.3957, 0.4801, 0.5548, 0.5080]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6128, 0.4022, 0.8737, 0.5067, 0.4983, 0.5231, 0.5364, 0.5064],
[0.0000, 0.0000, 0.9050, 0.3500, 0.5138, 0.2300, 0.7359, 0.5702],
[0.6115, 0.4005, 0.8838, 0.3867, 0.3762, 0.4700, 0.5800, 0.5550],
[0.6219, 0.4097, 0.8737, 0.3400, 0.3562, 0.4117, 0.5975, 0.5683],
[0.6260, 0.4153, 0.9000, 0.4533, 0.4025, 0.2633, 0.6223, 0.4967],
[0.6227, 0.4083, 0.8938, 0.4800, 0.3800, 0.2950, 0.5738, 0.5350],
[0.6198, 0.4093, 0.7912, 0.2533, 0.4288, 0.2467, 0.5975, 0.5700],
[0.6084, 0.4005, 0.8400, 0.4317, 0.3762, 0.4750, 0.5476, 0.5058]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05573676276253536
step: 53
running loss: 0.0010516370332553841
Train Steps: 53/90 Loss: 0.0011 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6250, 0.3961, 0.8672, 0.4929, 0.4199, 0.4972, 0.6312, 0.5301],
[0.6263, 0.4030, 0.9000, 0.4767, 0.3800, 0.5167, 0.6415, 0.4771],
[0.6187, 0.4104, 0.7126, 0.2069, 0.3950, 0.2517, 0.5913, 0.5683],
[0.6236, 0.3966, 0.8850, 0.4967, 0.3638, 0.4017, 0.5850, 0.5183],
[0.6075, 0.4007, 0.8275, 0.4917, 0.4050, 0.5100, 0.5167, 0.5280],
[0.6202, 0.3983, 0.8555, 0.5429, 0.3842, 0.4370, 0.5866, 0.5398],
[0.6068, 0.3963, 0.8650, 0.4317, 0.4037, 0.5083, 0.5253, 0.4999],
[0.6203, 0.4078, 0.8800, 0.5083, 0.3900, 0.5000, 0.6100, 0.5583]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6280, 0.4024, 0.9012, 0.5148, 0.4555, 0.4977, 0.6189, 0.5503],
[0.5665, 0.3724, 0.9334, 0.4956, 0.4231, 0.5474, 0.6169, 0.5207],
[0.6607, 0.4436, 0.7319, 0.2175, 0.4085, 0.2458, 0.5786, 0.5611],
[0.6557, 0.4170, 0.9130, 0.4984, 0.4010, 0.4071, 0.5816, 0.5355],
[0.6025, 0.3909, 0.8496, 0.5025, 0.4549, 0.5250, 0.5244, 0.5597],
[0.6019, 0.3968, 0.8792, 0.5568, 0.4240, 0.4326, 0.5877, 0.5582],
[0.6882, 0.4499, 0.8793, 0.4420, 0.4445, 0.5120, 0.5330, 0.5221],
[0.6171, 0.4100, 0.9059, 0.5125, 0.4226, 0.5082, 0.5894, 0.5972]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6250, 0.3961, 0.8672, 0.4929, 0.4199, 0.4972, 0.6312, 0.5301],
[0.6263, 0.4029, 0.9000, 0.4767, 0.3800, 0.5167, 0.6415, 0.4771],
[0.6187, 0.4103, 0.7126, 0.2069, 0.3950, 0.2517, 0.5913, 0.5683],
[0.6236, 0.3965, 0.8850, 0.4967, 0.3638, 0.4017, 0.5850, 0.5183],
[0.6075, 0.4006, 0.8275, 0.4917, 0.4050, 0.5100, 0.5167, 0.5280],
[0.6202, 0.3983, 0.8555, 0.5429, 0.3842, 0.4370, 0.5866, 0.5398],
[0.6068, 0.3963, 0.8650, 0.4317, 0.4038, 0.5083, 0.5253, 0.4999],
[0.6203, 0.4078, 0.8800, 0.5083, 0.3900, 0.5000, 0.6100, 0.5583]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.056453864090144634
step: 54
running loss: 0.001045441927595271
Train Steps: 54/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6226, 0.4001, 0.8438, 0.5733, 0.3862, 0.4250, 0.5750, 0.5283],
[0.6277, 0.4029, 0.8250, 0.2433, 0.4325, 0.2100, 0.6366, 0.5207],
[0.6272, 0.4120, 0.9038, 0.4117, 0.3725, 0.3200, 0.6175, 0.5250],
[0.6101, 0.3977, 0.8550, 0.5667, 0.3862, 0.4417, 0.5128, 0.4869],
[0.6129, 0.4063, 0.8738, 0.5250, 0.4313, 0.4733, 0.5230, 0.5874],
[0.6152, 0.4131, 0.6863, 0.2567, 0.3625, 0.3300, 0.5765, 0.5305],
[0.6169, 0.4108, 0.6821, 0.2722, 0.3825, 0.2550, 0.5550, 0.5717],
[0.6106, 0.4022, 0.7125, 0.2650, 0.3713, 0.2700, 0.5431, 0.5123]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5476, 0.3369, 0.8878, 0.5874, 0.4094, 0.4444, 0.5650, 0.5610],
[0.6466, 0.4018, 0.8539, 0.2829, 0.4648, 0.2358, 0.6455, 0.5369],
[0.5906, 0.3769, 0.9650, 0.4317, 0.3911, 0.3305, 0.6028, 0.5531],
[0.5458, 0.3493, 0.9107, 0.5839, 0.4247, 0.4551, 0.5193, 0.5251],
[0.6134, 0.3893, 0.9136, 0.5638, 0.4533, 0.5064, 0.5083, 0.6175],
[0.6576, 0.4241, 0.7325, 0.2693, 0.3812, 0.3485, 0.5727, 0.5774],
[0.6544, 0.4179, 0.7269, 0.2816, 0.4004, 0.2486, 0.5374, 0.5922],
[0.6109, 0.3914, 0.7628, 0.2722, 0.4018, 0.2721, 0.5324, 0.5373]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6226, 0.4001, 0.8438, 0.5733, 0.3862, 0.4250, 0.5750, 0.5283],
[0.6277, 0.4029, 0.8250, 0.2433, 0.4325, 0.2100, 0.6366, 0.5207],
[0.6272, 0.4120, 0.9038, 0.4117, 0.3725, 0.3200, 0.6175, 0.5250],
[0.6101, 0.3977, 0.8550, 0.5667, 0.3862, 0.4417, 0.5128, 0.4869],
[0.6130, 0.4063, 0.8737, 0.5250, 0.4313, 0.4733, 0.5230, 0.5874],
[0.6152, 0.4131, 0.6862, 0.2567, 0.3625, 0.3300, 0.5765, 0.5305],
[0.6169, 0.4108, 0.6821, 0.2722, 0.3825, 0.2550, 0.5550, 0.5717],
[0.6106, 0.4022, 0.7125, 0.2650, 0.3713, 0.2700, 0.5431, 0.5123]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.057424455240834504
step: 55
running loss: 0.0010440810043788093
Train Steps: 55/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6350, 0.4144, 0.9250, 0.4100, 0.4125, 0.3750, 0.7129, 0.5945],
[ nan, nan, 0.7412, 0.2200, 0.4450, 0.1517, 0.5312, 0.4983],
[0.6193, 0.4034, 0.7757, 0.2347, 0.3733, 0.2919, 0.5930, 0.4926],
[0.6205, 0.4016, 0.8350, 0.2717, 0.3987, 0.2550, 0.5787, 0.5133],
[0.6184, 0.4079, 0.8350, 0.3700, 0.3675, 0.2883, 0.5312, 0.5783],
[0.6175, 0.4013, 0.7734, 0.2783, 0.4475, 0.1786, 0.5790, 0.5351],
[0.6154, 0.4048, 0.7100, 0.2067, 0.4338, 0.1667, 0.5413, 0.5220],
[0.6076, 0.3953, 0.8125, 0.3917, 0.3525, 0.4083, 0.5346, 0.4954]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6488, 0.3997, 0.9324, 0.4416, 0.4320, 0.3891, 0.6941, 0.6133],
[0.0758, 0.0263, 0.7338, 0.2581, 0.4481, 0.1622, 0.5430, 0.5465],
[0.7226, 0.4630, 0.7617, 0.2752, 0.3950, 0.3043, 0.5740, 0.5084],
[0.6153, 0.3819, 0.8446, 0.3057, 0.4062, 0.2827, 0.5835, 0.5420],
[0.5881, 0.3800, 0.8620, 0.4081, 0.3653, 0.3207, 0.4853, 0.5845],
[0.6604, 0.4283, 0.7799, 0.3036, 0.4455, 0.1807, 0.5666, 0.5509],
[0.5751, 0.3707, 0.7140, 0.2635, 0.4521, 0.1633, 0.5350, 0.5606],
[0.6710, 0.4345, 0.8234, 0.4160, 0.3584, 0.4337, 0.5220, 0.5283]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6350, 0.4144, 0.9250, 0.4100, 0.4125, 0.3750, 0.7129, 0.5945],
[0.0000, 0.0000, 0.7412, 0.2200, 0.4450, 0.1517, 0.5312, 0.4983],
[0.6193, 0.4034, 0.7757, 0.2347, 0.3733, 0.2919, 0.5930, 0.4926],
[0.6205, 0.4015, 0.8350, 0.2717, 0.3988, 0.2550, 0.5788, 0.5133],
[0.6184, 0.4079, 0.8350, 0.3700, 0.3675, 0.2883, 0.5312, 0.5783],
[0.6175, 0.4013, 0.7734, 0.2783, 0.4475, 0.1786, 0.5790, 0.5351],
[0.6154, 0.4048, 0.7100, 0.2067, 0.4338, 0.1667, 0.5413, 0.5220],
[0.6076, 0.3952, 0.8125, 0.3917, 0.3525, 0.4083, 0.5346, 0.4954]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05837335210526362
step: 56
running loss: 0.0010423812875939933
Train Steps: 56/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6185, 0.4079, 0.8838, 0.4617, 0.4838, 0.5650, 0.6175, 0.5850],
[0.6336, 0.4191, 0.8938, 0.5167, 0.3937, 0.3517, 0.7343, 0.5748],
[0.6271, 0.4024, 0.9000, 0.3517, 0.3700, 0.4517, 0.6931, 0.5285],
[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837],
[0.6090, 0.4045, 0.7250, 0.2100, 0.4075, 0.2300, 0.5476, 0.5663],
[0.6282, 0.4029, 0.8988, 0.3000, 0.4250, 0.4183, 0.7042, 0.5575],
[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395],
[0.6275, 0.4071, 0.8075, 0.2100, 0.4700, 0.1533, 0.6148, 0.4834]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5535, 0.3603, 0.9047, 0.4861, 0.4687, 0.5778, 0.5736, 0.5600],
[0.5951, 0.3766, 0.8869, 0.5239, 0.3845, 0.3401, 0.6707, 0.5305],
[0.6612, 0.4110, 0.8894, 0.3805, 0.3492, 0.4530, 0.6655, 0.4991],
[0.6235, 0.4039, 0.6751, 0.3450, 0.3461, 0.2827, 0.4931, 0.5618],
[0.5802, 0.3689, 0.7180, 0.2602, 0.3880, 0.2208, 0.5133, 0.5405],
[0.6408, 0.4002, 0.8874, 0.3405, 0.3949, 0.4310, 0.6676, 0.5227],
[0.5665, 0.3689, 0.8803, 0.5668, 0.3373, 0.3560, 0.5179, 0.5180],
[0.5994, 0.3896, 0.8057, 0.2313, 0.4689, 0.1243, 0.6043, 0.4866]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6184, 0.4079, 0.8838, 0.4617, 0.4837, 0.5650, 0.6175, 0.5850],
[0.6336, 0.4191, 0.8938, 0.5167, 0.3938, 0.3517, 0.7343, 0.5748],
[0.6271, 0.4024, 0.9000, 0.3517, 0.3700, 0.4517, 0.6931, 0.5285],
[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837],
[0.6090, 0.4045, 0.7250, 0.2100, 0.4075, 0.2300, 0.5476, 0.5663],
[0.6282, 0.4029, 0.8988, 0.3000, 0.4250, 0.4183, 0.7042, 0.5575],
[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395],
[0.6275, 0.4071, 0.8075, 0.2100, 0.4700, 0.1533, 0.6148, 0.4834]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.059197709371801466
step: 57
running loss: 0.0010385563047684467
Train Steps: 57/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383],
[0.6198, 0.4075, 0.8650, 0.5617, 0.4150, 0.4367, 0.5450, 0.5650],
[0.6304, 0.4029, 0.8413, 0.5217, 0.4125, 0.5617, 0.7089, 0.5679],
[0.6339, 0.4112, 0.8838, 0.5067, 0.4000, 0.5433, 0.7549, 0.5378],
[0.6311, 0.4008, 0.7935, 0.5746, 0.3900, 0.5033, 0.6955, 0.5366],
[0.6169, 0.4052, 0.8742, 0.4779, 0.4288, 0.4917, 0.5763, 0.5617],
[0.6193, 0.4050, 0.7313, 0.2433, 0.4075, 0.2117, 0.5649, 0.5656],
[0.6289, 0.4019, 0.8113, 0.5467, 0.3875, 0.5017, 0.7367, 0.5332]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6581, 0.4206, 0.8478, 0.3237, 0.3369, 0.3658, 0.5894, 0.4957],
[0.6343, 0.4063, 0.8662, 0.5718, 0.3784, 0.4163, 0.5256, 0.5283],
[0.6484, 0.4191, 0.8517, 0.5362, 0.3857, 0.5657, 0.6739, 0.5407],
[0.6023, 0.3653, 0.8979, 0.5239, 0.3713, 0.5414, 0.6793, 0.5288],
[0.6106, 0.3916, 0.8149, 0.5506, 0.3792, 0.4707, 0.6510, 0.5134],
[0.6310, 0.4057, 0.8812, 0.4616, 0.4065, 0.4958, 0.5455, 0.5182],
[0.6720, 0.4215, 0.7415, 0.2647, 0.3884, 0.1843, 0.5366, 0.5280],
[0.6216, 0.3953, 0.8320, 0.5320, 0.3525, 0.4859, 0.6587, 0.5009]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383],
[0.6198, 0.4075, 0.8650, 0.5617, 0.4150, 0.4367, 0.5450, 0.5650],
[0.6304, 0.4029, 0.8413, 0.5217, 0.4125, 0.5617, 0.7089, 0.5679],
[0.6339, 0.4112, 0.8838, 0.5067, 0.4000, 0.5433, 0.7549, 0.5378],
[0.6311, 0.4008, 0.7935, 0.5746, 0.3900, 0.5033, 0.6955, 0.5366],
[0.6169, 0.4052, 0.8742, 0.4779, 0.4288, 0.4917, 0.5763, 0.5617],
[0.6193, 0.4050, 0.7312, 0.2433, 0.4075, 0.2117, 0.5649, 0.5656],
[0.6289, 0.4019, 0.8112, 0.5467, 0.3875, 0.5017, 0.7367, 0.5332]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05994822469074279
step: 58
running loss: 0.0010335900808748756
Train Steps: 58/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6261, 0.4029, 0.8720, 0.3364, 0.3665, 0.3753, 0.6531, 0.5183],
[0.6186, 0.4060, 0.8750, 0.5050, 0.3538, 0.4367, 0.5813, 0.6083],
[0.6199, 0.4093, 0.7913, 0.2533, 0.4288, 0.2467, 0.5975, 0.5700],
[0.6250, 0.4236, 0.8638, 0.3767, 0.4050, 0.3150, 0.5649, 0.5799],
[0.6222, 0.3937, 0.8350, 0.5617, 0.4138, 0.4600, 0.5800, 0.5233],
[0.6259, 0.4133, 0.8200, 0.2317, 0.5025, 0.1533, 0.6250, 0.4947],
[0.6161, 0.4099, 0.8738, 0.4383, 0.3788, 0.5483, 0.5605, 0.5019],
[0.6184, 0.4079, 0.8350, 0.3700, 0.3675, 0.2883, 0.5312, 0.5783]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6293, 0.4008, 0.8419, 0.3521, 0.3527, 0.3801, 0.6642, 0.4922],
[0.6315, 0.4160, 0.8540, 0.4946, 0.3421, 0.4459, 0.6039, 0.5588],
[0.5937, 0.4044, 0.7634, 0.2575, 0.3904, 0.2473, 0.6448, 0.5504],
[0.6096, 0.3997, 0.8519, 0.3804, 0.3719, 0.3151, 0.6080, 0.5556],
[0.5817, 0.3542, 0.8235, 0.5666, 0.3866, 0.4522, 0.6036, 0.5165],
[0.6386, 0.4336, 0.8146, 0.2436, 0.4702, 0.1479, 0.6958, 0.4712],
[0.5744, 0.3767, 0.8577, 0.4240, 0.3493, 0.5482, 0.5868, 0.4898],
[0.6189, 0.3986, 0.8186, 0.3587, 0.3306, 0.2866, 0.5438, 0.5318]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6261, 0.4029, 0.8720, 0.3364, 0.3665, 0.3753, 0.6531, 0.5183],
[0.6186, 0.4060, 0.8750, 0.5050, 0.3537, 0.4367, 0.5813, 0.6083],
[0.6198, 0.4093, 0.7912, 0.2533, 0.4288, 0.2467, 0.5975, 0.5700],
[0.6250, 0.4236, 0.8637, 0.3767, 0.4050, 0.3150, 0.5649, 0.5799],
[0.6222, 0.3937, 0.8350, 0.5617, 0.4137, 0.4600, 0.5800, 0.5233],
[0.6259, 0.4132, 0.8200, 0.2317, 0.5025, 0.1533, 0.6250, 0.4947],
[0.6161, 0.4099, 0.8737, 0.4383, 0.3787, 0.5483, 0.5605, 0.5019],
[0.6184, 0.4079, 0.8350, 0.3700, 0.3675, 0.2883, 0.5312, 0.5783]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.060535903030540794
step: 59
running loss: 0.0010260322547549288
Train Steps: 59/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6201, 0.4102, 0.7288, 0.2417, 0.4150, 0.2383, 0.6100, 0.5500],
[0.6115, 0.4081, 0.6725, 0.2433, 0.4088, 0.1933, 0.5167, 0.5544],
[0.6286, 0.4034, 0.8191, 0.2414, 0.4262, 0.2393, 0.6365, 0.5356],
[0.6170, 0.4102, 0.7468, 0.3695, 0.3463, 0.3767, 0.5238, 0.5823],
[0.6086, 0.3940, 0.8712, 0.4783, 0.4025, 0.4900, 0.5498, 0.5390],
[0.6212, 0.4033, 0.8938, 0.4167, 0.3813, 0.4267, 0.5613, 0.5583],
[0.6204, 0.4110, 0.7913, 0.2667, 0.4062, 0.2500, 0.6225, 0.5367],
[0.6076, 0.3953, 0.8125, 0.3917, 0.3525, 0.4083, 0.5346, 0.4954]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6403, 0.4280, 0.7446, 0.2610, 0.3933, 0.2408, 0.6553, 0.5600],
[0.6543, 0.4360, 0.6836, 0.2661, 0.4094, 0.1976, 0.5499, 0.5387],
[0.6499, 0.4227, 0.7998, 0.2759, 0.4333, 0.2275, 0.6982, 0.5251],
[0.5878, 0.3954, 0.7473, 0.3859, 0.3282, 0.3870, 0.5789, 0.5672],
[0.5764, 0.3836, 0.8764, 0.5084, 0.3964, 0.4931, 0.5974, 0.5081],
[0.5695, 0.3758, 0.8933, 0.4360, 0.3550, 0.4061, 0.6115, 0.5394],
[0.6436, 0.4339, 0.7857, 0.2777, 0.3960, 0.2413, 0.6778, 0.5352],
[0.5729, 0.3854, 0.8123, 0.3846, 0.3252, 0.4032, 0.5814, 0.4950]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6201, 0.4102, 0.7287, 0.2417, 0.4150, 0.2383, 0.6100, 0.5500],
[0.6115, 0.4081, 0.6725, 0.2433, 0.4087, 0.1933, 0.5167, 0.5544],
[0.6286, 0.4034, 0.8191, 0.2414, 0.4262, 0.2393, 0.6365, 0.5356],
[0.6170, 0.4102, 0.7468, 0.3695, 0.3462, 0.3767, 0.5238, 0.5823],
[0.6086, 0.3940, 0.8712, 0.4783, 0.4025, 0.4900, 0.5498, 0.5390],
[0.6212, 0.4033, 0.8938, 0.4167, 0.3812, 0.4267, 0.5612, 0.5583],
[0.6204, 0.4110, 0.7912, 0.2667, 0.4062, 0.2500, 0.6225, 0.5367],
[0.6076, 0.3952, 0.8125, 0.3917, 0.3525, 0.4083, 0.5346, 0.4954]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.061192915483843535
step: 60
running loss: 0.0010198819247307256
Train Steps: 60/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6332, 0.4128, 0.9200, 0.3517, 0.4400, 0.3833, 0.7461, 0.5494],
[0.6250, 0.4146, 0.8838, 0.3933, 0.3588, 0.4283, 0.6162, 0.5367],
[0.6087, 0.3976, 0.8337, 0.3867, 0.3713, 0.3117, 0.5938, 0.5300],
[0.6165, 0.4106, 0.7575, 0.1733, 0.3838, 0.2650, 0.5680, 0.5116],
[0.6198, 0.4075, 0.8650, 0.5617, 0.4150, 0.4367, 0.5450, 0.5650],
[0.6229, 0.4107, 0.8137, 0.2883, 0.4750, 0.1717, 0.5813, 0.5400],
[0.6133, 0.4094, 0.8495, 0.4028, 0.3588, 0.3200, 0.5003, 0.5407],
[0.6289, 0.4081, 0.8720, 0.3487, 0.3900, 0.3183, 0.6703, 0.5376]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6098, 0.4095, 0.8948, 0.3430, 0.4369, 0.3946, 0.7409, 0.5581],
[0.5593, 0.3761, 0.8257, 0.3682, 0.3557, 0.4102, 0.6401, 0.5402],
[0.5868, 0.4028, 0.8061, 0.3714, 0.3707, 0.3365, 0.6015, 0.5382],
[0.6645, 0.4425, 0.7266, 0.1562, 0.3846, 0.2444, 0.5894, 0.5023],
[0.5956, 0.4105, 0.8264, 0.5500, 0.3945, 0.4470, 0.5775, 0.5710],
[0.6154, 0.4200, 0.7679, 0.2885, 0.4765, 0.1840, 0.6045, 0.5576],
[0.5763, 0.3963, 0.8310, 0.3714, 0.3726, 0.3122, 0.5121, 0.5635],
[0.5984, 0.3993, 0.8475, 0.3177, 0.3888, 0.2935, 0.6982, 0.5648]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6332, 0.4128, 0.9200, 0.3517, 0.4400, 0.3833, 0.7461, 0.5494],
[0.6250, 0.4146, 0.8838, 0.3933, 0.3587, 0.4283, 0.6162, 0.5367],
[0.6087, 0.3976, 0.8338, 0.3867, 0.3713, 0.3117, 0.5938, 0.5300],
[0.6165, 0.4106, 0.7575, 0.1733, 0.3837, 0.2650, 0.5680, 0.5116],
[0.6198, 0.4075, 0.8650, 0.5617, 0.4150, 0.4367, 0.5450, 0.5650],
[0.6229, 0.4107, 0.8138, 0.2883, 0.4750, 0.1717, 0.5813, 0.5400],
[0.6133, 0.4094, 0.8495, 0.4028, 0.3587, 0.3200, 0.5003, 0.5407],
[0.6289, 0.4081, 0.8720, 0.3487, 0.3900, 0.3183, 0.6703, 0.5376]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06174909329274669
step: 61
running loss: 0.0010122802179138803
Train Steps: 61/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6186, 0.4060, 0.8750, 0.5050, 0.3538, 0.4367, 0.5813, 0.6083],
[0.6090, 0.4045, 0.7250, 0.2100, 0.4075, 0.2300, 0.5476, 0.5663],
[0.6229, 0.4066, 0.8513, 0.5717, 0.4500, 0.5050, 0.6025, 0.5350],
[0.6189, 0.3911, 0.8800, 0.4917, 0.3713, 0.4800, 0.6038, 0.4833],
[0.6200, 0.4070, 0.8938, 0.4183, 0.3538, 0.4567, 0.6175, 0.5400],
[ nan, nan, 0.6688, 0.2513, 0.4113, 0.2117, 0.5193, 0.5933],
[0.6132, 0.4066, 0.7259, 0.2402, 0.3588, 0.3300, 0.6000, 0.5600],
[0.6203, 0.4056, 0.8942, 0.4086, 0.3643, 0.3617, 0.5917, 0.5482]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6732, 0.4678, 0.8815, 0.4820, 0.3907, 0.4533, 0.6017, 0.6037],
[0.6412, 0.4282, 0.7319, 0.2063, 0.4344, 0.2330, 0.5760, 0.5694],
[0.6649, 0.4414, 0.8627, 0.5376, 0.4606, 0.4971, 0.6258, 0.5521],
[0.7022, 0.4611, 0.8948, 0.4707, 0.3917, 0.5046, 0.6166, 0.4972],
[0.7338, 0.4807, 0.8952, 0.3996, 0.3814, 0.4844, 0.6488, 0.5259],
[0.0807, 0.0648, 0.6899, 0.2234, 0.4330, 0.2029, 0.5665, 0.5873],
[0.6507, 0.4482, 0.7274, 0.2220, 0.3836, 0.3474, 0.6153, 0.5847],
[0.7269, 0.4700, 0.9090, 0.4028, 0.3918, 0.3560, 0.6513, 0.5766]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6186, 0.4060, 0.8750, 0.5050, 0.3537, 0.4367, 0.5813, 0.6083],
[0.6090, 0.4045, 0.7250, 0.2100, 0.4075, 0.2300, 0.5476, 0.5663],
[0.6229, 0.4066, 0.8512, 0.5717, 0.4500, 0.5050, 0.6025, 0.5350],
[0.6189, 0.3911, 0.8800, 0.4917, 0.3713, 0.4800, 0.6037, 0.4833],
[0.6200, 0.4070, 0.8938, 0.4183, 0.3537, 0.4567, 0.6175, 0.5400],
[0.0000, 0.0000, 0.6688, 0.2513, 0.4112, 0.2117, 0.5193, 0.5933],
[0.6132, 0.4066, 0.7259, 0.2402, 0.3587, 0.3300, 0.6000, 0.5600],
[0.6203, 0.4056, 0.8942, 0.4086, 0.3643, 0.3617, 0.5917, 0.5482]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06322128738975152
step: 62
running loss: 0.0010196981837056697
Train Steps: 62/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6146, 0.4124, 0.8800, 0.4867, 0.3800, 0.4500, 0.5106, 0.5524],
[0.6279, 0.4050, 0.8025, 0.2200, 0.4313, 0.2733, 0.6820, 0.5320],
[0.6093, 0.3990, 0.8400, 0.4333, 0.3688, 0.4633, 0.5560, 0.5656],
[0.6339, 0.4112, 0.8838, 0.5067, 0.4000, 0.5433, 0.7549, 0.5378],
[0.6332, 0.4165, 0.9100, 0.3350, 0.4188, 0.3683, 0.7438, 0.5528],
[0.6280, 0.4055, 0.8600, 0.5317, 0.3800, 0.4700, 0.6275, 0.5133],
[0.6257, 0.4034, 0.8287, 0.2333, 0.3925, 0.2717, 0.6330, 0.4901],
[0.6300, 0.4102, 0.9088, 0.4433, 0.4088, 0.3067, 0.6820, 0.5540]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6324, 0.4039, 0.8685, 0.4872, 0.4011, 0.4443, 0.4893, 0.5842],
[0.6219, 0.4002, 0.7847, 0.1992, 0.4461, 0.2610, 0.6476, 0.5553],
[0.6258, 0.4004, 0.8205, 0.4090, 0.3847, 0.4614, 0.5261, 0.5988],
[0.6113, 0.3853, 0.8718, 0.4939, 0.4130, 0.5536, 0.7076, 0.5905],
[0.6323, 0.4041, 0.8950, 0.3352, 0.4317, 0.3551, 0.7193, 0.5770],
[0.6194, 0.4062, 0.8558, 0.5051, 0.3982, 0.4593, 0.6008, 0.5352],
[0.6342, 0.4045, 0.8060, 0.2035, 0.4183, 0.2695, 0.5965, 0.5183],
[0.6079, 0.3940, 0.8847, 0.4094, 0.4375, 0.3078, 0.6545, 0.5843]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6146, 0.4124, 0.8800, 0.4867, 0.3800, 0.4500, 0.5106, 0.5524],
[0.6279, 0.4050, 0.8025, 0.2200, 0.4313, 0.2733, 0.6820, 0.5320],
[0.6093, 0.3990, 0.8400, 0.4333, 0.3688, 0.4633, 0.5560, 0.5656],
[0.6339, 0.4112, 0.8838, 0.5067, 0.4000, 0.5433, 0.7549, 0.5378],
[0.6332, 0.4165, 0.9100, 0.3350, 0.4187, 0.3683, 0.7438, 0.5528],
[0.6280, 0.4055, 0.8600, 0.5317, 0.3800, 0.4700, 0.6275, 0.5133],
[0.6257, 0.4034, 0.8288, 0.2333, 0.3925, 0.2717, 0.6330, 0.4901],
[0.6300, 0.4102, 0.9087, 0.4433, 0.4087, 0.3067, 0.6820, 0.5540]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06367821450112388
step: 63
running loss: 0.0010107653095416489
Train Steps: 63/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6126, 0.4039, 0.8237, 0.3967, 0.3625, 0.3600, 0.5894, 0.6138],
[0.6218, 0.4185, 0.7338, 0.2650, 0.4625, 0.1950, 0.5687, 0.5800],
[0.6260, 0.4161, 0.9000, 0.3833, 0.4450, 0.2133, 0.6237, 0.4986],
[0.6257, 0.4034, 0.8287, 0.2333, 0.3925, 0.2717, 0.6330, 0.4901],
[0.6179, 0.4008, 0.8600, 0.4015, 0.3932, 0.2515, 0.5711, 0.5438],
[0.6197, 0.4091, 0.8800, 0.4783, 0.3538, 0.4767, 0.5950, 0.5550],
[0.6129, 0.3925, 0.8720, 0.5246, 0.4534, 0.5515, 0.6026, 0.5114],
[0.6200, 0.4071, 0.7338, 0.1917, 0.4200, 0.2450, 0.6150, 0.5517]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6023, 0.3895, 0.8220, 0.3872, 0.3741, 0.3751, 0.5697, 0.6120],
[0.5667, 0.3706, 0.7275, 0.2095, 0.4766, 0.2035, 0.5421, 0.6021],
[0.5960, 0.3922, 0.9036, 0.3543, 0.4618, 0.2125, 0.6223, 0.5303],
[0.6050, 0.3791, 0.8262, 0.2050, 0.4125, 0.2759, 0.6123, 0.5004],
[0.5788, 0.3780, 0.8298, 0.3318, 0.4147, 0.2553, 0.5634, 0.5648],
[0.5880, 0.3790, 0.8971, 0.4535, 0.3892, 0.4829, 0.5863, 0.5748],
[0.5920, 0.3777, 0.8626, 0.4950, 0.4768, 0.5564, 0.5932, 0.5270],
[0.5899, 0.3935, 0.7271, 0.1832, 0.4383, 0.2355, 0.6159, 0.5777]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6126, 0.4038, 0.8238, 0.3967, 0.3625, 0.3600, 0.5894, 0.6138],
[0.6218, 0.4185, 0.7337, 0.2650, 0.4625, 0.1950, 0.5688, 0.5800],
[0.6260, 0.4161, 0.9000, 0.3833, 0.4450, 0.2133, 0.6237, 0.4986],
[0.6257, 0.4034, 0.8288, 0.2333, 0.3925, 0.2717, 0.6330, 0.4901],
[0.6179, 0.4008, 0.8600, 0.4015, 0.3932, 0.2515, 0.5711, 0.5438],
[0.6197, 0.4091, 0.8800, 0.4783, 0.3537, 0.4767, 0.5950, 0.5550],
[0.6129, 0.3925, 0.8720, 0.5246, 0.4534, 0.5515, 0.6026, 0.5114],
[0.6200, 0.4071, 0.7337, 0.1917, 0.4200, 0.2450, 0.6150, 0.5517]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06423556891968474
step: 64
running loss: 0.001003680764370074
Train Steps: 64/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.6992, 0.2791, 0.3950, 0.2383, 0.5483, 0.5819],
[0.6182, 0.3987, 0.7878, 0.2889, 0.3699, 0.3260, 0.6086, 0.5367],
[0.6212, 0.4171, 0.7875, 0.3633, 0.3813, 0.2933, 0.5675, 0.5700],
[0.6150, 0.3949, 0.8800, 0.4033, 0.3825, 0.4900, 0.5875, 0.5483],
[0.6223, 0.3990, 0.8037, 0.2800, 0.4000, 0.2283, 0.5864, 0.5208],
[0.6265, 0.4251, 0.7113, 0.3550, 0.4375, 0.2117, 0.5587, 0.6118],
[0.6204, 0.4055, 0.8438, 0.5733, 0.4574, 0.4801, 0.5487, 0.5617],
[0.6043, 0.4022, 0.6887, 0.1983, 0.3775, 0.2483, 0.5480, 0.5136]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.0176, 0.0051, 0.7073, 0.2451, 0.3940, 0.2041, 0.5673, 0.5674],
[0.7240, 0.4591, 0.8006, 0.2585, 0.3777, 0.3049, 0.6131, 0.5358],
[0.6416, 0.4175, 0.8055, 0.3550, 0.3874, 0.3014, 0.5880, 0.5704],
[0.6756, 0.4380, 0.8862, 0.3885, 0.3845, 0.4889, 0.5990, 0.5338],
[0.6557, 0.4121, 0.8220, 0.2495, 0.4030, 0.2284, 0.5946, 0.5053],
[0.6400, 0.4365, 0.7531, 0.3356, 0.4336, 0.2066, 0.5468, 0.6130],
[0.6865, 0.4423, 0.8561, 0.5533, 0.4550, 0.4492, 0.5814, 0.5617],
[0.6215, 0.4045, 0.7008, 0.1796, 0.4043, 0.2497, 0.5549, 0.5109]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.6992, 0.2791, 0.3950, 0.2383, 0.5483, 0.5819],
[0.6182, 0.3987, 0.7878, 0.2889, 0.3699, 0.3260, 0.6086, 0.5367],
[0.6212, 0.4171, 0.7875, 0.3633, 0.3812, 0.2933, 0.5675, 0.5700],
[0.6150, 0.3949, 0.8800, 0.4033, 0.3825, 0.4900, 0.5875, 0.5483],
[0.6223, 0.3990, 0.8037, 0.2800, 0.4000, 0.2283, 0.5864, 0.5208],
[0.6265, 0.4251, 0.7113, 0.3550, 0.4375, 0.2117, 0.5587, 0.6118],
[0.6204, 0.4055, 0.8438, 0.5733, 0.4574, 0.4801, 0.5487, 0.5617],
[0.6043, 0.4022, 0.6888, 0.1983, 0.3775, 0.2483, 0.5480, 0.5136]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06490114069310948
step: 65
running loss: 0.0009984790875862998
Train Steps: 65/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6115, 0.4081, 0.6725, 0.2433, 0.4088, 0.1933, 0.5167, 0.5544],
[ nan, nan, 0.8888, 0.3100, 0.5262, 0.2817, 0.7145, 0.6003],
[0.6286, 0.4034, 0.8191, 0.2414, 0.4262, 0.2393, 0.6365, 0.5356],
[0.6208, 0.4082, 0.8538, 0.3067, 0.3588, 0.3717, 0.6112, 0.5517],
[0.6339, 0.4123, 0.8638, 0.5367, 0.4075, 0.5467, 0.7517, 0.5436],
[0.6261, 0.3987, 0.9045, 0.4208, 0.3600, 0.4633, 0.6570, 0.5162],
[0.6122, 0.4048, 0.7506, 0.3014, 0.3475, 0.3333, 0.5487, 0.5749],
[0.6082, 0.4042, 0.6975, 0.1917, 0.4100, 0.1983, 0.5502, 0.5578]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6413, 0.4297, 0.6962, 0.2717, 0.4131, 0.2019, 0.4723, 0.5475],
[0.0419, 0.0319, 0.9071, 0.3396, 0.4849, 0.2528, 0.7129, 0.5819],
[0.6728, 0.4302, 0.8161, 0.2820, 0.4344, 0.2315, 0.6006, 0.5320],
[0.6691, 0.4475, 0.8545, 0.3254, 0.3570, 0.3591, 0.5835, 0.5511],
[0.6772, 0.4555, 0.8836, 0.5338, 0.3839, 0.5459, 0.7248, 0.5521],
[0.6453, 0.4206, 0.9209, 0.4473, 0.3538, 0.4860, 0.6285, 0.5191],
[0.6039, 0.3915, 0.7655, 0.3256, 0.3388, 0.3197, 0.5228, 0.5558],
[0.5965, 0.4058, 0.7044, 0.2233, 0.4040, 0.1886, 0.5195, 0.5606]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6115, 0.4081, 0.6725, 0.2433, 0.4087, 0.1933, 0.5167, 0.5544],
[0.0000, 0.0000, 0.8888, 0.3100, 0.5263, 0.2817, 0.7145, 0.6003],
[0.6286, 0.4034, 0.8191, 0.2414, 0.4262, 0.2393, 0.6365, 0.5356],
[0.6208, 0.4082, 0.8537, 0.3067, 0.3587, 0.3717, 0.6112, 0.5517],
[0.6339, 0.4123, 0.8637, 0.5367, 0.4075, 0.5467, 0.7517, 0.5436],
[0.6261, 0.3987, 0.9045, 0.4208, 0.3600, 0.4633, 0.6570, 0.5162],
[0.6122, 0.4048, 0.7506, 0.3014, 0.3475, 0.3333, 0.5487, 0.5749],
[0.6082, 0.4042, 0.6975, 0.1917, 0.4100, 0.1983, 0.5502, 0.5578]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06546252308180556
step: 66
running loss: 0.0009918564103303872
Train Steps: 66/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6257, 0.4024, 0.8612, 0.5352, 0.4361, 0.5253, 0.6680, 0.5166],
[0.6100, 0.4016, 0.8600, 0.5067, 0.4612, 0.5233, 0.5086, 0.5519],
[0.6239, 0.4107, 0.8162, 0.2763, 0.3625, 0.3600, 0.5988, 0.5700],
[0.6179, 0.3961, 0.8347, 0.6020, 0.3887, 0.4624, 0.5714, 0.5373],
[0.6260, 0.4133, 0.8800, 0.5117, 0.3713, 0.3283, 0.6223, 0.4967],
[0.6143, 0.4034, 0.8800, 0.4833, 0.4512, 0.5367, 0.5289, 0.5097],
[0.6275, 0.4111, 0.8463, 0.2617, 0.4487, 0.1983, 0.6211, 0.4904],
[0.6282, 0.4029, 0.8988, 0.3000, 0.4250, 0.4183, 0.7042, 0.5575]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6000, 0.3890, 0.8598, 0.5231, 0.3860, 0.4836, 0.6604, 0.5219],
[0.5418, 0.3529, 0.8517, 0.5108, 0.4181, 0.4930, 0.5155, 0.5245],
[0.5073, 0.3391, 0.7839, 0.2833, 0.3466, 0.3270, 0.5728, 0.5695],
[0.6115, 0.4022, 0.8242, 0.5736, 0.3559, 0.4262, 0.5729, 0.5374],
[0.6262, 0.4260, 0.8762, 0.5047, 0.3387, 0.2864, 0.6100, 0.5022],
[0.5922, 0.3897, 0.8660, 0.4663, 0.4117, 0.4919, 0.5157, 0.4979],
[0.5938, 0.3825, 0.8493, 0.2560, 0.4352, 0.2088, 0.6199, 0.4986],
[0.4856, 0.3118, 0.8906, 0.3083, 0.3727, 0.3904, 0.6850, 0.5458]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6257, 0.4024, 0.8612, 0.5352, 0.4361, 0.5253, 0.6680, 0.5166],
[0.6100, 0.4016, 0.8600, 0.5067, 0.4613, 0.5233, 0.5086, 0.5519],
[0.6239, 0.4107, 0.8162, 0.2763, 0.3625, 0.3600, 0.5987, 0.5700],
[0.6179, 0.3961, 0.8347, 0.6020, 0.3887, 0.4624, 0.5714, 0.5373],
[0.6260, 0.4133, 0.8800, 0.5117, 0.3713, 0.3283, 0.6223, 0.4967],
[0.6143, 0.4034, 0.8800, 0.4833, 0.4512, 0.5367, 0.5289, 0.5097],
[0.6275, 0.4111, 0.8462, 0.2617, 0.4487, 0.1983, 0.6211, 0.4904],
[0.6282, 0.4029, 0.8988, 0.3000, 0.4250, 0.4183, 0.7042, 0.5575]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06678534619277343
step: 67
running loss: 0.0009967962118324393
Train Steps: 67/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6136, 0.4117, 0.8700, 0.5167, 0.4188, 0.5083, 0.5147, 0.5495],
[0.6198, 0.4105, 0.7950, 0.3267, 0.3675, 0.3767, 0.6038, 0.6167],
[0.6162, 0.3949, 0.8838, 0.4517, 0.4250, 0.5183, 0.5837, 0.5500],
[0.6207, 0.4081, 0.7662, 0.2067, 0.3962, 0.3200, 0.6312, 0.5300],
[0.6107, 0.4050, 0.8700, 0.4850, 0.4470, 0.4848, 0.5043, 0.5431],
[ nan, nan, 0.7268, 0.2333, 0.4125, 0.1933, 0.5112, 0.5383],
[0.6193, 0.4165, 0.8838, 0.4700, 0.4150, 0.4867, 0.5427, 0.5261],
[0.6099, 0.4030, 0.8638, 0.5117, 0.4983, 0.4965, 0.5086, 0.5388]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6511, 0.4257, 0.8758, 0.5555, 0.3867, 0.4742, 0.5685, 0.5145],
[0.6889, 0.4593, 0.7985, 0.3512, 0.3446, 0.3632, 0.6308, 0.5870],
[0.6273, 0.4013, 0.8833, 0.4678, 0.3919, 0.5013, 0.6203, 0.5304],
[0.5450, 0.3481, 0.7664, 0.2362, 0.3711, 0.2955, 0.6387, 0.5304],
[0.6303, 0.4170, 0.8735, 0.5181, 0.4061, 0.4715, 0.5485, 0.4984],
[0.0494, 0.0384, 0.7164, 0.2535, 0.3838, 0.1804, 0.5373, 0.5331],
[0.6281, 0.4168, 0.8878, 0.5096, 0.3740, 0.4657, 0.5807, 0.5154],
[0.6367, 0.4216, 0.8746, 0.5444, 0.4802, 0.4629, 0.5561, 0.5284]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6136, 0.4117, 0.8700, 0.5167, 0.4187, 0.5083, 0.5147, 0.5495],
[0.6198, 0.4105, 0.7950, 0.3267, 0.3675, 0.3767, 0.6037, 0.6167],
[0.6162, 0.3949, 0.8838, 0.4517, 0.4250, 0.5183, 0.5838, 0.5500],
[0.6207, 0.4081, 0.7663, 0.2067, 0.3963, 0.3200, 0.6313, 0.5300],
[0.6107, 0.4050, 0.8700, 0.4850, 0.4470, 0.4848, 0.5043, 0.5431],
[0.0000, 0.0000, 0.7268, 0.2333, 0.4125, 0.1933, 0.5113, 0.5383],
[0.6193, 0.4165, 0.8838, 0.4700, 0.4150, 0.4867, 0.5427, 0.5261],
[0.6098, 0.4030, 0.8637, 0.5117, 0.4983, 0.4965, 0.5086, 0.5388]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06771578977350146
step: 68
running loss: 0.0009958204378456097
Train Steps: 68/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6271, 0.4040, 0.9000, 0.3250, 0.4938, 0.2300, 0.7192, 0.5413],
[0.6160, 0.4093, 0.8314, 0.4417, 0.3675, 0.4583, 0.5250, 0.5808],
[0.6176, 0.4030, 0.8850, 0.4850, 0.3688, 0.4050, 0.5312, 0.5783],
[0.6236, 0.4081, 0.8575, 0.3000, 0.3713, 0.3033, 0.5550, 0.5633],
[0.6053, 0.4035, 0.6897, 0.1916, 0.4000, 0.2117, 0.5440, 0.5168],
[0.6114, 0.4018, 0.7213, 0.1967, 0.3763, 0.2700, 0.5875, 0.5533],
[0.6164, 0.4102, 0.8850, 0.4867, 0.4213, 0.5983, 0.5609, 0.5038],
[0.6201, 0.4151, 0.8588, 0.5467, 0.3700, 0.3950, 0.5637, 0.5933]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5082, 0.3207, 0.9109, 0.3394, 0.5157, 0.2867, 0.7239, 0.5230],
[0.5908, 0.3902, 0.8460, 0.4669, 0.3775, 0.4759, 0.5441, 0.5613],
[0.6483, 0.4339, 0.8936, 0.5021, 0.3721, 0.4222, 0.5393, 0.5726],
[0.5676, 0.3806, 0.8563, 0.3392, 0.3757, 0.3146, 0.5798, 0.5350],
[0.5690, 0.3795, 0.6955, 0.2171, 0.4206, 0.2327, 0.5407, 0.5215],
[0.5241, 0.3457, 0.7194, 0.2207, 0.3837, 0.2938, 0.5650, 0.5470],
[0.5168, 0.3465, 0.8857, 0.5028, 0.4674, 0.6062, 0.6085, 0.5349],
[0.6198, 0.4226, 0.8568, 0.5667, 0.3677, 0.4148, 0.5821, 0.5672]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6271, 0.4040, 0.9000, 0.3250, 0.4938, 0.2300, 0.7192, 0.5413],
[0.6160, 0.4092, 0.8314, 0.4417, 0.3675, 0.4583, 0.5250, 0.5808],
[0.6176, 0.4030, 0.8850, 0.4850, 0.3688, 0.4050, 0.5312, 0.5783],
[0.6236, 0.4081, 0.8575, 0.3000, 0.3713, 0.3033, 0.5550, 0.5633],
[0.6054, 0.4035, 0.6897, 0.1916, 0.4000, 0.2117, 0.5440, 0.5168],
[0.6114, 0.4018, 0.7212, 0.1967, 0.3762, 0.2700, 0.5875, 0.5533],
[0.6164, 0.4102, 0.8850, 0.4867, 0.4212, 0.5983, 0.5609, 0.5038],
[0.6202, 0.4151, 0.8587, 0.5467, 0.3700, 0.3950, 0.5638, 0.5933]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06889769760891795
step: 69
running loss: 0.0009985173566509848
Train Steps: 69/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459],
[0.6185, 0.4042, 0.7700, 0.2250, 0.4062, 0.2117, 0.5763, 0.5150],
[0.6199, 0.4112, 0.8475, 0.3717, 0.3550, 0.4350, 0.6063, 0.6083],
[0.6250, 0.4146, 0.8838, 0.3933, 0.3588, 0.4283, 0.6162, 0.5367],
[ nan, nan, 0.7192, 0.2346, 0.4037, 0.2050, 0.5138, 0.5650],
[0.6163, 0.4006, 0.8788, 0.4683, 0.3663, 0.4883, 0.5887, 0.5017],
[0.6223, 0.4130, 0.8100, 0.2983, 0.3525, 0.3900, 0.5694, 0.5103],
[0.6286, 0.4040, 0.8696, 0.3047, 0.3924, 0.2887, 0.6300, 0.5367]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5883, 0.3851, 0.8589, 0.3032, 0.5168, 0.2417, 0.6563, 0.5515],
[0.5297, 0.3508, 0.7547, 0.2512, 0.4262, 0.2454, 0.5404, 0.5347],
[0.6445, 0.4419, 0.8571, 0.3767, 0.3818, 0.4626, 0.6121, 0.5993],
[0.6430, 0.4185, 0.8573, 0.4084, 0.3759, 0.4354, 0.6020, 0.5308],
[0.0117, 0.0080, 0.7005, 0.2403, 0.4421, 0.2541, 0.4979, 0.5550],
[0.6239, 0.4059, 0.8724, 0.4794, 0.3975, 0.5280, 0.5794, 0.5216],
[0.6547, 0.4375, 0.7912, 0.3228, 0.3815, 0.4045, 0.5427, 0.5234],
[0.6379, 0.4056, 0.8605, 0.3202, 0.4096, 0.3092, 0.6162, 0.5334]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459],
[0.6184, 0.4042, 0.7700, 0.2250, 0.4062, 0.2117, 0.5763, 0.5150],
[0.6199, 0.4112, 0.8475, 0.3717, 0.3550, 0.4350, 0.6062, 0.6083],
[0.6250, 0.4146, 0.8838, 0.3933, 0.3587, 0.4283, 0.6162, 0.5367],
[0.0000, 0.0000, 0.7192, 0.2346, 0.4038, 0.2050, 0.5138, 0.5650],
[0.6163, 0.4006, 0.8788, 0.4683, 0.3663, 0.4883, 0.5888, 0.5017],
[0.6223, 0.4130, 0.8100, 0.2983, 0.3525, 0.3900, 0.5694, 0.5103],
[0.6286, 0.4040, 0.8696, 0.3047, 0.3924, 0.2887, 0.6300, 0.5367]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06951731926528737
step: 70
running loss: 0.0009931045609326767
Train Steps: 70/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.8213, 0.2700, 0.3775, 0.2817, 0.5425, 0.5533],
[0.6124, 0.4030, 0.8650, 0.4867, 0.4999, 0.5106, 0.5137, 0.5773],
[0.6127, 0.4084, 0.8700, 0.4467, 0.3987, 0.4317, 0.5013, 0.5471],
[0.6276, 0.4235, 0.8888, 0.5333, 0.3800, 0.3117, 0.5427, 0.6164],
[ nan, nan, 0.8625, 0.2550, 0.5487, 0.2200, 0.7335, 0.5737],
[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383],
[0.6234, 0.4023, 0.8888, 0.4633, 0.3975, 0.5767, 0.6400, 0.5183],
[0.6343, 0.4097, 0.9287, 0.4367, 0.4313, 0.3600, 0.7248, 0.5841]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.1622, 0.1066, 0.7874, 0.3014, 0.3781, 0.3310, 0.5317, 0.5481],
[0.6755, 0.4376, 0.8550, 0.4936, 0.4995, 0.5143, 0.4808, 0.5582],
[0.6905, 0.4685, 0.8566, 0.4401, 0.3896, 0.4463, 0.4683, 0.5373],
[0.7136, 0.4800, 0.8401, 0.5447, 0.4031, 0.3674, 0.5622, 0.5945],
[0.0378, 0.0286, 0.8293, 0.2527, 0.5296, 0.2630, 0.6928, 0.5580],
[0.6766, 0.4412, 0.8797, 0.4461, 0.4491, 0.5980, 0.6137, 0.5414],
[0.6949, 0.4499, 0.8717, 0.4481, 0.4151, 0.5993, 0.6216, 0.5185],
[0.6602, 0.4530, 0.9019, 0.4224, 0.4236, 0.3748, 0.6915, 0.5616]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.8213, 0.2700, 0.3775, 0.2817, 0.5425, 0.5533],
[0.6124, 0.4030, 0.8650, 0.4867, 0.4999, 0.5106, 0.5137, 0.5773],
[0.6127, 0.4084, 0.8700, 0.4467, 0.3988, 0.4317, 0.5013, 0.5471],
[0.6276, 0.4235, 0.8888, 0.5333, 0.3800, 0.3117, 0.5427, 0.6164],
[0.0000, 0.0000, 0.8625, 0.2550, 0.5487, 0.2200, 0.7335, 0.5737],
[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383],
[0.6234, 0.4023, 0.8888, 0.4633, 0.3975, 0.5767, 0.6400, 0.5183],
[0.6343, 0.4097, 0.9287, 0.4367, 0.4313, 0.3600, 0.7248, 0.5841]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07116618793224916
step: 71
running loss: 0.0010023406751021007
Train Steps: 71/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6201, 0.4082, 0.8827, 0.3715, 0.3825, 0.2712, 0.5845, 0.5412],
[0.6224, 0.4061, 0.8988, 0.4300, 0.3838, 0.4750, 0.6112, 0.5483],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3513, 0.4050, 0.6112, 0.5500],
[0.6160, 0.4086, 0.8775, 0.3983, 0.3750, 0.3783, 0.5128, 0.4882],
[0.6263, 0.4057, 0.8800, 0.3833, 0.3650, 0.3717, 0.6375, 0.4804],
[0.6260, 0.4153, 0.9000, 0.4533, 0.4025, 0.2633, 0.6223, 0.4967],
[0.6102, 0.3999, 0.8750, 0.5133, 0.3825, 0.4750, 0.5637, 0.5083],
[0.6199, 0.4071, 0.7600, 0.2117, 0.4037, 0.2767, 0.6138, 0.5550]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6020, 0.3793, 0.8858, 0.3604, 0.3895, 0.2816, 0.5661, 0.5512],
[0.5487, 0.3592, 0.8974, 0.4165, 0.3968, 0.4994, 0.6111, 0.5781],
[0.5426, 0.3551, 0.7878, 0.2664, 0.3672, 0.4156, 0.6022, 0.5935],
[0.5907, 0.3904, 0.8766, 0.3900, 0.3722, 0.4003, 0.5070, 0.5364],
[0.5848, 0.3734, 0.8911, 0.3657, 0.3688, 0.3688, 0.6141, 0.5162],
[0.5836, 0.3809, 0.8993, 0.4411, 0.4129, 0.2957, 0.6122, 0.5266],
[0.5586, 0.3550, 0.8771, 0.5170, 0.4175, 0.4976, 0.5237, 0.5390],
[0.6279, 0.4028, 0.7860, 0.2222, 0.4409, 0.3015, 0.6051, 0.5704]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6201, 0.4082, 0.8827, 0.3715, 0.3825, 0.2712, 0.5845, 0.5412],
[0.6224, 0.4061, 0.8988, 0.4300, 0.3837, 0.4750, 0.6112, 0.5483],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3512, 0.4050, 0.6112, 0.5500],
[0.6160, 0.4086, 0.8775, 0.3983, 0.3750, 0.3783, 0.5128, 0.4882],
[0.6263, 0.4057, 0.8800, 0.3833, 0.3650, 0.3717, 0.6375, 0.4804],
[0.6260, 0.4153, 0.9000, 0.4533, 0.4025, 0.2633, 0.6223, 0.4967],
[0.6102, 0.3999, 0.8750, 0.5133, 0.3825, 0.4750, 0.5638, 0.5083],
[0.6199, 0.4071, 0.7600, 0.2117, 0.4038, 0.2767, 0.6137, 0.5550]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07192522671539336
step: 72
running loss: 0.000998961482158241
Train Steps: 72/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6182, 0.4099, 0.7812, 0.3000, 0.3937, 0.2367, 0.5325, 0.5750],
[0.6222, 0.4172, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633],
[0.6224, 0.4061, 0.8988, 0.4300, 0.3838, 0.4750, 0.6112, 0.5483],
[0.6124, 0.4030, 0.8650, 0.4867, 0.4999, 0.5106, 0.5137, 0.5773],
[0.6198, 0.4075, 0.8650, 0.5617, 0.4150, 0.4367, 0.5450, 0.5650],
[0.6208, 0.4082, 0.8538, 0.3067, 0.3588, 0.3717, 0.6112, 0.5517],
[0.6132, 0.4066, 0.7259, 0.2402, 0.3588, 0.3300, 0.6000, 0.5600],
[0.6212, 0.4033, 0.8938, 0.4167, 0.3813, 0.4267, 0.5613, 0.5583]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5656, 0.3701, 0.8129, 0.3049, 0.4055, 0.2572, 0.5526, 0.5638],
[0.5737, 0.3879, 0.9114, 0.5173, 0.3807, 0.4555, 0.5800, 0.5659],
[0.5693, 0.3739, 0.9095, 0.4160, 0.3864, 0.4838, 0.6312, 0.5468],
[0.5836, 0.3736, 0.8785, 0.4841, 0.4992, 0.5042, 0.5113, 0.5590],
[0.5832, 0.3820, 0.8750, 0.5604, 0.4101, 0.4439, 0.5613, 0.5650],
[0.5447, 0.3638, 0.8757, 0.3092, 0.3734, 0.3732, 0.6159, 0.5459],
[0.5780, 0.3907, 0.7475, 0.2412, 0.3644, 0.3376, 0.6089, 0.5725],
[0.6014, 0.3843, 0.9054, 0.4120, 0.3852, 0.4092, 0.5635, 0.5452]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6182, 0.4099, 0.7812, 0.3000, 0.3938, 0.2367, 0.5325, 0.5750],
[0.6222, 0.4171, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633],
[0.6224, 0.4061, 0.8988, 0.4300, 0.3837, 0.4750, 0.6112, 0.5483],
[0.6124, 0.4030, 0.8650, 0.4867, 0.4999, 0.5106, 0.5137, 0.5773],
[0.6198, 0.4075, 0.8650, 0.5617, 0.4150, 0.4367, 0.5450, 0.5650],
[0.6208, 0.4082, 0.8537, 0.3067, 0.3587, 0.3717, 0.6112, 0.5517],
[0.6132, 0.4066, 0.7259, 0.2402, 0.3587, 0.3300, 0.6000, 0.5600],
[0.6212, 0.4033, 0.8938, 0.4167, 0.3812, 0.4267, 0.5612, 0.5583]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07242716127075255
step: 73
running loss: 0.000992152894119898
Train Steps: 73/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6199, 0.4071, 0.7600, 0.2117, 0.4037, 0.2767, 0.6138, 0.5550],
[0.6200, 0.3998, 0.8850, 0.3950, 0.3500, 0.4650, 0.6138, 0.5400],
[0.6264, 0.4248, 0.8938, 0.4183, 0.3875, 0.4100, 0.5400, 0.5350],
[0.6267, 0.4065, 0.8313, 0.2467, 0.4788, 0.1733, 0.6312, 0.5133],
[0.6169, 0.4108, 0.6821, 0.2722, 0.3825, 0.2550, 0.5550, 0.5717],
[0.6114, 0.4018, 0.7213, 0.1967, 0.3763, 0.2700, 0.5875, 0.5533],
[ nan, nan, 0.6793, 0.2110, 0.4012, 0.2167, 0.5112, 0.5583],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6857, 0.4347, 0.8096, 0.2185, 0.4308, 0.2854, 0.6269, 0.5558],
[ 0.6357, 0.4159, 0.9101, 0.4135, 0.3712, 0.4606, 0.6289, 0.5638],
[ 0.6290, 0.4377, 0.9140, 0.4249, 0.3806, 0.4106, 0.5434, 0.5583],
[ 0.5919, 0.3861, 0.8664, 0.2422, 0.4864, 0.1704, 0.6385, 0.5383],
[ 0.5907, 0.3928, 0.7141, 0.2533, 0.3866, 0.2558, 0.5609, 0.5914],
[ 0.6507, 0.4208, 0.7482, 0.1980, 0.3761, 0.2632, 0.5899, 0.5728],
[-0.0138, -0.0199, 0.7143, 0.2253, 0.4229, 0.2101, 0.5316, 0.5606],
[ 0.6328, 0.3930, 0.9018, 0.4740, 0.3764, 0.5228, 0.6135, 0.5193]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6199, 0.4071, 0.7600, 0.2117, 0.4038, 0.2767, 0.6137, 0.5550],
[0.6200, 0.3998, 0.8850, 0.3950, 0.3500, 0.4650, 0.6137, 0.5400],
[0.6264, 0.4248, 0.8938, 0.4183, 0.3875, 0.4100, 0.5400, 0.5350],
[0.6266, 0.4065, 0.8313, 0.2467, 0.4787, 0.1733, 0.6313, 0.5133],
[0.6169, 0.4108, 0.6821, 0.2722, 0.3825, 0.2550, 0.5550, 0.5717],
[0.6114, 0.4018, 0.7212, 0.1967, 0.3762, 0.2700, 0.5875, 0.5533],
[0.0000, 0.0000, 0.6793, 0.2110, 0.4013, 0.2167, 0.5113, 0.5583],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07284825743408874
step: 74
running loss: 0.0009844359112714694
Train Steps: 74/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6266, 0.4101, 0.8350, 0.2333, 0.3950, 0.2950, 0.6264, 0.4921],
[0.6212, 0.4033, 0.8938, 0.4167, 0.3813, 0.4267, 0.5613, 0.5583],
[0.6289, 0.4032, 0.8419, 0.5446, 0.4075, 0.5017, 0.6312, 0.5117],
[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383],
[0.6186, 0.4154, 0.6825, 0.2633, 0.4150, 0.2300, 0.5713, 0.5517],
[0.6260, 0.4106, 0.8025, 0.2583, 0.4550, 0.1867, 0.6281, 0.4869],
[0.6164, 0.3956, 0.8757, 0.5088, 0.4300, 0.5320, 0.6022, 0.5202],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6102, 0.3897, 0.8551, 0.2125, 0.3776, 0.2651, 0.6252, 0.5094],
[0.6052, 0.3984, 0.9014, 0.4016, 0.3618, 0.3818, 0.5351, 0.5663],
[0.6176, 0.4032, 0.8555, 0.5277, 0.3850, 0.4669, 0.6429, 0.5278],
[0.5970, 0.3958, 0.8931, 0.4394, 0.4216, 0.5530, 0.6155, 0.5644],
[0.5029, 0.3541, 0.7187, 0.2376, 0.3972, 0.2121, 0.5850, 0.5618],
[0.5635, 0.3682, 0.8465, 0.2279, 0.4235, 0.1639, 0.6123, 0.5153],
[0.5826, 0.3937, 0.8821, 0.4890, 0.4012, 0.4987, 0.5960, 0.5400],
[0.5946, 0.4059, 0.8974, 0.4093, 0.4117, 0.4826, 0.5654, 0.5658]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6266, 0.4101, 0.8350, 0.2333, 0.3950, 0.2950, 0.6264, 0.4921],
[0.6212, 0.4033, 0.8938, 0.4167, 0.3812, 0.4267, 0.5612, 0.5583],
[0.6289, 0.4031, 0.8419, 0.5446, 0.4075, 0.5017, 0.6313, 0.5117],
[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383],
[0.6186, 0.4154, 0.6825, 0.2633, 0.4150, 0.2300, 0.5713, 0.5517],
[0.6260, 0.4106, 0.8025, 0.2583, 0.4550, 0.1867, 0.6281, 0.4869],
[0.6164, 0.3956, 0.8757, 0.5088, 0.4300, 0.5320, 0.6022, 0.5202],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0736210917821154
step: 75
running loss: 0.000981614557094872
Train Steps: 75/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6271, 0.4020, 0.8375, 0.6083, 0.3925, 0.4867, 0.6037, 0.4626],
[0.6241, 0.4143, 0.8938, 0.4650, 0.4075, 0.5350, 0.6250, 0.5550],
[0.6202, 0.4079, 0.8025, 0.2500, 0.3763, 0.3217, 0.6125, 0.5533],
[0.6176, 0.4030, 0.8850, 0.4850, 0.3688, 0.4050, 0.5312, 0.5783],
[0.6129, 0.4114, 0.6950, 0.2467, 0.4050, 0.2133, 0.5363, 0.5550],
[0.6102, 0.4005, 0.8688, 0.5100, 0.4813, 0.5400, 0.5404, 0.5064],
[0.6332, 0.4118, 0.9238, 0.4267, 0.4012, 0.4733, 0.7525, 0.5436],
[0.6255, 0.4017, 0.8688, 0.3217, 0.3638, 0.3550, 0.6344, 0.4901]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6487, 0.4125, 0.8374, 0.5678, 0.3638, 0.4479, 0.6072, 0.4584],
[0.5668, 0.3660, 0.8805, 0.4362, 0.3959, 0.5112, 0.6293, 0.5503],
[0.5917, 0.3874, 0.7891, 0.2344, 0.3570, 0.2849, 0.6054, 0.5305],
[0.5951, 0.3889, 0.8693, 0.4499, 0.3407, 0.3709, 0.5155, 0.5738],
[0.6648, 0.4452, 0.7050, 0.2302, 0.3687, 0.1957, 0.5489, 0.5349],
[0.5661, 0.3774, 0.8431, 0.4716, 0.4545, 0.4936, 0.5221, 0.5009],
[0.6120, 0.4011, 0.9029, 0.4008, 0.3748, 0.4457, 0.7348, 0.5422],
[0.6432, 0.4102, 0.8724, 0.3048, 0.3337, 0.3145, 0.6142, 0.4937]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6271, 0.4020, 0.8375, 0.6083, 0.3925, 0.4867, 0.6037, 0.4626],
[0.6241, 0.4142, 0.8938, 0.4650, 0.4075, 0.5350, 0.6250, 0.5550],
[0.6202, 0.4079, 0.8025, 0.2500, 0.3762, 0.3217, 0.6125, 0.5533],
[0.6176, 0.4030, 0.8850, 0.4850, 0.3688, 0.4050, 0.5312, 0.5783],
[0.6129, 0.4114, 0.6950, 0.2467, 0.4050, 0.2133, 0.5362, 0.5550],
[0.6102, 0.4005, 0.8687, 0.5100, 0.4812, 0.5400, 0.5404, 0.5064],
[0.6332, 0.4118, 0.9237, 0.4267, 0.4013, 0.4733, 0.7525, 0.5436],
[0.6255, 0.4017, 0.8687, 0.3217, 0.3638, 0.3550, 0.6344, 0.4901]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07427169638685882
step: 76
running loss: 0.0009772591629849845
Train Steps: 76/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334],
[0.6125, 0.4035, 0.7825, 0.3100, 0.3463, 0.4900, 0.5832, 0.5637],
[0.6186, 0.4060, 0.8750, 0.5050, 0.3538, 0.4367, 0.5813, 0.6083],
[0.6275, 0.4048, 0.8488, 0.2883, 0.4463, 0.2033, 0.6321, 0.5155],
[0.6259, 0.4133, 0.8200, 0.2317, 0.5025, 0.1533, 0.6250, 0.4947],
[0.6260, 0.4214, 0.8538, 0.5500, 0.3663, 0.3767, 0.5587, 0.5983],
[0.6255, 0.4017, 0.8688, 0.3217, 0.3638, 0.3550, 0.6344, 0.4901],
[0.6216, 0.4167, 0.8588, 0.5583, 0.3975, 0.5167, 0.5775, 0.5667]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6554, 0.4331, 0.7440, 0.2241, 0.3653, 0.3191, 0.6177, 0.5078],
[0.5756, 0.3785, 0.7637, 0.3179, 0.3499, 0.4842, 0.5989, 0.5165],
[0.6087, 0.3967, 0.8508, 0.5047, 0.3572, 0.4255, 0.5865, 0.5805],
[0.6427, 0.4099, 0.8366, 0.2696, 0.4381, 0.2028, 0.6484, 0.4932],
[0.6039, 0.3984, 0.8158, 0.2238, 0.4992, 0.1749, 0.6391, 0.4684],
[0.6422, 0.4182, 0.8247, 0.5406, 0.3554, 0.3843, 0.5606, 0.5869],
[0.6590, 0.4183, 0.8570, 0.3301, 0.3534, 0.3471, 0.6224, 0.4780],
[0.6645, 0.4232, 0.8241, 0.5647, 0.3989, 0.5272, 0.6056, 0.5310]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334],
[0.6125, 0.4035, 0.7825, 0.3100, 0.3462, 0.4900, 0.5832, 0.5637],
[0.6186, 0.4060, 0.8750, 0.5050, 0.3537, 0.4367, 0.5813, 0.6083],
[0.6275, 0.4048, 0.8487, 0.2883, 0.4462, 0.2033, 0.6321, 0.5155],
[0.6259, 0.4132, 0.8200, 0.2317, 0.5025, 0.1533, 0.6250, 0.4947],
[0.6260, 0.4214, 0.8537, 0.5500, 0.3663, 0.3767, 0.5587, 0.5983],
[0.6255, 0.4017, 0.8687, 0.3217, 0.3638, 0.3550, 0.6344, 0.4901],
[0.6216, 0.4167, 0.8587, 0.5583, 0.3975, 0.5167, 0.5775, 0.5667]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07463139062747359
step: 77
running loss: 0.0009692388393178388
Train Steps: 77/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6130, 0.4072, 0.8550, 0.4567, 0.3638, 0.3667, 0.5290, 0.5892],
[0.6286, 0.4274, 0.8500, 0.4500, 0.4525, 0.2583, 0.5440, 0.6209],
[0.6214, 0.4112, 0.7838, 0.2117, 0.3650, 0.3133, 0.5675, 0.5083],
[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466],
[0.6274, 0.4270, 0.8938, 0.4967, 0.3550, 0.4283, 0.5700, 0.5733],
[0.6199, 0.4065, 0.7598, 0.2385, 0.4317, 0.1981, 0.5933, 0.5221],
[0.6266, 0.4070, 0.8712, 0.5600, 0.3713, 0.4783, 0.5775, 0.6100],
[0.6168, 0.4055, 0.7575, 0.2950, 0.4050, 0.2717, 0.5938, 0.6167]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6023, 0.3914, 0.8483, 0.4306, 0.3720, 0.3634, 0.5348, 0.5365],
[0.6116, 0.4021, 0.8334, 0.4468, 0.4512, 0.2645, 0.5703, 0.5711],
[0.6597, 0.4230, 0.7794, 0.1988, 0.3646, 0.2922, 0.6104, 0.4579],
[0.5780, 0.3787, 0.7765, 0.3631, 0.3513, 0.4057, 0.5427, 0.5166],
[0.6164, 0.3919, 0.8649, 0.4805, 0.3788, 0.4427, 0.6133, 0.5166],
[0.6889, 0.4362, 0.7362, 0.2125, 0.4312, 0.2173, 0.6049, 0.4742],
[0.5940, 0.3791, 0.8297, 0.5513, 0.3694, 0.4709, 0.6086, 0.5311],
[0.6342, 0.4165, 0.7445, 0.2720, 0.4020, 0.2731, 0.6232, 0.5852]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6130, 0.4072, 0.8550, 0.4567, 0.3638, 0.3667, 0.5290, 0.5892],
[0.6286, 0.4274, 0.8500, 0.4500, 0.4525, 0.2583, 0.5440, 0.6209],
[0.6214, 0.4112, 0.7837, 0.2117, 0.3650, 0.3133, 0.5675, 0.5083],
[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466],
[0.6274, 0.4270, 0.8938, 0.4967, 0.3550, 0.4283, 0.5700, 0.5733],
[0.6199, 0.4065, 0.7598, 0.2385, 0.4317, 0.1981, 0.5933, 0.5221],
[0.6266, 0.4070, 0.8712, 0.5600, 0.3713, 0.4783, 0.5775, 0.6100],
[0.6168, 0.4055, 0.7575, 0.2950, 0.4050, 0.2717, 0.5938, 0.6167]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07542235916480422
step: 78
running loss: 0.0009669533226256951
Train Steps: 78/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6186, 0.4013, 0.8191, 0.3188, 0.4279, 0.2060, 0.5767, 0.5411],
[0.6275, 0.4024, 0.8500, 0.5383, 0.3912, 0.4883, 0.6288, 0.5100],
[0.6226, 0.4098, 0.8912, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367],
[0.6197, 0.4091, 0.8800, 0.4783, 0.3538, 0.4767, 0.5950, 0.5550],
[0.6346, 0.4086, 0.7938, 0.5500, 0.3962, 0.4867, 0.7343, 0.5702],
[0.6201, 0.4065, 0.7300, 0.1933, 0.4075, 0.2533, 0.6162, 0.5483],
[0.6350, 0.4043, 0.8738, 0.5650, 0.3850, 0.4750, 0.6401, 0.4950],
[0.6199, 0.3952, 0.8573, 0.5374, 0.4075, 0.4687, 0.5942, 0.5377]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6322, 0.4329, 0.8176, 0.2788, 0.4258, 0.2343, 0.5572, 0.5423],
[0.6476, 0.4297, 0.8261, 0.5259, 0.4003, 0.5108, 0.5924, 0.4821],
[0.6028, 0.4122, 0.8890, 0.4161, 0.4090, 0.2621, 0.5544, 0.5396],
[0.6388, 0.4294, 0.8767, 0.4735, 0.3778, 0.4834, 0.5753, 0.5458],
[0.6263, 0.4230, 0.8026, 0.5230, 0.3972, 0.5063, 0.6677, 0.5665],
[0.6590, 0.4498, 0.7379, 0.1787, 0.4037, 0.2600, 0.6136, 0.5496],
[0.6252, 0.4112, 0.8502, 0.5726, 0.3917, 0.4984, 0.6056, 0.4986],
[0.6329, 0.4150, 0.8400, 0.5292, 0.4007, 0.4738, 0.5812, 0.5399]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6186, 0.4013, 0.8191, 0.3188, 0.4279, 0.2060, 0.5767, 0.5411],
[0.6275, 0.4024, 0.8500, 0.5383, 0.3913, 0.4883, 0.6288, 0.5100],
[0.6226, 0.4098, 0.8913, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367],
[0.6197, 0.4091, 0.8800, 0.4783, 0.3537, 0.4767, 0.5950, 0.5550],
[0.6346, 0.4086, 0.7937, 0.5500, 0.3963, 0.4867, 0.7343, 0.5702],
[0.6201, 0.4065, 0.7300, 0.1933, 0.4075, 0.2533, 0.6162, 0.5483],
[0.6350, 0.4043, 0.8737, 0.5650, 0.3850, 0.4750, 0.6401, 0.4950],
[0.6199, 0.3952, 0.8573, 0.5374, 0.4075, 0.4687, 0.5942, 0.5377]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07581857420154847
step: 79
running loss: 0.000959728787361373
Train Steps: 79/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6293, 0.4024, 0.8750, 0.5000, 0.4012, 0.5733, 0.7121, 0.5633],
[0.6276, 0.4120, 0.8738, 0.3133, 0.4225, 0.2217, 0.6203, 0.4892],
[0.6353, 0.4128, 0.9138, 0.3533, 0.4688, 0.3250, 0.7145, 0.5991],
[0.6114, 0.4018, 0.7213, 0.1967, 0.3763, 0.2700, 0.5875, 0.5533],
[0.6169, 0.4052, 0.8742, 0.4779, 0.4288, 0.4917, 0.5763, 0.5617],
[0.6299, 0.4303, 0.7963, 0.3933, 0.4850, 0.2283, 0.5480, 0.6222],
[0.6265, 0.4088, 0.8025, 0.1850, 0.4163, 0.2500, 0.6290, 0.4947],
[0.6201, 0.4050, 0.7757, 0.2234, 0.4459, 0.1798, 0.5975, 0.5426]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6582, 0.4217, 0.8559, 0.5431, 0.3977, 0.5892, 0.6823, 0.5507],
[0.5421, 0.3751, 0.8435, 0.3560, 0.4198, 0.2311, 0.5940, 0.4788],
[0.5280, 0.3593, 0.8839, 0.3768, 0.4569, 0.3085, 0.7006, 0.6056],
[0.6138, 0.4281, 0.6970, 0.2340, 0.3655, 0.2705, 0.5795, 0.5592],
[0.6089, 0.4218, 0.8466, 0.4879, 0.4248, 0.5155, 0.5631, 0.5667],
[0.6077, 0.4128, 0.7871, 0.4091, 0.4669, 0.2647, 0.5149, 0.6082],
[0.6323, 0.4149, 0.7712, 0.2223, 0.4029, 0.2477, 0.6125, 0.5030],
[0.6510, 0.4502, 0.7419, 0.2712, 0.4474, 0.1928, 0.5697, 0.5589]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6293, 0.4024, 0.8750, 0.5000, 0.4013, 0.5733, 0.7121, 0.5633],
[0.6276, 0.4120, 0.8737, 0.3133, 0.4225, 0.2217, 0.6203, 0.4892],
[0.6353, 0.4128, 0.9137, 0.3533, 0.4688, 0.3250, 0.7145, 0.5991],
[0.6114, 0.4018, 0.7212, 0.1967, 0.3762, 0.2700, 0.5875, 0.5533],
[0.6169, 0.4052, 0.8742, 0.4779, 0.4288, 0.4917, 0.5763, 0.5617],
[0.6299, 0.4303, 0.7962, 0.3933, 0.4850, 0.2283, 0.5480, 0.6222],
[0.6265, 0.4088, 0.8025, 0.1850, 0.4162, 0.2500, 0.6290, 0.4947],
[0.6201, 0.4050, 0.7757, 0.2234, 0.4459, 0.1798, 0.5975, 0.5426]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07664816980832256
step: 80
running loss: 0.000958102122604032
Train Steps: 80/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6350, 0.4144, 0.9250, 0.4100, 0.4125, 0.3750, 0.7129, 0.5945],
[0.6339, 0.4081, 0.8425, 0.5417, 0.3850, 0.4833, 0.7335, 0.5760],
[0.6201, 0.4036, 0.8596, 0.3850, 0.3492, 0.3785, 0.5978, 0.5131],
[0.6132, 0.4118, 0.8200, 0.3633, 0.3563, 0.5400, 0.5787, 0.5136],
[0.6113, 0.4088, 0.6859, 0.2208, 0.4363, 0.1700, 0.5188, 0.5533],
[0.6070, 0.3979, 0.8575, 0.5083, 0.4350, 0.5400, 0.5180, 0.5466],
[0.6364, 0.4144, 0.8625, 0.3083, 0.4913, 0.2000, 0.6448, 0.5274],
[0.6166, 0.4008, 0.8563, 0.5667, 0.4388, 0.4933, 0.5575, 0.5567]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6689, 0.4372, 0.9093, 0.4226, 0.4324, 0.3600, 0.7135, 0.6139],
[0.6498, 0.4387, 0.8441, 0.5649, 0.3814, 0.4846, 0.7158, 0.5975],
[0.6646, 0.4442, 0.8671, 0.4075, 0.3482, 0.3767, 0.5877, 0.5507],
[0.6307, 0.4162, 0.8190, 0.3802, 0.3695, 0.5152, 0.5928, 0.5423],
[0.6437, 0.4392, 0.6882, 0.2361, 0.4377, 0.1644, 0.5355, 0.5713],
[0.6287, 0.4257, 0.8331, 0.5270, 0.4388, 0.5462, 0.5233, 0.5611],
[0.6295, 0.4227, 0.8565, 0.3296, 0.4674, 0.2036, 0.6249, 0.5424],
[0.5897, 0.3983, 0.8491, 0.5866, 0.4412, 0.4888, 0.5794, 0.5939]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6350, 0.4144, 0.9250, 0.4100, 0.4125, 0.3750, 0.7129, 0.5945],
[0.6339, 0.4081, 0.8425, 0.5417, 0.3850, 0.4833, 0.7335, 0.5760],
[0.6201, 0.4036, 0.8596, 0.3850, 0.3492, 0.3785, 0.5978, 0.5131],
[0.6132, 0.4118, 0.8200, 0.3633, 0.3562, 0.5400, 0.5787, 0.5136],
[0.6113, 0.4088, 0.6859, 0.2208, 0.4363, 0.1700, 0.5188, 0.5533],
[0.6070, 0.3979, 0.8575, 0.5083, 0.4350, 0.5400, 0.5180, 0.5466],
[0.6364, 0.4144, 0.8625, 0.3083, 0.4913, 0.2000, 0.6448, 0.5274],
[0.6166, 0.4008, 0.8562, 0.5667, 0.4387, 0.4933, 0.5575, 0.5567]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07702205292298459
step: 81
running loss: 0.0009508895422590689
Train Steps: 81/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6263, 0.4030, 0.9000, 0.4767, 0.3800, 0.5167, 0.6415, 0.4771],
[ nan, nan, 0.9050, 0.3500, 0.5138, 0.2300, 0.7359, 0.5702],
[0.6226, 0.4098, 0.8912, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367],
[0.6339, 0.4159, 0.8400, 0.5617, 0.3825, 0.4150, 0.7343, 0.5748],
[0.6286, 0.4086, 0.8408, 0.2801, 0.4163, 0.2800, 0.6725, 0.5393],
[0.6168, 0.4029, 0.8523, 0.3417, 0.3588, 0.5000, 0.6125, 0.5400],
[0.6250, 0.4106, 0.8700, 0.3717, 0.3588, 0.4967, 0.6038, 0.5167],
[ nan, nan, 0.7525, 0.2291, 0.3838, 0.3017, 0.6050, 0.5667]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7931, 0.5002, 0.9014, 0.4972, 0.3986, 0.5360, 0.6156, 0.5124],
[0.2200, 0.1395, 0.9035, 0.3557, 0.5113, 0.2155, 0.6968, 0.6014],
[0.7179, 0.4789, 0.8840, 0.4460, 0.4199, 0.2446, 0.5541, 0.5812],
[0.7196, 0.4776, 0.8282, 0.5575, 0.4153, 0.4038, 0.6555, 0.5852],
[0.7195, 0.4702, 0.8308, 0.2887, 0.4164, 0.2733, 0.6438, 0.5775],
[0.7504, 0.4889, 0.8567, 0.3720, 0.3693, 0.4779, 0.6205, 0.5722],
[0.7627, 0.4916, 0.8883, 0.4007, 0.3814, 0.4807, 0.6480, 0.5714],
[0.1268, 0.0987, 0.7463, 0.2425, 0.3991, 0.2815, 0.5947, 0.6059]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6263, 0.4029, 0.9000, 0.4767, 0.3800, 0.5167, 0.6415, 0.4771],
[0.0000, 0.0000, 0.9050, 0.3500, 0.5138, 0.2300, 0.7359, 0.5702],
[0.6226, 0.4098, 0.8913, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367],
[0.6339, 0.4159, 0.8400, 0.5617, 0.3825, 0.4150, 0.7343, 0.5748],
[0.6286, 0.4086, 0.8408, 0.2801, 0.4162, 0.2800, 0.6725, 0.5393],
[0.6168, 0.4029, 0.8523, 0.3417, 0.3587, 0.5000, 0.6125, 0.5400],
[0.6250, 0.4105, 0.8700, 0.3717, 0.3587, 0.4967, 0.6037, 0.5167],
[0.0000, 0.0000, 0.7525, 0.2291, 0.3837, 0.3017, 0.6050, 0.5667]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0039, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0039, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.08094305740087293
step: 82
running loss: 0.0009871104561082066
Train Steps: 82/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6182, 0.4099, 0.7812, 0.3000, 0.3937, 0.2367, 0.5325, 0.5750],
[0.6224, 0.3964, 0.8225, 0.5717, 0.4150, 0.4617, 0.5775, 0.5267],
[0.6307, 0.3998, 0.8500, 0.5233, 0.3850, 0.5050, 0.7446, 0.5320],
[0.6333, 0.4037, 0.8638, 0.5733, 0.4012, 0.4717, 0.6369, 0.4938],
[0.6198, 0.4105, 0.7950, 0.3267, 0.3675, 0.3767, 0.6038, 0.6167],
[ nan, nan, 0.8037, 0.2483, 0.3975, 0.2517, 0.5575, 0.5600],
[0.6296, 0.3989, 0.9000, 0.4150, 0.3613, 0.3867, 0.6400, 0.5100],
[0.6280, 0.4055, 0.8600, 0.5317, 0.3800, 0.4700, 0.6275, 0.5133]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6775, 0.4409, 0.8038, 0.2923, 0.4102, 0.2379, 0.5431, 0.5955],
[0.7007, 0.4416, 0.8367, 0.5775, 0.4175, 0.4591, 0.5865, 0.5586],
[0.6926, 0.4455, 0.8810, 0.4902, 0.4014, 0.5026, 0.7283, 0.5516],
[0.6904, 0.4220, 0.8995, 0.5639, 0.4153, 0.4616, 0.6263, 0.5324],
[0.6587, 0.4276, 0.8119, 0.3081, 0.3876, 0.3840, 0.6036, 0.6393],
[0.1182, 0.0820, 0.8003, 0.2678, 0.4247, 0.2427, 0.5935, 0.6027],
[0.6364, 0.4076, 0.9295, 0.4042, 0.3742, 0.3750, 0.6706, 0.5503],
[0.6407, 0.4136, 0.8899, 0.5239, 0.3889, 0.4709, 0.6358, 0.5303]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6182, 0.4099, 0.7812, 0.3000, 0.3938, 0.2367, 0.5325, 0.5750],
[0.6224, 0.3964, 0.8225, 0.5717, 0.4150, 0.4617, 0.5775, 0.5267],
[0.6307, 0.3998, 0.8500, 0.5233, 0.3850, 0.5050, 0.7446, 0.5320],
[0.6334, 0.4037, 0.8637, 0.5733, 0.4013, 0.4717, 0.6369, 0.4938],
[0.6198, 0.4105, 0.7950, 0.3267, 0.3675, 0.3767, 0.6037, 0.6167],
[0.0000, 0.0000, 0.8037, 0.2483, 0.3975, 0.2517, 0.5575, 0.5600],
[0.6296, 0.3989, 0.9000, 0.4150, 0.3613, 0.3867, 0.6400, 0.5100],
[0.6280, 0.4055, 0.8600, 0.5317, 0.3800, 0.4700, 0.6275, 0.5133]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0819609404716175
step: 83
running loss: 0.0009874812105014157
Train Steps: 83/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6283, 0.4283, 0.7477, 0.3542, 0.5125, 0.1917, 0.5500, 0.6167],
[0.6179, 0.4082, 0.6688, 0.2667, 0.3588, 0.3317, 0.5750, 0.5783],
[0.6161, 0.4099, 0.8738, 0.4383, 0.3788, 0.5483, 0.5605, 0.5019],
[0.6267, 0.4094, 0.8712, 0.3083, 0.4400, 0.2267, 0.6250, 0.5200],
[0.6200, 0.4059, 0.8700, 0.4900, 0.4163, 0.5000, 0.6162, 0.5467],
[0.6332, 0.4165, 0.9100, 0.3350, 0.4188, 0.3683, 0.7438, 0.5528],
[0.6100, 0.4016, 0.8600, 0.5067, 0.4612, 0.5233, 0.5086, 0.5519],
[0.6073, 0.3932, 0.8363, 0.5817, 0.4425, 0.5117, 0.5204, 0.4817]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6161, 0.3941, 0.7660, 0.3402, 0.4910, 0.1819, 0.5801, 0.6160],
[0.6550, 0.4167, 0.7156, 0.2698, 0.3404, 0.3261, 0.6140, 0.5784],
[0.5628, 0.3644, 0.9160, 0.4328, 0.3729, 0.5294, 0.5967, 0.5198],
[0.5325, 0.3280, 0.8888, 0.3057, 0.4375, 0.2048, 0.6688, 0.5315],
[0.5760, 0.3584, 0.9019, 0.4981, 0.4276, 0.5066, 0.6589, 0.5600],
[0.6087, 0.3825, 0.9356, 0.3558, 0.4076, 0.3620, 0.7728, 0.5539],
[0.5557, 0.3471, 0.8858, 0.5116, 0.4644, 0.5172, 0.5522, 0.5472],
[0.5297, 0.3323, 0.8645, 0.5822, 0.4484, 0.5120, 0.5551, 0.5111]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6283, 0.4283, 0.7477, 0.3542, 0.5125, 0.1917, 0.5500, 0.6167],
[0.6179, 0.4082, 0.6687, 0.2667, 0.3587, 0.3317, 0.5750, 0.5783],
[0.6161, 0.4099, 0.8737, 0.4383, 0.3787, 0.5483, 0.5605, 0.5019],
[0.6267, 0.4094, 0.8712, 0.3083, 0.4400, 0.2267, 0.6250, 0.5200],
[0.6199, 0.4059, 0.8700, 0.4900, 0.4162, 0.5000, 0.6162, 0.5467],
[0.6332, 0.4165, 0.9100, 0.3350, 0.4187, 0.3683, 0.7438, 0.5528],
[0.6100, 0.4016, 0.8600, 0.5067, 0.4613, 0.5233, 0.5086, 0.5519],
[0.6073, 0.3932, 0.8363, 0.5817, 0.4425, 0.5117, 0.5204, 0.4817]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.08303061101469211
step: 84
running loss: 0.0009884596549368109
Train Steps: 84/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6200, 0.3998, 0.8850, 0.3950, 0.3500, 0.4650, 0.6138, 0.5400],
[0.6336, 0.4191, 0.8938, 0.5167, 0.3937, 0.3517, 0.7343, 0.5748],
[0.6302, 0.4007, 0.8850, 0.5500, 0.3613, 0.4517, 0.6335, 0.5012],
[0.6339, 0.4112, 0.8838, 0.5067, 0.4000, 0.5433, 0.7549, 0.5378],
[0.6364, 0.4154, 0.8938, 0.3717, 0.4500, 0.2583, 0.6448, 0.5285],
[0.6307, 0.4045, 0.8025, 0.5833, 0.3775, 0.4867, 0.6892, 0.5459],
[0.6219, 0.4114, 0.8175, 0.2817, 0.3925, 0.2783, 0.5900, 0.5350],
[0.6201, 0.4151, 0.8588, 0.5467, 0.3700, 0.3950, 0.5637, 0.5933]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5600, 0.3587, 0.8868, 0.3793, 0.3792, 0.4846, 0.6134, 0.5291],
[0.6271, 0.4055, 0.9044, 0.4859, 0.4086, 0.3777, 0.7089, 0.5524],
[0.5926, 0.3717, 0.8923, 0.5424, 0.3704, 0.4701, 0.6231, 0.5157],
[0.6262, 0.3905, 0.9014, 0.4869, 0.3972, 0.5699, 0.7311, 0.5323],
[0.5637, 0.3538, 0.9013, 0.3600, 0.4607, 0.2612, 0.6273, 0.5327],
[0.5475, 0.3581, 0.8491, 0.5177, 0.4012, 0.4949, 0.6715, 0.5227],
[0.4972, 0.3167, 0.8166, 0.2413, 0.4067, 0.2753, 0.5941, 0.5354],
[0.5164, 0.3416, 0.8693, 0.5236, 0.3773, 0.4062, 0.5634, 0.5922]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6200, 0.3998, 0.8850, 0.3950, 0.3500, 0.4650, 0.6137, 0.5400],
[0.6336, 0.4191, 0.8938, 0.5167, 0.3938, 0.3517, 0.7343, 0.5748],
[0.6302, 0.4007, 0.8850, 0.5500, 0.3613, 0.4517, 0.6335, 0.5012],
[0.6339, 0.4112, 0.8838, 0.5067, 0.4000, 0.5433, 0.7549, 0.5378],
[0.6364, 0.4154, 0.8938, 0.3717, 0.4500, 0.2583, 0.6448, 0.5285],
[0.6307, 0.4045, 0.8025, 0.5833, 0.3775, 0.4867, 0.6892, 0.5459],
[0.6219, 0.4114, 0.8175, 0.2817, 0.3925, 0.2783, 0.5900, 0.5350],
[0.6202, 0.4151, 0.8587, 0.5467, 0.3700, 0.3950, 0.5638, 0.5933]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.08437361448886804
step: 85
running loss: 0.0009926307586925651
Train Steps: 85/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.6488, 0.1817, 0.4325, 0.1867, 0.5475, 0.5733],
[0.6211, 0.4069, 0.8750, 0.5117, 0.4150, 0.4900, 0.5875, 0.5167],
[0.6271, 0.4024, 0.9000, 0.3517, 0.3700, 0.4517, 0.6931, 0.5285],
[ nan, nan, 0.6688, 0.2513, 0.4113, 0.2117, 0.5193, 0.5933],
[0.6196, 0.4094, 0.7562, 0.2817, 0.3937, 0.3183, 0.6013, 0.6183],
[0.6222, 0.4169, 0.8638, 0.5650, 0.4313, 0.4783, 0.5637, 0.5633],
[0.6185, 0.4042, 0.7700, 0.2250, 0.4062, 0.2117, 0.5763, 0.5150],
[0.6176, 0.3911, 0.8738, 0.4217, 0.3488, 0.4033, 0.6025, 0.4817]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.0196, 0.0066, 0.7102, 0.2163, 0.4524, 0.2058, 0.6032, 0.5641],
[0.6906, 0.4361, 0.8928, 0.5351, 0.4137, 0.5438, 0.6143, 0.5024],
[0.6659, 0.4039, 0.9054, 0.3828, 0.3644, 0.4686, 0.7225, 0.4885],
[0.0653, 0.0219, 0.6876, 0.2563, 0.4154, 0.2180, 0.5575, 0.5544],
[0.6370, 0.3989, 0.7716, 0.3058, 0.3992, 0.3338, 0.6395, 0.5891],
[0.6990, 0.4554, 0.8908, 0.5944, 0.4268, 0.5075, 0.5973, 0.5411],
[0.6624, 0.4194, 0.7643, 0.2401, 0.4091, 0.2334, 0.6098, 0.5052],
[0.6629, 0.4042, 0.8942, 0.4275, 0.3569, 0.4162, 0.6152, 0.4653]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.6488, 0.1817, 0.4325, 0.1867, 0.5475, 0.5733],
[0.6211, 0.4069, 0.8750, 0.5117, 0.4150, 0.4900, 0.5875, 0.5167],
[0.6271, 0.4024, 0.9000, 0.3517, 0.3700, 0.4517, 0.6931, 0.5285],
[0.0000, 0.0000, 0.6688, 0.2513, 0.4112, 0.2117, 0.5193, 0.5933],
[0.6196, 0.4094, 0.7563, 0.2817, 0.3938, 0.3183, 0.6012, 0.6183],
[0.6222, 0.4169, 0.8637, 0.5650, 0.4313, 0.4783, 0.5638, 0.5633],
[0.6184, 0.4042, 0.7700, 0.2250, 0.4062, 0.2117, 0.5763, 0.5150],
[0.6176, 0.3911, 0.8737, 0.4217, 0.3487, 0.4033, 0.6025, 0.4817]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.08524726060568355
step: 86
running loss: 0.0009912472163451575
Train Steps: 86/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6300, 0.4102, 0.9088, 0.4433, 0.4088, 0.3067, 0.6820, 0.5540],
[0.6273, 0.4105, 0.8988, 0.4517, 0.3912, 0.2550, 0.5894, 0.4811],
[0.6093, 0.3990, 0.8400, 0.4333, 0.3688, 0.4633, 0.5560, 0.5656],
[0.6042, 0.3990, 0.6831, 0.2875, 0.3500, 0.3133, 0.5143, 0.5510],
[0.6102, 0.4005, 0.8688, 0.5100, 0.4813, 0.5400, 0.5404, 0.5064],
[0.6133, 0.4066, 0.6787, 0.2617, 0.3800, 0.2433, 0.5147, 0.5358],
[0.6126, 0.3954, 0.8538, 0.4983, 0.4250, 0.4700, 0.5355, 0.5350],
[0.6179, 0.3961, 0.8347, 0.6020, 0.3887, 0.4624, 0.5714, 0.5373]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5647, 0.3489, 0.9124, 0.4385, 0.4083, 0.3114, 0.7018, 0.5291],
[0.5665, 0.3577, 0.9090, 0.4379, 0.3979, 0.2554, 0.6149, 0.4734],
[0.5564, 0.3416, 0.8504, 0.4353, 0.3480, 0.4655, 0.5663, 0.5339],
[0.4692, 0.2868, 0.6970, 0.2790, 0.3601, 0.3093, 0.5470, 0.5174],
[0.5477, 0.3552, 0.8623, 0.5110, 0.4692, 0.5417, 0.5568, 0.4848],
[0.5594, 0.3586, 0.6936, 0.2703, 0.3643, 0.2353, 0.5577, 0.4833],
[0.6098, 0.3628, 0.8656, 0.5068, 0.4168, 0.4914, 0.5540, 0.5095],
[0.5030, 0.3005, 0.8339, 0.5956, 0.3856, 0.4719, 0.5939, 0.5110]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6300, 0.4102, 0.9087, 0.4433, 0.4087, 0.3067, 0.6820, 0.5540],
[0.6273, 0.4105, 0.8988, 0.4517, 0.3913, 0.2550, 0.5894, 0.4811],
[0.6093, 0.3990, 0.8400, 0.4333, 0.3688, 0.4633, 0.5560, 0.5656],
[0.6042, 0.3990, 0.6831, 0.2875, 0.3500, 0.3133, 0.5143, 0.5510],
[0.6102, 0.4005, 0.8687, 0.5100, 0.4812, 0.5400, 0.5404, 0.5064],
[0.6133, 0.4065, 0.6787, 0.2617, 0.3800, 0.2433, 0.5147, 0.5358],
[0.6126, 0.3954, 0.8537, 0.4983, 0.4250, 0.4700, 0.5355, 0.5350],
[0.6179, 0.3961, 0.8347, 0.6020, 0.3887, 0.4624, 0.5714, 0.5373]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.08683439713786356
step: 87
running loss: 0.000998096518826018
Train Steps: 87/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758],
[0.6198, 0.4115, 0.7762, 0.2717, 0.3713, 0.3200, 0.5837, 0.5683],
[0.6104, 0.4029, 0.8738, 0.4900, 0.4088, 0.4533, 0.5070, 0.5510],
[0.6269, 0.4073, 0.8900, 0.4933, 0.3625, 0.4183, 0.6288, 0.5150],
[0.6284, 0.4029, 0.8838, 0.3783, 0.3975, 0.2850, 0.6335, 0.5090],
[0.6256, 0.4199, 0.8638, 0.5800, 0.3987, 0.4383, 0.5600, 0.5950],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3788, 0.4900, 0.7121, 0.5864],
[0.6308, 0.3990, 0.8688, 0.5183, 0.3950, 0.4983, 0.6388, 0.5133]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5745, 0.3609, 0.8605, 0.4861, 0.3773, 0.5457, 0.6321, 0.4751],
[0.6006, 0.3970, 0.7590, 0.2772, 0.3567, 0.3082, 0.5580, 0.5534],
[0.5465, 0.3792, 0.8374, 0.4923, 0.3945, 0.4651, 0.4942, 0.5230],
[0.5758, 0.3915, 0.8660, 0.4992, 0.3439, 0.4264, 0.6091, 0.4961],
[0.5833, 0.3887, 0.8603, 0.3826, 0.3814, 0.2886, 0.6262, 0.4685],
[0.5718, 0.3936, 0.8292, 0.5865, 0.3843, 0.4386, 0.5741, 0.5793],
[0.5968, 0.3960, 0.8556, 0.5090, 0.3664, 0.4894, 0.6865, 0.5578],
[0.5435, 0.3496, 0.8422, 0.5232, 0.3791, 0.5010, 0.6271, 0.4993]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758],
[0.6198, 0.4115, 0.7763, 0.2717, 0.3713, 0.3200, 0.5838, 0.5683],
[0.6104, 0.4029, 0.8737, 0.4900, 0.4087, 0.4533, 0.5070, 0.5510],
[0.6269, 0.4073, 0.8900, 0.4933, 0.3625, 0.4183, 0.6288, 0.5150],
[0.6284, 0.4029, 0.8838, 0.3783, 0.3975, 0.2850, 0.6335, 0.5090],
[0.6256, 0.4199, 0.8637, 0.5800, 0.3988, 0.4383, 0.5600, 0.5950],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3787, 0.4900, 0.7121, 0.5864],
[0.6308, 0.3990, 0.8687, 0.5183, 0.3950, 0.4983, 0.6388, 0.5133]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0875556360988412
step: 88
running loss: 0.0009949504102141045
Train Steps: 88/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6206, 0.4123, 0.7175, 0.2400, 0.3887, 0.2933, 0.6225, 0.5750],
[0.6117, 0.4019, 0.8538, 0.4067, 0.3513, 0.3583, 0.5663, 0.5133],
[0.6226, 0.4125, 0.8800, 0.4900, 0.4512, 0.5600, 0.6275, 0.5517],
[0.6284, 0.4029, 0.8838, 0.3783, 0.3975, 0.2850, 0.6335, 0.5090],
[0.6098, 0.3991, 0.8638, 0.4717, 0.4263, 0.4967, 0.5212, 0.5650],
[0.6277, 0.4029, 0.8250, 0.2433, 0.4325, 0.2100, 0.6366, 0.5207],
[0.6275, 0.4111, 0.8463, 0.2617, 0.4487, 0.1983, 0.6211, 0.4904],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4012, 0.4633, 0.5338, 0.5767]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5855, 0.3954, 0.6825, 0.2724, 0.3647, 0.2915, 0.5967, 0.5634],
[0.5919, 0.3891, 0.8399, 0.4297, 0.3236, 0.3514, 0.5381, 0.5206],
[0.5814, 0.3986, 0.8560, 0.4971, 0.4336, 0.5638, 0.6024, 0.5450],
[0.5850, 0.3971, 0.8536, 0.3945, 0.3774, 0.2862, 0.6237, 0.4889],
[0.5602, 0.3785, 0.8340, 0.4917, 0.4045, 0.5007, 0.5293, 0.5463],
[0.5367, 0.3529, 0.7761, 0.2756, 0.4170, 0.2268, 0.6246, 0.5053],
[0.6315, 0.4231, 0.8110, 0.2677, 0.4568, 0.2181, 0.6119, 0.4950],
[0.5476, 0.3665, 0.8404, 0.5231, 0.3812, 0.4663, 0.5407, 0.5821]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6206, 0.4123, 0.7175, 0.2400, 0.3887, 0.2933, 0.6225, 0.5750],
[0.6116, 0.4019, 0.8537, 0.4067, 0.3512, 0.3583, 0.5663, 0.5133],
[0.6226, 0.4125, 0.8800, 0.4900, 0.4512, 0.5600, 0.6275, 0.5517],
[0.6284, 0.4029, 0.8838, 0.3783, 0.3975, 0.2850, 0.6335, 0.5090],
[0.6098, 0.3991, 0.8637, 0.4717, 0.4263, 0.4967, 0.5213, 0.5650],
[0.6277, 0.4029, 0.8250, 0.2433, 0.4325, 0.2100, 0.6366, 0.5207],
[0.6275, 0.4111, 0.8462, 0.2617, 0.4487, 0.1983, 0.6211, 0.4904],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4013, 0.4633, 0.5337, 0.5767]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.08827467539231293
step: 89
running loss: 0.000991850285306887
Train Steps: 89/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6307, 0.3998, 0.8500, 0.5233, 0.3850, 0.5050, 0.7446, 0.5320],
[0.6182, 0.3987, 0.7878, 0.2889, 0.3699, 0.3260, 0.6086, 0.5367],
[0.6284, 0.4093, 0.8900, 0.4700, 0.3650, 0.3850, 0.6212, 0.5167],
[0.6038, 0.3946, 0.8413, 0.4883, 0.3563, 0.4550, 0.5266, 0.4693],
[0.6196, 0.4068, 0.7645, 0.2234, 0.4575, 0.1737, 0.5926, 0.5284],
[0.6185, 0.4042, 0.7700, 0.2250, 0.4062, 0.2117, 0.5763, 0.5150],
[0.6276, 0.4095, 0.8237, 0.2250, 0.4662, 0.1783, 0.6171, 0.4869],
[0.6205, 0.4004, 0.8938, 0.4883, 0.3663, 0.5000, 0.6357, 0.4947]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5839, 0.3950, 0.8307, 0.5161, 0.3785, 0.4998, 0.6994, 0.5390],
[0.5677, 0.3877, 0.7637, 0.2760, 0.3595, 0.3222, 0.5726, 0.5647],
[0.6210, 0.4307, 0.8743, 0.4635, 0.3645, 0.3866, 0.5997, 0.5272],
[0.5621, 0.3761, 0.8384, 0.4889, 0.3639, 0.4513, 0.4973, 0.5228],
[0.5775, 0.3924, 0.7376, 0.2344, 0.4520, 0.1773, 0.5464, 0.5549],
[0.5597, 0.3808, 0.7354, 0.2337, 0.4123, 0.2073, 0.5410, 0.5483],
[0.6110, 0.4146, 0.8000, 0.2184, 0.4810, 0.1910, 0.5711, 0.5012],
[0.5807, 0.3846, 0.8845, 0.4835, 0.3652, 0.4919, 0.6218, 0.5216]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6307, 0.3998, 0.8500, 0.5233, 0.3850, 0.5050, 0.7446, 0.5320],
[0.6182, 0.3987, 0.7878, 0.2889, 0.3699, 0.3260, 0.6086, 0.5367],
[0.6284, 0.4092, 0.8900, 0.4700, 0.3650, 0.3850, 0.6212, 0.5167],
[0.6038, 0.3946, 0.8413, 0.4883, 0.3562, 0.4550, 0.5266, 0.4693],
[0.6196, 0.4068, 0.7645, 0.2234, 0.4575, 0.1737, 0.5926, 0.5284],
[0.6184, 0.4042, 0.7700, 0.2250, 0.4062, 0.2117, 0.5763, 0.5150],
[0.6276, 0.4095, 0.8238, 0.2250, 0.4663, 0.1783, 0.6171, 0.4869],
[0.6205, 0.4004, 0.8938, 0.4883, 0.3663, 0.5000, 0.6357, 0.4947]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.08886227456969209
step: 90
running loss: 0.000987358606329912
Valid Steps: 10/10 Loss: nan 9.3309
--------------------------------------------------
Epoch: 6 Train Loss: 0.0010 Valid Loss: nan
--------------------------------------------------
size of train loader is: 90
torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6284, 0.4029, 0.8838, 0.3783, 0.3975, 0.2850, 0.6335, 0.5090],
[0.6275, 0.4081, 0.8063, 0.2017, 0.4825, 0.1583, 0.6156, 0.4869],
[0.6145, 0.4007, 0.8775, 0.4533, 0.4562, 0.5533, 0.6088, 0.5533],
[ nan, nan, 0.6512, 0.1717, 0.4100, 0.1983, 0.5253, 0.5240],
[0.6200, 0.3913, 0.8788, 0.5217, 0.4075, 0.5100, 0.6060, 0.4913],
[0.6196, 0.4094, 0.7562, 0.2817, 0.3937, 0.3183, 0.6013, 0.6183],
[0.6277, 0.4083, 0.8350, 0.2717, 0.4562, 0.1800, 0.5918, 0.4878],
[0.6193, 0.4165, 0.8838, 0.4700, 0.4150, 0.4867, 0.5427, 0.5261]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6453, 0.4394, 0.8678, 0.3829, 0.3862, 0.2651, 0.6238, 0.5143],
[ 0.6626, 0.4516, 0.7857, 0.2041, 0.4790, 0.1266, 0.6018, 0.5084],
[ 0.5989, 0.4005, 0.8487, 0.4353, 0.4402, 0.5201, 0.5815, 0.5510],
[-0.0018, -0.0064, 0.6547, 0.1877, 0.4051, 0.1848, 0.5274, 0.5574],
[ 0.6113, 0.3946, 0.8557, 0.5194, 0.3778, 0.4875, 0.5826, 0.4969],
[ 0.6051, 0.4128, 0.7403, 0.2913, 0.3818, 0.2822, 0.5789, 0.6328],
[ 0.6751, 0.4404, 0.8000, 0.2561, 0.4524, 0.1953, 0.5601, 0.5146],
[ 0.6628, 0.4574, 0.8744, 0.4788, 0.3909, 0.4544, 0.5270, 0.5527]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6284, 0.4029, 0.8838, 0.3783, 0.3975, 0.2850, 0.6335, 0.5090],
[0.6275, 0.4081, 0.8062, 0.2017, 0.4825, 0.1583, 0.6156, 0.4869],
[0.6145, 0.4007, 0.8775, 0.4533, 0.4563, 0.5533, 0.6087, 0.5533],
[0.0000, 0.0000, 0.6513, 0.1717, 0.4100, 0.1983, 0.5253, 0.5240],
[0.6199, 0.3913, 0.8788, 0.5217, 0.4075, 0.5100, 0.6060, 0.4913],
[0.6196, 0.4094, 0.7563, 0.2817, 0.3938, 0.3183, 0.6012, 0.6183],
[0.6277, 0.4083, 0.8350, 0.2717, 0.4563, 0.1800, 0.5918, 0.4878],
[0.6193, 0.4165, 0.8838, 0.4700, 0.4150, 0.4867, 0.5427, 0.5261]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0004884650697931647
step: 1
running loss: 0.0004884650697931647
Train Steps: 1/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6261, 0.4066, 0.8325, 0.2150, 0.4763, 0.2667, 0.7002, 0.5633],
[0.6275, 0.4071, 0.8075, 0.2100, 0.4700, 0.1533, 0.6148, 0.4834],
[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459],
[0.6154, 0.4112, 0.7037, 0.2317, 0.4238, 0.1833, 0.5350, 0.5600],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3788, 0.4900, 0.7121, 0.5864],
[0.6125, 0.4010, 0.8650, 0.4567, 0.3663, 0.3900, 0.5600, 0.5567],
[0.6276, 0.4120, 0.8738, 0.3133, 0.4225, 0.2217, 0.6203, 0.4892],
[0.6286, 0.4055, 0.9000, 0.4717, 0.3763, 0.4683, 0.7018, 0.5494]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6640, 0.4397, 0.8230, 0.2081, 0.4813, 0.2426, 0.6619, 0.5524],
[0.5629, 0.3849, 0.7947, 0.1877, 0.4817, 0.1585, 0.5632, 0.4943],
[0.6622, 0.4429, 0.8487, 0.2691, 0.4924, 0.1942, 0.6363, 0.5429],
[0.5763, 0.4041, 0.6908, 0.2247, 0.4289, 0.1865, 0.4956, 0.5708],
[0.6442, 0.4362, 0.8877, 0.5054, 0.3816, 0.4920, 0.6745, 0.5856],
[0.5904, 0.4002, 0.8679, 0.4434, 0.3575, 0.4028, 0.5257, 0.5667],
[0.6361, 0.4374, 0.8812, 0.3180, 0.4441, 0.2118, 0.5942, 0.4950],
[0.6376, 0.4275, 0.9151, 0.4626, 0.3637, 0.4694, 0.6836, 0.5516]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6261, 0.4066, 0.8325, 0.2150, 0.4762, 0.2667, 0.7002, 0.5633],
[0.6275, 0.4071, 0.8075, 0.2100, 0.4700, 0.1533, 0.6148, 0.4834],
[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459],
[0.6154, 0.4112, 0.7038, 0.2317, 0.4238, 0.1833, 0.5350, 0.5600],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3787, 0.4900, 0.7121, 0.5864],
[0.6125, 0.4010, 0.8650, 0.4567, 0.3663, 0.3900, 0.5600, 0.5567],
[0.6276, 0.4120, 0.8737, 0.3133, 0.4225, 0.2217, 0.6203, 0.4892],
[0.6286, 0.4055, 0.9000, 0.4717, 0.3762, 0.4683, 0.7018, 0.5494]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.000938043842324987
step: 2
running loss: 0.0004690219211624935
Train Steps: 2/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6193, 0.4050, 0.7313, 0.2433, 0.4075, 0.2117, 0.5649, 0.5656],
[0.6200, 0.3993, 0.8519, 0.4923, 0.3962, 0.4717, 0.6013, 0.5433],
[0.6245, 0.4100, 0.7762, 0.2583, 0.4963, 0.1517, 0.5875, 0.5417],
[0.6250, 0.4116, 0.8700, 0.4850, 0.4650, 0.5567, 0.6088, 0.5183],
[0.6284, 0.4093, 0.8900, 0.4700, 0.3650, 0.3850, 0.6212, 0.5167],
[0.6246, 0.4090, 0.6964, 0.2027, 0.3925, 0.2683, 0.6088, 0.5583],
[0.6203, 0.4056, 0.8942, 0.4086, 0.3643, 0.3617, 0.5917, 0.5482],
[0.6145, 0.4008, 0.8750, 0.5383, 0.3975, 0.4650, 0.5563, 0.5533]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5811, 0.3845, 0.7509, 0.2356, 0.4348, 0.2075, 0.5513, 0.5607],
[0.6369, 0.4152, 0.8912, 0.4861, 0.3891, 0.4627, 0.6156, 0.5446],
[0.7136, 0.4810, 0.7813, 0.2562, 0.4903, 0.1406, 0.6018, 0.5508],
[0.6665, 0.4429, 0.9152, 0.4684, 0.4712, 0.5621, 0.6198, 0.5209],
[0.7010, 0.4706, 0.9237, 0.4485, 0.3770, 0.3864, 0.6339, 0.5018],
[0.6253, 0.4285, 0.7250, 0.2029, 0.3956, 0.2703, 0.5921, 0.5407],
[0.6760, 0.4365, 0.9321, 0.4231, 0.3687, 0.3669, 0.6178, 0.5479],
[0.6130, 0.4115, 0.8999, 0.5236, 0.4055, 0.4553, 0.5712, 0.5576]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6193, 0.4050, 0.7312, 0.2433, 0.4075, 0.2117, 0.5649, 0.5656],
[0.6200, 0.3993, 0.8519, 0.4923, 0.3963, 0.4717, 0.6012, 0.5433],
[0.6245, 0.4100, 0.7763, 0.2583, 0.4963, 0.1517, 0.5875, 0.5417],
[0.6251, 0.4116, 0.8700, 0.4850, 0.4650, 0.5567, 0.6087, 0.5183],
[0.6284, 0.4092, 0.8900, 0.4700, 0.3650, 0.3850, 0.6212, 0.5167],
[0.6246, 0.4090, 0.6964, 0.2027, 0.3925, 0.2683, 0.6087, 0.5583],
[0.6203, 0.4056, 0.8942, 0.4086, 0.3643, 0.3617, 0.5917, 0.5482],
[0.6145, 0.4008, 0.8750, 0.5383, 0.3975, 0.4650, 0.5562, 0.5533]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.001644053525524214
step: 3
running loss: 0.0005480178418414047
Train Steps: 3/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6286, 0.4274, 0.8500, 0.4500, 0.4525, 0.2583, 0.5440, 0.6209],
[0.6198, 0.4075, 0.8650, 0.5617, 0.4150, 0.4367, 0.5450, 0.5650],
[0.6229, 0.4066, 0.8513, 0.5717, 0.4500, 0.5050, 0.6025, 0.5350],
[0.6201, 0.4029, 0.8776, 0.4602, 0.3683, 0.4203, 0.5938, 0.5450],
[0.6264, 0.4069, 0.7900, 0.1650, 0.4275, 0.2267, 0.6290, 0.4947],
[0.6202, 0.4053, 0.8638, 0.5283, 0.4546, 0.5108, 0.5900, 0.5133],
[0.6260, 0.4153, 0.9000, 0.4533, 0.4025, 0.2633, 0.6223, 0.4967],
[0.6261, 0.4029, 0.8720, 0.3364, 0.3665, 0.3753, 0.6531, 0.5183]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6809, 0.4596, 0.8557, 0.4188, 0.4484, 0.2379, 0.5578, 0.6116],
[0.6355, 0.4162, 0.8816, 0.5361, 0.4015, 0.4226, 0.5648, 0.5624],
[0.6737, 0.4352, 0.8612, 0.5365, 0.4400, 0.4808, 0.6048, 0.5333],
[0.6598, 0.4225, 0.8887, 0.4296, 0.3856, 0.4134, 0.6230, 0.5433],
[0.6424, 0.3978, 0.7910, 0.1386, 0.4325, 0.2133, 0.6732, 0.5020],
[0.6612, 0.4249, 0.8707, 0.4846, 0.4547, 0.4941, 0.5900, 0.5281],
[0.6900, 0.4489, 0.9203, 0.4105, 0.4064, 0.2570, 0.6465, 0.5050],
[0.6496, 0.4127, 0.8628, 0.3158, 0.3697, 0.3593, 0.6484, 0.5083]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6286, 0.4274, 0.8500, 0.4500, 0.4525, 0.2583, 0.5440, 0.6209],
[0.6198, 0.4075, 0.8650, 0.5617, 0.4150, 0.4367, 0.5450, 0.5650],
[0.6229, 0.4066, 0.8512, 0.5717, 0.4500, 0.5050, 0.6025, 0.5350],
[0.6201, 0.4029, 0.8776, 0.4602, 0.3683, 0.4203, 0.5938, 0.5450],
[0.6264, 0.4069, 0.7900, 0.1650, 0.4275, 0.2267, 0.6290, 0.4947],
[0.6202, 0.4053, 0.8637, 0.5283, 0.4546, 0.5108, 0.5900, 0.5133],
[0.6260, 0.4153, 0.9000, 0.4533, 0.4025, 0.2633, 0.6223, 0.4967],
[0.6261, 0.4029, 0.8720, 0.3364, 0.3665, 0.3753, 0.6531, 0.5183]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0021857938554603606
step: 4
running loss: 0.0005464484638650902
Train Steps: 4/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.7335, 0.2569, 0.3788, 0.2667, 0.5066, 0.5578],
[0.6296, 0.4076, 0.8400, 0.5583, 0.3700, 0.4367, 0.6876, 0.5494],
[0.6251, 0.4163, 0.8662, 0.4467, 0.3625, 0.3567, 0.6038, 0.5533],
[0.6086, 0.3940, 0.8712, 0.4783, 0.4025, 0.4900, 0.5498, 0.5390],
[0.6193, 0.4079, 0.7288, 0.2500, 0.4250, 0.2550, 0.5989, 0.6266],
[0.6346, 0.4086, 0.7938, 0.5500, 0.3962, 0.4867, 0.7343, 0.5702],
[0.6263, 0.4030, 0.9000, 0.4767, 0.3800, 0.5167, 0.6415, 0.4771],
[0.6310, 0.4017, 0.8563, 0.5800, 0.3688, 0.4750, 0.6326, 0.5006]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.1280, 0.0777, 0.7659, 0.2281, 0.4004, 0.2490, 0.5271, 0.5553],
[0.7083, 0.4421, 0.8876, 0.5065, 0.4055, 0.4180, 0.7057, 0.5312],
[0.7266, 0.4623, 0.9024, 0.4195, 0.3830, 0.3276, 0.6195, 0.5389],
[0.7253, 0.4551, 0.9119, 0.4579, 0.4334, 0.4596, 0.5622, 0.5170],
[0.6726, 0.4309, 0.7633, 0.2221, 0.4598, 0.2383, 0.6116, 0.6030],
[0.7279, 0.4571, 0.8371, 0.5180, 0.4143, 0.4637, 0.7164, 0.5570],
[0.7040, 0.4440, 0.9334, 0.4408, 0.3999, 0.5113, 0.6502, 0.4685],
[0.7033, 0.4410, 0.8890, 0.5672, 0.3969, 0.4621, 0.6445, 0.4977]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.7335, 0.2569, 0.3787, 0.2667, 0.5066, 0.5578],
[0.6296, 0.4076, 0.8400, 0.5583, 0.3700, 0.4367, 0.6876, 0.5494],
[0.6252, 0.4162, 0.8662, 0.4467, 0.3625, 0.3567, 0.6037, 0.5533],
[0.6086, 0.3940, 0.8712, 0.4783, 0.4025, 0.4900, 0.5498, 0.5390],
[0.6193, 0.4078, 0.7287, 0.2500, 0.4250, 0.2550, 0.5989, 0.6266],
[0.6346, 0.4086, 0.7937, 0.5500, 0.3963, 0.4867, 0.7343, 0.5702],
[0.6263, 0.4029, 0.9000, 0.4767, 0.3800, 0.5167, 0.6415, 0.4771],
[0.6310, 0.4017, 0.8562, 0.5800, 0.3688, 0.4750, 0.6326, 0.5006]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.004074420110555366
step: 5
running loss: 0.0008148840221110732
Train Steps: 5/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6296, 0.4045, 0.9138, 0.4100, 0.4232, 0.4242, 0.7422, 0.5297],
[0.6126, 0.4039, 0.8237, 0.3967, 0.3625, 0.3600, 0.5894, 0.6138],
[0.6262, 0.4085, 0.8438, 0.3150, 0.4025, 0.2633, 0.6339, 0.4810],
[0.6164, 0.4102, 0.8850, 0.4867, 0.4213, 0.5983, 0.5609, 0.5038],
[0.6203, 0.4072, 0.8892, 0.3523, 0.3783, 0.3017, 0.5898, 0.5478],
[0.6250, 0.3961, 0.8672, 0.4929, 0.4199, 0.4972, 0.6312, 0.5301],
[0.6144, 0.4032, 0.8563, 0.3283, 0.3525, 0.4200, 0.5775, 0.5583],
[0.6201, 0.4036, 0.8596, 0.3850, 0.3492, 0.3785, 0.5978, 0.5131]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7257, 0.4661, 0.8940, 0.4321, 0.4246, 0.4201, 0.7156, 0.5389],
[0.6664, 0.4251, 0.8172, 0.4186, 0.3816, 0.3503, 0.6246, 0.6174],
[0.6524, 0.4117, 0.8400, 0.3153, 0.4190, 0.2505, 0.6523, 0.4660],
[0.6420, 0.4179, 0.8749, 0.5114, 0.4585, 0.5876, 0.6144, 0.5262],
[0.6775, 0.4307, 0.8955, 0.3628, 0.3980, 0.2863, 0.6482, 0.5436],
[0.6652, 0.4166, 0.8540, 0.5090, 0.4253, 0.5043, 0.6642, 0.5239],
[0.6302, 0.3965, 0.8610, 0.3333, 0.3732, 0.4108, 0.5898, 0.5453],
[0.6933, 0.4378, 0.8574, 0.4011, 0.3623, 0.3861, 0.6253, 0.5153]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6296, 0.4045, 0.9137, 0.4100, 0.4232, 0.4242, 0.7422, 0.5297],
[0.6126, 0.4038, 0.8238, 0.3967, 0.3625, 0.3600, 0.5894, 0.6138],
[0.6262, 0.4085, 0.8438, 0.3150, 0.4025, 0.2633, 0.6339, 0.4810],
[0.6164, 0.4102, 0.8850, 0.4867, 0.4212, 0.5983, 0.5609, 0.5038],
[0.6203, 0.4072, 0.8892, 0.3523, 0.3783, 0.3017, 0.5898, 0.5478],
[0.6250, 0.3961, 0.8672, 0.4929, 0.4199, 0.4972, 0.6312, 0.5301],
[0.6144, 0.4032, 0.8562, 0.3283, 0.3525, 0.4200, 0.5775, 0.5583],
[0.6201, 0.4036, 0.8596, 0.3850, 0.3492, 0.3785, 0.5978, 0.5131]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.004839719942538068
step: 6
running loss: 0.0008066199904230112
Train Steps: 6/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6239, 0.4107, 0.8162, 0.2763, 0.3625, 0.3600, 0.5988, 0.5700],
[0.6132, 0.4066, 0.7259, 0.2402, 0.3588, 0.3300, 0.6000, 0.5600],
[0.6216, 0.4167, 0.8588, 0.5583, 0.3975, 0.5167, 0.5775, 0.5667],
[0.6176, 0.4017, 0.8788, 0.5100, 0.4075, 0.5250, 0.5913, 0.5033],
[0.6127, 0.4066, 0.8550, 0.5567, 0.4662, 0.5141, 0.5070, 0.5412],
[0.6083, 0.3957, 0.8638, 0.4950, 0.4363, 0.5083, 0.5346, 0.4980],
[0.6109, 0.3943, 0.8525, 0.4950, 0.4338, 0.4800, 0.5449, 0.5383],
[0.6245, 0.4115, 0.8700, 0.4883, 0.4625, 0.5517, 0.6100, 0.5217]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5816, 0.3644, 0.7977, 0.2874, 0.3627, 0.3423, 0.6396, 0.5712],
[0.6387, 0.4050, 0.7193, 0.2647, 0.3624, 0.3305, 0.6420, 0.5596],
[0.6548, 0.4103, 0.8759, 0.5895, 0.4044, 0.4977, 0.6551, 0.5572],
[0.6460, 0.4036, 0.8800, 0.5074, 0.4045, 0.5317, 0.6356, 0.5149],
[0.6181, 0.4096, 0.8668, 0.5840, 0.4459, 0.4698, 0.5891, 0.5323],
[0.6339, 0.3948, 0.8712, 0.4996, 0.4313, 0.5057, 0.5855, 0.4824],
[0.6447, 0.4080, 0.8645, 0.4941, 0.4178, 0.4753, 0.5918, 0.5320],
[0.6328, 0.4041, 0.8715, 0.4879, 0.4285, 0.5262, 0.6690, 0.5281]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6239, 0.4107, 0.8162, 0.2763, 0.3625, 0.3600, 0.5987, 0.5700],
[0.6132, 0.4066, 0.7259, 0.2402, 0.3587, 0.3300, 0.6000, 0.5600],
[0.6216, 0.4167, 0.8587, 0.5583, 0.3975, 0.5167, 0.5775, 0.5667],
[0.6176, 0.4017, 0.8788, 0.5100, 0.4075, 0.5250, 0.5913, 0.5033],
[0.6127, 0.4066, 0.8550, 0.5567, 0.4662, 0.5141, 0.5070, 0.5412],
[0.6083, 0.3957, 0.8637, 0.4950, 0.4363, 0.5083, 0.5346, 0.4980],
[0.6109, 0.3943, 0.8525, 0.4950, 0.4338, 0.4800, 0.5449, 0.5383],
[0.6245, 0.4115, 0.8700, 0.4883, 0.4625, 0.5517, 0.6100, 0.5217]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.005535328615223989
step: 7
running loss: 0.0007907612307462841
Train Steps: 7/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.8850, 0.2817, 0.5112, 0.2183, 0.7184, 0.5436],
[ nan, nan, 0.9050, 0.3500, 0.5138, 0.2300, 0.7359, 0.5702],
[0.6236, 0.4081, 0.8575, 0.3000, 0.3713, 0.3033, 0.5550, 0.5633],
[0.6122, 0.3993, 0.8738, 0.4667, 0.4517, 0.4879, 0.5155, 0.4927],
[0.6186, 0.4060, 0.8750, 0.5050, 0.3538, 0.4367, 0.5813, 0.6083],
[0.6361, 0.4076, 0.8862, 0.5350, 0.3713, 0.4650, 0.6654, 0.5297],
[0.6289, 0.4019, 0.8113, 0.5467, 0.3875, 0.5017, 0.7367, 0.5332],
[ nan, nan, 0.8037, 0.2483, 0.3975, 0.2517, 0.5575, 0.5600]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.2315, 0.1313, 0.8693, 0.2834, 0.5037, 0.2446, 0.6931, 0.5315],
[0.1525, 0.0825, 0.9006, 0.3641, 0.5002, 0.2595, 0.7082, 0.5658],
[0.6859, 0.4555, 0.8358, 0.3334, 0.3620, 0.3177, 0.5499, 0.5456],
[0.7301, 0.4657, 0.8544, 0.5141, 0.4441, 0.5523, 0.5109, 0.4873],
[0.7582, 0.4908, 0.8610, 0.5299, 0.3585, 0.4687, 0.5936, 0.6015],
[0.7582, 0.4922, 0.8566, 0.5872, 0.3775, 0.5032, 0.6848, 0.5286],
[0.7481, 0.4672, 0.7994, 0.5595, 0.3788, 0.5282, 0.7132, 0.5261],
[0.1357, 0.0802, 0.7567, 0.2895, 0.4016, 0.2786, 0.5403, 0.5677]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.8850, 0.2817, 0.5113, 0.2183, 0.7184, 0.5436],
[0.0000, 0.0000, 0.9050, 0.3500, 0.5138, 0.2300, 0.7359, 0.5702],
[0.6236, 0.4081, 0.8575, 0.3000, 0.3713, 0.3033, 0.5550, 0.5633],
[0.6122, 0.3993, 0.8737, 0.4667, 0.4517, 0.4879, 0.5155, 0.4927],
[0.6186, 0.4060, 0.8750, 0.5050, 0.3537, 0.4367, 0.5813, 0.6083],
[0.6361, 0.4076, 0.8863, 0.5350, 0.3713, 0.4650, 0.6654, 0.5297],
[0.6289, 0.4019, 0.8112, 0.5467, 0.3875, 0.5017, 0.7367, 0.5332],
[0.0000, 0.0000, 0.8037, 0.2483, 0.3975, 0.2517, 0.5575, 0.5600]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0038, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0038, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.009357340022688732
step: 8
running loss: 0.0011696675028360914
Train Steps: 8/90 Loss: 0.0012 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6268, 0.4102, 0.8938, 0.3667, 0.4025, 0.2833, 0.6275, 0.5183],
[0.6204, 0.4091, 0.8950, 0.4783, 0.3613, 0.4617, 0.6063, 0.5617],
[0.6226, 0.4185, 0.8850, 0.5500, 0.3800, 0.4250, 0.5625, 0.5617],
[0.6296, 0.4060, 0.9100, 0.3267, 0.4726, 0.3367, 0.7446, 0.5355],
[0.6214, 0.4112, 0.7838, 0.2117, 0.3650, 0.3133, 0.5675, 0.5083],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098],
[0.6113, 0.4006, 0.8700, 0.5350, 0.3638, 0.3767, 0.5097, 0.4882],
[0.6148, 0.4053, 0.8750, 0.4550, 0.4850, 0.5218, 0.5863, 0.5567]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5513, 0.3499, 0.8754, 0.3885, 0.4092, 0.2980, 0.6123, 0.5509],
[0.5079, 0.3261, 0.8825, 0.5033, 0.3551, 0.4708, 0.5870, 0.5716],
[0.5486, 0.3592, 0.8733, 0.5777, 0.3856, 0.4378, 0.5609, 0.5814],
[0.5862, 0.3672, 0.8805, 0.3626, 0.4499, 0.3485, 0.7259, 0.5326],
[0.5220, 0.3297, 0.7695, 0.2367, 0.3591, 0.3185, 0.5644, 0.5184],
[0.5648, 0.3485, 0.8498, 0.4890, 0.3768, 0.5428, 0.5952, 0.5136],
[0.5259, 0.3511, 0.8384, 0.5438, 0.3694, 0.4067, 0.5304, 0.5357],
[0.5168, 0.3309, 0.8624, 0.4739, 0.4763, 0.5202, 0.5775, 0.5674]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6268, 0.4102, 0.8938, 0.3667, 0.4025, 0.2833, 0.6275, 0.5183],
[0.6204, 0.4091, 0.8950, 0.4783, 0.3613, 0.4617, 0.6062, 0.5617],
[0.6226, 0.4185, 0.8850, 0.5500, 0.3800, 0.4250, 0.5625, 0.5617],
[0.6296, 0.4060, 0.9100, 0.3267, 0.4726, 0.3367, 0.7446, 0.5355],
[0.6214, 0.4112, 0.7837, 0.2117, 0.3650, 0.3133, 0.5675, 0.5083],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098],
[0.6113, 0.4006, 0.8700, 0.5350, 0.3638, 0.3767, 0.5097, 0.4882],
[0.6148, 0.4053, 0.8750, 0.4550, 0.4850, 0.5218, 0.5863, 0.5567]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.01096438625245355
step: 9
running loss: 0.0012182651391615057
Train Steps: 9/90 Loss: 0.0012 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.6900, 0.1917, 0.3937, 0.2367, 0.5240, 0.5246],
[0.6207, 0.4081, 0.7662, 0.2067, 0.3962, 0.3200, 0.6312, 0.5300],
[0.6082, 0.4024, 0.8738, 0.4017, 0.3688, 0.3950, 0.5306, 0.5136],
[0.6124, 0.4069, 0.8314, 0.5001, 0.3738, 0.4650, 0.5167, 0.5402],
[0.6275, 0.4024, 0.8500, 0.5383, 0.3912, 0.4883, 0.6288, 0.5100],
[0.6283, 0.4283, 0.7477, 0.3542, 0.5125, 0.1917, 0.5500, 0.6167],
[0.6255, 0.4017, 0.8688, 0.3217, 0.3638, 0.3550, 0.6344, 0.4901],
[0.6085, 0.4008, 0.8588, 0.5200, 0.4959, 0.4977, 0.5175, 0.5283]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[-0.1154, -0.0725, 0.7042, 0.2203, 0.4047, 0.2516, 0.5119, 0.5439],
[ 0.6155, 0.3898, 0.7578, 0.2185, 0.3942, 0.3477, 0.6270, 0.5514],
[ 0.5186, 0.3507, 0.8849, 0.4107, 0.3595, 0.4197, 0.5105, 0.5245],
[ 0.5673, 0.3583, 0.8317, 0.5371, 0.3788, 0.4971, 0.5513, 0.5711],
[ 0.5857, 0.3667, 0.8425, 0.5602, 0.4127, 0.5175, 0.6205, 0.5132],
[ 0.5985, 0.3863, 0.7517, 0.3606, 0.5034, 0.2179, 0.5441, 0.6325],
[ 0.5683, 0.3477, 0.8672, 0.3361, 0.3666, 0.3888, 0.6350, 0.5105],
[ 0.5255, 0.3333, 0.8658, 0.5461, 0.4960, 0.5110, 0.5175, 0.5537]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.6900, 0.1917, 0.3938, 0.2367, 0.5240, 0.5246],
[0.6207, 0.4081, 0.7663, 0.2067, 0.3963, 0.3200, 0.6313, 0.5300],
[0.6082, 0.4024, 0.8737, 0.4017, 0.3688, 0.3950, 0.5306, 0.5136],
[0.6123, 0.4069, 0.8314, 0.5001, 0.3738, 0.4650, 0.5167, 0.5402],
[0.6275, 0.4024, 0.8500, 0.5383, 0.3913, 0.4883, 0.6288, 0.5100],
[0.6283, 0.4283, 0.7477, 0.3542, 0.5125, 0.1917, 0.5500, 0.6167],
[0.6255, 0.4017, 0.8687, 0.3217, 0.3638, 0.3550, 0.6344, 0.4901],
[0.6084, 0.4008, 0.8587, 0.5200, 0.4959, 0.4977, 0.5175, 0.5283]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0121056787611451
step: 10
running loss: 0.00121056787611451
Train Steps: 10/90 Loss: 0.0012 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837],
[0.6226, 0.4098, 0.8912, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367],
[0.6269, 0.4073, 0.8900, 0.4933, 0.3625, 0.4183, 0.6288, 0.5150],
[0.6214, 0.4116, 0.7750, 0.2317, 0.4487, 0.1883, 0.6200, 0.5400],
[0.6129, 0.3930, 0.8769, 0.5105, 0.4146, 0.5642, 0.6000, 0.5082],
[0.6339, 0.4081, 0.8425, 0.5417, 0.3850, 0.4833, 0.7335, 0.5760],
[0.6227, 0.4049, 0.8750, 0.5367, 0.3775, 0.3667, 0.5725, 0.5317],
[0.6264, 0.4035, 0.8888, 0.4883, 0.4050, 0.5217, 0.6361, 0.4791]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4749, 0.3249, 0.6890, 0.2968, 0.3606, 0.3122, 0.4926, 0.5845],
[0.5149, 0.3481, 0.9194, 0.4068, 0.4093, 0.2657, 0.5357, 0.5565],
[0.5039, 0.3380, 0.8925, 0.4838, 0.3632, 0.4430, 0.5818, 0.5308],
[0.5325, 0.3546, 0.7897, 0.2229, 0.4606, 0.2118, 0.5699, 0.5353],
[0.5349, 0.3446, 0.8689, 0.5037, 0.4380, 0.5839, 0.5417, 0.5008],
[0.5464, 0.3667, 0.8537, 0.5286, 0.3979, 0.4906, 0.6903, 0.5944],
[0.4846, 0.3226, 0.8902, 0.5299, 0.3904, 0.3915, 0.5313, 0.5475],
[0.4769, 0.3094, 0.8922, 0.4655, 0.4012, 0.5251, 0.5598, 0.4930]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837],
[0.6226, 0.4098, 0.8913, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367],
[0.6269, 0.4073, 0.8900, 0.4933, 0.3625, 0.4183, 0.6288, 0.5150],
[0.6214, 0.4116, 0.7750, 0.2317, 0.4487, 0.1883, 0.6200, 0.5400],
[0.6129, 0.3930, 0.8769, 0.5105, 0.4146, 0.5642, 0.6000, 0.5082],
[0.6339, 0.4081, 0.8425, 0.5417, 0.3850, 0.4833, 0.7335, 0.5760],
[0.6227, 0.4049, 0.8750, 0.5367, 0.3775, 0.3667, 0.5725, 0.5317],
[0.6264, 0.4035, 0.8888, 0.4883, 0.4050, 0.5217, 0.6361, 0.4791]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0028, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0028, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0149084952136036
step: 11
running loss: 0.0013553177466912364
Train Steps: 11/90 Loss: 0.0014 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6152, 0.4131, 0.6863, 0.2567, 0.3625, 0.3300, 0.5765, 0.5305],
[0.6112, 0.4029, 0.8638, 0.4800, 0.4875, 0.5083, 0.5763, 0.5567],
[ nan, nan, 0.7648, 0.2722, 0.3962, 0.2183, 0.5060, 0.5422],
[0.6346, 0.4165, 0.9138, 0.3983, 0.3875, 0.4317, 0.7469, 0.5471],
[0.6175, 0.4093, 0.8800, 0.4433, 0.4075, 0.4367, 0.5128, 0.4901],
[0.6293, 0.4024, 0.8750, 0.5000, 0.4012, 0.5733, 0.7121, 0.5633],
[0.6336, 0.4191, 0.8938, 0.5167, 0.3937, 0.3517, 0.7343, 0.5748],
[ nan, nan, 0.6859, 0.2194, 0.4150, 0.1867, 0.5153, 0.5729]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5501, 0.3820, 0.7020, 0.2429, 0.3641, 0.3376, 0.5606, 0.5479],
[0.6051, 0.4123, 0.8787, 0.4856, 0.4827, 0.4924, 0.5378, 0.5501],
[0.0207, 0.0367, 0.7621, 0.2604, 0.3706, 0.2205, 0.4753, 0.5109],
[0.6254, 0.4297, 0.9316, 0.4102, 0.3995, 0.4381, 0.7016, 0.5453],
[0.5953, 0.4058, 0.8951, 0.4503, 0.3976, 0.4549, 0.4712, 0.5083],
[0.6086, 0.3952, 0.8804, 0.4871, 0.3942, 0.5839, 0.6646, 0.5367],
[0.6103, 0.4185, 0.8988, 0.5163, 0.3965, 0.3625, 0.7024, 0.5593],
[0.0516, 0.0381, 0.7138, 0.2252, 0.4206, 0.1837, 0.4850, 0.5502]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6152, 0.4131, 0.6862, 0.2567, 0.3625, 0.3300, 0.5765, 0.5305],
[0.6112, 0.4029, 0.8637, 0.4800, 0.4875, 0.5083, 0.5763, 0.5567],
[0.0000, 0.0000, 0.7648, 0.2722, 0.3963, 0.2183, 0.5060, 0.5422],
[0.6346, 0.4165, 0.9137, 0.3983, 0.3875, 0.4317, 0.7469, 0.5471],
[0.6175, 0.4093, 0.8800, 0.4433, 0.4075, 0.4367, 0.5128, 0.4901],
[0.6293, 0.4024, 0.8750, 0.5000, 0.4013, 0.5733, 0.7121, 0.5633],
[0.6336, 0.4191, 0.8938, 0.5167, 0.3938, 0.3517, 0.7343, 0.5748],
[0.0000, 0.0000, 0.6859, 0.2194, 0.4150, 0.1867, 0.5153, 0.5729]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.015397945273434743
step: 12
running loss: 0.001283162106119562
Train Steps: 12/90 Loss: 0.0013 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6192, 0.3980, 0.7078, 0.2750, 0.4250, 0.2100, 0.5450, 0.5783],
[0.6302, 0.4007, 0.8850, 0.5500, 0.3613, 0.4517, 0.6335, 0.5012],
[0.6197, 0.3986, 0.8800, 0.4617, 0.4188, 0.4783, 0.5687, 0.5550],
[0.6226, 0.4103, 0.8575, 0.3450, 0.4388, 0.2067, 0.5787, 0.5383],
[ nan, nan, 0.8675, 0.2833, 0.5350, 0.1983, 0.6678, 0.5621],
[0.6201, 0.4004, 0.8786, 0.5043, 0.3833, 0.5138, 0.5997, 0.5092],
[0.6202, 0.4054, 0.8892, 0.4428, 0.3642, 0.3249, 0.5840, 0.5426],
[0.6127, 0.4084, 0.8700, 0.4467, 0.3987, 0.4317, 0.5013, 0.5471]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.2244, 0.1580, 0.7232, 0.2552, 0.4145, 0.2532, 0.5267, 0.5611],
[0.6021, 0.4020, 0.8655, 0.5411, 0.3562, 0.4406, 0.6404, 0.4828],
[0.5888, 0.3883, 0.8618, 0.4325, 0.3983, 0.4777, 0.5589, 0.5230],
[0.6022, 0.4384, 0.8692, 0.3581, 0.4352, 0.2404, 0.5637, 0.5412],
[0.0772, 0.0743, 0.8547, 0.2651, 0.5129, 0.2014, 0.6702, 0.5527],
[0.5748, 0.3815, 0.8642, 0.5016, 0.3821, 0.5142, 0.5752, 0.4859],
[0.6070, 0.4108, 0.8904, 0.4143, 0.3503, 0.3365, 0.5993, 0.5210],
[0.5782, 0.4060, 0.8511, 0.4246, 0.3702, 0.4451, 0.4878, 0.5240]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6192, 0.3980, 0.7078, 0.2750, 0.4250, 0.2100, 0.5450, 0.5783],
[0.6302, 0.4007, 0.8850, 0.5500, 0.3613, 0.4517, 0.6335, 0.5012],
[0.6197, 0.3986, 0.8800, 0.4617, 0.4187, 0.4783, 0.5688, 0.5550],
[0.6226, 0.4103, 0.8575, 0.3450, 0.4387, 0.2067, 0.5788, 0.5383],
[0.0000, 0.0000, 0.8675, 0.2833, 0.5350, 0.1983, 0.6678, 0.5621],
[0.6201, 0.4004, 0.8786, 0.5043, 0.3833, 0.5138, 0.5997, 0.5092],
[0.6202, 0.4054, 0.8892, 0.4428, 0.3642, 0.3249, 0.5840, 0.5426],
[0.6127, 0.4084, 0.8700, 0.4467, 0.3988, 0.4317, 0.5013, 0.5471]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0039, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0039, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.019262570276623592
step: 13
running loss: 0.0014817361751248916
Train Steps: 13/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6043, 0.4022, 0.6887, 0.1983, 0.3775, 0.2483, 0.5480, 0.5136],
[0.6205, 0.4012, 0.8675, 0.3283, 0.3713, 0.3050, 0.5813, 0.5117],
[0.6125, 0.4010, 0.8650, 0.4567, 0.3663, 0.3900, 0.5600, 0.5567],
[0.6219, 0.4089, 0.8938, 0.4800, 0.3825, 0.4450, 0.5850, 0.5200],
[0.6100, 0.4016, 0.8600, 0.5067, 0.4612, 0.5233, 0.5086, 0.5519],
[0.6197, 0.4091, 0.8800, 0.4783, 0.3538, 0.4767, 0.5950, 0.5550],
[0.6031, 0.3986, 0.7462, 0.2833, 0.3638, 0.2717, 0.5253, 0.4726],
[0.6210, 0.4164, 0.7202, 0.2930, 0.4025, 0.2483, 0.5687, 0.5567]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5710, 0.3831, 0.7021, 0.1966, 0.3722, 0.2206, 0.5852, 0.5107],
[0.5573, 0.3777, 0.8761, 0.3221, 0.3587, 0.2827, 0.6023, 0.4967],
[0.5786, 0.3829, 0.8698, 0.4437, 0.3681, 0.3612, 0.5885, 0.5433],
[0.5425, 0.3700, 0.9020, 0.4852, 0.3674, 0.4227, 0.6205, 0.5100],
[0.5838, 0.3936, 0.8620, 0.5194, 0.4552, 0.4883, 0.5314, 0.5250],
[0.5672, 0.3824, 0.8751, 0.4618, 0.3647, 0.4477, 0.6069, 0.5339],
[0.5511, 0.3646, 0.7593, 0.2733, 0.3573, 0.2556, 0.5577, 0.4689],
[0.4920, 0.3405, 0.7663, 0.2715, 0.4157, 0.2283, 0.5999, 0.5700]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6043, 0.4022, 0.6888, 0.1983, 0.3775, 0.2483, 0.5480, 0.5136],
[0.6205, 0.4012, 0.8675, 0.3283, 0.3713, 0.3050, 0.5813, 0.5117],
[0.6125, 0.4010, 0.8650, 0.4567, 0.3663, 0.3900, 0.5600, 0.5567],
[0.6219, 0.4089, 0.8938, 0.4800, 0.3825, 0.4450, 0.5850, 0.5200],
[0.6100, 0.4016, 0.8600, 0.5067, 0.4613, 0.5233, 0.5086, 0.5519],
[0.6197, 0.4091, 0.8800, 0.4783, 0.3537, 0.4767, 0.5950, 0.5550],
[0.6031, 0.3986, 0.7462, 0.2833, 0.3638, 0.2717, 0.5253, 0.4726],
[0.6210, 0.4164, 0.7202, 0.2930, 0.4025, 0.2483, 0.5688, 0.5567]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.020266804698621854
step: 14
running loss: 0.0014476289070444182
Train Steps: 14/90 Loss: 0.0014 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150],
[0.6250, 0.4131, 0.8688, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367],
[0.6214, 0.4116, 0.7750, 0.2317, 0.4487, 0.1883, 0.6200, 0.5400],
[0.6213, 0.4001, 0.7712, 0.2117, 0.4338, 0.1800, 0.5850, 0.5183],
[0.6149, 0.4054, 0.6713, 0.2333, 0.4025, 0.2017, 0.5213, 0.5695],
[0.6203, 0.4096, 0.8862, 0.4267, 0.3538, 0.4117, 0.6025, 0.5650],
[0.6161, 0.4099, 0.8738, 0.4383, 0.3788, 0.5483, 0.5605, 0.5019],
[0.6205, 0.4016, 0.8350, 0.2717, 0.3987, 0.2550, 0.5787, 0.5133]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5906, 0.4013, 0.8613, 0.4550, 0.4265, 0.5389, 0.6329, 0.5143],
[0.5986, 0.4023, 0.8560, 0.2970, 0.4190, 0.2048, 0.6304, 0.5300],
[0.5941, 0.4060, 0.7585, 0.2281, 0.4382, 0.1613, 0.6238, 0.5178],
[0.5804, 0.3693, 0.7585, 0.2230, 0.4211, 0.1526, 0.6025, 0.5110],
[0.5636, 0.3875, 0.6671, 0.2289, 0.3848, 0.1903, 0.5313, 0.5479],
[0.5481, 0.3683, 0.8799, 0.4000, 0.3423, 0.3808, 0.6015, 0.5648],
[0.5518, 0.3761, 0.8546, 0.4256, 0.3682, 0.4922, 0.5651, 0.4971],
[0.5714, 0.3834, 0.8223, 0.2560, 0.3741, 0.2333, 0.5960, 0.5108]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150],
[0.6250, 0.4131, 0.8687, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367],
[0.6214, 0.4116, 0.7750, 0.2317, 0.4487, 0.1883, 0.6200, 0.5400],
[0.6213, 0.4001, 0.7713, 0.2117, 0.4338, 0.1800, 0.5850, 0.5183],
[0.6149, 0.4054, 0.6712, 0.2333, 0.4025, 0.2017, 0.5213, 0.5695],
[0.6203, 0.4096, 0.8863, 0.4267, 0.3537, 0.4117, 0.6025, 0.5650],
[0.6161, 0.4099, 0.8737, 0.4383, 0.3787, 0.5483, 0.5605, 0.5019],
[0.6205, 0.4015, 0.8350, 0.2717, 0.3988, 0.2550, 0.5788, 0.5133]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.020893012144370005
step: 15
running loss: 0.0013928674762913337
Train Steps: 15/90 Loss: 0.0014 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6214, 0.4116, 0.7750, 0.2317, 0.4487, 0.1883, 0.6200, 0.5400],
[0.6168, 0.4029, 0.8523, 0.3417, 0.3588, 0.5000, 0.6125, 0.5400],
[0.6353, 0.4128, 0.8488, 0.2600, 0.5525, 0.1616, 0.6694, 0.5540],
[0.6211, 0.3935, 0.8636, 0.4841, 0.4417, 0.5126, 0.6331, 0.5268],
[0.6272, 0.4045, 0.8538, 0.5900, 0.3750, 0.4417, 0.5989, 0.4649],
[0.6218, 0.4098, 0.7238, 0.1850, 0.4238, 0.2517, 0.6288, 0.5350],
[0.6307, 0.4029, 0.8988, 0.4817, 0.3937, 0.3500, 0.7311, 0.5378],
[0.6296, 0.4060, 0.9100, 0.3267, 0.4726, 0.3367, 0.7446, 0.5355]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6354, 0.4278, 0.7517, 0.2153, 0.4245, 0.1671, 0.5917, 0.5210],
[0.5721, 0.3818, 0.8357, 0.3290, 0.3228, 0.4648, 0.6028, 0.5294],
[0.6360, 0.4356, 0.8251, 0.2208, 0.5036, 0.1596, 0.6466, 0.5631],
[0.5783, 0.3829, 0.8533, 0.4649, 0.3959, 0.4808, 0.5663, 0.5193],
[0.6522, 0.4228, 0.8267, 0.5780, 0.3619, 0.4118, 0.5654, 0.4704],
[0.6159, 0.4050, 0.7258, 0.1741, 0.4098, 0.2255, 0.6184, 0.5360],
[0.6335, 0.4194, 0.8854, 0.4637, 0.3663, 0.3228, 0.6904, 0.5412],
[0.5684, 0.3690, 0.8838, 0.3206, 0.4286, 0.3061, 0.7137, 0.5155]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6214, 0.4116, 0.7750, 0.2317, 0.4487, 0.1883, 0.6200, 0.5400],
[0.6168, 0.4029, 0.8523, 0.3417, 0.3587, 0.5000, 0.6125, 0.5400],
[0.6353, 0.4128, 0.8487, 0.2600, 0.5525, 0.1616, 0.6694, 0.5540],
[0.6211, 0.3935, 0.8636, 0.4841, 0.4417, 0.5126, 0.6331, 0.5268],
[0.6271, 0.4045, 0.8537, 0.5900, 0.3750, 0.4417, 0.5989, 0.4649],
[0.6218, 0.4098, 0.7237, 0.1850, 0.4238, 0.2517, 0.6288, 0.5350],
[0.6307, 0.4029, 0.8988, 0.4817, 0.3938, 0.3500, 0.7311, 0.5378],
[0.6296, 0.4060, 0.9100, 0.3267, 0.4726, 0.3367, 0.7446, 0.5355]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.02157996202004142
step: 16
running loss: 0.0013487476262525888
Train Steps: 16/90 Loss: 0.0013 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6151, 0.4125, 0.8738, 0.4417, 0.3575, 0.3783, 0.5138, 0.5483],
[0.6277, 0.4083, 0.8350, 0.2717, 0.4562, 0.1800, 0.5918, 0.4878],
[0.6192, 0.3980, 0.7078, 0.2750, 0.4250, 0.2100, 0.5450, 0.5783],
[0.6186, 0.4060, 0.8750, 0.5050, 0.3538, 0.4367, 0.5813, 0.6083],
[0.6087, 0.3976, 0.8337, 0.3867, 0.3713, 0.3117, 0.5938, 0.5300],
[ nan, nan, 0.8750, 0.2467, 0.5138, 0.2617, 0.7382, 0.5552],
[0.6198, 0.4101, 0.8838, 0.5283, 0.3763, 0.5267, 0.5913, 0.5567],
[0.6199, 0.4015, 0.8716, 0.5228, 0.3833, 0.4772, 0.5883, 0.5148]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7122, 0.4747, 0.8445, 0.4124, 0.3622, 0.3767, 0.5372, 0.5509],
[0.7166, 0.4586, 0.8083, 0.2608, 0.4620, 0.2070, 0.5982, 0.4951],
[0.5601, 0.3597, 0.7098, 0.2516, 0.4317, 0.2329, 0.5504, 0.5738],
[0.6958, 0.4550, 0.8660, 0.4839, 0.3600, 0.4225, 0.6120, 0.5877],
[0.6833, 0.4521, 0.8362, 0.3760, 0.3806, 0.3086, 0.6095, 0.5258],
[0.0834, 0.0515, 0.8465, 0.2422, 0.5094, 0.2428, 0.7514, 0.5423],
[0.7125, 0.4723, 0.8479, 0.5150, 0.3856, 0.5142, 0.6055, 0.5365],
[0.7223, 0.4807, 0.8598, 0.5261, 0.3942, 0.4611, 0.6115, 0.5069]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6151, 0.4125, 0.8737, 0.4417, 0.3575, 0.3783, 0.5138, 0.5483],
[0.6277, 0.4083, 0.8350, 0.2717, 0.4563, 0.1800, 0.5918, 0.4878],
[0.6192, 0.3980, 0.7078, 0.2750, 0.4250, 0.2100, 0.5450, 0.5783],
[0.6186, 0.4060, 0.8750, 0.5050, 0.3537, 0.4367, 0.5813, 0.6083],
[0.6087, 0.3976, 0.8338, 0.3867, 0.3713, 0.3117, 0.5938, 0.5300],
[0.0000, 0.0000, 0.8750, 0.2467, 0.5138, 0.2617, 0.7382, 0.5552],
[0.6198, 0.4101, 0.8838, 0.5283, 0.3762, 0.5267, 0.5913, 0.5567],
[0.6199, 0.4015, 0.8716, 0.5228, 0.3833, 0.4772, 0.5883, 0.5148]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0230987589166034
step: 17
running loss: 0.0013587505245060824
Train Steps: 17/90 Loss: 0.0014 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6157, 0.3956, 0.8323, 0.4138, 0.3479, 0.4431, 0.5914, 0.5131],
[0.6175, 0.3997, 0.6737, 0.2500, 0.4313, 0.1933, 0.5513, 0.5750],
[0.6198, 0.4075, 0.8650, 0.5617, 0.4150, 0.4367, 0.5450, 0.5650],
[0.6300, 0.4102, 0.9088, 0.4433, 0.4088, 0.3067, 0.6820, 0.5540],
[0.6070, 0.3979, 0.8575, 0.5083, 0.4350, 0.5400, 0.5180, 0.5466],
[0.6080, 0.4010, 0.8750, 0.4500, 0.4825, 0.5617, 0.5837, 0.5583],
[ nan, nan, 0.8850, 0.3000, 0.5363, 0.2250, 0.7343, 0.5771],
[0.6197, 0.4091, 0.8800, 0.4783, 0.3538, 0.4767, 0.5950, 0.5550]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6948, 0.4342, 0.8274, 0.3955, 0.3516, 0.4189, 0.5985, 0.5181],
[0.6616, 0.4353, 0.6757, 0.2311, 0.4291, 0.1741, 0.5695, 0.5668],
[0.7638, 0.4901, 0.8623, 0.5660, 0.4073, 0.4236, 0.5623, 0.5521],
[0.7171, 0.4646, 0.8997, 0.4317, 0.4204, 0.2874, 0.6812, 0.5608],
[0.7199, 0.4767, 0.8423, 0.4943, 0.4293, 0.5077, 0.5502, 0.5317],
[0.7093, 0.4723, 0.8679, 0.4347, 0.4737, 0.5264, 0.5791, 0.5443],
[0.1111, 0.0722, 0.8653, 0.2842, 0.5132, 0.2146, 0.7645, 0.5478],
[0.7002, 0.4582, 0.8673, 0.4589, 0.3723, 0.4649, 0.6140, 0.5413]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6157, 0.3956, 0.8323, 0.4138, 0.3479, 0.4431, 0.5914, 0.5131],
[0.6175, 0.3997, 0.6737, 0.2500, 0.4313, 0.1933, 0.5512, 0.5750],
[0.6198, 0.4075, 0.8650, 0.5617, 0.4150, 0.4367, 0.5450, 0.5650],
[0.6300, 0.4102, 0.9087, 0.4433, 0.4087, 0.3067, 0.6820, 0.5540],
[0.6070, 0.3979, 0.8575, 0.5083, 0.4350, 0.5400, 0.5180, 0.5466],
[0.6080, 0.4010, 0.8750, 0.4500, 0.4825, 0.5617, 0.5838, 0.5583],
[0.0000, 0.0000, 0.8850, 0.3000, 0.5362, 0.2250, 0.7343, 0.5771],
[0.6197, 0.4091, 0.8800, 0.4783, 0.3537, 0.4767, 0.5950, 0.5550]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.02501470936113037
step: 18
running loss: 0.001389706075618354
Train Steps: 18/90 Loss: 0.0014 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6102, 0.4001, 0.7738, 0.3583, 0.3463, 0.3800, 0.5524, 0.5689],
[0.6200, 0.3993, 0.8639, 0.3687, 0.3658, 0.3139, 0.6002, 0.5374],
[0.6310, 0.4017, 0.8563, 0.5800, 0.3688, 0.4750, 0.6326, 0.5006],
[0.6083, 0.3957, 0.8638, 0.4950, 0.4363, 0.5083, 0.5346, 0.4980],
[0.6292, 0.4010, 0.8988, 0.4800, 0.3638, 0.3817, 0.6357, 0.5051],
[0.6269, 0.4073, 0.8900, 0.4933, 0.3625, 0.4183, 0.6288, 0.5150],
[0.6171, 0.4127, 0.8900, 0.4800, 0.4325, 0.5783, 0.5769, 0.5090],
[0.6196, 0.4068, 0.7645, 0.2234, 0.4575, 0.1737, 0.5926, 0.5284]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6704, 0.4291, 0.7901, 0.3458, 0.3656, 0.3822, 0.5583, 0.5874],
[0.6621, 0.4222, 0.8653, 0.3725, 0.3861, 0.3233, 0.6159, 0.5628],
[0.7010, 0.4444, 0.8489, 0.5905, 0.3913, 0.4867, 0.6440, 0.5469],
[0.6631, 0.4274, 0.8679, 0.4871, 0.4668, 0.5191, 0.5627, 0.5301],
[0.6619, 0.4045, 0.9055, 0.4651, 0.3786, 0.3689, 0.6459, 0.5426],
[0.7109, 0.4619, 0.8841, 0.5022, 0.3762, 0.4304, 0.6520, 0.5508],
[0.6863, 0.4545, 0.8942, 0.4778, 0.4615, 0.5887, 0.5857, 0.5413],
[0.7541, 0.4829, 0.7754, 0.2297, 0.4743, 0.1854, 0.6195, 0.5590]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6102, 0.4001, 0.7738, 0.3583, 0.3462, 0.3800, 0.5524, 0.5689],
[0.6200, 0.3993, 0.8639, 0.3687, 0.3658, 0.3139, 0.6002, 0.5374],
[0.6310, 0.4017, 0.8562, 0.5800, 0.3688, 0.4750, 0.6326, 0.5006],
[0.6083, 0.3957, 0.8637, 0.4950, 0.4363, 0.5083, 0.5346, 0.4980],
[0.6292, 0.4010, 0.8988, 0.4800, 0.3638, 0.3817, 0.6357, 0.5051],
[0.6269, 0.4073, 0.8900, 0.4933, 0.3625, 0.4183, 0.6288, 0.5150],
[0.6171, 0.4127, 0.8900, 0.4800, 0.4325, 0.5783, 0.5769, 0.5090],
[0.6196, 0.4068, 0.7645, 0.2234, 0.4575, 0.1737, 0.5926, 0.5284]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.026208211231278256
step: 19
running loss: 0.0013793795384883293
Train Steps: 19/90 Loss: 0.0014 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6275, 0.4003, 0.9100, 0.3783, 0.4388, 0.3133, 0.7058, 0.5343],
[0.6122, 0.4006, 0.8850, 0.4217, 0.4088, 0.5517, 0.6063, 0.5517],
[0.6364, 0.4165, 0.9088, 0.4367, 0.4075, 0.3150, 0.6448, 0.5297],
[0.6299, 0.4303, 0.7963, 0.3933, 0.4850, 0.2283, 0.5480, 0.6222],
[0.6256, 0.4199, 0.8638, 0.5800, 0.3987, 0.4383, 0.5600, 0.5950],
[0.6201, 0.4027, 0.8029, 0.2728, 0.4042, 0.2310, 0.5980, 0.5391],
[0.6147, 0.4107, 0.8137, 0.3333, 0.3750, 0.2683, 0.5006, 0.5412],
[ nan, nan, 0.8750, 0.2467, 0.5138, 0.2617, 0.7382, 0.5552]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6235, 0.3860, 0.8834, 0.3867, 0.4348, 0.3253, 0.7166, 0.5325],
[0.6541, 0.4193, 0.8757, 0.4302, 0.4235, 0.5741, 0.5998, 0.5390],
[0.6558, 0.4154, 0.8989, 0.4283, 0.4241, 0.3357, 0.6506, 0.5496],
[0.7330, 0.4808, 0.7978, 0.3939, 0.4796, 0.2567, 0.5489, 0.6241],
[0.7382, 0.4679, 0.8532, 0.5744, 0.3992, 0.4674, 0.5695, 0.5939],
[0.6836, 0.4243, 0.8089, 0.2868, 0.4234, 0.2646, 0.6214, 0.5413],
[0.6716, 0.4293, 0.7856, 0.3307, 0.3658, 0.2910, 0.4913, 0.5589],
[0.0623, 0.0216, 0.8508, 0.2625, 0.5168, 0.2670, 0.7309, 0.5608]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6275, 0.4003, 0.9100, 0.3783, 0.4387, 0.3133, 0.7058, 0.5343],
[0.6122, 0.4006, 0.8850, 0.4217, 0.4087, 0.5517, 0.6062, 0.5517],
[0.6364, 0.4165, 0.9087, 0.4367, 0.4075, 0.3150, 0.6448, 0.5297],
[0.6299, 0.4303, 0.7962, 0.3933, 0.4850, 0.2283, 0.5480, 0.6222],
[0.6256, 0.4199, 0.8637, 0.5800, 0.3988, 0.4383, 0.5600, 0.5950],
[0.6201, 0.4027, 0.8029, 0.2728, 0.4042, 0.2310, 0.5980, 0.5391],
[0.6147, 0.4107, 0.8138, 0.3333, 0.3750, 0.2683, 0.5006, 0.5412],
[0.0000, 0.0000, 0.8750, 0.2467, 0.5138, 0.2617, 0.7382, 0.5552]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.027047252719057724
step: 20
running loss: 0.0013523626359528862
Train Steps: 20/90 Loss: 0.0014 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.8525, 0.2217, 0.5413, 0.2367, 0.7367, 0.5482],
[0.6160, 0.4093, 0.8314, 0.4417, 0.3675, 0.4583, 0.5250, 0.5808],
[0.6202, 0.4066, 0.8398, 0.2648, 0.3925, 0.2627, 0.5845, 0.5124],
[0.6148, 0.3996, 0.8488, 0.3867, 0.3488, 0.4067, 0.5863, 0.5000],
[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334],
[ nan, nan, 0.8750, 0.2467, 0.5138, 0.2617, 0.7382, 0.5552],
[0.6271, 0.4081, 0.9081, 0.4894, 0.3700, 0.4283, 0.6661, 0.5274],
[0.6275, 0.4048, 0.8488, 0.2883, 0.4463, 0.2033, 0.6321, 0.5155]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.1991, 0.1185, 0.8436, 0.2488, 0.5410, 0.2496, 0.7251, 0.5584],
[0.6871, 0.4371, 0.8549, 0.5069, 0.3750, 0.4871, 0.5453, 0.5909],
[0.7278, 0.4729, 0.8267, 0.3110, 0.4081, 0.2709, 0.5883, 0.5380],
[0.6961, 0.4302, 0.8692, 0.4282, 0.3687, 0.4330, 0.5951, 0.5323],
[0.6967, 0.4432, 0.7616, 0.2722, 0.3858, 0.3439, 0.6094, 0.5486],
[0.0834, 0.0346, 0.8687, 0.2925, 0.5354, 0.2652, 0.7239, 0.5716],
[0.7481, 0.4821, 0.8982, 0.5283, 0.3879, 0.4561, 0.6644, 0.5748],
[0.7045, 0.4447, 0.8591, 0.3253, 0.4729, 0.2292, 0.6392, 0.5443]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.8525, 0.2217, 0.5412, 0.2367, 0.7367, 0.5482],
[0.6160, 0.4092, 0.8314, 0.4417, 0.3675, 0.4583, 0.5250, 0.5808],
[0.6202, 0.4066, 0.8398, 0.2648, 0.3925, 0.2627, 0.5845, 0.5124],
[0.6148, 0.3996, 0.8487, 0.3867, 0.3487, 0.4067, 0.5863, 0.5000],
[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334],
[0.0000, 0.0000, 0.8750, 0.2467, 0.5138, 0.2617, 0.7382, 0.5552],
[0.6271, 0.4081, 0.9081, 0.4894, 0.3700, 0.4283, 0.6661, 0.5274],
[0.6275, 0.4048, 0.8487, 0.2883, 0.4462, 0.2033, 0.6321, 0.5155]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0024, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0024, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.029495812923414633
step: 21
running loss: 0.0014045625201626016
Train Steps: 21/90 Loss: 0.0014 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6165, 0.4106, 0.7575, 0.1733, 0.3838, 0.2650, 0.5680, 0.5116],
[ nan, nan, 0.8488, 0.2300, 0.5563, 0.2100, 0.7390, 0.5679],
[0.6086, 0.3998, 0.8788, 0.4450, 0.4025, 0.4650, 0.5306, 0.5103],
[0.6214, 0.4175, 0.7300, 0.2883, 0.4338, 0.2167, 0.5698, 0.5773],
[0.6204, 0.4110, 0.7913, 0.2667, 0.4062, 0.2500, 0.6225, 0.5367],
[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.6133, 0.4094, 0.8495, 0.4028, 0.3588, 0.3200, 0.5003, 0.5407],
[0.6080, 0.4010, 0.8750, 0.4500, 0.4825, 0.5617, 0.5837, 0.5583]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6522, 0.4116, 0.7930, 0.2094, 0.4086, 0.2687, 0.5724, 0.5104],
[0.1545, 0.0771, 0.8851, 0.2805, 0.5526, 0.2638, 0.7352, 0.5587],
[0.5950, 0.3730, 0.9092, 0.4708, 0.4053, 0.4660, 0.5343, 0.5407],
[0.6627, 0.4341, 0.7680, 0.3104, 0.4542, 0.2209, 0.5618, 0.5739],
[0.6252, 0.3891, 0.8365, 0.2923, 0.4193, 0.2608, 0.6167, 0.5603],
[0.5939, 0.3655, 0.8846, 0.5923, 0.4072, 0.5317, 0.6605, 0.5606],
[0.6327, 0.4021, 0.8764, 0.4260, 0.3743, 0.3276, 0.5130, 0.5581],
[0.5707, 0.3681, 0.9099, 0.4746, 0.4918, 0.5689, 0.5726, 0.5683]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6165, 0.4106, 0.7575, 0.1733, 0.3837, 0.2650, 0.5680, 0.5116],
[0.0000, 0.0000, 0.8487, 0.2300, 0.5562, 0.2100, 0.7390, 0.5679],
[0.6086, 0.3998, 0.8788, 0.4450, 0.4025, 0.4650, 0.5306, 0.5103],
[0.6214, 0.4175, 0.7300, 0.2883, 0.4338, 0.2167, 0.5698, 0.5773],
[0.6204, 0.4110, 0.7912, 0.2667, 0.4062, 0.2500, 0.6225, 0.5367],
[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.6133, 0.4094, 0.8495, 0.4028, 0.3587, 0.3200, 0.5003, 0.5407],
[0.6080, 0.4010, 0.8750, 0.4500, 0.4825, 0.5617, 0.5838, 0.5583]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.030567696288926527
step: 22
running loss: 0.0013894407404057513
Train Steps: 22/90 Loss: 0.0014 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6095, 0.4002, 0.8533, 0.5168, 0.5031, 0.5094, 0.5125, 0.5433],
[0.6283, 0.4283, 0.7477, 0.3542, 0.5125, 0.1917, 0.5500, 0.6167],
[0.6336, 0.4086, 0.8900, 0.3950, 0.3900, 0.2950, 0.6504, 0.5066],
[ nan, nan, 0.9088, 0.3783, 0.4562, 0.2617, 0.6741, 0.5575],
[ nan, nan, 0.6935, 0.1930, 0.4150, 0.2250, 0.5450, 0.5650],
[ nan, nan, 0.7725, 0.2611, 0.3675, 0.2733, 0.5413, 0.5167],
[0.6259, 0.4156, 0.8812, 0.3183, 0.4775, 0.1867, 0.6219, 0.4960],
[0.6136, 0.4029, 0.8263, 0.3350, 0.3625, 0.3067, 0.5675, 0.5167]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6392, 0.4052, 0.8825, 0.5237, 0.4866, 0.5350, 0.5361, 0.5516],
[0.7080, 0.4577, 0.7620, 0.3528, 0.5123, 0.1878, 0.5503, 0.6081],
[0.6843, 0.4237, 0.9446, 0.3873, 0.4054, 0.3337, 0.6932, 0.5064],
[0.1743, 0.1102, 0.9388, 0.3837, 0.4724, 0.2862, 0.6806, 0.5682],
[0.1335, 0.0885, 0.7111, 0.2123, 0.4566, 0.2587, 0.5505, 0.5482],
[0.1014, 0.0485, 0.7536, 0.2699, 0.3843, 0.2945, 0.5392, 0.5497],
[0.5646, 0.3630, 0.9077, 0.3126, 0.4761, 0.2239, 0.6187, 0.5062],
[0.6201, 0.4074, 0.8433, 0.3348, 0.3664, 0.3087, 0.5544, 0.5099]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6095, 0.4002, 0.8533, 0.5168, 0.5031, 0.5094, 0.5125, 0.5433],
[0.6283, 0.4283, 0.7477, 0.3542, 0.5125, 0.1917, 0.5500, 0.6167],
[0.6336, 0.4086, 0.8900, 0.3950, 0.3900, 0.2950, 0.6504, 0.5066],
[0.0000, 0.0000, 0.9087, 0.3783, 0.4563, 0.2617, 0.6741, 0.5575],
[0.0000, 0.0000, 0.6935, 0.1930, 0.4150, 0.2250, 0.5450, 0.5650],
[0.0000, 0.0000, 0.7725, 0.2611, 0.3675, 0.2733, 0.5412, 0.5167],
[0.6259, 0.4156, 0.8813, 0.3183, 0.4775, 0.1867, 0.6219, 0.4960],
[0.6136, 0.4029, 0.8263, 0.3350, 0.3625, 0.3067, 0.5675, 0.5167]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03241958349826746
step: 23
running loss: 0.0014095471086203243
Train Steps: 23/90 Loss: 0.0014 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6361, 0.4071, 0.9100, 0.4783, 0.3738, 0.3967, 0.6670, 0.5332],
[0.6092, 0.4001, 0.8638, 0.4867, 0.4288, 0.5367, 0.5484, 0.5064],
[0.6260, 0.4161, 0.9000, 0.3833, 0.4450, 0.2133, 0.6237, 0.4986],
[0.6109, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117],
[0.6171, 0.4127, 0.8900, 0.4800, 0.4325, 0.5783, 0.5769, 0.5090],
[0.6153, 0.4119, 0.8463, 0.3833, 0.3600, 0.3200, 0.5106, 0.5563],
[0.6129, 0.3930, 0.8769, 0.5105, 0.4146, 0.5642, 0.6000, 0.5082],
[0.6223, 0.4171, 0.8750, 0.5500, 0.4050, 0.4817, 0.5675, 0.5600]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5196, 0.3046, 0.9327, 0.4675, 0.3851, 0.3874, 0.6833, 0.5238],
[0.5047, 0.3282, 0.8866, 0.4704, 0.4349, 0.5383, 0.5316, 0.5102],
[0.4951, 0.3208, 0.9140, 0.3828, 0.4615, 0.2056, 0.6317, 0.5085],
[0.5170, 0.3447, 0.8880, 0.4490, 0.3800, 0.3987, 0.5487, 0.5116],
[0.4440, 0.2850, 0.9048, 0.4702, 0.4556, 0.5799, 0.5876, 0.5062],
[0.4837, 0.3263, 0.8488, 0.3854, 0.3605, 0.3197, 0.5185, 0.5563],
[0.4881, 0.3055, 0.8886, 0.5065, 0.4360, 0.5546, 0.6133, 0.5081],
[0.5354, 0.3664, 0.8931, 0.5447, 0.4107, 0.4721, 0.5752, 0.5636]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6361, 0.4071, 0.9100, 0.4783, 0.3738, 0.3967, 0.6670, 0.5332],
[0.6092, 0.4001, 0.8637, 0.4867, 0.4288, 0.5367, 0.5484, 0.5064],
[0.6260, 0.4161, 0.9000, 0.3833, 0.4450, 0.2133, 0.6237, 0.4986],
[0.6108, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117],
[0.6171, 0.4127, 0.8900, 0.4800, 0.4325, 0.5783, 0.5769, 0.5090],
[0.6153, 0.4119, 0.8462, 0.3833, 0.3600, 0.3200, 0.5106, 0.5563],
[0.6129, 0.3930, 0.8769, 0.5105, 0.4146, 0.5642, 0.6000, 0.5082],
[0.6223, 0.4171, 0.8750, 0.5500, 0.4050, 0.4817, 0.5675, 0.5600]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0030, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0030, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.035387905983952805
step: 24
running loss: 0.0014744960826647002
Train Steps: 24/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6196, 0.4090, 0.8450, 0.3900, 0.3575, 0.3933, 0.5975, 0.5583],
[0.6250, 0.4131, 0.8688, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367],
[0.6343, 0.4097, 0.9287, 0.4367, 0.4313, 0.3600, 0.7248, 0.5841],
[0.6270, 0.4267, 0.7150, 0.3317, 0.4900, 0.1817, 0.5560, 0.6183],
[ nan, nan, 0.7097, 0.2346, 0.4250, 0.1850, 0.5175, 0.5583],
[0.6200, 0.4112, 0.8862, 0.4100, 0.3638, 0.4917, 0.6088, 0.6050],
[0.6307, 0.4060, 0.8950, 0.5183, 0.3750, 0.3850, 0.6338, 0.4938],
[0.6064, 0.4019, 0.8650, 0.4517, 0.4037, 0.5367, 0.5703, 0.5609]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.5617, 0.3751, 0.8700, 0.3838, 0.3548, 0.3857, 0.5578, 0.5258],
[ 0.5048, 0.3418, 0.8775, 0.3221, 0.4436, 0.2397, 0.6185, 0.4976],
[ 0.5276, 0.3512, 0.9314, 0.4296, 0.4197, 0.3713, 0.7200, 0.5474],
[ 0.5901, 0.4103, 0.7223, 0.2898, 0.4692, 0.1786, 0.5616, 0.5901],
[-0.0880, -0.0387, 0.7203, 0.2246, 0.4522, 0.1743, 0.5261, 0.5415],
[ 0.4960, 0.3342, 0.8938, 0.4103, 0.3636, 0.5101, 0.6043, 0.5562],
[ 0.4895, 0.3157, 0.9209, 0.5233, 0.3707, 0.3770, 0.6103, 0.4452],
[ 0.4501, 0.3161, 0.8708, 0.4482, 0.4058, 0.5794, 0.5658, 0.5021]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6196, 0.4090, 0.8450, 0.3900, 0.3575, 0.3933, 0.5975, 0.5583],
[0.6250, 0.4131, 0.8687, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367],
[0.6343, 0.4097, 0.9287, 0.4367, 0.4313, 0.3600, 0.7248, 0.5841],
[0.6270, 0.4266, 0.7150, 0.3317, 0.4900, 0.1817, 0.5560, 0.6183],
[0.0000, 0.0000, 0.7097, 0.2346, 0.4250, 0.1850, 0.5175, 0.5583],
[0.6200, 0.4112, 0.8863, 0.4100, 0.3638, 0.4917, 0.6087, 0.6050],
[0.6307, 0.4060, 0.8950, 0.5183, 0.3750, 0.3850, 0.6338, 0.4938],
[0.6064, 0.4019, 0.8650, 0.4517, 0.4038, 0.5367, 0.5703, 0.5609]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0024, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0024, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03780612416449003
step: 25
running loss: 0.0015122449665796011
Train Steps: 25/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6261, 0.4131, 0.8938, 0.3550, 0.4000, 0.2683, 0.6188, 0.5283],
[ nan, nan, 0.7192, 0.2346, 0.4037, 0.2050, 0.5138, 0.5650],
[0.6219, 0.4097, 0.8738, 0.3400, 0.3563, 0.4117, 0.5975, 0.5683],
[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466],
[0.6204, 0.4007, 0.7838, 0.2100, 0.4475, 0.1733, 0.5825, 0.5167],
[0.6226, 0.4103, 0.8575, 0.3450, 0.4388, 0.2067, 0.5787, 0.5383],
[0.6222, 0.3957, 0.8838, 0.5017, 0.3937, 0.4600, 0.5900, 0.5017],
[0.6346, 0.4165, 0.9138, 0.3983, 0.3875, 0.4317, 0.7469, 0.5471]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.4933, 0.3324, 0.9031, 0.3576, 0.3816, 0.2557, 0.6110, 0.5010],
[-0.1040, -0.0676, 0.7089, 0.2206, 0.4172, 0.1880, 0.5342, 0.5466],
[ 0.5285, 0.3772, 0.8592, 0.3481, 0.3227, 0.3968, 0.5869, 0.5273],
[ 0.5383, 0.3741, 0.7581, 0.3609, 0.3283, 0.4108, 0.5078, 0.5228],
[ 0.5499, 0.3637, 0.7490, 0.2379, 0.4342, 0.1393, 0.5775, 0.4974],
[ 0.4884, 0.3450, 0.8489, 0.3635, 0.4307, 0.2122, 0.5531, 0.5142],
[ 0.4173, 0.2685, 0.8786, 0.4987, 0.3810, 0.4578, 0.5729, 0.4654],
[ 0.4876, 0.3254, 0.9143, 0.3999, 0.3792, 0.4312, 0.7038, 0.5270]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6261, 0.4131, 0.8938, 0.3550, 0.4000, 0.2683, 0.6187, 0.5283],
[0.0000, 0.0000, 0.7192, 0.2346, 0.4038, 0.2050, 0.5138, 0.5650],
[0.6219, 0.4097, 0.8737, 0.3400, 0.3562, 0.4117, 0.5975, 0.5683],
[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466],
[0.6204, 0.4007, 0.7837, 0.2100, 0.4475, 0.1733, 0.5825, 0.5167],
[0.6226, 0.4103, 0.8575, 0.3450, 0.4387, 0.2067, 0.5788, 0.5383],
[0.6222, 0.3957, 0.8838, 0.5017, 0.3938, 0.4600, 0.5900, 0.5017],
[0.6346, 0.4165, 0.9137, 0.3983, 0.3875, 0.4317, 0.7469, 0.5471]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0029, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0029, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.040753726119874045
step: 26
running loss: 0.0015674510046105401
Train Steps: 26/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6211, 0.3935, 0.8636, 0.4841, 0.4417, 0.5126, 0.6331, 0.5268],
[0.6161, 0.4099, 0.8738, 0.4383, 0.3788, 0.5483, 0.5605, 0.5019],
[0.6151, 0.4125, 0.8738, 0.4417, 0.3575, 0.3783, 0.5138, 0.5483],
[0.6277, 0.4013, 0.8888, 0.4767, 0.3600, 0.3567, 0.6148, 0.4672],
[0.6176, 0.4030, 0.8850, 0.4850, 0.3688, 0.4050, 0.5312, 0.5783],
[0.6193, 0.4165, 0.8838, 0.4700, 0.4150, 0.4867, 0.5427, 0.5261],
[0.6277, 0.4118, 0.8988, 0.3833, 0.3950, 0.2650, 0.6290, 0.4938],
[0.6095, 0.3970, 0.8688, 0.4767, 0.4860, 0.4879, 0.5191, 0.4940]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4985, 0.3262, 0.8613, 0.4730, 0.4176, 0.4879, 0.6350, 0.5325],
[0.5425, 0.3775, 0.8711, 0.4228, 0.3583, 0.5446, 0.5575, 0.5107],
[0.5347, 0.3735, 0.8484, 0.4161, 0.3385, 0.3609, 0.5067, 0.5492],
[0.5321, 0.3510, 0.8759, 0.4189, 0.3166, 0.3310, 0.6180, 0.4916],
[0.5305, 0.3616, 0.8636, 0.4562, 0.3478, 0.3919, 0.5319, 0.5672],
[0.5022, 0.3362, 0.8598, 0.4538, 0.3929, 0.4576, 0.5421, 0.5218],
[0.5116, 0.3473, 0.8895, 0.3635, 0.3684, 0.2352, 0.6363, 0.5174],
[0.4949, 0.3282, 0.8744, 0.4593, 0.4581, 0.4634, 0.5353, 0.5341]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6211, 0.3935, 0.8636, 0.4841, 0.4417, 0.5126, 0.6331, 0.5268],
[0.6161, 0.4099, 0.8737, 0.4383, 0.3787, 0.5483, 0.5605, 0.5019],
[0.6151, 0.4125, 0.8737, 0.4417, 0.3575, 0.3783, 0.5138, 0.5483],
[0.6277, 0.4013, 0.8888, 0.4767, 0.3600, 0.3567, 0.6148, 0.4672],
[0.6176, 0.4030, 0.8850, 0.4850, 0.3688, 0.4050, 0.5312, 0.5783],
[0.6193, 0.4165, 0.8838, 0.4700, 0.4150, 0.4867, 0.5427, 0.5261],
[0.6277, 0.4117, 0.8988, 0.3833, 0.3950, 0.2650, 0.6290, 0.4938],
[0.6095, 0.3970, 0.8687, 0.4767, 0.4860, 0.4879, 0.5191, 0.4940]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0021, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0021, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.042814259621081874
step: 27
running loss: 0.0015857133192993286
Train Steps: 27/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6185, 0.4129, 0.8900, 0.4567, 0.3937, 0.5417, 0.5734, 0.5110],
[0.6250, 0.4013, 0.8525, 0.5417, 0.4037, 0.5117, 0.6325, 0.5017],
[0.6254, 0.4076, 0.8700, 0.3267, 0.4150, 0.3083, 0.7050, 0.5609],
[ nan, nan, 0.7335, 0.2569, 0.3788, 0.2667, 0.5066, 0.5578],
[0.6229, 0.4086, 0.7538, 0.2600, 0.4775, 0.1617, 0.5900, 0.5383],
[0.6173, 0.4114, 0.7325, 0.2500, 0.4213, 0.1917, 0.5338, 0.5700],
[0.6307, 0.3998, 0.8500, 0.5233, 0.3850, 0.5050, 0.7446, 0.5320],
[0.6209, 0.3920, 0.8650, 0.5367, 0.4400, 0.5067, 0.6025, 0.4950]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.5983, 0.4167, 0.8870, 0.4386, 0.3617, 0.5374, 0.5467, 0.5090],
[ 0.6104, 0.4011, 0.8272, 0.5336, 0.3790, 0.4975, 0.5823, 0.4976],
[ 0.5249, 0.3588, 0.8783, 0.3062, 0.3926, 0.2847, 0.6929, 0.5565],
[-0.1273, -0.0658, 0.7397, 0.2481, 0.3711, 0.2330, 0.5285, 0.5775],
[ 0.5797, 0.4041, 0.7436, 0.2373, 0.4315, 0.1334, 0.5688, 0.5258],
[ 0.6172, 0.4352, 0.7226, 0.2292, 0.3858, 0.1790, 0.5193, 0.5609],
[ 0.6064, 0.3998, 0.8377, 0.5035, 0.3568, 0.5040, 0.6954, 0.5307],
[ 0.6284, 0.4079, 0.8532, 0.4978, 0.3948, 0.4959, 0.5576, 0.4846]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6186, 0.4129, 0.8900, 0.4567, 0.3938, 0.5417, 0.5734, 0.5110],
[0.6250, 0.4013, 0.8525, 0.5417, 0.4038, 0.5117, 0.6325, 0.5017],
[0.6254, 0.4076, 0.8700, 0.3267, 0.4150, 0.3083, 0.7050, 0.5609],
[0.0000, 0.0000, 0.7335, 0.2569, 0.3787, 0.2667, 0.5066, 0.5578],
[0.6229, 0.4086, 0.7538, 0.2600, 0.4775, 0.1617, 0.5900, 0.5383],
[0.6173, 0.4114, 0.7325, 0.2500, 0.4212, 0.1917, 0.5337, 0.5700],
[0.6307, 0.3998, 0.8500, 0.5233, 0.3850, 0.5050, 0.7446, 0.5320],
[0.6209, 0.3920, 0.8650, 0.5367, 0.4400, 0.5067, 0.6025, 0.4950]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.043800648621981964
step: 28
running loss: 0.0015643088793564988
Train Steps: 28/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6147, 0.4107, 0.8137, 0.3333, 0.3750, 0.2683, 0.5006, 0.5412],
[0.6185, 0.4080, 0.8625, 0.3483, 0.3788, 0.2650, 0.5320, 0.5272],
[0.6251, 0.4163, 0.8662, 0.4467, 0.3625, 0.3567, 0.6038, 0.5533],
[0.6164, 0.3972, 0.7818, 0.3381, 0.3599, 0.3387, 0.5880, 0.5153],
[0.6125, 0.4010, 0.8650, 0.4567, 0.3663, 0.3900, 0.5600, 0.5567],
[0.6276, 0.4235, 0.8888, 0.5333, 0.3800, 0.3117, 0.5427, 0.6164],
[0.6111, 0.4033, 0.8300, 0.3267, 0.3588, 0.3333, 0.5444, 0.5637],
[0.6130, 0.4072, 0.8550, 0.4567, 0.3638, 0.3667, 0.5290, 0.5892]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5070, 0.3404, 0.7796, 0.3037, 0.3528, 0.2542, 0.5178, 0.5303],
[0.5961, 0.3965, 0.8401, 0.3414, 0.3790, 0.2841, 0.5402, 0.5174],
[0.6057, 0.3977, 0.8470, 0.4220, 0.3571, 0.3361, 0.6071, 0.5284],
[0.5779, 0.3969, 0.7766, 0.3082, 0.3443, 0.3543, 0.5923, 0.5151],
[0.6144, 0.4063, 0.8500, 0.4293, 0.3710, 0.4007, 0.5790, 0.5648],
[0.5379, 0.3636, 0.8434, 0.5175, 0.3964, 0.3437, 0.5801, 0.5920],
[0.6287, 0.4280, 0.8185, 0.3094, 0.3471, 0.3301, 0.5489, 0.5375],
[0.6084, 0.4077, 0.8355, 0.4366, 0.3513, 0.3734, 0.5412, 0.5617]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6147, 0.4107, 0.8138, 0.3333, 0.3750, 0.2683, 0.5006, 0.5412],
[0.6186, 0.4080, 0.8625, 0.3483, 0.3787, 0.2650, 0.5320, 0.5272],
[0.6252, 0.4162, 0.8662, 0.4467, 0.3625, 0.3567, 0.6037, 0.5533],
[0.6164, 0.3972, 0.7818, 0.3381, 0.3599, 0.3387, 0.5880, 0.5153],
[0.6125, 0.4010, 0.8650, 0.4567, 0.3663, 0.3900, 0.5600, 0.5567],
[0.6276, 0.4235, 0.8888, 0.5333, 0.3800, 0.3117, 0.5427, 0.6164],
[0.6111, 0.4033, 0.8300, 0.3267, 0.3587, 0.3333, 0.5444, 0.5637],
[0.6130, 0.4072, 0.8550, 0.4567, 0.3638, 0.3667, 0.5290, 0.5892]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.044581994734471664
step: 29
running loss: 0.0015373101632576436
Train Steps: 29/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6148, 0.4053, 0.8750, 0.4550, 0.4850, 0.5218, 0.5863, 0.5567],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533],
[0.6339, 0.4159, 0.8400, 0.5617, 0.3825, 0.4150, 0.7343, 0.5748],
[0.6084, 0.3981, 0.8588, 0.5233, 0.4600, 0.5367, 0.5680, 0.5006],
[0.6282, 0.4029, 0.8988, 0.3000, 0.4250, 0.4183, 0.7042, 0.5575],
[0.6339, 0.4123, 0.8638, 0.5367, 0.4075, 0.5467, 0.7517, 0.5436],
[0.6040, 0.4002, 0.7338, 0.2267, 0.3975, 0.2100, 0.5231, 0.4778],
[0.6202, 0.4054, 0.8892, 0.4428, 0.3642, 0.3249, 0.5840, 0.5426]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5954, 0.4118, 0.8543, 0.4456, 0.4525, 0.4905, 0.5458, 0.5619],
[0.6419, 0.4508, 0.8598, 0.4282, 0.4053, 0.5013, 0.5462, 0.5402],
[0.6981, 0.4758, 0.8232, 0.5364, 0.3724, 0.3886, 0.6626, 0.5528],
[0.6648, 0.4608, 0.8242, 0.5233, 0.4306, 0.5186, 0.5066, 0.5186],
[0.6749, 0.4485, 0.8571, 0.3060, 0.3899, 0.3924, 0.6725, 0.5735],
[0.6380, 0.4405, 0.8437, 0.5172, 0.3811, 0.5291, 0.7002, 0.5559],
[0.6293, 0.4254, 0.7027, 0.2040, 0.3756, 0.1766, 0.5020, 0.5047],
[0.6604, 0.4439, 0.8687, 0.4279, 0.3489, 0.3185, 0.5489, 0.5276]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6148, 0.4053, 0.8750, 0.4550, 0.4850, 0.5218, 0.5863, 0.5567],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533],
[0.6339, 0.4159, 0.8400, 0.5617, 0.3825, 0.4150, 0.7343, 0.5748],
[0.6084, 0.3981, 0.8587, 0.5233, 0.4600, 0.5367, 0.5680, 0.5006],
[0.6282, 0.4029, 0.8988, 0.3000, 0.4250, 0.4183, 0.7042, 0.5575],
[0.6339, 0.4123, 0.8637, 0.5367, 0.4075, 0.5467, 0.7517, 0.5436],
[0.6040, 0.4002, 0.7337, 0.2267, 0.3975, 0.2100, 0.5231, 0.4778],
[0.6202, 0.4054, 0.8892, 0.4428, 0.3642, 0.3249, 0.5840, 0.5426]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04559074839926325
step: 30
running loss: 0.001519691613308775
Train Steps: 30/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6060, 0.3924, 0.8450, 0.5717, 0.4200, 0.5217, 0.5253, 0.4752],
[0.6305, 0.3983, 0.8950, 0.4833, 0.3688, 0.4683, 0.6375, 0.5117],
[0.6147, 0.4112, 0.7988, 0.3200, 0.3775, 0.2767, 0.5150, 0.5550],
[0.6167, 0.4048, 0.6831, 0.3639, 0.3763, 0.3017, 0.5700, 0.5883],
[0.6201, 0.4004, 0.8786, 0.5043, 0.3833, 0.5138, 0.5997, 0.5092],
[0.6110, 0.3984, 0.8750, 0.4933, 0.4625, 0.4950, 0.5578, 0.5676],
[0.6196, 0.4068, 0.7645, 0.2234, 0.4575, 0.1737, 0.5926, 0.5284],
[0.6332, 0.4118, 0.9238, 0.4267, 0.4012, 0.4733, 0.7525, 0.5436]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6383, 0.4051, 0.8426, 0.5858, 0.4593, 0.5259, 0.5491, 0.5228],
[0.7065, 0.4534, 0.8905, 0.4899, 0.3710, 0.4799, 0.6445, 0.5080],
[0.6552, 0.4527, 0.7933, 0.3352, 0.3711, 0.2825, 0.5235, 0.5575],
[0.7061, 0.4787, 0.7113, 0.3436, 0.3689, 0.3042, 0.5457, 0.5738],
[0.6846, 0.4498, 0.8709, 0.5279, 0.3860, 0.5291, 0.6037, 0.5104],
[0.6956, 0.4875, 0.8825, 0.5053, 0.4610, 0.5115, 0.5537, 0.5858],
[0.5936, 0.3968, 0.7494, 0.2417, 0.4437, 0.1887, 0.5902, 0.5428],
[0.7195, 0.4881, 0.8953, 0.4497, 0.4147, 0.4874, 0.7514, 0.5634]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6060, 0.3924, 0.8450, 0.5717, 0.4200, 0.5217, 0.5253, 0.4752],
[0.6305, 0.3983, 0.8950, 0.4833, 0.3688, 0.4683, 0.6375, 0.5117],
[0.6147, 0.4112, 0.7987, 0.3200, 0.3775, 0.2767, 0.5150, 0.5550],
[0.6167, 0.4048, 0.6831, 0.3639, 0.3762, 0.3017, 0.5700, 0.5883],
[0.6201, 0.4004, 0.8786, 0.5043, 0.3833, 0.5138, 0.5997, 0.5092],
[0.6110, 0.3984, 0.8750, 0.4933, 0.4625, 0.4950, 0.5578, 0.5676],
[0.6196, 0.4068, 0.7645, 0.2234, 0.4575, 0.1737, 0.5926, 0.5284],
[0.6332, 0.4118, 0.9237, 0.4267, 0.4013, 0.4733, 0.7525, 0.5436]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04676109258434735
step: 31
running loss: 0.0015084223414305598
Train Steps: 31/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6277, 0.4057, 0.8300, 0.2650, 0.4363, 0.1850, 0.6140, 0.4823],
[0.6197, 0.4090, 0.7825, 0.2500, 0.4200, 0.2483, 0.5988, 0.5667],
[0.6125, 0.3999, 0.8750, 0.4883, 0.4750, 0.4700, 0.5533, 0.5617],
[0.6222, 0.3957, 0.8838, 0.5017, 0.3937, 0.4600, 0.5900, 0.5017],
[0.6225, 0.4116, 0.8662, 0.3517, 0.3663, 0.3233, 0.5837, 0.5317],
[0.6307, 0.4029, 0.8988, 0.4817, 0.3937, 0.3500, 0.7311, 0.5378],
[0.6059, 0.4002, 0.7562, 0.2767, 0.3538, 0.3033, 0.5529, 0.5455],
[0.6280, 0.4055, 0.8600, 0.5317, 0.3800, 0.4700, 0.6275, 0.5133]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6692, 0.4374, 0.8151, 0.2765, 0.4514, 0.2167, 0.6261, 0.5162],
[0.5933, 0.3883, 0.7637, 0.2549, 0.4119, 0.2749, 0.5830, 0.6016],
[0.6993, 0.4590, 0.8689, 0.5085, 0.4934, 0.4897, 0.5562, 0.5860],
[0.6885, 0.4309, 0.8752, 0.5305, 0.4021, 0.4740, 0.5839, 0.5138],
[0.7271, 0.4863, 0.8403, 0.3473, 0.3716, 0.3249, 0.5934, 0.5531],
[0.7110, 0.4639, 0.8905, 0.4920, 0.4118, 0.3469, 0.7221, 0.5454],
[0.7115, 0.4821, 0.7279, 0.3006, 0.3740, 0.3376, 0.5692, 0.5613],
[0.7465, 0.4876, 0.8552, 0.5547, 0.3968, 0.4857, 0.6460, 0.5347]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6277, 0.4056, 0.8300, 0.2650, 0.4363, 0.1850, 0.6140, 0.4823],
[0.6197, 0.4090, 0.7825, 0.2500, 0.4200, 0.2483, 0.5987, 0.5667],
[0.6125, 0.3999, 0.8750, 0.4883, 0.4750, 0.4700, 0.5533, 0.5617],
[0.6222, 0.3957, 0.8838, 0.5017, 0.3938, 0.4600, 0.5900, 0.5017],
[0.6225, 0.4116, 0.8662, 0.3517, 0.3663, 0.3233, 0.5838, 0.5317],
[0.6307, 0.4029, 0.8988, 0.4817, 0.3938, 0.3500, 0.7311, 0.5378],
[0.6059, 0.4002, 0.7563, 0.2767, 0.3537, 0.3033, 0.5529, 0.5455],
[0.6280, 0.4055, 0.8600, 0.5317, 0.3800, 0.4700, 0.6275, 0.5133]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.048350871045840904
step: 32
running loss: 0.0015109647201825283
Train Steps: 32/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6204, 0.4007, 0.7838, 0.2100, 0.4475, 0.1733, 0.5825, 0.5167],
[0.6223, 0.3990, 0.8037, 0.2800, 0.4000, 0.2283, 0.5864, 0.5208],
[0.6196, 0.4090, 0.8450, 0.3900, 0.3575, 0.3933, 0.5975, 0.5583],
[0.6140, 0.4070, 0.8700, 0.5000, 0.4612, 0.4900, 0.5260, 0.5852],
[0.6311, 0.4008, 0.7935, 0.5746, 0.3900, 0.5033, 0.6955, 0.5366],
[ nan, nan, 0.7515, 0.2708, 0.3987, 0.2267, 0.5162, 0.5567],
[0.6271, 0.4024, 0.9000, 0.3517, 0.3700, 0.4517, 0.6931, 0.5285],
[0.6101, 0.3977, 0.8550, 0.5667, 0.3862, 0.4417, 0.5128, 0.4869]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7183, 0.4435, 0.7780, 0.2519, 0.4622, 0.1673, 0.6079, 0.5254],
[0.6890, 0.4253, 0.8122, 0.2988, 0.4185, 0.2408, 0.6214, 0.5200],
[0.7704, 0.4847, 0.8624, 0.4061, 0.3801, 0.4079, 0.6020, 0.5743],
[0.7668, 0.4961, 0.9040, 0.5122, 0.4858, 0.4915, 0.5727, 0.5860],
[0.7760, 0.4867, 0.8250, 0.5689, 0.4193, 0.4985, 0.7223, 0.5521],
[0.1626, 0.0791, 0.7773, 0.2831, 0.4128, 0.2344, 0.5432, 0.5718],
[0.7430, 0.4662, 0.8972, 0.3785, 0.4033, 0.4556, 0.7315, 0.5490],
[0.7862, 0.4972, 0.8749, 0.5722, 0.4226, 0.4457, 0.5695, 0.4978]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6204, 0.4007, 0.7837, 0.2100, 0.4475, 0.1733, 0.5825, 0.5167],
[0.6223, 0.3990, 0.8037, 0.2800, 0.4000, 0.2283, 0.5864, 0.5208],
[0.6196, 0.4090, 0.8450, 0.3900, 0.3575, 0.3933, 0.5975, 0.5583],
[0.6140, 0.4070, 0.8700, 0.5000, 0.4613, 0.4900, 0.5260, 0.5852],
[0.6311, 0.4008, 0.7935, 0.5746, 0.3900, 0.5033, 0.6955, 0.5366],
[0.0000, 0.0000, 0.7515, 0.2708, 0.3988, 0.2267, 0.5163, 0.5567],
[0.6271, 0.4024, 0.9000, 0.3517, 0.3700, 0.4517, 0.6931, 0.5285],
[0.6101, 0.3977, 0.8550, 0.5667, 0.3862, 0.4417, 0.5128, 0.4869]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0034, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0034, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0517900716222357
step: 33
running loss: 0.0015693961097647182
Train Steps: 33/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6239, 0.4123, 0.8313, 0.2550, 0.4500, 0.2050, 0.6175, 0.5400],
[0.6200, 0.4049, 0.8638, 0.5617, 0.4125, 0.5100, 0.6013, 0.5317],
[0.6225, 0.4116, 0.8662, 0.3517, 0.3663, 0.3233, 0.5837, 0.5317],
[0.6286, 0.4040, 0.8696, 0.3047, 0.3924, 0.2887, 0.6300, 0.5367],
[0.6224, 0.4097, 0.7438, 0.2267, 0.3850, 0.2850, 0.5988, 0.5250],
[0.6138, 0.4020, 0.8800, 0.4717, 0.4375, 0.4717, 0.5502, 0.5611],
[0.6129, 0.4063, 0.8738, 0.5250, 0.4313, 0.4733, 0.5230, 0.5874],
[0.6307, 0.4060, 0.8950, 0.5183, 0.3750, 0.3850, 0.6338, 0.4938]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6262, 0.4034, 0.8379, 0.2548, 0.4757, 0.2024, 0.6381, 0.5267],
[0.6725, 0.4191, 0.8749, 0.5841, 0.4385, 0.5090, 0.6299, 0.5375],
[0.6988, 0.4461, 0.8549, 0.3476, 0.3818, 0.3153, 0.6010, 0.5361],
[0.6572, 0.4037, 0.8795, 0.3257, 0.4055, 0.2845, 0.6564, 0.5286],
[0.6318, 0.4080, 0.7481, 0.2524, 0.4223, 0.3030, 0.6058, 0.5469],
[0.6642, 0.4098, 0.8865, 0.4767, 0.4578, 0.4683, 0.5849, 0.5601],
[0.6951, 0.4315, 0.8775, 0.5485, 0.4589, 0.4654, 0.5631, 0.5894],
[0.6888, 0.4206, 0.9079, 0.5414, 0.3968, 0.3758, 0.6470, 0.4819]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6239, 0.4123, 0.8313, 0.2550, 0.4500, 0.2050, 0.6175, 0.5400],
[0.6199, 0.4049, 0.8637, 0.5617, 0.4125, 0.5100, 0.6012, 0.5317],
[0.6225, 0.4116, 0.8662, 0.3517, 0.3663, 0.3233, 0.5838, 0.5317],
[0.6286, 0.4040, 0.8696, 0.3047, 0.3924, 0.2887, 0.6300, 0.5367],
[0.6224, 0.4097, 0.7437, 0.2267, 0.3850, 0.2850, 0.5987, 0.5250],
[0.6138, 0.4020, 0.8800, 0.4717, 0.4375, 0.4717, 0.5502, 0.5611],
[0.6130, 0.4063, 0.8737, 0.5250, 0.4313, 0.4733, 0.5230, 0.5874],
[0.6307, 0.4060, 0.8950, 0.5183, 0.3750, 0.3850, 0.6338, 0.4938]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.052406656759558246
step: 34
running loss: 0.001541372257634066
Train Steps: 34/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6229, 0.4066, 0.7612, 0.2967, 0.4250, 0.2167, 0.5925, 0.5350],
[0.6268, 0.4029, 0.8500, 0.2683, 0.3937, 0.3500, 0.6860, 0.5297],
[0.6264, 0.4035, 0.8888, 0.4883, 0.4050, 0.5217, 0.6361, 0.4791],
[0.6329, 0.4196, 0.9238, 0.4583, 0.4263, 0.2933, 0.7343, 0.5748],
[0.6185, 0.4129, 0.8900, 0.4567, 0.3937, 0.5417, 0.5734, 0.5110],
[0.6137, 0.4035, 0.8850, 0.4417, 0.3900, 0.4283, 0.5449, 0.5617],
[0.6250, 0.4106, 0.8700, 0.3717, 0.3588, 0.4967, 0.6038, 0.5167],
[0.6192, 0.4128, 0.8513, 0.5617, 0.4200, 0.5267, 0.5850, 0.5633]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6202, 0.3780, 0.7768, 0.2914, 0.4400, 0.2355, 0.5699, 0.5551],
[0.6527, 0.4156, 0.8333, 0.2886, 0.3895, 0.3419, 0.6861, 0.5263],
[0.7031, 0.4200, 0.8915, 0.5075, 0.4197, 0.4965, 0.6249, 0.4885],
[0.5822, 0.3480, 0.9264, 0.4856, 0.4590, 0.2685, 0.7117, 0.5417],
[0.7206, 0.4528, 0.9131, 0.4676, 0.4242, 0.5323, 0.5750, 0.5227],
[0.6428, 0.3892, 0.8874, 0.4650, 0.4004, 0.4453, 0.5611, 0.5443],
[0.6559, 0.4030, 0.8732, 0.3825, 0.3912, 0.4849, 0.6456, 0.5597],
[0.6766, 0.4138, 0.8838, 0.5775, 0.4509, 0.5091, 0.5833, 0.5711]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6229, 0.4066, 0.7613, 0.2967, 0.4250, 0.2167, 0.5925, 0.5350],
[0.6268, 0.4029, 0.8500, 0.2683, 0.3938, 0.3500, 0.6860, 0.5297],
[0.6264, 0.4035, 0.8888, 0.4883, 0.4050, 0.5217, 0.6361, 0.4791],
[0.6329, 0.4196, 0.9237, 0.4583, 0.4263, 0.2933, 0.7343, 0.5748],
[0.6186, 0.4129, 0.8900, 0.4567, 0.3938, 0.5417, 0.5734, 0.5110],
[0.6137, 0.4035, 0.8850, 0.4417, 0.3900, 0.4283, 0.5449, 0.5617],
[0.6250, 0.4105, 0.8700, 0.3717, 0.3587, 0.4967, 0.6037, 0.5167],
[0.6192, 0.4128, 0.8512, 0.5617, 0.4200, 0.5267, 0.5850, 0.5633]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05321587107027881
step: 35
running loss: 0.001520453459150823
Train Steps: 35/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6274, 0.4117, 0.8100, 0.5801, 0.4000, 0.4583, 0.5582, 0.6118],
[0.6199, 0.4060, 0.8888, 0.4667, 0.3800, 0.5050, 0.6188, 0.5433],
[0.6127, 0.4118, 0.8650, 0.5083, 0.4088, 0.5367, 0.5300, 0.5456],
[0.6261, 0.4066, 0.8325, 0.2150, 0.4763, 0.2667, 0.7002, 0.5633],
[ nan, nan, 0.8888, 0.3100, 0.5262, 0.2817, 0.7145, 0.6003],
[0.6182, 0.3998, 0.8793, 0.4191, 0.3552, 0.4285, 0.6038, 0.5312],
[0.6317, 0.4038, 0.8287, 0.5900, 0.3800, 0.4717, 0.6295, 0.4986],
[0.6072, 0.4029, 0.7037, 0.2150, 0.3912, 0.2267, 0.5516, 0.5507]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6875, 0.4320, 0.8564, 0.5744, 0.4058, 0.4555, 0.5670, 0.5928],
[0.6644, 0.4154, 0.9198, 0.4740, 0.3834, 0.5058, 0.6488, 0.5174],
[0.6649, 0.4253, 0.8915, 0.5074, 0.4305, 0.5249, 0.5541, 0.5414],
[0.6130, 0.3686, 0.8652, 0.2302, 0.4823, 0.2487, 0.7005, 0.5395],
[0.0716, 0.0118, 0.9327, 0.3118, 0.5047, 0.2719, 0.7061, 0.5590],
[0.7000, 0.4239, 0.8849, 0.3953, 0.3745, 0.4427, 0.6062, 0.5183],
[0.6816, 0.4226, 0.8694, 0.5829, 0.3913, 0.4535, 0.6265, 0.4815],
[0.7006, 0.4562, 0.7253, 0.2361, 0.4113, 0.2272, 0.5532, 0.5245]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6274, 0.4117, 0.8100, 0.5801, 0.4000, 0.4583, 0.5582, 0.6118],
[0.6199, 0.4060, 0.8888, 0.4667, 0.3800, 0.5050, 0.6187, 0.5433],
[0.6127, 0.4118, 0.8650, 0.5083, 0.4087, 0.5367, 0.5300, 0.5456],
[0.6261, 0.4066, 0.8325, 0.2150, 0.4762, 0.2667, 0.7002, 0.5633],
[0.0000, 0.0000, 0.8888, 0.3100, 0.5263, 0.2817, 0.7145, 0.6003],
[0.6182, 0.3998, 0.8793, 0.4191, 0.3552, 0.4285, 0.6038, 0.5312],
[0.6317, 0.4038, 0.8288, 0.5900, 0.3800, 0.4717, 0.6295, 0.4986],
[0.6072, 0.4029, 0.7038, 0.2150, 0.3913, 0.2267, 0.5516, 0.5507]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05410699962521903
step: 36
running loss: 0.0015029722118116398
Train Steps: 36/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.7225, 0.2167, 0.3987, 0.2283, 0.5427, 0.5181],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4012, 0.4633, 0.5338, 0.5767],
[0.6196, 0.4090, 0.8450, 0.3900, 0.3575, 0.3933, 0.5975, 0.5583],
[0.6229, 0.4107, 0.8137, 0.2883, 0.4750, 0.1717, 0.5813, 0.5400],
[0.6192, 0.3980, 0.7078, 0.2750, 0.4250, 0.2100, 0.5450, 0.5783],
[0.6198, 0.4164, 0.8700, 0.5067, 0.4625, 0.5650, 0.5464, 0.5197],
[0.6274, 0.4270, 0.8938, 0.4967, 0.3550, 0.4283, 0.5700, 0.5733],
[0.6277, 0.4029, 0.8250, 0.2433, 0.4325, 0.2100, 0.6366, 0.5207]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.1819, 0.1039, 0.7380, 0.1940, 0.3809, 0.2428, 0.5503, 0.5216],
[0.5895, 0.3619, 0.9011, 0.5202, 0.3940, 0.4769, 0.5646, 0.5651],
[0.6023, 0.3690, 0.8773, 0.3985, 0.3527, 0.3939, 0.6104, 0.5608],
[0.5871, 0.3863, 0.8467, 0.2964, 0.4725, 0.2073, 0.5912, 0.5331],
[0.5822, 0.3717, 0.7326, 0.2561, 0.4252, 0.2154, 0.5554, 0.5833],
[0.5647, 0.3731, 0.8998, 0.5127, 0.4519, 0.5512, 0.5964, 0.5058],
[0.6267, 0.3978, 0.9258, 0.5146, 0.3502, 0.4465, 0.6199, 0.5489],
[0.6408, 0.3909, 0.8375, 0.2682, 0.4460, 0.2356, 0.6727, 0.5104]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.7225, 0.2167, 0.3988, 0.2283, 0.5427, 0.5181],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4013, 0.4633, 0.5337, 0.5767],
[0.6196, 0.4090, 0.8450, 0.3900, 0.3575, 0.3933, 0.5975, 0.5583],
[0.6229, 0.4107, 0.8138, 0.2883, 0.4750, 0.1717, 0.5813, 0.5400],
[0.6192, 0.3980, 0.7078, 0.2750, 0.4250, 0.2100, 0.5450, 0.5783],
[0.6198, 0.4164, 0.8700, 0.5067, 0.4625, 0.5650, 0.5464, 0.5197],
[0.6274, 0.4270, 0.8938, 0.4967, 0.3550, 0.4283, 0.5700, 0.5733],
[0.6277, 0.4029, 0.8250, 0.2433, 0.4325, 0.2100, 0.6366, 0.5207]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05532921847770922
step: 37
running loss: 0.0014953842831813302
Train Steps: 37/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6283, 0.4283, 0.7477, 0.3542, 0.5125, 0.1917, 0.5500, 0.6167],
[0.6200, 0.4071, 0.7338, 0.1917, 0.4200, 0.2450, 0.6150, 0.5517],
[0.6164, 0.3972, 0.7818, 0.3381, 0.3599, 0.3387, 0.5880, 0.5153],
[ nan, nan, 0.8625, 0.2550, 0.5487, 0.2200, 0.7335, 0.5737],
[0.6185, 0.4098, 0.8838, 0.4900, 0.4537, 0.5800, 0.6288, 0.5400],
[0.6268, 0.4029, 0.8500, 0.2683, 0.3937, 0.3500, 0.6860, 0.5297],
[0.6203, 0.4021, 0.8780, 0.5031, 0.3667, 0.3882, 0.5842, 0.5405],
[0.6207, 0.4110, 0.8738, 0.5000, 0.4800, 0.5633, 0.6300, 0.5433]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.5584, 0.3814, 0.7396, 0.3220, 0.4831, 0.1942, 0.5172, 0.6068],
[ 0.5950, 0.3975, 0.7396, 0.1990, 0.3960, 0.2508, 0.5917, 0.5550],
[ 0.5619, 0.3668, 0.7915, 0.3295, 0.3272, 0.3418, 0.5757, 0.5112],
[-0.0712, -0.0459, 0.8614, 0.2210, 0.4886, 0.2268, 0.6629, 0.5561],
[ 0.5797, 0.3691, 0.8868, 0.4916, 0.4381, 0.5639, 0.5886, 0.5283],
[ 0.5762, 0.3851, 0.8199, 0.2775, 0.3516, 0.3389, 0.6678, 0.5093],
[ 0.6372, 0.4073, 0.8711, 0.5256, 0.3495, 0.3846, 0.5695, 0.5189],
[ 0.6062, 0.3832, 0.8912, 0.4883, 0.4486, 0.5551, 0.5764, 0.5444]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6283, 0.4283, 0.7477, 0.3542, 0.5125, 0.1917, 0.5500, 0.6167],
[0.6200, 0.4071, 0.7337, 0.1917, 0.4200, 0.2450, 0.6150, 0.5517],
[0.6164, 0.3972, 0.7818, 0.3381, 0.3599, 0.3387, 0.5880, 0.5153],
[0.0000, 0.0000, 0.8625, 0.2550, 0.5487, 0.2200, 0.7335, 0.5737],
[0.6185, 0.4098, 0.8838, 0.4900, 0.4538, 0.5800, 0.6288, 0.5400],
[0.6268, 0.4029, 0.8500, 0.2683, 0.3938, 0.3500, 0.6860, 0.5297],
[0.6203, 0.4020, 0.8780, 0.5031, 0.3667, 0.3882, 0.5842, 0.5405],
[0.6207, 0.4110, 0.8737, 0.5000, 0.4800, 0.5633, 0.6300, 0.5433]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.056172026408603415
step: 38
running loss: 0.0014782112212790373
Train Steps: 38/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6150, 0.3935, 0.8696, 0.5158, 0.4647, 0.5329, 0.6041, 0.5153],
[0.6214, 0.4175, 0.7300, 0.2883, 0.4338, 0.2167, 0.5698, 0.5773],
[0.6282, 0.4029, 0.8988, 0.3000, 0.4250, 0.4183, 0.7042, 0.5575],
[0.6205, 0.4016, 0.8350, 0.2717, 0.3987, 0.2550, 0.5787, 0.5133],
[0.6022, 0.3994, 0.8025, 0.3350, 0.3350, 0.4400, 0.5565, 0.5025],
[0.6115, 0.4081, 0.6725, 0.2433, 0.4088, 0.1933, 0.5167, 0.5544],
[0.6173, 0.4013, 0.8713, 0.4640, 0.4800, 0.5700, 0.6025, 0.5600],
[0.6176, 0.4017, 0.8788, 0.5100, 0.4075, 0.5250, 0.5913, 0.5033]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4933, 0.3400, 0.8663, 0.5160, 0.4407, 0.5056, 0.5874, 0.5225],
[0.4956, 0.3527, 0.7297, 0.2796, 0.4278, 0.2104, 0.5411, 0.5783],
[0.4876, 0.3190, 0.8714, 0.2921, 0.3974, 0.3867, 0.7012, 0.5721],
[0.5360, 0.3603, 0.8380, 0.2608, 0.3976, 0.2755, 0.5699, 0.5331],
[0.4918, 0.3276, 0.7912, 0.3296, 0.3477, 0.4230, 0.5811, 0.5216],
[0.4919, 0.3439, 0.6967, 0.2405, 0.4097, 0.2051, 0.5022, 0.5646],
[0.4976, 0.3403, 0.8864, 0.4499, 0.4459, 0.5219, 0.5894, 0.5640],
[0.5277, 0.3468, 0.8753, 0.4974, 0.3895, 0.5026, 0.5835, 0.5277]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6150, 0.3935, 0.8696, 0.5158, 0.4647, 0.5329, 0.6041, 0.5153],
[0.6214, 0.4175, 0.7300, 0.2883, 0.4338, 0.2167, 0.5698, 0.5773],
[0.6282, 0.4029, 0.8988, 0.3000, 0.4250, 0.4183, 0.7042, 0.5575],
[0.6205, 0.4015, 0.8350, 0.2717, 0.3988, 0.2550, 0.5788, 0.5133],
[0.6022, 0.3994, 0.8025, 0.3350, 0.3350, 0.4400, 0.5565, 0.5025],
[0.6115, 0.4081, 0.6725, 0.2433, 0.4087, 0.1933, 0.5167, 0.5544],
[0.6173, 0.4013, 0.8713, 0.4640, 0.4800, 0.5700, 0.6025, 0.5600],
[0.6176, 0.4017, 0.8788, 0.5100, 0.4075, 0.5250, 0.5913, 0.5033]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0024, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0024, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05856394310831092
step: 39
running loss: 0.0015016395668797672
Train Steps: 39/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6201, 0.3970, 0.8413, 0.4950, 0.4413, 0.5183, 0.6088, 0.5400],
[0.6198, 0.4101, 0.8838, 0.5283, 0.3763, 0.5267, 0.5913, 0.5567],
[0.6182, 0.3972, 0.8552, 0.5914, 0.3683, 0.4181, 0.5688, 0.5378],
[0.6098, 0.3991, 0.8638, 0.4717, 0.4263, 0.4967, 0.5212, 0.5650],
[0.6124, 0.4083, 0.6954, 0.3069, 0.3650, 0.2750, 0.5163, 0.5485],
[0.6250, 0.4106, 0.8700, 0.3717, 0.3588, 0.4967, 0.6038, 0.5167],
[0.6129, 0.4114, 0.6950, 0.2467, 0.4050, 0.2133, 0.5363, 0.5550],
[0.6222, 0.4072, 0.7164, 0.2166, 0.3738, 0.3167, 0.6100, 0.5533]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4798, 0.3501, 0.8590, 0.4827, 0.4369, 0.5005, 0.6019, 0.5522],
[0.5323, 0.3763, 0.8803, 0.5342, 0.3938, 0.5222, 0.5869, 0.5534],
[0.5625, 0.3739, 0.8506, 0.5645, 0.3774, 0.4322, 0.5961, 0.5285],
[0.4954, 0.3495, 0.8718, 0.4683, 0.4258, 0.4900, 0.5436, 0.5614],
[0.5050, 0.3452, 0.7314, 0.2752, 0.3728, 0.3034, 0.5197, 0.5486],
[0.5076, 0.3545, 0.8631, 0.3498, 0.3658, 0.4916, 0.6479, 0.5467],
[0.5609, 0.3935, 0.7184, 0.2431, 0.4048, 0.2111, 0.5341, 0.5568],
[0.5422, 0.3743, 0.7302, 0.2188, 0.3692, 0.3188, 0.6069, 0.5689]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6201, 0.3970, 0.8413, 0.4950, 0.4412, 0.5183, 0.6087, 0.5400],
[0.6198, 0.4101, 0.8838, 0.5283, 0.3762, 0.5267, 0.5913, 0.5567],
[0.6182, 0.3972, 0.8552, 0.5914, 0.3683, 0.4181, 0.5688, 0.5378],
[0.6098, 0.3991, 0.8637, 0.4717, 0.4263, 0.4967, 0.5213, 0.5650],
[0.6123, 0.4083, 0.6954, 0.3069, 0.3650, 0.2750, 0.5163, 0.5485],
[0.6250, 0.4105, 0.8700, 0.3717, 0.3587, 0.4967, 0.6037, 0.5167],
[0.6129, 0.4114, 0.6950, 0.2467, 0.4050, 0.2133, 0.5362, 0.5550],
[0.6222, 0.4072, 0.7164, 0.2166, 0.3738, 0.3167, 0.6100, 0.5533]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.060194525722181424
step: 40
running loss: 0.0015048631430545356
Train Steps: 40/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6201, 0.4098, 0.8575, 0.3617, 0.3700, 0.3550, 0.5988, 0.5667],
[0.6289, 0.4019, 0.8113, 0.5467, 0.3875, 0.5017, 0.7367, 0.5332],
[0.6280, 0.4101, 0.9050, 0.4533, 0.3775, 0.3217, 0.6338, 0.4915],
[0.6118, 0.4052, 0.8463, 0.3917, 0.3538, 0.3450, 0.5053, 0.5593],
[0.6276, 0.4095, 0.8237, 0.2250, 0.4662, 0.1783, 0.6171, 0.4869],
[0.6173, 0.4013, 0.8713, 0.4640, 0.4800, 0.5700, 0.6025, 0.5600],
[0.6227, 0.4083, 0.8938, 0.4800, 0.3800, 0.2950, 0.5737, 0.5350],
[0.6114, 0.4018, 0.7213, 0.1967, 0.3763, 0.2700, 0.5875, 0.5533]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5218, 0.3743, 0.8242, 0.3354, 0.3818, 0.3548, 0.5813, 0.5783],
[0.5036, 0.3452, 0.7850, 0.4899, 0.3735, 0.4991, 0.6932, 0.5218],
[0.5335, 0.3687, 0.8543, 0.4282, 0.3633, 0.3501, 0.5961, 0.5151],
[0.5147, 0.3757, 0.8075, 0.3539, 0.3500, 0.3448, 0.4714, 0.5646],
[0.5429, 0.3846, 0.7967, 0.2209, 0.4756, 0.2256, 0.6027, 0.5078],
[0.5002, 0.3524, 0.8492, 0.4275, 0.4547, 0.5480, 0.5696, 0.5613],
[0.5504, 0.4018, 0.8314, 0.4504, 0.3838, 0.3229, 0.5412, 0.5547],
[0.5075, 0.3631, 0.7072, 0.2028, 0.3909, 0.2826, 0.5505, 0.5508]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6201, 0.4098, 0.8575, 0.3617, 0.3700, 0.3550, 0.5987, 0.5667],
[0.6289, 0.4019, 0.8112, 0.5467, 0.3875, 0.5017, 0.7367, 0.5332],
[0.6280, 0.4101, 0.9050, 0.4533, 0.3775, 0.3217, 0.6338, 0.4915],
[0.6118, 0.4052, 0.8462, 0.3917, 0.3537, 0.3450, 0.5053, 0.5593],
[0.6276, 0.4095, 0.8238, 0.2250, 0.4663, 0.1783, 0.6171, 0.4869],
[0.6173, 0.4013, 0.8713, 0.4640, 0.4800, 0.5700, 0.6025, 0.5600],
[0.6227, 0.4083, 0.8938, 0.4800, 0.3800, 0.2950, 0.5738, 0.5350],
[0.6114, 0.4018, 0.7212, 0.1967, 0.3762, 0.2700, 0.5875, 0.5533]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0020, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0020, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.062190487602492794
step: 41
running loss: 0.0015168411610364096
Train Steps: 41/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6245, 0.4100, 0.7762, 0.2583, 0.4963, 0.1517, 0.5875, 0.5417],
[0.6167, 0.4048, 0.6831, 0.3639, 0.3763, 0.3017, 0.5700, 0.5883],
[0.6085, 0.4005, 0.8400, 0.4317, 0.3763, 0.4750, 0.5476, 0.5058],
[0.6229, 0.4066, 0.8513, 0.5717, 0.4500, 0.5050, 0.6025, 0.5350],
[0.6268, 0.4061, 0.8350, 0.2433, 0.4575, 0.2283, 0.6350, 0.5300],
[0.6325, 0.4066, 0.8438, 0.5350, 0.3925, 0.5267, 0.7113, 0.5795],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5413, 0.5683],
[0.6166, 0.4008, 0.8563, 0.5667, 0.4388, 0.4933, 0.5575, 0.5567]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5534, 0.3963, 0.7433, 0.2502, 0.4639, 0.1631, 0.5861, 0.5406],
[0.4998, 0.3601, 0.7076, 0.3060, 0.3642, 0.3174, 0.5446, 0.5721],
[0.5338, 0.3740, 0.8254, 0.3796, 0.3466, 0.4556, 0.5302, 0.5044],
[0.5335, 0.3762, 0.8138, 0.5281, 0.4133, 0.4841, 0.5833, 0.5231],
[0.5301, 0.3713, 0.8326, 0.2195, 0.4565, 0.2315, 0.6110, 0.5118],
[0.5860, 0.4042, 0.8220, 0.4887, 0.3692, 0.5435, 0.6988, 0.5536],
[0.5799, 0.4024, 0.8479, 0.4923, 0.3590, 0.3807, 0.5321, 0.5592],
[0.5488, 0.3756, 0.8268, 0.5125, 0.4210, 0.4862, 0.5559, 0.5352]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6245, 0.4100, 0.7763, 0.2583, 0.4963, 0.1517, 0.5875, 0.5417],
[0.6167, 0.4048, 0.6831, 0.3639, 0.3762, 0.3017, 0.5700, 0.5883],
[0.6084, 0.4005, 0.8400, 0.4317, 0.3762, 0.4750, 0.5476, 0.5058],
[0.6229, 0.4066, 0.8512, 0.5717, 0.4500, 0.5050, 0.6025, 0.5350],
[0.6268, 0.4060, 0.8350, 0.2433, 0.4575, 0.2283, 0.6350, 0.5300],
[0.6325, 0.4066, 0.8438, 0.5350, 0.3925, 0.5267, 0.7113, 0.5795],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5412, 0.5683],
[0.6166, 0.4008, 0.8562, 0.5667, 0.4387, 0.4933, 0.5575, 0.5567]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06355495491879992
step: 42
running loss: 0.0015132132123523792
Train Steps: 42/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6284, 0.4127, 0.8538, 0.5867, 0.4363, 0.5083, 0.6038, 0.5433],
[0.6201, 0.4055, 0.7717, 0.1919, 0.4250, 0.2079, 0.5871, 0.5044],
[0.6173, 0.4114, 0.7325, 0.2500, 0.4213, 0.1917, 0.5338, 0.5700],
[ nan, nan, 0.8888, 0.3100, 0.5262, 0.2817, 0.7145, 0.6003],
[0.6100, 0.4016, 0.8600, 0.5067, 0.4612, 0.5233, 0.5086, 0.5519],
[0.6293, 0.4097, 0.8800, 0.2517, 0.5262, 0.2600, 0.7430, 0.5378],
[0.6185, 0.4129, 0.8900, 0.4567, 0.3937, 0.5417, 0.5734, 0.5110],
[0.6264, 0.4071, 0.9038, 0.3867, 0.3663, 0.3917, 0.6338, 0.5283]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6403, 0.4367, 0.8090, 0.5827, 0.4012, 0.4859, 0.5567, 0.5294],
[0.6944, 0.4701, 0.7308, 0.2138, 0.4012, 0.2153, 0.5763, 0.5016],
[0.6507, 0.4582, 0.7047, 0.2664, 0.4054, 0.1817, 0.5152, 0.5649],
[0.0979, 0.0755, 0.8524, 0.3215, 0.4901, 0.2879, 0.6982, 0.5806],
[0.6130, 0.4266, 0.8024, 0.5167, 0.4311, 0.5133, 0.5184, 0.5435],
[0.5819, 0.3945, 0.8331, 0.2693, 0.4923, 0.2523, 0.7011, 0.5474],
[0.6537, 0.4636, 0.8480, 0.4701, 0.3679, 0.5577, 0.5616, 0.5122],
[0.5964, 0.4112, 0.8555, 0.3988, 0.3533, 0.4023, 0.6510, 0.5319]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6284, 0.4127, 0.8537, 0.5867, 0.4363, 0.5083, 0.6037, 0.5433],
[0.6202, 0.4055, 0.7717, 0.1919, 0.4250, 0.2079, 0.5871, 0.5044],
[0.6173, 0.4114, 0.7325, 0.2500, 0.4212, 0.1917, 0.5337, 0.5700],
[0.0000, 0.0000, 0.8888, 0.3100, 0.5263, 0.2817, 0.7145, 0.6003],
[0.6100, 0.4016, 0.8600, 0.5067, 0.4613, 0.5233, 0.5086, 0.5519],
[0.6293, 0.4097, 0.8800, 0.2517, 0.5263, 0.2600, 0.7430, 0.5378],
[0.6186, 0.4129, 0.8900, 0.4567, 0.3938, 0.5417, 0.5734, 0.5110],
[0.6264, 0.4071, 0.9038, 0.3867, 0.3663, 0.3917, 0.6338, 0.5283]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0646070629300084
step: 43
running loss: 0.0015024898355815905
Train Steps: 43/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6199, 0.4112, 0.8475, 0.3717, 0.3550, 0.4350, 0.6063, 0.6083],
[0.6236, 0.4081, 0.8575, 0.3000, 0.3713, 0.3033, 0.5550, 0.5633],
[0.6339, 0.4081, 0.8425, 0.5417, 0.3850, 0.4833, 0.7335, 0.5760],
[0.6240, 0.4217, 0.8150, 0.3133, 0.4425, 0.2650, 0.5650, 0.5817],
[0.6148, 0.4053, 0.8750, 0.4550, 0.4850, 0.5218, 0.5863, 0.5567],
[0.6357, 0.4118, 0.8400, 0.2500, 0.5413, 0.1633, 0.6725, 0.5586],
[0.6186, 0.4154, 0.6825, 0.2633, 0.4150, 0.2300, 0.5713, 0.5517],
[0.6250, 0.4054, 0.8770, 0.4723, 0.4662, 0.5367, 0.6162, 0.5433]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6535, 0.4311, 0.8405, 0.3824, 0.3650, 0.4421, 0.6013, 0.5688],
[0.6359, 0.4276, 0.8393, 0.3346, 0.3727, 0.3086, 0.5698, 0.5271],
[0.6506, 0.4239, 0.8290, 0.5575, 0.3890, 0.4996, 0.7215, 0.5566],
[0.5780, 0.3946, 0.8061, 0.3165, 0.4428, 0.2544, 0.5824, 0.5658],
[0.6421, 0.4263, 0.8572, 0.4694, 0.4742, 0.5226, 0.5898, 0.5518],
[0.5819, 0.3656, 0.8441, 0.2752, 0.5485, 0.1852, 0.6449, 0.5419],
[0.6521, 0.4286, 0.7027, 0.2786, 0.4204, 0.2309, 0.5696, 0.5364],
[0.6317, 0.4114, 0.8712, 0.4954, 0.4499, 0.5450, 0.6113, 0.5097]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6199, 0.4112, 0.8475, 0.3717, 0.3550, 0.4350, 0.6062, 0.6083],
[0.6236, 0.4081, 0.8575, 0.3000, 0.3713, 0.3033, 0.5550, 0.5633],
[0.6339, 0.4081, 0.8425, 0.5417, 0.3850, 0.4833, 0.7335, 0.5760],
[0.6240, 0.4217, 0.8150, 0.3133, 0.4425, 0.2650, 0.5650, 0.5817],
[0.6148, 0.4053, 0.8750, 0.4550, 0.4850, 0.5218, 0.5863, 0.5567],
[0.6357, 0.4118, 0.8400, 0.2500, 0.5412, 0.1633, 0.6725, 0.5586],
[0.6186, 0.4154, 0.6825, 0.2633, 0.4150, 0.2300, 0.5713, 0.5517],
[0.6250, 0.4054, 0.8770, 0.4723, 0.4663, 0.5367, 0.6162, 0.5433]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06501127360388637
step: 44
running loss: 0.001477528945542872
Train Steps: 44/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6161, 0.4040, 0.7525, 0.2133, 0.4125, 0.2067, 0.5787, 0.5117],
[ nan, nan, 0.8463, 0.2550, 0.5850, 0.2133, 0.7129, 0.6072],
[0.6223, 0.4171, 0.8750, 0.5500, 0.4050, 0.4817, 0.5675, 0.5600],
[ nan, nan, 0.7335, 0.2569, 0.3788, 0.2667, 0.5066, 0.5578],
[0.6153, 0.4117, 0.8688, 0.5167, 0.4895, 0.5647, 0.5524, 0.5136],
[0.6245, 0.4100, 0.7762, 0.2583, 0.4963, 0.1517, 0.5875, 0.5417],
[0.6216, 0.4099, 0.7225, 0.2033, 0.4188, 0.2217, 0.5975, 0.5283],
[0.6268, 0.4061, 0.8350, 0.2433, 0.4575, 0.2283, 0.6350, 0.5300]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7726, 0.4826, 0.7481, 0.2335, 0.4231, 0.2256, 0.5740, 0.5187],
[0.3963, 0.2433, 0.8701, 0.3023, 0.5606, 0.2781, 0.7299, 0.5774],
[0.7517, 0.4843, 0.8652, 0.5935, 0.4058, 0.5193, 0.5969, 0.5574],
[0.2212, 0.1395, 0.7287, 0.2680, 0.3992, 0.2929, 0.5313, 0.5597],
[0.6715, 0.4485, 0.8737, 0.5333, 0.4792, 0.5533, 0.5826, 0.5285],
[0.7009, 0.4446, 0.7609, 0.2963, 0.4872, 0.1567, 0.6087, 0.5468],
[0.7345, 0.4826, 0.7151, 0.2483, 0.4275, 0.2223, 0.5629, 0.5467],
[0.7022, 0.4410, 0.8480, 0.2651, 0.4787, 0.2276, 0.6324, 0.5189]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6161, 0.4040, 0.7525, 0.2133, 0.4125, 0.2067, 0.5788, 0.5117],
[0.0000, 0.0000, 0.8462, 0.2550, 0.5850, 0.2133, 0.7129, 0.6072],
[0.6223, 0.4171, 0.8750, 0.5500, 0.4050, 0.4817, 0.5675, 0.5600],
[0.0000, 0.0000, 0.7335, 0.2569, 0.3787, 0.2667, 0.5066, 0.5578],
[0.6154, 0.4117, 0.8687, 0.5167, 0.4895, 0.5647, 0.5524, 0.5136],
[0.6245, 0.4100, 0.7763, 0.2583, 0.4963, 0.1517, 0.5875, 0.5417],
[0.6216, 0.4099, 0.7225, 0.2033, 0.4187, 0.2217, 0.5975, 0.5283],
[0.6268, 0.4060, 0.8350, 0.2433, 0.4575, 0.2283, 0.6350, 0.5300]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0062, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0062, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07122712582349777
step: 45
running loss: 0.0015828250182999505
Train Steps: 45/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6161, 0.4040, 0.7525, 0.2133, 0.4125, 0.2067, 0.5787, 0.5117],
[0.6169, 0.4052, 0.8742, 0.4779, 0.4288, 0.4917, 0.5763, 0.5617],
[0.6268, 0.4029, 0.8500, 0.2683, 0.3937, 0.3500, 0.6860, 0.5297],
[0.6346, 0.4092, 0.7712, 0.5917, 0.4037, 0.4767, 0.7343, 0.5725],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098],
[0.6135, 0.4115, 0.8838, 0.4667, 0.4288, 0.6050, 0.5778, 0.5097],
[0.6293, 0.4097, 0.8800, 0.2517, 0.5262, 0.2600, 0.7430, 0.5378],
[0.6226, 0.4185, 0.8850, 0.5500, 0.3800, 0.4250, 0.5625, 0.5617]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7331, 0.4592, 0.7735, 0.2241, 0.4503, 0.1924, 0.5746, 0.5400],
[0.6419, 0.4064, 0.8766, 0.4838, 0.4706, 0.4968, 0.5743, 0.5954],
[0.7422, 0.4753, 0.8519, 0.2872, 0.4188, 0.3272, 0.6793, 0.5440],
[0.6730, 0.4350, 0.8086, 0.5327, 0.4291, 0.4629, 0.6900, 0.5999],
[0.6489, 0.4106, 0.8866, 0.4799, 0.4025, 0.5063, 0.6117, 0.5371],
[0.6957, 0.4588, 0.8931, 0.4718, 0.4490, 0.5881, 0.5687, 0.5560],
[0.6324, 0.4016, 0.9098, 0.2668, 0.5592, 0.2225, 0.7408, 0.5735],
[0.6425, 0.4179, 0.9084, 0.5664, 0.4185, 0.4261, 0.5618, 0.6009]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6161, 0.4040, 0.7525, 0.2133, 0.4125, 0.2067, 0.5788, 0.5117],
[0.6169, 0.4052, 0.8742, 0.4779, 0.4288, 0.4917, 0.5763, 0.5617],
[0.6268, 0.4029, 0.8500, 0.2683, 0.3938, 0.3500, 0.6860, 0.5297],
[0.6346, 0.4092, 0.7713, 0.5917, 0.4038, 0.4767, 0.7343, 0.5725],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098],
[0.6135, 0.4115, 0.8838, 0.4667, 0.4288, 0.6050, 0.5778, 0.5097],
[0.6293, 0.4097, 0.8800, 0.2517, 0.5263, 0.2600, 0.7430, 0.5378],
[0.6226, 0.4185, 0.8850, 0.5500, 0.3800, 0.4250, 0.5625, 0.5617]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07247095857746899
step: 46
running loss: 0.001575455621249326
Train Steps: 46/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6117, 0.4018, 0.6562, 0.1967, 0.3738, 0.2550, 0.5280, 0.5103],
[0.6255, 0.4017, 0.8688, 0.3217, 0.3638, 0.3550, 0.6344, 0.4901],
[0.6252, 0.4158, 0.8988, 0.4083, 0.3788, 0.4783, 0.6225, 0.5633],
[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837],
[0.6114, 0.4018, 0.7213, 0.1967, 0.3763, 0.2700, 0.5875, 0.5533],
[0.6086, 0.4019, 0.7782, 0.4278, 0.3625, 0.4350, 0.5150, 0.5285],
[0.6307, 0.4029, 0.8650, 0.5200, 0.3763, 0.4017, 0.7311, 0.5366],
[0.6168, 0.4055, 0.7575, 0.2950, 0.4050, 0.2717, 0.5938, 0.6167]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6574, 0.4007, 0.7161, 0.2415, 0.4372, 0.2182, 0.5540, 0.5274],
[0.7188, 0.4395, 0.9126, 0.3551, 0.4240, 0.3446, 0.6664, 0.5151],
[0.6449, 0.4115, 0.9352, 0.4280, 0.4575, 0.4946, 0.6595, 0.5656],
[0.6935, 0.4357, 0.7239, 0.3226, 0.4177, 0.2775, 0.5561, 0.5865],
[0.6732, 0.4144, 0.7784, 0.2303, 0.4354, 0.2535, 0.6162, 0.5620],
[0.6671, 0.4141, 0.8405, 0.4290, 0.4107, 0.4286, 0.5424, 0.5497],
[0.6732, 0.4279, 0.9269, 0.5229, 0.4582, 0.3990, 0.7307, 0.5606],
[0.6479, 0.4105, 0.8007, 0.3074, 0.4547, 0.2792, 0.6077, 0.6354]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6116, 0.4018, 0.6562, 0.1967, 0.3738, 0.2550, 0.5280, 0.5103],
[0.6255, 0.4017, 0.8687, 0.3217, 0.3638, 0.3550, 0.6344, 0.4901],
[0.6252, 0.4158, 0.8988, 0.4083, 0.3787, 0.4783, 0.6225, 0.5633],
[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837],
[0.6114, 0.4018, 0.7212, 0.1967, 0.3762, 0.2700, 0.5875, 0.5533],
[0.6086, 0.4019, 0.7782, 0.4278, 0.3625, 0.4350, 0.5150, 0.5285],
[0.6307, 0.4029, 0.8650, 0.5200, 0.3762, 0.4017, 0.7311, 0.5366],
[0.6168, 0.4055, 0.7575, 0.2950, 0.4050, 0.2717, 0.5938, 0.6167]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07407605787739158
step: 47
running loss: 0.001576086337816842
Train Steps: 47/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6336, 0.4191, 0.8938, 0.5167, 0.3937, 0.3517, 0.7343, 0.5748],
[0.6082, 0.4024, 0.8738, 0.4017, 0.3688, 0.3950, 0.5306, 0.5136],
[0.6107, 0.4013, 0.8700, 0.4650, 0.5049, 0.5176, 0.5850, 0.5550],
[0.6277, 0.4118, 0.8988, 0.3833, 0.3950, 0.2650, 0.6290, 0.4938],
[0.6086, 0.3998, 0.8788, 0.4450, 0.4025, 0.4650, 0.5306, 0.5103],
[0.6163, 0.4114, 0.7650, 0.2017, 0.3763, 0.2867, 0.5631, 0.5071],
[0.6075, 0.4007, 0.8275, 0.4917, 0.4050, 0.5100, 0.5167, 0.5280],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5413, 0.5683]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6368, 0.3935, 0.8968, 0.4891, 0.4338, 0.3506, 0.7530, 0.5938],
[0.6039, 0.3732, 0.8718, 0.3862, 0.3848, 0.3704, 0.5681, 0.5286],
[0.6556, 0.4214, 0.8814, 0.4510, 0.5159, 0.4949, 0.6190, 0.5738],
[0.6569, 0.4089, 0.9095, 0.3692, 0.4205, 0.2534, 0.6525, 0.5490],
[0.6146, 0.3732, 0.8748, 0.4358, 0.4161, 0.4537, 0.5730, 0.5365],
[0.7169, 0.4363, 0.7584, 0.1976, 0.4032, 0.2690, 0.6160, 0.5167],
[0.6273, 0.3904, 0.8306, 0.4688, 0.4328, 0.4919, 0.5570, 0.5485],
[0.6928, 0.4262, 0.8915, 0.5248, 0.4117, 0.3709, 0.5685, 0.5948]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6336, 0.4191, 0.8938, 0.5167, 0.3938, 0.3517, 0.7343, 0.5748],
[0.6082, 0.4024, 0.8737, 0.4017, 0.3688, 0.3950, 0.5306, 0.5136],
[0.6107, 0.4013, 0.8700, 0.4650, 0.5049, 0.5176, 0.5850, 0.5550],
[0.6277, 0.4117, 0.8988, 0.3833, 0.3950, 0.2650, 0.6290, 0.4938],
[0.6086, 0.3998, 0.8788, 0.4450, 0.4025, 0.4650, 0.5306, 0.5103],
[0.6163, 0.4114, 0.7650, 0.2017, 0.3762, 0.2867, 0.5631, 0.5071],
[0.6075, 0.4006, 0.8275, 0.4917, 0.4050, 0.5100, 0.5167, 0.5280],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5412, 0.5683]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07483209832571447
step: 48
running loss: 0.0015590020484523848
Train Steps: 48/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.8213, 0.2700, 0.3775, 0.2817, 0.5425, 0.5533],
[0.6169, 0.4052, 0.8742, 0.4779, 0.4288, 0.4917, 0.5763, 0.5617],
[0.6198, 0.4075, 0.8650, 0.5617, 0.4150, 0.4367, 0.5450, 0.5650],
[0.6197, 0.3986, 0.8800, 0.4617, 0.4188, 0.4783, 0.5687, 0.5550],
[0.6079, 0.3964, 0.7420, 0.2958, 0.3563, 0.2917, 0.5351, 0.4980],
[ nan, nan, 0.7515, 0.2708, 0.3987, 0.2267, 0.5162, 0.5567],
[0.6199, 0.3952, 0.8573, 0.5374, 0.4075, 0.4687, 0.5942, 0.5377],
[0.6236, 0.3966, 0.8850, 0.4967, 0.3638, 0.4017, 0.5850, 0.5183]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.1510, 0.0802, 0.8048, 0.3031, 0.3931, 0.2843, 0.6019, 0.5653],
[0.7519, 0.4651, 0.8721, 0.4573, 0.4482, 0.5135, 0.6305, 0.5623],
[0.7314, 0.4637, 0.8811, 0.5660, 0.4295, 0.4587, 0.5821, 0.5647],
[0.7187, 0.4577, 0.8832, 0.4578, 0.4222, 0.4926, 0.6105, 0.5489],
[0.7343, 0.4611, 0.7655, 0.2794, 0.3611, 0.2828, 0.5849, 0.4956],
[0.0396, 0.0147, 0.7697, 0.2914, 0.4217, 0.2391, 0.5808, 0.5600],
[0.7838, 0.4756, 0.8688, 0.5498, 0.4112, 0.4997, 0.6354, 0.5302],
[0.7763, 0.4855, 0.8959, 0.4841, 0.3739, 0.4266, 0.6179, 0.5216]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.8213, 0.2700, 0.3775, 0.2817, 0.5425, 0.5533],
[0.6169, 0.4052, 0.8742, 0.4779, 0.4288, 0.4917, 0.5763, 0.5617],
[0.6198, 0.4075, 0.8650, 0.5617, 0.4150, 0.4367, 0.5450, 0.5650],
[0.6197, 0.3986, 0.8800, 0.4617, 0.4187, 0.4783, 0.5688, 0.5550],
[0.6079, 0.3964, 0.7420, 0.2958, 0.3562, 0.2917, 0.5351, 0.4980],
[0.0000, 0.0000, 0.7515, 0.2708, 0.3988, 0.2267, 0.5163, 0.5567],
[0.6199, 0.3952, 0.8573, 0.5374, 0.4075, 0.4687, 0.5942, 0.5377],
[0.6236, 0.3965, 0.8850, 0.4967, 0.3638, 0.4017, 0.5850, 0.5183]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0030, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0030, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07787081459537148
step: 49
running loss: 0.0015892002978647242
Train Steps: 49/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.7225, 0.2167, 0.3987, 0.2283, 0.5427, 0.5181],
[0.6250, 0.4146, 0.8838, 0.3933, 0.3588, 0.4283, 0.6162, 0.5367],
[0.6064, 0.4019, 0.8650, 0.4517, 0.4037, 0.5367, 0.5703, 0.5609],
[0.6245, 0.4115, 0.8700, 0.4883, 0.4625, 0.5517, 0.6100, 0.5217],
[0.6162, 0.4134, 0.6700, 0.2467, 0.3962, 0.2533, 0.5737, 0.5467],
[0.6277, 0.4036, 0.8688, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742],
[0.6263, 0.4065, 0.9038, 0.4317, 0.3588, 0.4550, 0.6325, 0.5250],
[0.6286, 0.4086, 0.8408, 0.2801, 0.4163, 0.2800, 0.6725, 0.5393]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[-0.0325, -0.0318, 0.7265, 0.2437, 0.4054, 0.2141, 0.5640, 0.5116],
[ 0.5875, 0.3782, 0.8540, 0.4057, 0.3558, 0.4153, 0.6077, 0.5356],
[ 0.6916, 0.4526, 0.8666, 0.4584, 0.4000, 0.5510, 0.5852, 0.5289],
[ 0.6534, 0.4066, 0.8812, 0.5019, 0.4452, 0.5662, 0.6000, 0.5215],
[ 0.6641, 0.4348, 0.6917, 0.2722, 0.3654, 0.2443, 0.5700, 0.5324],
[ 0.6990, 0.4371, 0.8753, 0.3732, 0.3904, 0.2664, 0.6206, 0.4665],
[ 0.6395, 0.3998, 0.9076, 0.4593, 0.3602, 0.4819, 0.6314, 0.5227],
[ 0.5846, 0.3655, 0.8533, 0.2823, 0.4021, 0.2868, 0.7068, 0.5403]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.7225, 0.2167, 0.3988, 0.2283, 0.5427, 0.5181],
[0.6250, 0.4146, 0.8838, 0.3933, 0.3587, 0.4283, 0.6162, 0.5367],
[0.6064, 0.4019, 0.8650, 0.4517, 0.4038, 0.5367, 0.5703, 0.5609],
[0.6245, 0.4115, 0.8700, 0.4883, 0.4625, 0.5517, 0.6100, 0.5217],
[0.6162, 0.4134, 0.6700, 0.2467, 0.3963, 0.2533, 0.5738, 0.5467],
[0.6277, 0.4036, 0.8687, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742],
[0.6263, 0.4065, 0.9038, 0.4317, 0.3587, 0.4550, 0.6325, 0.5250],
[0.6286, 0.4086, 0.8408, 0.2801, 0.4162, 0.2800, 0.6725, 0.5393]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07848756696330383
step: 50
running loss: 0.0015697513392660767
Train Steps: 50/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6201, 0.4027, 0.8029, 0.2728, 0.4042, 0.2310, 0.5980, 0.5391],
[0.6222, 0.4169, 0.8638, 0.5650, 0.4313, 0.4783, 0.5637, 0.5633],
[ nan, nan, 0.7981, 0.3194, 0.3625, 0.3167, 0.5040, 0.5563],
[0.6197, 0.3930, 0.8793, 0.4736, 0.4152, 0.5464, 0.6308, 0.5235],
[0.6196, 0.4068, 0.7645, 0.2234, 0.4575, 0.1737, 0.5926, 0.5284],
[ nan, nan, 0.8300, 0.3150, 0.3588, 0.3383, 0.5208, 0.5194],
[0.6336, 0.4191, 0.8938, 0.5167, 0.3937, 0.3517, 0.7343, 0.5748],
[0.6064, 0.3953, 0.8738, 0.4417, 0.3663, 0.4683, 0.5511, 0.5416]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6583, 0.4061, 0.7852, 0.2628, 0.3901, 0.2268, 0.5825, 0.5011],
[0.6119, 0.4043, 0.8460, 0.5443, 0.3911, 0.4834, 0.5273, 0.5403],
[0.0739, 0.0346, 0.7801, 0.3044, 0.3294, 0.3241, 0.5190, 0.5207],
[0.6127, 0.3999, 0.8732, 0.4730, 0.3982, 0.5596, 0.6111, 0.5051],
[0.6407, 0.4011, 0.7635, 0.2083, 0.4314, 0.1839, 0.5845, 0.4947],
[0.1436, 0.0885, 0.7909, 0.3158, 0.3326, 0.3305, 0.5361, 0.5008],
[0.6194, 0.4075, 0.8671, 0.4859, 0.3701, 0.3710, 0.7046, 0.5399],
[0.6698, 0.4239, 0.8582, 0.4529, 0.3303, 0.4754, 0.5364, 0.4863]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6201, 0.4027, 0.8029, 0.2728, 0.4042, 0.2310, 0.5980, 0.5391],
[0.6222, 0.4169, 0.8637, 0.5650, 0.4313, 0.4783, 0.5638, 0.5633],
[0.0000, 0.0000, 0.7981, 0.3194, 0.3625, 0.3167, 0.5040, 0.5563],
[0.6197, 0.3930, 0.8793, 0.4736, 0.4152, 0.5464, 0.6308, 0.5235],
[0.6196, 0.4068, 0.7645, 0.2234, 0.4575, 0.1737, 0.5926, 0.5284],
[0.0000, 0.0000, 0.8300, 0.3150, 0.3587, 0.3383, 0.5208, 0.5194],
[0.6336, 0.4191, 0.8938, 0.5167, 0.3938, 0.3517, 0.7343, 0.5748],
[0.6064, 0.3952, 0.8737, 0.4417, 0.3663, 0.4683, 0.5511, 0.5416]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07955434458563104
step: 51
running loss: 0.0015598891095221772
Train Steps: 51/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6197, 0.4050, 0.7527, 0.2000, 0.4042, 0.2249, 0.5895, 0.4995],
[0.6204, 0.4007, 0.7838, 0.2100, 0.4475, 0.1733, 0.5825, 0.5167],
[0.6213, 0.4131, 0.8438, 0.3550, 0.3513, 0.4400, 0.5716, 0.5123],
[0.6145, 0.3983, 0.8700, 0.5017, 0.4400, 0.4800, 0.5375, 0.5750],
[0.6189, 0.4029, 0.8375, 0.5767, 0.4745, 0.4829, 0.5551, 0.5598],
[0.6042, 0.3990, 0.6831, 0.2875, 0.3500, 0.3133, 0.5143, 0.5510],
[ nan, nan, 0.8900, 0.3217, 0.5038, 0.2233, 0.6694, 0.5609],
[0.6183, 0.4076, 0.8838, 0.4517, 0.3813, 0.4483, 0.5775, 0.5633]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.5704, 0.3827, 0.7387, 0.2036, 0.3578, 0.2297, 0.5657, 0.4697],
[ 0.5516, 0.3512, 0.7640, 0.2236, 0.4117, 0.1581, 0.5666, 0.4943],
[ 0.5503, 0.3709, 0.8578, 0.3682, 0.3118, 0.4334, 0.5395, 0.4950],
[ 0.5605, 0.3689, 0.8584, 0.5159, 0.3863, 0.4964, 0.5315, 0.5135],
[ 0.5507, 0.3585, 0.8238, 0.5576, 0.4316, 0.4736, 0.5286, 0.5450],
[ 0.5587, 0.3720, 0.6769, 0.2708, 0.3132, 0.3024, 0.4931, 0.5178],
[-0.1807, -0.1097, 0.8726, 0.3411, 0.4731, 0.2189, 0.6576, 0.5594],
[ 0.5047, 0.3208, 0.8690, 0.4605, 0.3415, 0.4591, 0.5479, 0.5489]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6197, 0.4050, 0.7527, 0.2000, 0.4042, 0.2249, 0.5895, 0.4995],
[0.6204, 0.4007, 0.7837, 0.2100, 0.4475, 0.1733, 0.5825, 0.5167],
[0.6213, 0.4131, 0.8438, 0.3550, 0.3512, 0.4400, 0.5716, 0.5123],
[0.6145, 0.3983, 0.8700, 0.5017, 0.4400, 0.4800, 0.5375, 0.5750],
[0.6189, 0.4029, 0.8375, 0.5767, 0.4745, 0.4829, 0.5551, 0.5598],
[0.6042, 0.3990, 0.6831, 0.2875, 0.3500, 0.3133, 0.5143, 0.5510],
[0.0000, 0.0000, 0.8900, 0.3217, 0.5038, 0.2233, 0.6694, 0.5609],
[0.6183, 0.4076, 0.8838, 0.4517, 0.3812, 0.4483, 0.5775, 0.5633]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.08149451989447698
step: 52
running loss: 0.001567202305663019
Train Steps: 52/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6199, 0.3952, 0.8573, 0.5374, 0.4075, 0.4687, 0.5942, 0.5377],
[0.6205, 0.4081, 0.8950, 0.4017, 0.3788, 0.4700, 0.5963, 0.5667],
[ nan, nan, 0.6900, 0.1917, 0.3937, 0.2367, 0.5240, 0.5246],
[0.6275, 0.4071, 0.8075, 0.2100, 0.4700, 0.1533, 0.6148, 0.4834],
[0.6262, 0.4163, 0.8850, 0.5183, 0.3763, 0.4150, 0.6025, 0.5500],
[0.6222, 0.4108, 0.8938, 0.4233, 0.3600, 0.3817, 0.5825, 0.5283],
[0.6076, 0.3953, 0.8125, 0.3917, 0.3525, 0.4083, 0.5346, 0.4954],
[ nan, nan, 0.6935, 0.1930, 0.4150, 0.2250, 0.5450, 0.5650]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6065, 0.3959, 0.8548, 0.5664, 0.3848, 0.4831, 0.5509, 0.5286],
[ 0.6251, 0.4124, 0.8550, 0.3978, 0.3658, 0.4721, 0.5616, 0.5464],
[-0.0914, -0.0326, 0.6882, 0.2071, 0.3913, 0.2299, 0.5179, 0.5272],
[ 0.5802, 0.3960, 0.7924, 0.1981, 0.4634, 0.1556, 0.6002, 0.4862],
[ 0.5282, 0.3601, 0.8603, 0.5014, 0.3412, 0.3819, 0.5508, 0.5523],
[ 0.5425, 0.3861, 0.8650, 0.4160, 0.3282, 0.3782, 0.5710, 0.5371],
[ 0.6114, 0.4252, 0.8005, 0.3769, 0.3246, 0.4035, 0.5220, 0.4932],
[-0.0446, -0.0088, 0.6980, 0.1995, 0.4239, 0.2405, 0.5390, 0.5463]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6199, 0.3952, 0.8573, 0.5374, 0.4075, 0.4687, 0.5942, 0.5377],
[0.6205, 0.4081, 0.8950, 0.4017, 0.3787, 0.4700, 0.5962, 0.5667],
[0.0000, 0.0000, 0.6900, 0.1917, 0.3938, 0.2367, 0.5240, 0.5246],
[0.6275, 0.4071, 0.8075, 0.2100, 0.4700, 0.1533, 0.6148, 0.4834],
[0.6262, 0.4163, 0.8850, 0.5183, 0.3762, 0.4150, 0.6025, 0.5500],
[0.6222, 0.4108, 0.8938, 0.4233, 0.3600, 0.3817, 0.5825, 0.5283],
[0.6076, 0.3952, 0.8125, 0.3917, 0.3525, 0.4083, 0.5346, 0.4954],
[0.0000, 0.0000, 0.6935, 0.1930, 0.4150, 0.2250, 0.5450, 0.5650]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.08231787505792454
step: 53
running loss: 0.0015531674539231044
Train Steps: 53/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6204, 0.4013, 0.8075, 0.2400, 0.4313, 0.2050, 0.5800, 0.5150],
[0.6107, 0.4050, 0.8700, 0.4850, 0.4470, 0.4848, 0.5043, 0.5431],
[0.6110, 0.4047, 0.8700, 0.4483, 0.3713, 0.3967, 0.5088, 0.5517],
[0.6145, 0.3983, 0.8700, 0.5017, 0.4400, 0.4800, 0.5375, 0.5750],
[0.6339, 0.4112, 0.8838, 0.5067, 0.4000, 0.5433, 0.7549, 0.5378],
[0.6212, 0.4033, 0.8938, 0.4167, 0.3813, 0.4267, 0.5613, 0.5583],
[0.6058, 0.3978, 0.8287, 0.3600, 0.3400, 0.4050, 0.5529, 0.5461],
[0.6201, 0.4065, 0.7300, 0.1933, 0.4075, 0.2533, 0.6162, 0.5483]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4633, 0.3053, 0.7813, 0.2637, 0.4218, 0.2074, 0.5650, 0.5414],
[0.4423, 0.3266, 0.8592, 0.4890, 0.4347, 0.4827, 0.4844, 0.5379],
[0.4234, 0.3148, 0.8460, 0.4503, 0.3582, 0.4114, 0.4690, 0.5458],
[0.4643, 0.3248, 0.8627, 0.5094, 0.4220, 0.4801, 0.5468, 0.5422],
[0.4713, 0.3208, 0.8873, 0.5206, 0.4017, 0.5500, 0.6978, 0.5498],
[0.4593, 0.3276, 0.8906, 0.4396, 0.3651, 0.4203, 0.5323, 0.5475],
[0.4902, 0.3599, 0.8177, 0.3682, 0.3393, 0.4011, 0.5317, 0.5457],
[0.5154, 0.3562, 0.7241, 0.1829, 0.3850, 0.2528, 0.5751, 0.5372]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6204, 0.4013, 0.8075, 0.2400, 0.4313, 0.2050, 0.5800, 0.5150],
[0.6107, 0.4050, 0.8700, 0.4850, 0.4470, 0.4848, 0.5043, 0.5431],
[0.6110, 0.4047, 0.8700, 0.4483, 0.3713, 0.3967, 0.5088, 0.5517],
[0.6145, 0.3983, 0.8700, 0.5017, 0.4400, 0.4800, 0.5375, 0.5750],
[0.6339, 0.4112, 0.8838, 0.5067, 0.4000, 0.5433, 0.7549, 0.5378],
[0.6212, 0.4033, 0.8938, 0.4167, 0.3812, 0.4267, 0.5612, 0.5583],
[0.6058, 0.3978, 0.8288, 0.3600, 0.3400, 0.4050, 0.5529, 0.5461],
[0.6201, 0.4065, 0.7300, 0.1933, 0.4075, 0.2533, 0.6162, 0.5483]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0039, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0039, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.08622756163822487
step: 54
running loss: 0.0015968066970041643
Train Steps: 54/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6299, 0.4303, 0.7963, 0.3933, 0.4850, 0.2283, 0.5480, 0.6222],
[0.6284, 0.4127, 0.8538, 0.5867, 0.4363, 0.5083, 0.6038, 0.5433],
[0.6282, 0.4034, 0.7830, 0.2080, 0.4532, 0.2080, 0.6404, 0.5323],
[0.6132, 0.4066, 0.7259, 0.2402, 0.3588, 0.3300, 0.6000, 0.5600],
[ nan, nan, 0.8213, 0.2700, 0.3775, 0.2817, 0.5425, 0.5533],
[0.6350, 0.4144, 0.9250, 0.4100, 0.4125, 0.3750, 0.7129, 0.5945],
[0.6214, 0.4175, 0.7300, 0.2883, 0.4338, 0.2167, 0.5698, 0.5773],
[0.6222, 0.4108, 0.8938, 0.4233, 0.3600, 0.3817, 0.5825, 0.5283]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.4549, 0.3279, 0.8062, 0.3474, 0.4819, 0.2351, 0.5100, 0.6041],
[ 0.4452, 0.3079, 0.8588, 0.5672, 0.4430, 0.4954, 0.5422, 0.5496],
[ 0.5699, 0.3944, 0.7603, 0.1899, 0.4359, 0.2076, 0.5866, 0.5161],
[ 0.5667, 0.3971, 0.7179, 0.2186, 0.3601, 0.3267, 0.5661, 0.5567],
[-0.0764, -0.0384, 0.7836, 0.2590, 0.3608, 0.2841, 0.4919, 0.5454],
[ 0.4562, 0.3183, 0.9138, 0.3884, 0.4177, 0.3604, 0.6740, 0.5921],
[ 0.5548, 0.4049, 0.7312, 0.2623, 0.4146, 0.2199, 0.5294, 0.5516],
[ 0.5124, 0.3712, 0.8831, 0.3997, 0.3388, 0.3850, 0.5597, 0.5397]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6299, 0.4303, 0.7962, 0.3933, 0.4850, 0.2283, 0.5480, 0.6222],
[0.6284, 0.4127, 0.8537, 0.5867, 0.4363, 0.5083, 0.6037, 0.5433],
[0.6282, 0.4034, 0.7830, 0.2080, 0.4532, 0.2080, 0.6404, 0.5323],
[0.6132, 0.4066, 0.7259, 0.2402, 0.3587, 0.3300, 0.6000, 0.5600],
[0.0000, 0.0000, 0.8213, 0.2700, 0.3775, 0.2817, 0.5425, 0.5533],
[0.6350, 0.4144, 0.9250, 0.4100, 0.4125, 0.3750, 0.7129, 0.5945],
[0.6214, 0.4175, 0.7300, 0.2883, 0.4338, 0.2167, 0.5698, 0.5773],
[0.6222, 0.4108, 0.8938, 0.4233, 0.3600, 0.3817, 0.5825, 0.5283]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0029, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0029, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0891112532117404
step: 55
running loss: 0.0016202046038498255
Train Steps: 55/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6353, 0.4128, 0.9138, 0.3533, 0.4688, 0.3250, 0.7145, 0.5991],
[0.6350, 0.4144, 0.9250, 0.4100, 0.4125, 0.3750, 0.7129, 0.5945],
[0.6200, 0.4112, 0.8862, 0.4100, 0.3638, 0.4917, 0.6088, 0.6050],
[0.6339, 0.4081, 0.8425, 0.5417, 0.3850, 0.4833, 0.7335, 0.5760],
[0.6102, 0.4005, 0.8688, 0.5100, 0.4813, 0.5400, 0.5404, 0.5064],
[0.6333, 0.4037, 0.8638, 0.5733, 0.4012, 0.4717, 0.6369, 0.4938],
[0.6200, 0.4086, 0.8414, 0.2974, 0.4117, 0.2274, 0.5869, 0.5391],
[0.6133, 0.4066, 0.6787, 0.2617, 0.3800, 0.2433, 0.5147, 0.5358]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.2841, 0.2073, 0.8971, 0.3288, 0.4746, 0.3006, 0.6896, 0.6023],
[0.4716, 0.3356, 0.9035, 0.3814, 0.4286, 0.3491, 0.6755, 0.6058],
[0.5666, 0.3886, 0.8688, 0.3893, 0.3700, 0.4776, 0.5625, 0.5985],
[0.5145, 0.3731, 0.8393, 0.5072, 0.3919, 0.4774, 0.6830, 0.5975],
[0.5068, 0.3861, 0.8645, 0.4706, 0.4755, 0.5139, 0.5026, 0.5105],
[0.5235, 0.3674, 0.8710, 0.5243, 0.4125, 0.4725, 0.5630, 0.5267],
[0.5493, 0.3891, 0.8318, 0.2677, 0.4237, 0.2318, 0.5512, 0.5450],
[0.5084, 0.3757, 0.6835, 0.2245, 0.3632, 0.2362, 0.4987, 0.5296]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6353, 0.4128, 0.9137, 0.3533, 0.4688, 0.3250, 0.7145, 0.5991],
[0.6350, 0.4144, 0.9250, 0.4100, 0.4125, 0.3750, 0.7129, 0.5945],
[0.6200, 0.4112, 0.8863, 0.4100, 0.3638, 0.4917, 0.6087, 0.6050],
[0.6339, 0.4081, 0.8425, 0.5417, 0.3850, 0.4833, 0.7335, 0.5760],
[0.6102, 0.4005, 0.8687, 0.5100, 0.4812, 0.5400, 0.5404, 0.5064],
[0.6334, 0.4037, 0.8637, 0.5733, 0.4013, 0.4717, 0.6369, 0.4938],
[0.6199, 0.4086, 0.8414, 0.2974, 0.4117, 0.2274, 0.5869, 0.5391],
[0.6133, 0.4065, 0.6787, 0.2617, 0.3800, 0.2433, 0.5147, 0.5358]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0045, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0045, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.09363721316913143
step: 56
running loss: 0.0016720930923059183
Train Steps: 56/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6339, 0.4081, 0.8425, 0.5417, 0.3850, 0.4833, 0.7335, 0.5760],
[0.6201, 0.4029, 0.8776, 0.4602, 0.3683, 0.4203, 0.5938, 0.5450],
[0.6279, 0.4008, 0.8600, 0.4883, 0.4325, 0.5283, 0.7010, 0.5378],
[0.6229, 0.4066, 0.8513, 0.5717, 0.4500, 0.5050, 0.6025, 0.5350],
[0.6117, 0.4019, 0.8538, 0.4067, 0.3513, 0.3583, 0.5663, 0.5133],
[0.6321, 0.4048, 0.8738, 0.5617, 0.3875, 0.4417, 0.6361, 0.4927],
[0.6296, 0.4045, 0.9138, 0.4100, 0.4232, 0.4242, 0.7422, 0.5297],
[0.6200, 0.4086, 0.8414, 0.2974, 0.4117, 0.2274, 0.5869, 0.5391]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5629, 0.4024, 0.8491, 0.5074, 0.3920, 0.4756, 0.7119, 0.6109],
[0.5554, 0.3866, 0.8785, 0.4322, 0.3812, 0.4299, 0.5717, 0.5626],
[0.5874, 0.3855, 0.8805, 0.4502, 0.4399, 0.5208, 0.6653, 0.5731],
[0.5419, 0.3820, 0.8656, 0.5302, 0.4593, 0.4908, 0.5758, 0.5832],
[0.6008, 0.4064, 0.8500, 0.3611, 0.3444, 0.3462, 0.5353, 0.5433],
[0.5880, 0.4068, 0.8797, 0.5273, 0.3888, 0.4454, 0.5944, 0.5271],
[0.5795, 0.4050, 0.9005, 0.3755, 0.4074, 0.4259, 0.6626, 0.5615],
[0.6131, 0.4276, 0.8416, 0.2677, 0.4248, 0.2244, 0.5816, 0.5584]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6339, 0.4081, 0.8425, 0.5417, 0.3850, 0.4833, 0.7335, 0.5760],
[0.6201, 0.4029, 0.8776, 0.4602, 0.3683, 0.4203, 0.5938, 0.5450],
[0.6279, 0.4008, 0.8600, 0.4883, 0.4325, 0.5283, 0.7010, 0.5378],
[0.6229, 0.4066, 0.8512, 0.5717, 0.4500, 0.5050, 0.6025, 0.5350],
[0.6116, 0.4019, 0.8537, 0.4067, 0.3512, 0.3583, 0.5663, 0.5133],
[0.6321, 0.4048, 0.8737, 0.5617, 0.3875, 0.4417, 0.6361, 0.4927],
[0.6296, 0.4045, 0.9137, 0.4100, 0.4232, 0.4242, 0.7422, 0.5297],
[0.6199, 0.4086, 0.8414, 0.2974, 0.4117, 0.2274, 0.5869, 0.5391]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.09452643216354772
step: 57
running loss: 0.0016583584590096092
Train Steps: 57/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6064, 0.4019, 0.8650, 0.4517, 0.4037, 0.5367, 0.5703, 0.5609],
[0.6190, 0.4135, 0.8000, 0.4883, 0.3566, 0.3647, 0.5613, 0.5900],
[0.6258, 0.4143, 0.8525, 0.2617, 0.4950, 0.1667, 0.6219, 0.4967],
[0.6086, 0.3981, 0.8700, 0.4750, 0.4512, 0.5283, 0.5324, 0.5038],
[0.6262, 0.4085, 0.8438, 0.3150, 0.4025, 0.2633, 0.6339, 0.4810],
[0.6120, 0.4014, 0.6863, 0.2817, 0.3700, 0.2783, 0.5513, 0.5667],
[0.6261, 0.4131, 0.8938, 0.3550, 0.4000, 0.2683, 0.6188, 0.5283],
[ nan, nan, 0.7192, 0.2346, 0.4037, 0.2050, 0.5138, 0.5650]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6112, 0.4222, 0.8758, 0.4470, 0.4294, 0.5529, 0.6551, 0.5872],
[0.6808, 0.4543, 0.8444, 0.5078, 0.3648, 0.3772, 0.6150, 0.5839],
[0.6741, 0.4665, 0.8564, 0.2615, 0.5054, 0.1738, 0.6894, 0.5344],
[0.6551, 0.4307, 0.8836, 0.5045, 0.4541, 0.5239, 0.6172, 0.5367],
[0.6273, 0.4249, 0.8685, 0.2997, 0.4325, 0.2790, 0.6880, 0.5231],
[0.5907, 0.3875, 0.7082, 0.2678, 0.3756, 0.2957, 0.5998, 0.5691],
[0.7871, 0.5148, 0.9175, 0.3656, 0.4089, 0.2759, 0.7013, 0.5536],
[0.1344, 0.0876, 0.7245, 0.2278, 0.4096, 0.2233, 0.5401, 0.5740]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6064, 0.4019, 0.8650, 0.4517, 0.4038, 0.5367, 0.5703, 0.5609],
[0.6190, 0.4135, 0.8000, 0.4883, 0.3566, 0.3647, 0.5612, 0.5900],
[0.6258, 0.4143, 0.8525, 0.2617, 0.4950, 0.1667, 0.6219, 0.4967],
[0.6086, 0.3981, 0.8700, 0.4750, 0.4512, 0.5283, 0.5324, 0.5038],
[0.6262, 0.4085, 0.8438, 0.3150, 0.4025, 0.2633, 0.6339, 0.4810],
[0.6120, 0.4013, 0.6862, 0.2817, 0.3700, 0.2783, 0.5512, 0.5667],
[0.6261, 0.4131, 0.8938, 0.3550, 0.4000, 0.2683, 0.6187, 0.5283],
[0.0000, 0.0000, 0.7192, 0.2346, 0.4038, 0.2050, 0.5138, 0.5650]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0020, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0020, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.09650458296528086
step: 58
running loss: 0.0016638721200910494
Train Steps: 58/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6148, 0.4076, 0.8666, 0.4820, 0.4138, 0.5067, 0.5250, 0.5767],
[0.6080, 0.4010, 0.8750, 0.4500, 0.4825, 0.5617, 0.5837, 0.5583],
[0.6201, 0.4055, 0.7717, 0.1919, 0.4250, 0.2079, 0.5871, 0.5044],
[0.6109, 0.3943, 0.8525, 0.4950, 0.4338, 0.4800, 0.5449, 0.5383],
[0.6189, 0.3911, 0.8800, 0.4917, 0.3713, 0.4800, 0.6038, 0.4833],
[0.6293, 0.4024, 0.8750, 0.5000, 0.4012, 0.5733, 0.7121, 0.5633],
[ nan, nan, 0.6793, 0.2110, 0.4012, 0.2167, 0.5112, 0.5583],
[0.6075, 0.4000, 0.8513, 0.5183, 0.4510, 0.5329, 0.5180, 0.5280]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7382, 0.4823, 0.8761, 0.5222, 0.4304, 0.4852, 0.6209, 0.5718],
[0.7312, 0.4900, 0.8813, 0.4541, 0.4890, 0.5090, 0.6586, 0.5728],
[0.6612, 0.4320, 0.7609, 0.2048, 0.4153, 0.2033, 0.6580, 0.5155],
[0.6932, 0.4531, 0.8719, 0.5102, 0.4333, 0.4629, 0.6154, 0.5461],
[0.7277, 0.4609, 0.8940, 0.5155, 0.4000, 0.4746, 0.6561, 0.5016],
[0.7316, 0.4616, 0.9022, 0.5313, 0.4126, 0.5640, 0.7744, 0.5645],
[0.1607, 0.0987, 0.6774, 0.2018, 0.4002, 0.1998, 0.5467, 0.5342],
[0.7042, 0.4623, 0.8553, 0.5422, 0.4580, 0.5011, 0.6179, 0.5370]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6148, 0.4076, 0.8666, 0.4820, 0.4137, 0.5067, 0.5250, 0.5767],
[0.6080, 0.4010, 0.8750, 0.4500, 0.4825, 0.5617, 0.5838, 0.5583],
[0.6202, 0.4055, 0.7717, 0.1919, 0.4250, 0.2079, 0.5871, 0.5044],
[0.6109, 0.3943, 0.8525, 0.4950, 0.4338, 0.4800, 0.5449, 0.5383],
[0.6189, 0.3911, 0.8800, 0.4917, 0.3713, 0.4800, 0.6037, 0.4833],
[0.6293, 0.4024, 0.8750, 0.5000, 0.4013, 0.5733, 0.7121, 0.5633],
[0.0000, 0.0000, 0.6793, 0.2110, 0.4013, 0.2167, 0.5113, 0.5583],
[0.6075, 0.4000, 0.8512, 0.5183, 0.4510, 0.5329, 0.5180, 0.5280]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0030, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0030, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.09950864681741223
step: 59
running loss: 0.0016865872341934275
Train Steps: 59/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6204, 0.4007, 0.7838, 0.2100, 0.4475, 0.1733, 0.5825, 0.5167],
[0.6202, 0.4066, 0.8398, 0.2648, 0.3925, 0.2627, 0.5845, 0.5124],
[0.6182, 0.3930, 0.8841, 0.3892, 0.3556, 0.4967, 0.6222, 0.5279],
[0.6273, 0.4143, 0.8750, 0.5700, 0.3987, 0.4717, 0.6013, 0.5467],
[0.6193, 0.4108, 0.7438, 0.2700, 0.3650, 0.3683, 0.6238, 0.5717],
[0.6259, 0.4133, 0.8200, 0.2317, 0.5025, 0.1533, 0.6250, 0.4947],
[0.6263, 0.4039, 0.9000, 0.4400, 0.3625, 0.4667, 0.6424, 0.4804],
[0.6251, 0.4163, 0.8662, 0.4467, 0.3625, 0.3567, 0.6038, 0.5533]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6482, 0.3921, 0.7578, 0.2343, 0.4396, 0.1740, 0.6194, 0.5175],
[0.7013, 0.4344, 0.8072, 0.2890, 0.4050, 0.2726, 0.6344, 0.5235],
[0.6638, 0.3961, 0.8857, 0.4162, 0.3702, 0.4941, 0.6593, 0.5240],
[0.6293, 0.3778, 0.8640, 0.6180, 0.4028, 0.4876, 0.6442, 0.5462],
[0.6033, 0.3709, 0.7571, 0.2885, 0.3631, 0.3846, 0.6689, 0.5528],
[0.7017, 0.4492, 0.8180, 0.2445, 0.4934, 0.1715, 0.6521, 0.4938],
[0.6669, 0.3932, 0.9262, 0.4911, 0.3702, 0.4925, 0.6464, 0.5024],
[0.7239, 0.4449, 0.8679, 0.4768, 0.3647, 0.3830, 0.6458, 0.5466]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6204, 0.4007, 0.7837, 0.2100, 0.4475, 0.1733, 0.5825, 0.5167],
[0.6202, 0.4066, 0.8398, 0.2648, 0.3925, 0.2627, 0.5845, 0.5124],
[0.6182, 0.3930, 0.8841, 0.3892, 0.3556, 0.4967, 0.6222, 0.5279],
[0.6273, 0.4143, 0.8750, 0.5700, 0.3988, 0.4717, 0.6012, 0.5467],
[0.6193, 0.4108, 0.7437, 0.2700, 0.3650, 0.3683, 0.6237, 0.5717],
[0.6259, 0.4132, 0.8200, 0.2317, 0.5025, 0.1533, 0.6250, 0.4947],
[0.6263, 0.4038, 0.9000, 0.4400, 0.3625, 0.4667, 0.6424, 0.4804],
[0.6252, 0.4162, 0.8662, 0.4467, 0.3625, 0.3567, 0.6037, 0.5533]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.10043607087573037
step: 60
running loss: 0.0016739345145955061
Train Steps: 60/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6109, 0.4015, 0.7668, 0.3639, 0.3513, 0.3667, 0.5200, 0.5641],
[0.6203, 0.4056, 0.8942, 0.4086, 0.3643, 0.3617, 0.5917, 0.5482],
[0.6218, 0.4137, 0.7263, 0.2233, 0.4075, 0.2650, 0.6212, 0.5783],
[0.6128, 0.4116, 0.8450, 0.4583, 0.3675, 0.4867, 0.5337, 0.5446],
[0.6329, 0.4196, 0.9238, 0.4583, 0.4263, 0.2933, 0.7343, 0.5748],
[0.6226, 0.4103, 0.8575, 0.3450, 0.4388, 0.2067, 0.5787, 0.5383],
[0.6302, 0.4007, 0.8850, 0.5500, 0.3613, 0.4517, 0.6335, 0.5012],
[0.6175, 0.4091, 0.7863, 0.2800, 0.3638, 0.3583, 0.6188, 0.5433]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6287, 0.3835, 0.7721, 0.3537, 0.3589, 0.3807, 0.5404, 0.5136],
[0.7034, 0.4113, 0.8991, 0.4467, 0.3619, 0.3990, 0.6077, 0.5131],
[0.6951, 0.4118, 0.7277, 0.2470, 0.4020, 0.2793, 0.6083, 0.5252],
[0.7054, 0.4191, 0.8589, 0.4918, 0.3990, 0.4911, 0.5657, 0.5131],
[0.7142, 0.4282, 0.9088, 0.4964, 0.4427, 0.3011, 0.7445, 0.5255],
[0.7862, 0.4827, 0.8517, 0.3759, 0.4657, 0.2416, 0.5966, 0.5169],
[0.7011, 0.4088, 0.8817, 0.5840, 0.3721, 0.4897, 0.6431, 0.4846],
[0.5986, 0.3631, 0.7848, 0.2676, 0.3712, 0.3852, 0.6174, 0.5040]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6109, 0.4015, 0.7668, 0.3639, 0.3512, 0.3667, 0.5200, 0.5641],
[0.6203, 0.4056, 0.8942, 0.4086, 0.3643, 0.3617, 0.5917, 0.5482],
[0.6218, 0.4137, 0.7262, 0.2233, 0.4075, 0.2650, 0.6212, 0.5783],
[0.6128, 0.4116, 0.8450, 0.4583, 0.3675, 0.4867, 0.5337, 0.5446],
[0.6329, 0.4196, 0.9237, 0.4583, 0.4263, 0.2933, 0.7343, 0.5748],
[0.6226, 0.4103, 0.8575, 0.3450, 0.4387, 0.2067, 0.5788, 0.5383],
[0.6302, 0.4007, 0.8850, 0.5500, 0.3613, 0.4517, 0.6335, 0.5012],
[0.6175, 0.4091, 0.7862, 0.2800, 0.3638, 0.3583, 0.6187, 0.5433]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.10195993207162246
step: 61
running loss: 0.0016714742962561059
Train Steps: 61/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6192, 0.3980, 0.7078, 0.2750, 0.4250, 0.2100, 0.5450, 0.5783],
[0.6275, 0.4013, 0.8850, 0.2833, 0.4975, 0.2233, 0.7058, 0.5343],
[0.6216, 0.4167, 0.8588, 0.5583, 0.3975, 0.5167, 0.5775, 0.5667],
[0.6070, 0.3979, 0.8575, 0.5083, 0.4350, 0.5400, 0.5180, 0.5466],
[0.6193, 0.4050, 0.7313, 0.2433, 0.4075, 0.2117, 0.5649, 0.5656],
[0.6154, 0.4112, 0.7037, 0.2317, 0.4238, 0.1833, 0.5350, 0.5600],
[0.6271, 0.4024, 0.9000, 0.3517, 0.3700, 0.4517, 0.6931, 0.5285],
[0.6218, 0.4185, 0.7338, 0.2650, 0.4625, 0.1950, 0.5687, 0.5800]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6247, 0.3661, 0.7157, 0.2869, 0.4271, 0.2154, 0.5333, 0.5766],
[0.6447, 0.3784, 0.8774, 0.2905, 0.5059, 0.2369, 0.7035, 0.5209],
[0.7440, 0.4345, 0.8946, 0.6275, 0.4013, 0.5598, 0.6141, 0.5292],
[0.7049, 0.4133, 0.8685, 0.5509, 0.4432, 0.5565, 0.5157, 0.5046],
[0.6179, 0.3676, 0.7443, 0.2568, 0.4057, 0.2316, 0.5449, 0.5404],
[0.6160, 0.3691, 0.7046, 0.2429, 0.4079, 0.1970, 0.5292, 0.5258],
[0.6514, 0.3870, 0.9177, 0.3847, 0.3822, 0.4629, 0.6947, 0.5112],
[0.6073, 0.3739, 0.7232, 0.2653, 0.4281, 0.1929, 0.5387, 0.5596]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6192, 0.3980, 0.7078, 0.2750, 0.4250, 0.2100, 0.5450, 0.5783],
[0.6275, 0.4013, 0.8850, 0.2833, 0.4975, 0.2233, 0.7058, 0.5343],
[0.6216, 0.4167, 0.8587, 0.5583, 0.3975, 0.5167, 0.5775, 0.5667],
[0.6070, 0.3979, 0.8575, 0.5083, 0.4350, 0.5400, 0.5180, 0.5466],
[0.6193, 0.4050, 0.7312, 0.2433, 0.4075, 0.2117, 0.5649, 0.5656],
[0.6154, 0.4112, 0.7038, 0.2317, 0.4238, 0.1833, 0.5350, 0.5600],
[0.6271, 0.4024, 0.9000, 0.3517, 0.3700, 0.4517, 0.6931, 0.5285],
[0.6218, 0.4185, 0.7337, 0.2650, 0.4625, 0.1950, 0.5688, 0.5800]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.10285078029846773
step: 62
running loss: 0.0016588835532010922
Train Steps: 62/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6332, 0.4128, 0.9200, 0.3517, 0.4400, 0.3833, 0.7461, 0.5494],
[ nan, nan, 0.7412, 0.2200, 0.4450, 0.1517, 0.5312, 0.4983],
[0.6258, 0.4143, 0.8525, 0.2617, 0.4950, 0.1667, 0.6219, 0.4967],
[0.6145, 0.4007, 0.8775, 0.4533, 0.4562, 0.5533, 0.6088, 0.5533],
[0.6262, 0.4085, 0.8438, 0.3150, 0.4025, 0.2633, 0.6339, 0.4810],
[0.6126, 0.4039, 0.8237, 0.3967, 0.3625, 0.3600, 0.5894, 0.6138],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098],
[0.6361, 0.4076, 0.8862, 0.5350, 0.3713, 0.4650, 0.6654, 0.5297]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7079, 0.4305, 0.9018, 0.3640, 0.4346, 0.3790, 0.6754, 0.5370],
[0.1807, 0.0795, 0.7081, 0.2036, 0.4204, 0.1630, 0.4939, 0.5363],
[0.7387, 0.4639, 0.8380, 0.2717, 0.4993, 0.1799, 0.5849, 0.5192],
[0.7147, 0.4226, 0.8808, 0.4658, 0.4636, 0.5462, 0.5793, 0.5490],
[0.7203, 0.4444, 0.8488, 0.3098, 0.4027, 0.2778, 0.5885, 0.4940],
[0.6518, 0.3961, 0.8113, 0.4107, 0.3574, 0.3735, 0.5625, 0.5967],
[0.6976, 0.4263, 0.8730, 0.4764, 0.3820, 0.5138, 0.5499, 0.5146],
[0.7670, 0.4823, 0.8740, 0.5626, 0.3858, 0.4831, 0.6404, 0.5375]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6332, 0.4128, 0.9200, 0.3517, 0.4400, 0.3833, 0.7461, 0.5494],
[0.0000, 0.0000, 0.7412, 0.2200, 0.4450, 0.1517, 0.5312, 0.4983],
[0.6258, 0.4143, 0.8525, 0.2617, 0.4950, 0.1667, 0.6219, 0.4967],
[0.6145, 0.4007, 0.8775, 0.4533, 0.4563, 0.5533, 0.6087, 0.5533],
[0.6262, 0.4085, 0.8438, 0.3150, 0.4025, 0.2633, 0.6339, 0.4810],
[0.6126, 0.4038, 0.8238, 0.3967, 0.3625, 0.3600, 0.5894, 0.6138],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098],
[0.6361, 0.4076, 0.8863, 0.5350, 0.3713, 0.4650, 0.6654, 0.5297]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0021, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0021, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.10497850127285346
step: 63
running loss: 0.00166632541702942
Train Steps: 63/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6150, 0.4097, 0.7468, 0.3194, 0.3825, 0.2633, 0.5463, 0.5800],
[0.6273, 0.4100, 0.7137, 0.2133, 0.4000, 0.2650, 0.6075, 0.5633],
[0.6250, 0.3961, 0.8672, 0.4929, 0.4199, 0.4972, 0.6312, 0.5301],
[0.6332, 0.4165, 0.9100, 0.3350, 0.4188, 0.3683, 0.7438, 0.5528],
[0.6075, 0.4000, 0.8513, 0.5183, 0.4510, 0.5329, 0.5180, 0.5280],
[0.6207, 0.4110, 0.8738, 0.5000, 0.4800, 0.5633, 0.6300, 0.5433],
[0.6126, 0.4073, 0.8750, 0.5133, 0.3800, 0.4333, 0.4986, 0.5378],
[0.6131, 0.4037, 0.6907, 0.2819, 0.3688, 0.2700, 0.5217, 0.5680]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5489, 0.3741, 0.7715, 0.3019, 0.3528, 0.2394, 0.5202, 0.5679],
[0.5608, 0.3765, 0.7200, 0.2122, 0.3870, 0.2277, 0.5736, 0.5654],
[0.6949, 0.4254, 0.8806, 0.4887, 0.4158, 0.4699, 0.6067, 0.5323],
[0.6474, 0.4089, 0.9201, 0.3635, 0.4119, 0.3545, 0.7003, 0.5663],
[0.6503, 0.4275, 0.8552, 0.5129, 0.4399, 0.4933, 0.5123, 0.5289],
[0.7275, 0.4710, 0.8964, 0.4896, 0.4696, 0.5465, 0.5877, 0.5373],
[0.6598, 0.4386, 0.8856, 0.5192, 0.3787, 0.4187, 0.4934, 0.5376],
[0.5645, 0.3624, 0.7051, 0.2746, 0.3734, 0.2543, 0.5114, 0.5627]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6150, 0.4097, 0.7468, 0.3194, 0.3825, 0.2633, 0.5462, 0.5800],
[0.6273, 0.4099, 0.7138, 0.2133, 0.4000, 0.2650, 0.6075, 0.5633],
[0.6250, 0.3961, 0.8672, 0.4929, 0.4199, 0.4972, 0.6312, 0.5301],
[0.6332, 0.4165, 0.9100, 0.3350, 0.4187, 0.3683, 0.7438, 0.5528],
[0.6075, 0.4000, 0.8512, 0.5183, 0.4510, 0.5329, 0.5180, 0.5280],
[0.6207, 0.4110, 0.8737, 0.5000, 0.4800, 0.5633, 0.6300, 0.5433],
[0.6126, 0.4073, 0.8750, 0.5133, 0.3800, 0.4333, 0.4986, 0.5378],
[0.6131, 0.4036, 0.6907, 0.2819, 0.3688, 0.2700, 0.5217, 0.5680]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.10589164070552215
step: 64
running loss: 0.0016545568860237836
Train Steps: 64/90 Loss: 0.0017 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5413, 0.5683],
[0.6336, 0.4191, 0.8938, 0.5167, 0.3937, 0.3517, 0.7343, 0.5748],
[0.6058, 0.3978, 0.8287, 0.3600, 0.3400, 0.4050, 0.5529, 0.5461],
[0.6161, 0.4099, 0.8738, 0.4383, 0.3788, 0.5483, 0.5605, 0.5019],
[0.6264, 0.4049, 0.8988, 0.4633, 0.3813, 0.4983, 0.6326, 0.4843],
[0.6113, 0.4006, 0.8700, 0.5350, 0.3638, 0.3767, 0.5097, 0.4882],
[0.6258, 0.4038, 0.8750, 0.4883, 0.3900, 0.5500, 0.6375, 0.5217],
[0.6280, 0.4101, 0.9050, 0.4533, 0.3775, 0.3217, 0.6338, 0.4915]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6221, 0.4283, 0.8628, 0.4962, 0.3900, 0.3418, 0.5310, 0.5983],
[0.7085, 0.4884, 0.8724, 0.4659, 0.4139, 0.3262, 0.6839, 0.5850],
[0.5233, 0.3546, 0.8350, 0.3252, 0.3570, 0.3759, 0.5416, 0.5449],
[0.5835, 0.3883, 0.8672, 0.3821, 0.3898, 0.5025, 0.5429, 0.5312],
[0.6488, 0.4269, 0.8925, 0.4275, 0.3925, 0.4656, 0.6009, 0.5248],
[0.5921, 0.4094, 0.8436, 0.4683, 0.3680, 0.3727, 0.5096, 0.5457],
[0.6816, 0.4483, 0.8707, 0.4532, 0.4092, 0.5143, 0.6279, 0.5406],
[0.6375, 0.4225, 0.8894, 0.4271, 0.3852, 0.3125, 0.6002, 0.5315]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5412, 0.5683],
[0.6336, 0.4191, 0.8938, 0.5167, 0.3938, 0.3517, 0.7343, 0.5748],
[0.6058, 0.3978, 0.8288, 0.3600, 0.3400, 0.4050, 0.5529, 0.5461],
[0.6161, 0.4099, 0.8737, 0.4383, 0.3787, 0.5483, 0.5605, 0.5019],
[0.6264, 0.4049, 0.8988, 0.4633, 0.3812, 0.4983, 0.6326, 0.4843],
[0.6113, 0.4006, 0.8700, 0.5350, 0.3638, 0.3767, 0.5097, 0.4882],
[0.6258, 0.4038, 0.8750, 0.4883, 0.3900, 0.5500, 0.6375, 0.5217],
[0.6280, 0.4101, 0.9050, 0.4533, 0.3775, 0.3217, 0.6338, 0.4915]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.10696358111454174
step: 65
running loss: 0.0016455935556083344
Train Steps: 65/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6201, 0.4055, 0.7717, 0.1919, 0.4250, 0.2079, 0.5871, 0.5044],
[0.6064, 0.4019, 0.8650, 0.4517, 0.4037, 0.5367, 0.5703, 0.5609],
[0.6138, 0.4020, 0.8800, 0.4717, 0.4375, 0.4717, 0.5502, 0.5611],
[0.6102, 0.4020, 0.8638, 0.3717, 0.3625, 0.5017, 0.6038, 0.5500],
[0.6286, 0.4078, 0.8063, 0.2267, 0.4788, 0.1533, 0.5953, 0.4913],
[ nan, nan, 0.8900, 0.3217, 0.5038, 0.2233, 0.6694, 0.5609],
[0.6336, 0.4191, 0.8938, 0.5167, 0.3937, 0.3517, 0.7343, 0.5748],
[0.6185, 0.4080, 0.8625, 0.3483, 0.3788, 0.2650, 0.5320, 0.5272]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5393, 0.3889, 0.7657, 0.1986, 0.4130, 0.1993, 0.5852, 0.5261],
[0.5829, 0.4071, 0.8496, 0.4321, 0.3864, 0.5271, 0.5797, 0.5473],
[0.6193, 0.4327, 0.8669, 0.4604, 0.4150, 0.4514, 0.5412, 0.5538],
[0.5629, 0.3962, 0.8623, 0.3543, 0.3623, 0.4686, 0.6162, 0.5318],
[0.4795, 0.3447, 0.7762, 0.2536, 0.4611, 0.1480, 0.5585, 0.5314],
[0.1735, 0.1281, 0.8874, 0.2998, 0.4933, 0.2157, 0.6412, 0.5723],
[0.6627, 0.4651, 0.8768, 0.4995, 0.3844, 0.3360, 0.7009, 0.5691],
[0.6295, 0.4397, 0.8468, 0.3628, 0.3846, 0.2779, 0.5188, 0.5498]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6202, 0.4055, 0.7717, 0.1919, 0.4250, 0.2079, 0.5871, 0.5044],
[0.6064, 0.4019, 0.8650, 0.4517, 0.4038, 0.5367, 0.5703, 0.5609],
[0.6138, 0.4020, 0.8800, 0.4717, 0.4375, 0.4717, 0.5502, 0.5611],
[0.6102, 0.4020, 0.8637, 0.3717, 0.3625, 0.5017, 0.6037, 0.5500],
[0.6286, 0.4078, 0.8062, 0.2267, 0.4787, 0.1533, 0.5953, 0.4913],
[0.0000, 0.0000, 0.8900, 0.3217, 0.5038, 0.2233, 0.6694, 0.5609],
[0.6336, 0.4191, 0.8938, 0.5167, 0.3938, 0.3517, 0.7343, 0.5748],
[0.6186, 0.4080, 0.8625, 0.3483, 0.3787, 0.2650, 0.5320, 0.5272]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.10856805794173852
step: 66
running loss: 0.001644970574874826
Train Steps: 66/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6279, 0.4050, 0.8025, 0.2200, 0.4313, 0.2733, 0.6820, 0.5320],
[0.6161, 0.4024, 0.8838, 0.4583, 0.3688, 0.3733, 0.5311, 0.5344],
[0.6258, 0.4143, 0.8525, 0.2617, 0.4950, 0.1667, 0.6219, 0.4967],
[0.6248, 0.4185, 0.8500, 0.5767, 0.4463, 0.4550, 0.5613, 0.5917],
[0.6093, 0.3990, 0.8400, 0.4333, 0.3688, 0.4633, 0.5560, 0.5656],
[0.6211, 0.3935, 0.8636, 0.4841, 0.4417, 0.5126, 0.6331, 0.5268],
[0.6203, 0.4021, 0.8780, 0.5031, 0.3667, 0.3882, 0.5842, 0.5405],
[0.6160, 0.4093, 0.8314, 0.4417, 0.3675, 0.4583, 0.5250, 0.5808]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5448, 0.3894, 0.8145, 0.2338, 0.4142, 0.2702, 0.6812, 0.5341],
[0.5694, 0.3942, 0.8913, 0.4585, 0.3639, 0.3936, 0.5592, 0.5375],
[0.5310, 0.3859, 0.8618, 0.2606, 0.4940, 0.1833, 0.6343, 0.5224],
[0.5874, 0.4226, 0.8470, 0.5582, 0.4386, 0.4280, 0.5736, 0.5882],
[0.5255, 0.3685, 0.8450, 0.4086, 0.3649, 0.4420, 0.5704, 0.5609],
[0.5708, 0.3805, 0.8753, 0.4588, 0.4241, 0.4992, 0.6315, 0.5281],
[0.5485, 0.3756, 0.8864, 0.5135, 0.3552, 0.4017, 0.6095, 0.5225],
[0.5485, 0.3837, 0.8391, 0.4335, 0.3586, 0.4426, 0.5607, 0.5755]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6279, 0.4050, 0.8025, 0.2200, 0.4313, 0.2733, 0.6820, 0.5320],
[0.6161, 0.4024, 0.8838, 0.4583, 0.3688, 0.3733, 0.5311, 0.5344],
[0.6258, 0.4143, 0.8525, 0.2617, 0.4950, 0.1667, 0.6219, 0.4967],
[0.6248, 0.4185, 0.8500, 0.5767, 0.4462, 0.4550, 0.5612, 0.5917],
[0.6093, 0.3990, 0.8400, 0.4333, 0.3688, 0.4633, 0.5560, 0.5656],
[0.6211, 0.3935, 0.8636, 0.4841, 0.4417, 0.5126, 0.6331, 0.5268],
[0.6203, 0.4020, 0.8780, 0.5031, 0.3667, 0.3882, 0.5842, 0.5405],
[0.6160, 0.4092, 0.8314, 0.4417, 0.3675, 0.4583, 0.5250, 0.5808]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.10938900749897584
step: 67
running loss: 0.0016326717537160573
Train Steps: 67/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6175, 0.3997, 0.6737, 0.2500, 0.4313, 0.1933, 0.5513, 0.5750],
[0.6100, 0.4071, 0.7601, 0.3444, 0.3400, 0.4117, 0.5625, 0.5617],
[0.6197, 0.3930, 0.8793, 0.4736, 0.4152, 0.5464, 0.6308, 0.5235],
[0.6223, 0.4028, 0.8988, 0.4200, 0.3763, 0.5733, 0.6375, 0.5167],
[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466],
[0.6268, 0.4029, 0.8500, 0.2683, 0.3937, 0.3500, 0.6860, 0.5297],
[0.6131, 0.4037, 0.6907, 0.2819, 0.3688, 0.2700, 0.5217, 0.5680],
[0.6138, 0.4020, 0.8800, 0.4717, 0.4375, 0.4717, 0.5502, 0.5611]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4256, 0.3133, 0.7312, 0.2664, 0.4504, 0.1735, 0.5968, 0.5748],
[0.5070, 0.3664, 0.8311, 0.3491, 0.3637, 0.4180, 0.6030, 0.5581],
[0.5938, 0.4139, 0.9050, 0.5002, 0.4267, 0.5329, 0.6676, 0.5504],
[0.5597, 0.3864, 0.9127, 0.4380, 0.4046, 0.5862, 0.6737, 0.5258],
[0.4858, 0.3554, 0.8112, 0.3820, 0.3644, 0.4135, 0.5584, 0.5594],
[0.6025, 0.4247, 0.8645, 0.2894, 0.3939, 0.3295, 0.7073, 0.5438],
[0.5373, 0.3748, 0.7314, 0.3082, 0.4009, 0.2635, 0.5578, 0.5699],
[0.5954, 0.4201, 0.8981, 0.4821, 0.4482, 0.4694, 0.5724, 0.5615]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6175, 0.3997, 0.6737, 0.2500, 0.4313, 0.1933, 0.5512, 0.5750],
[0.6100, 0.4071, 0.7601, 0.3444, 0.3400, 0.4117, 0.5625, 0.5617],
[0.6197, 0.3930, 0.8793, 0.4736, 0.4152, 0.5464, 0.6308, 0.5235],
[0.6223, 0.4028, 0.8988, 0.4200, 0.3762, 0.5733, 0.6375, 0.5167],
[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466],
[0.6268, 0.4029, 0.8500, 0.2683, 0.3938, 0.3500, 0.6860, 0.5297],
[0.6131, 0.4036, 0.6907, 0.2819, 0.3688, 0.2700, 0.5217, 0.5680],
[0.6138, 0.4020, 0.8800, 0.4717, 0.4375, 0.4717, 0.5502, 0.5611]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.11124868033220991
step: 68
running loss: 0.00163601000488544
Train Steps: 68/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6198, 0.4164, 0.8700, 0.5067, 0.4625, 0.5650, 0.5464, 0.5197],
[0.6069, 0.3975, 0.8625, 0.5083, 0.4388, 0.5483, 0.5650, 0.4967],
[0.6229, 0.4107, 0.8137, 0.2883, 0.4750, 0.1717, 0.5813, 0.5400],
[0.6192, 0.4128, 0.8513, 0.5617, 0.4200, 0.5267, 0.5850, 0.5633],
[0.6317, 0.4038, 0.8287, 0.5900, 0.3800, 0.4717, 0.6295, 0.4986],
[0.6218, 0.4137, 0.7263, 0.2233, 0.4075, 0.2650, 0.6212, 0.5783],
[0.6293, 0.4024, 0.8750, 0.5000, 0.4012, 0.5733, 0.7121, 0.5633],
[0.6250, 0.3993, 0.9138, 0.4333, 0.3763, 0.5217, 0.6995, 0.5320]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5563, 0.3870, 0.8563, 0.4827, 0.4403, 0.5231, 0.5433, 0.5044],
[0.5492, 0.3759, 0.8491, 0.4923, 0.4246, 0.5409, 0.5634, 0.5205],
[0.5895, 0.4069, 0.8284, 0.2998, 0.4732, 0.1896, 0.5892, 0.5576],
[0.5430, 0.3776, 0.8512, 0.5306, 0.4005, 0.5172, 0.5993, 0.5526],
[0.5404, 0.3731, 0.8525, 0.5451, 0.3619, 0.4570, 0.6332, 0.5041],
[0.5671, 0.3874, 0.7579, 0.2432, 0.3995, 0.2573, 0.6219, 0.5672],
[0.5508, 0.3591, 0.8674, 0.4709, 0.3768, 0.5651, 0.6735, 0.5446],
[0.5503, 0.3572, 0.9081, 0.4160, 0.3851, 0.5056, 0.7052, 0.5347]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6198, 0.4164, 0.8700, 0.5067, 0.4625, 0.5650, 0.5464, 0.5197],
[0.6069, 0.3975, 0.8625, 0.5083, 0.4387, 0.5483, 0.5650, 0.4967],
[0.6229, 0.4107, 0.8138, 0.2883, 0.4750, 0.1717, 0.5813, 0.5400],
[0.6192, 0.4128, 0.8512, 0.5617, 0.4200, 0.5267, 0.5850, 0.5633],
[0.6317, 0.4038, 0.8288, 0.5900, 0.3800, 0.4717, 0.6295, 0.4986],
[0.6218, 0.4137, 0.7262, 0.2233, 0.4075, 0.2650, 0.6212, 0.5783],
[0.6293, 0.4024, 0.8750, 0.5000, 0.4013, 0.5733, 0.7121, 0.5633],
[0.6250, 0.3993, 0.9137, 0.4333, 0.3762, 0.5217, 0.6995, 0.5320]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.11220953316660598
step: 69
running loss: 0.0016262251183566084
Train Steps: 69/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6173, 0.4013, 0.8713, 0.4640, 0.4800, 0.5700, 0.6025, 0.5600],
[0.6073, 0.3932, 0.8363, 0.5817, 0.4425, 0.5117, 0.5204, 0.4817],
[0.6172, 0.4055, 0.8175, 0.2650, 0.3550, 0.3683, 0.5787, 0.5550],
[0.6060, 0.3924, 0.8450, 0.5717, 0.4200, 0.5217, 0.5253, 0.4752],
[ nan, nan, 0.7097, 0.2346, 0.4250, 0.1850, 0.5175, 0.5583],
[0.6161, 0.4040, 0.7525, 0.2133, 0.4125, 0.2067, 0.5787, 0.5117],
[0.6255, 0.4017, 0.8688, 0.3217, 0.3638, 0.3550, 0.6344, 0.4901],
[0.6361, 0.4165, 0.9038, 0.5017, 0.3750, 0.3783, 0.6448, 0.5309]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5894, 0.3943, 0.8446, 0.4361, 0.4505, 0.5642, 0.6108, 0.5490],
[0.5916, 0.3702, 0.8096, 0.5563, 0.4293, 0.5186, 0.5392, 0.4968],
[0.6256, 0.4082, 0.8094, 0.2928, 0.3440, 0.3792, 0.5929, 0.5366],
[0.5960, 0.3767, 0.8206, 0.5812, 0.4219, 0.5179, 0.5555, 0.4948],
[0.1566, 0.1218, 0.7175, 0.2339, 0.4316, 0.1995, 0.5217, 0.5481],
[0.6159, 0.4071, 0.7354, 0.2169, 0.4185, 0.2362, 0.6050, 0.5164],
[0.6355, 0.4033, 0.8359, 0.3240, 0.3578, 0.3834, 0.6605, 0.5133],
[0.6122, 0.3977, 0.8758, 0.4785, 0.3735, 0.3831, 0.6451, 0.5342]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6173, 0.4013, 0.8713, 0.4640, 0.4800, 0.5700, 0.6025, 0.5600],
[0.6073, 0.3932, 0.8363, 0.5817, 0.4425, 0.5117, 0.5204, 0.4817],
[0.6172, 0.4055, 0.8175, 0.2650, 0.3550, 0.3683, 0.5788, 0.5550],
[0.6060, 0.3924, 0.8450, 0.5717, 0.4200, 0.5217, 0.5253, 0.4752],
[0.0000, 0.0000, 0.7097, 0.2346, 0.4250, 0.1850, 0.5175, 0.5583],
[0.6161, 0.4040, 0.7525, 0.2133, 0.4125, 0.2067, 0.5788, 0.5117],
[0.6255, 0.4017, 0.8687, 0.3217, 0.3638, 0.3550, 0.6344, 0.4901],
[0.6361, 0.4165, 0.9038, 0.5017, 0.3750, 0.3783, 0.6448, 0.5309]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.11311025434406474
step: 70
running loss: 0.001615860776343782
Train Steps: 70/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6175, 0.3997, 0.6737, 0.2500, 0.4313, 0.1933, 0.5513, 0.5750],
[0.6250, 0.4054, 0.8770, 0.4723, 0.4662, 0.5367, 0.6162, 0.5433],
[0.6257, 0.4167, 0.8775, 0.3433, 0.3563, 0.4133, 0.6200, 0.5667],
[0.6250, 0.4116, 0.8700, 0.4850, 0.4650, 0.5567, 0.6088, 0.5183],
[0.6275, 0.4048, 0.8488, 0.2883, 0.4463, 0.2033, 0.6321, 0.5155],
[0.6261, 0.3987, 0.9045, 0.4208, 0.3600, 0.4633, 0.6570, 0.5162],
[0.6097, 0.4000, 0.7325, 0.2667, 0.3450, 0.3517, 0.5284, 0.5045],
[0.6085, 0.4005, 0.8400, 0.4317, 0.3763, 0.4750, 0.5476, 0.5058]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5502, 0.3574, 0.6851, 0.2700, 0.4356, 0.2077, 0.5738, 0.5523],
[0.5865, 0.3874, 0.8746, 0.4779, 0.4575, 0.5594, 0.6084, 0.5240],
[0.6299, 0.3938, 0.8675, 0.3658, 0.3588, 0.4424, 0.6396, 0.5507],
[0.5341, 0.3422, 0.8595, 0.4866, 0.4463, 0.5918, 0.5941, 0.5159],
[0.6748, 0.4351, 0.8300, 0.2889, 0.4593, 0.2303, 0.6556, 0.5105],
[0.5803, 0.3658, 0.8792, 0.4309, 0.3655, 0.5083, 0.6469, 0.5170],
[0.5794, 0.3641, 0.7371, 0.3003, 0.3485, 0.3589, 0.5397, 0.5130],
[0.6032, 0.3811, 0.8296, 0.4438, 0.3641, 0.4955, 0.5187, 0.5050]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6175, 0.3997, 0.6737, 0.2500, 0.4313, 0.1933, 0.5512, 0.5750],
[0.6250, 0.4054, 0.8770, 0.4723, 0.4663, 0.5367, 0.6162, 0.5433],
[0.6257, 0.4167, 0.8775, 0.3433, 0.3562, 0.4133, 0.6200, 0.5667],
[0.6251, 0.4116, 0.8700, 0.4850, 0.4650, 0.5567, 0.6087, 0.5183],
[0.6275, 0.4048, 0.8487, 0.2883, 0.4462, 0.2033, 0.6321, 0.5155],
[0.6261, 0.3987, 0.9045, 0.4208, 0.3600, 0.4633, 0.6570, 0.5162],
[0.6097, 0.4000, 0.7325, 0.2667, 0.3450, 0.3517, 0.5284, 0.5045],
[0.6084, 0.4005, 0.8400, 0.4317, 0.3762, 0.4750, 0.5476, 0.5058]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.11381898814579472
step: 71
running loss: 0.0016030843400816157
Train Steps: 71/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6307, 0.4029, 0.8988, 0.4817, 0.3937, 0.3500, 0.7311, 0.5378],
[0.6189, 0.4049, 0.8888, 0.4417, 0.4213, 0.5200, 0.5988, 0.5633],
[0.6275, 0.4071, 0.8075, 0.2100, 0.4700, 0.1533, 0.6148, 0.4834],
[0.6339, 0.4112, 0.8838, 0.5067, 0.4000, 0.5433, 0.7549, 0.5378],
[0.6125, 0.3999, 0.8750, 0.4883, 0.4750, 0.4700, 0.5533, 0.5617],
[0.6283, 0.4283, 0.7477, 0.3542, 0.5125, 0.1917, 0.5500, 0.6167],
[0.6136, 0.4060, 0.8025, 0.3217, 0.3650, 0.3000, 0.5060, 0.5646],
[0.6142, 0.3982, 0.8650, 0.4883, 0.3912, 0.4317, 0.5315, 0.5350]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6276, 0.3894, 0.8747, 0.4654, 0.3921, 0.3863, 0.6660, 0.5179],
[0.6014, 0.3731, 0.8574, 0.4411, 0.4104, 0.5811, 0.5857, 0.5430],
[0.6147, 0.3785, 0.7877, 0.2300, 0.4743, 0.1988, 0.6161, 0.4771],
[0.6622, 0.4007, 0.8515, 0.5078, 0.3759, 0.5819, 0.6995, 0.5133],
[0.5559, 0.3539, 0.8504, 0.4778, 0.4623, 0.5141, 0.5119, 0.5238],
[0.6134, 0.3951, 0.7303, 0.3397, 0.5047, 0.2150, 0.5570, 0.5806],
[0.5881, 0.3722, 0.7941, 0.3264, 0.3500, 0.3278, 0.4857, 0.5187],
[0.5848, 0.3471, 0.8362, 0.4906, 0.3879, 0.4857, 0.5017, 0.4967]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6307, 0.4029, 0.8988, 0.4817, 0.3938, 0.3500, 0.7311, 0.5378],
[0.6189, 0.4049, 0.8888, 0.4417, 0.4212, 0.5200, 0.5987, 0.5633],
[0.6275, 0.4071, 0.8075, 0.2100, 0.4700, 0.1533, 0.6148, 0.4834],
[0.6339, 0.4112, 0.8838, 0.5067, 0.4000, 0.5433, 0.7549, 0.5378],
[0.6125, 0.3999, 0.8750, 0.4883, 0.4750, 0.4700, 0.5533, 0.5617],
[0.6283, 0.4283, 0.7477, 0.3542, 0.5125, 0.1917, 0.5500, 0.6167],
[0.6136, 0.4060, 0.8025, 0.3217, 0.3650, 0.3000, 0.5060, 0.5646],
[0.6143, 0.3982, 0.8650, 0.4883, 0.3913, 0.4317, 0.5315, 0.5350]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.11468475608853623
step: 72
running loss: 0.0015928438345630032
Train Steps: 72/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6098, 0.3991, 0.8638, 0.4717, 0.4263, 0.4967, 0.5212, 0.5650],
[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586],
[0.6300, 0.4102, 0.9088, 0.4433, 0.4088, 0.3067, 0.6820, 0.5540],
[0.6262, 0.4163, 0.8850, 0.5183, 0.3763, 0.4150, 0.6025, 0.5500],
[0.6228, 0.4119, 0.7938, 0.2233, 0.4674, 0.1773, 0.6188, 0.5433],
[0.6274, 0.4003, 0.8638, 0.5967, 0.3688, 0.4900, 0.6108, 0.4661],
[0.6135, 0.4115, 0.8838, 0.4667, 0.4288, 0.6050, 0.5778, 0.5097],
[0.6140, 0.4070, 0.8700, 0.5000, 0.4612, 0.4900, 0.5260, 0.5852]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6321, 0.3942, 0.8170, 0.4639, 0.4226, 0.4967, 0.5175, 0.5260],
[0.6072, 0.3800, 0.8428, 0.2650, 0.4421, 0.2778, 0.6690, 0.5455],
[0.6211, 0.3606, 0.8914, 0.4243, 0.4077, 0.3264, 0.6256, 0.5129],
[0.6232, 0.3805, 0.8581, 0.4738, 0.3662, 0.4002, 0.5599, 0.5180],
[0.6466, 0.4008, 0.7879, 0.2387, 0.4705, 0.1779, 0.5898, 0.5244],
[0.6400, 0.3735, 0.8262, 0.5660, 0.3768, 0.4563, 0.6083, 0.4759],
[0.5742, 0.3790, 0.8567, 0.4308, 0.4156, 0.5919, 0.5513, 0.5092],
[0.6213, 0.3897, 0.8506, 0.4837, 0.4374, 0.4786, 0.5193, 0.5460]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6098, 0.3991, 0.8637, 0.4717, 0.4263, 0.4967, 0.5213, 0.5650],
[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586],
[0.6300, 0.4102, 0.9087, 0.4433, 0.4087, 0.3067, 0.6820, 0.5540],
[0.6262, 0.4163, 0.8850, 0.5183, 0.3762, 0.4150, 0.6025, 0.5500],
[0.6228, 0.4119, 0.7937, 0.2233, 0.4674, 0.1773, 0.6187, 0.5433],
[0.6274, 0.4003, 0.8637, 0.5967, 0.3688, 0.4900, 0.6108, 0.4661],
[0.6135, 0.4115, 0.8838, 0.4667, 0.4288, 0.6050, 0.5778, 0.5097],
[0.6140, 0.4070, 0.8700, 0.5000, 0.4613, 0.4900, 0.5260, 0.5852]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.11528142628958449
step: 73
running loss: 0.001579197620405267
Train Steps: 73/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6227, 0.4049, 0.8750, 0.5367, 0.3775, 0.3667, 0.5725, 0.5317],
[0.6224, 0.4061, 0.8988, 0.4300, 0.3838, 0.4750, 0.6112, 0.5483],
[0.6270, 0.4267, 0.7150, 0.3317, 0.4900, 0.1817, 0.5560, 0.6183],
[ nan, nan, 0.7850, 0.2700, 0.4288, 0.1717, 0.5199, 0.4999],
[0.6269, 0.4073, 0.8900, 0.4933, 0.3625, 0.4183, 0.6288, 0.5150],
[0.6321, 0.4048, 0.8738, 0.5617, 0.3875, 0.4417, 0.6361, 0.4927],
[0.6273, 0.4143, 0.8750, 0.5700, 0.3987, 0.4717, 0.6013, 0.5467],
[0.6357, 0.4097, 0.9038, 0.3883, 0.4213, 0.2950, 0.6686, 0.5390]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7195, 0.4545, 0.8844, 0.5364, 0.3846, 0.4108, 0.5699, 0.5352],
[0.6740, 0.4419, 0.9011, 0.4222, 0.3800, 0.5256, 0.5829, 0.5424],
[0.6853, 0.4666, 0.7156, 0.2920, 0.4794, 0.2020, 0.5704, 0.5991],
[0.2321, 0.1452, 0.7913, 0.2523, 0.4388, 0.2067, 0.5140, 0.5255],
[0.6632, 0.4370, 0.8896, 0.4825, 0.3672, 0.4591, 0.6066, 0.5275],
[0.6851, 0.4356, 0.8823, 0.5456, 0.3809, 0.4654, 0.6006, 0.5075],
[0.6783, 0.4285, 0.8513, 0.5570, 0.3972, 0.4829, 0.5697, 0.5386],
[0.7579, 0.4764, 0.8849, 0.3669, 0.4426, 0.3150, 0.6563, 0.5561]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6227, 0.4049, 0.8750, 0.5367, 0.3775, 0.3667, 0.5725, 0.5317],
[0.6224, 0.4061, 0.8988, 0.4300, 0.3837, 0.4750, 0.6112, 0.5483],
[0.6270, 0.4266, 0.7150, 0.3317, 0.4900, 0.1817, 0.5560, 0.6183],
[0.0000, 0.0000, 0.7850, 0.2700, 0.4288, 0.1717, 0.5199, 0.4999],
[0.6269, 0.4073, 0.8900, 0.4933, 0.3625, 0.4183, 0.6288, 0.5150],
[0.6321, 0.4048, 0.8737, 0.5617, 0.3875, 0.4417, 0.6361, 0.4927],
[0.6273, 0.4143, 0.8750, 0.5700, 0.3988, 0.4717, 0.6012, 0.5467],
[0.6357, 0.4097, 0.9038, 0.3883, 0.4212, 0.2950, 0.6686, 0.5390]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0022, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0022, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.11752213741419837
step: 74
running loss: 0.0015881369920837617
Train Steps: 74/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6102, 0.4020, 0.8638, 0.3717, 0.3625, 0.5017, 0.6038, 0.5500],
[0.6097, 0.3988, 0.8650, 0.5250, 0.4213, 0.5200, 0.5675, 0.5050],
[0.6212, 0.4159, 0.8675, 0.5783, 0.4088, 0.4317, 0.5613, 0.5917],
[0.6152, 0.4131, 0.6863, 0.2567, 0.3625, 0.3300, 0.5765, 0.5305],
[0.6267, 0.4065, 0.8313, 0.2467, 0.4788, 0.1733, 0.6312, 0.5133],
[0.6317, 0.4038, 0.8287, 0.5900, 0.3800, 0.4717, 0.6295, 0.4986],
[0.6273, 0.4100, 0.7137, 0.2133, 0.4000, 0.2650, 0.6075, 0.5633],
[0.6115, 0.4081, 0.6725, 0.2433, 0.4088, 0.1933, 0.5167, 0.5544]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6591, 0.4333, 0.8948, 0.4122, 0.3788, 0.4922, 0.6208, 0.5571],
[0.6427, 0.4237, 0.9069, 0.5538, 0.4507, 0.5241, 0.5406, 0.5316],
[0.6362, 0.4339, 0.8928, 0.5974, 0.4273, 0.4166, 0.5866, 0.6091],
[0.6376, 0.4100, 0.7270, 0.2893, 0.3867, 0.3177, 0.5819, 0.5739],
[0.6525, 0.4261, 0.8762, 0.2520, 0.5085, 0.1691, 0.6501, 0.5437],
[0.6357, 0.4092, 0.8949, 0.6106, 0.3867, 0.4622, 0.6421, 0.5256],
[0.6220, 0.4065, 0.7542, 0.2496, 0.4231, 0.2386, 0.6143, 0.5739],
[0.6334, 0.4142, 0.7204, 0.2827, 0.4284, 0.2035, 0.5362, 0.5713]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6102, 0.4020, 0.8637, 0.3717, 0.3625, 0.5017, 0.6037, 0.5500],
[0.6097, 0.3988, 0.8650, 0.5250, 0.4212, 0.5200, 0.5675, 0.5050],
[0.6212, 0.4159, 0.8675, 0.5783, 0.4087, 0.4317, 0.5612, 0.5917],
[0.6152, 0.4131, 0.6862, 0.2567, 0.3625, 0.3300, 0.5765, 0.5305],
[0.6266, 0.4065, 0.8313, 0.2467, 0.4787, 0.1733, 0.6313, 0.5133],
[0.6317, 0.4038, 0.8288, 0.5900, 0.3800, 0.4717, 0.6295, 0.4986],
[0.6273, 0.4099, 0.7138, 0.2133, 0.4000, 0.2650, 0.6075, 0.5633],
[0.6115, 0.4081, 0.6725, 0.2433, 0.4087, 0.1933, 0.5167, 0.5544]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.11819850071333349
step: 75
running loss: 0.001575980009511113
Train Steps: 75/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6200, 0.3978, 0.8900, 0.4550, 0.3775, 0.5200, 0.6150, 0.5367],
[0.6201, 0.4036, 0.8596, 0.3850, 0.3492, 0.3785, 0.5978, 0.5131],
[0.6201, 0.3970, 0.8413, 0.4950, 0.4413, 0.5183, 0.6088, 0.5400],
[0.6175, 0.4091, 0.7863, 0.2800, 0.3638, 0.3583, 0.6188, 0.5433],
[0.6279, 0.4050, 0.8025, 0.2200, 0.4313, 0.2733, 0.6820, 0.5320],
[0.6249, 0.4142, 0.8350, 0.3283, 0.3613, 0.3700, 0.6188, 0.5400],
[0.6203, 0.4056, 0.8942, 0.4086, 0.3643, 0.3617, 0.5917, 0.5482],
[0.6219, 0.4089, 0.8938, 0.4800, 0.3825, 0.4450, 0.5850, 0.5200]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6172, 0.3995, 0.8901, 0.5058, 0.3956, 0.4915, 0.6131, 0.5523],
[0.6882, 0.4489, 0.8780, 0.4083, 0.3668, 0.3666, 0.5890, 0.5351],
[0.5328, 0.3744, 0.8810, 0.5341, 0.4609, 0.4898, 0.5960, 0.5529],
[0.7211, 0.4788, 0.8036, 0.3136, 0.3870, 0.3325, 0.6272, 0.5799],
[0.6880, 0.4580, 0.8173, 0.2626, 0.4443, 0.2419, 0.6816, 0.5460],
[0.6753, 0.4548, 0.8753, 0.3632, 0.3737, 0.2981, 0.6539, 0.5604],
[0.6129, 0.3984, 0.9226, 0.4563, 0.3824, 0.3320, 0.6079, 0.5717],
[0.6587, 0.4387, 0.9108, 0.5261, 0.4108, 0.4428, 0.5994, 0.5486]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6199, 0.3978, 0.8900, 0.4550, 0.3775, 0.5200, 0.6150, 0.5367],
[0.6201, 0.4036, 0.8596, 0.3850, 0.3492, 0.3785, 0.5978, 0.5131],
[0.6201, 0.3970, 0.8413, 0.4950, 0.4412, 0.5183, 0.6087, 0.5400],
[0.6175, 0.4091, 0.7862, 0.2800, 0.3638, 0.3583, 0.6187, 0.5433],
[0.6279, 0.4050, 0.8025, 0.2200, 0.4313, 0.2733, 0.6820, 0.5320],
[0.6249, 0.4142, 0.8350, 0.3283, 0.3613, 0.3700, 0.6187, 0.5400],
[0.6203, 0.4056, 0.8942, 0.4086, 0.3643, 0.3617, 0.5917, 0.5482],
[0.6219, 0.4089, 0.8938, 0.4800, 0.3825, 0.4450, 0.5850, 0.5200]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.11945557687431574
step: 76
running loss: 0.0015717839062409965
Train Steps: 76/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6182, 0.3967, 0.8263, 0.3065, 0.3526, 0.4161, 0.6192, 0.5290],
[0.6197, 0.4118, 0.8688, 0.5517, 0.4037, 0.5233, 0.5875, 0.5600],
[0.6111, 0.4033, 0.8300, 0.3267, 0.3588, 0.3333, 0.5444, 0.5637],
[0.6189, 0.4033, 0.8650, 0.5267, 0.4487, 0.5150, 0.5925, 0.5050],
[0.6200, 0.4112, 0.8862, 0.4100, 0.3638, 0.4917, 0.6088, 0.6050],
[0.6113, 0.4104, 0.8650, 0.4250, 0.3925, 0.5967, 0.5787, 0.5116],
[0.6265, 0.4088, 0.8025, 0.1850, 0.4163, 0.2500, 0.6290, 0.4947],
[0.6200, 0.4098, 0.8237, 0.2917, 0.4012, 0.2967, 0.6000, 0.5683]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6638, 0.4265, 0.8378, 0.3199, 0.3502, 0.3498, 0.6437, 0.5390],
[0.6458, 0.4382, 0.8623, 0.5751, 0.4099, 0.4719, 0.6228, 0.5623],
[0.6353, 0.4273, 0.8509, 0.3646, 0.3605, 0.2750, 0.5698, 0.5699],
[0.6264, 0.4253, 0.8758, 0.5270, 0.4639, 0.4688, 0.6128, 0.5361],
[0.6012, 0.4146, 0.8752, 0.4587, 0.3832, 0.4310, 0.6454, 0.6015],
[0.6165, 0.4263, 0.8658, 0.4376, 0.4099, 0.5349, 0.6132, 0.5368],
[0.6423, 0.4167, 0.8071, 0.2262, 0.4394, 0.1830, 0.6501, 0.5213],
[0.6808, 0.4402, 0.8347, 0.3076, 0.4046, 0.2507, 0.6324, 0.5565]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6182, 0.3967, 0.8263, 0.3065, 0.3526, 0.4161, 0.6192, 0.5290],
[0.6197, 0.4118, 0.8687, 0.5517, 0.4038, 0.5233, 0.5875, 0.5600],
[0.6111, 0.4033, 0.8300, 0.3267, 0.3587, 0.3333, 0.5444, 0.5637],
[0.6189, 0.4033, 0.8650, 0.5267, 0.4487, 0.5150, 0.5925, 0.5050],
[0.6200, 0.4112, 0.8863, 0.4100, 0.3638, 0.4917, 0.6087, 0.6050],
[0.6113, 0.4104, 0.8650, 0.4250, 0.3925, 0.5967, 0.5787, 0.5116],
[0.6265, 0.4088, 0.8025, 0.1850, 0.4162, 0.2500, 0.6290, 0.4947],
[0.6200, 0.4098, 0.8238, 0.2917, 0.4013, 0.2967, 0.6000, 0.5683]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.12034609029069543
step: 77
running loss: 0.001562936237541499
Train Steps: 77/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6259, 0.4156, 0.8812, 0.3183, 0.4775, 0.1867, 0.6219, 0.4960],
[0.6185, 0.4067, 0.8838, 0.4450, 0.4037, 0.4733, 0.5213, 0.5142],
[0.6276, 0.4002, 0.8800, 0.5533, 0.3575, 0.4400, 0.6132, 0.4672],
[ nan, nan, 0.8300, 0.3150, 0.3588, 0.3383, 0.5208, 0.5194],
[0.6161, 0.4055, 0.8675, 0.3867, 0.3713, 0.4033, 0.5195, 0.5162],
[0.6160, 0.4086, 0.8775, 0.3983, 0.3750, 0.3783, 0.5128, 0.4882],
[0.6112, 0.4029, 0.8638, 0.4800, 0.4875, 0.5083, 0.5763, 0.5567],
[0.6226, 0.4125, 0.8800, 0.4900, 0.4512, 0.5600, 0.6275, 0.5517]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6829, 0.4321, 0.8792, 0.2930, 0.4530, 0.1758, 0.6499, 0.5164],
[0.6334, 0.4151, 0.8681, 0.4462, 0.3797, 0.4307, 0.5416, 0.5134],
[0.7628, 0.4811, 0.8505, 0.5250, 0.3577, 0.4349, 0.6527, 0.5248],
[0.2527, 0.1632, 0.8017, 0.3036, 0.3434, 0.2813, 0.5369, 0.5235],
[0.5974, 0.3909, 0.8661, 0.3871, 0.3583, 0.3448, 0.5662, 0.5360],
[0.6522, 0.4458, 0.8638, 0.3950, 0.3395, 0.3446, 0.5653, 0.5265],
[0.6673, 0.4463, 0.8625, 0.4778, 0.4617, 0.4634, 0.6032, 0.5708],
[0.6972, 0.4597, 0.8791, 0.4854, 0.4432, 0.5452, 0.6703, 0.5676]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6259, 0.4156, 0.8813, 0.3183, 0.4775, 0.1867, 0.6219, 0.4960],
[0.6185, 0.4067, 0.8838, 0.4450, 0.4038, 0.4733, 0.5213, 0.5142],
[0.6276, 0.4002, 0.8800, 0.5533, 0.3575, 0.4400, 0.6132, 0.4672],
[0.0000, 0.0000, 0.8300, 0.3150, 0.3587, 0.3383, 0.5208, 0.5194],
[0.6161, 0.4055, 0.8675, 0.3867, 0.3713, 0.4033, 0.5195, 0.5162],
[0.6160, 0.4086, 0.8775, 0.3983, 0.3750, 0.3783, 0.5128, 0.4882],
[0.6112, 0.4029, 0.8637, 0.4800, 0.4875, 0.5083, 0.5763, 0.5567],
[0.6226, 0.4125, 0.8800, 0.4900, 0.4512, 0.5600, 0.6275, 0.5517]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0027, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0027, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.12301964685320854
step: 78
running loss: 0.0015771749596565198
Train Steps: 78/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6264, 0.4069, 0.7900, 0.1650, 0.4275, 0.2267, 0.6290, 0.4947],
[0.6128, 0.4022, 0.8738, 0.5067, 0.4983, 0.5231, 0.5364, 0.5064],
[0.6257, 0.4024, 0.8672, 0.5422, 0.4196, 0.5198, 0.6694, 0.5204],
[0.6124, 0.4069, 0.8314, 0.5001, 0.3738, 0.4650, 0.5167, 0.5402],
[0.6132, 0.4037, 0.6963, 0.2217, 0.4100, 0.1950, 0.5395, 0.5175],
[0.6250, 0.3993, 0.9138, 0.4333, 0.3763, 0.5217, 0.6995, 0.5320],
[ nan, nan, 0.6688, 0.2513, 0.4113, 0.2117, 0.5193, 0.5933],
[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6981, 0.4461, 0.7920, 0.1761, 0.4232, 0.2350, 0.6595, 0.5030],
[0.6089, 0.4098, 0.8837, 0.4997, 0.4948, 0.5058, 0.5205, 0.5163],
[0.6776, 0.4383, 0.8625, 0.5327, 0.4152, 0.5352, 0.6680, 0.5216],
[0.6112, 0.3980, 0.8476, 0.4931, 0.3843, 0.4628, 0.5391, 0.5513],
[0.5809, 0.3944, 0.7159, 0.2180, 0.3969, 0.1966, 0.5366, 0.4958],
[0.7036, 0.4519, 0.9253, 0.4453, 0.3807, 0.5351, 0.7349, 0.5451],
[0.0905, 0.0750, 0.6754, 0.2421, 0.3957, 0.2056, 0.5225, 0.5518],
[0.6353, 0.4183, 0.8821, 0.5299, 0.3436, 0.3670, 0.5775, 0.5352]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6264, 0.4069, 0.7900, 0.1650, 0.4275, 0.2267, 0.6290, 0.4947],
[0.6128, 0.4022, 0.8737, 0.5067, 0.4983, 0.5231, 0.5364, 0.5064],
[0.6257, 0.4024, 0.8672, 0.5422, 0.4196, 0.5198, 0.6694, 0.5204],
[0.6123, 0.4069, 0.8314, 0.5001, 0.3738, 0.4650, 0.5167, 0.5402],
[0.6132, 0.4037, 0.6963, 0.2217, 0.4100, 0.1950, 0.5395, 0.5175],
[0.6250, 0.3993, 0.9137, 0.4333, 0.3762, 0.5217, 0.6995, 0.5320],
[0.0000, 0.0000, 0.6688, 0.2513, 0.4112, 0.2117, 0.5193, 0.5933],
[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.12372523982776329
step: 79
running loss: 0.0015661422763008012
Train Steps: 79/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6250, 0.4106, 0.8700, 0.3717, 0.3588, 0.4967, 0.6038, 0.5167],
[0.6180, 0.4064, 0.7200, 0.2467, 0.4275, 0.2367, 0.5963, 0.6217],
[0.6300, 0.4102, 0.9088, 0.4433, 0.4088, 0.3067, 0.6820, 0.5540],
[0.6300, 0.4013, 0.8938, 0.5350, 0.3675, 0.4600, 0.6456, 0.4973],
[0.6346, 0.4086, 0.7938, 0.5500, 0.3962, 0.4867, 0.7343, 0.5702],
[0.6274, 0.4117, 0.8100, 0.5801, 0.4000, 0.4583, 0.5582, 0.6118],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3513, 0.4050, 0.6112, 0.5500],
[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6288, 0.4135, 0.8620, 0.3507, 0.3612, 0.5392, 0.5979, 0.4968],
[0.5228, 0.3384, 0.7171, 0.2279, 0.4291, 0.2401, 0.5491, 0.5494],
[0.5521, 0.3427, 0.9261, 0.4161, 0.4091, 0.3444, 0.6386, 0.4978],
[0.5937, 0.3695, 0.8879, 0.5150, 0.3578, 0.4873, 0.5942, 0.4688],
[0.6119, 0.3992, 0.8160, 0.5159, 0.3865, 0.5166, 0.6645, 0.5292],
[0.5653, 0.3847, 0.8176, 0.5684, 0.3951, 0.4822, 0.5524, 0.5696],
[0.5591, 0.3564, 0.7779, 0.2521, 0.3498, 0.4319, 0.5708, 0.5020],
[0.5886, 0.3754, 0.8601, 0.2555, 0.4770, 0.2343, 0.6406, 0.5053]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6250, 0.4105, 0.8700, 0.3717, 0.3587, 0.4967, 0.6037, 0.5167],
[0.6180, 0.4064, 0.7200, 0.2467, 0.4275, 0.2367, 0.5962, 0.6217],
[0.6300, 0.4102, 0.9087, 0.4433, 0.4087, 0.3067, 0.6820, 0.5540],
[0.6300, 0.4013, 0.8938, 0.5350, 0.3675, 0.4600, 0.6456, 0.4973],
[0.6346, 0.4086, 0.7937, 0.5500, 0.3963, 0.4867, 0.7343, 0.5702],
[0.6274, 0.4117, 0.8100, 0.5801, 0.4000, 0.4583, 0.5582, 0.6118],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3512, 0.4050, 0.6112, 0.5500],
[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.12507811159593984
step: 80
running loss: 0.001563476394949248
Train Steps: 80/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6277, 0.4103, 0.8087, 0.5717, 0.4188, 0.4750, 0.5663, 0.6083],
[0.6227, 0.4083, 0.8938, 0.4800, 0.3800, 0.2950, 0.5737, 0.5350],
[0.6218, 0.4185, 0.7338, 0.2650, 0.4625, 0.1950, 0.5687, 0.5800],
[0.6085, 0.4008, 0.8588, 0.5200, 0.4959, 0.4977, 0.5175, 0.5283],
[0.6198, 0.4101, 0.8838, 0.5283, 0.3763, 0.5267, 0.5913, 0.5567],
[0.6205, 0.4004, 0.8938, 0.4883, 0.3663, 0.5000, 0.6357, 0.4947],
[0.6203, 0.4072, 0.8892, 0.3523, 0.3783, 0.3017, 0.5898, 0.5478],
[0.6205, 0.4012, 0.8675, 0.3283, 0.3713, 0.3050, 0.5813, 0.5117]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6061, 0.3938, 0.8173, 0.5448, 0.4088, 0.4903, 0.6078, 0.5864],
[0.6013, 0.3893, 0.8713, 0.4460, 0.3765, 0.3447, 0.5802, 0.5218],
[0.5587, 0.3764, 0.7229, 0.2238, 0.4488, 0.2153, 0.5614, 0.5439],
[0.5299, 0.3311, 0.8490, 0.4794, 0.4807, 0.5188, 0.5202, 0.4970],
[0.5694, 0.3743, 0.8593, 0.5075, 0.3752, 0.5695, 0.5847, 0.5236],
[0.5815, 0.3632, 0.8861, 0.4526, 0.3648, 0.5317, 0.6349, 0.4731],
[0.5626, 0.3566, 0.8745, 0.3104, 0.3800, 0.3518, 0.5987, 0.5117],
[0.5221, 0.3276, 0.8707, 0.3038, 0.3811, 0.3485, 0.5562, 0.4916]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6277, 0.4103, 0.8087, 0.5717, 0.4187, 0.4750, 0.5663, 0.6083],
[0.6227, 0.4083, 0.8938, 0.4800, 0.3800, 0.2950, 0.5738, 0.5350],
[0.6218, 0.4185, 0.7337, 0.2650, 0.4625, 0.1950, 0.5688, 0.5800],
[0.6084, 0.4008, 0.8587, 0.5200, 0.4959, 0.4977, 0.5175, 0.5283],
[0.6198, 0.4101, 0.8838, 0.5283, 0.3762, 0.5267, 0.5913, 0.5567],
[0.6205, 0.4004, 0.8938, 0.4883, 0.3663, 0.5000, 0.6357, 0.4947],
[0.6203, 0.4072, 0.8892, 0.3523, 0.3783, 0.3017, 0.5898, 0.5478],
[0.6205, 0.4012, 0.8675, 0.3283, 0.3713, 0.3050, 0.5813, 0.5117]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.12628521776059642
step: 81
running loss: 0.001559076762476499
Train Steps: 81/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6109, 0.4041, 0.6975, 0.3167, 0.3513, 0.3383, 0.5153, 0.5319],
[0.6083, 0.3957, 0.8638, 0.4950, 0.4363, 0.5083, 0.5346, 0.4980],
[0.6136, 0.3955, 0.8400, 0.3267, 0.3500, 0.4200, 0.5863, 0.5467],
[0.6201, 0.4029, 0.8776, 0.4602, 0.3683, 0.4203, 0.5938, 0.5450],
[0.6132, 0.4118, 0.8200, 0.3633, 0.3563, 0.5400, 0.5787, 0.5136],
[0.6225, 0.4191, 0.8500, 0.4167, 0.3688, 0.3233, 0.5650, 0.5650],
[0.6164, 0.3956, 0.8757, 0.5088, 0.4300, 0.5320, 0.6022, 0.5202],
[0.6329, 0.4175, 0.8550, 0.2333, 0.5425, 0.2250, 0.7398, 0.5609]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5418, 0.3460, 0.7083, 0.3052, 0.3531, 0.3603, 0.5018, 0.5154],
[0.5441, 0.3577, 0.8451, 0.4836, 0.4316, 0.5414, 0.5323, 0.4998],
[0.5531, 0.3617, 0.8243, 0.3293, 0.3425, 0.4509, 0.5539, 0.5333],
[0.5925, 0.3804, 0.8683, 0.4660, 0.3918, 0.4476, 0.5878, 0.5417],
[0.6002, 0.4011, 0.8016, 0.3649, 0.3546, 0.5386, 0.5675, 0.5146],
[0.5849, 0.4086, 0.8510, 0.4163, 0.3650, 0.3590, 0.5596, 0.5523],
[0.5821, 0.3788, 0.8625, 0.5083, 0.4160, 0.5501, 0.5990, 0.5181],
[0.4306, 0.2809, 0.8359, 0.2389, 0.5374, 0.2232, 0.7439, 0.5276]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6109, 0.4041, 0.6975, 0.3167, 0.3512, 0.3383, 0.5153, 0.5319],
[0.6083, 0.3957, 0.8637, 0.4950, 0.4363, 0.5083, 0.5346, 0.4980],
[0.6136, 0.3955, 0.8400, 0.3267, 0.3500, 0.4200, 0.5863, 0.5467],
[0.6201, 0.4029, 0.8776, 0.4602, 0.3683, 0.4203, 0.5938, 0.5450],
[0.6132, 0.4118, 0.8200, 0.3633, 0.3562, 0.5400, 0.5787, 0.5136],
[0.6225, 0.4191, 0.8500, 0.4167, 0.3688, 0.3233, 0.5650, 0.5650],
[0.6164, 0.3956, 0.8757, 0.5088, 0.4300, 0.5320, 0.6022, 0.5202],
[0.6329, 0.4175, 0.8550, 0.2333, 0.5425, 0.2250, 0.7398, 0.5609]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.12774768978124484
step: 82
running loss: 0.0015578986558688395
Train Steps: 82/90 Loss: 0.0016 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.6197, 0.3930, 0.8793, 0.4736, 0.4152, 0.5464, 0.6308, 0.5235],
[0.6197, 0.3986, 0.8800, 0.4617, 0.4188, 0.4783, 0.5687, 0.5550],
[0.6222, 0.3957, 0.8838, 0.5017, 0.3937, 0.4600, 0.5900, 0.5017],
[ nan, nan, 0.7553, 0.2722, 0.3875, 0.2550, 0.5125, 0.5633],
[0.6219, 0.3934, 0.8688, 0.5267, 0.4313, 0.4967, 0.5988, 0.4983],
[0.6277, 0.4118, 0.8988, 0.3833, 0.3950, 0.2650, 0.6290, 0.4938],
[0.6198, 0.4075, 0.8650, 0.5617, 0.4150, 0.4367, 0.5450, 0.5650]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6675, 0.4397, 0.8381, 0.5552, 0.3738, 0.5097, 0.6472, 0.5416],
[ 0.5951, 0.3972, 0.8532, 0.4696, 0.4206, 0.5650, 0.6118, 0.5556],
[ 0.6322, 0.4160, 0.8588, 0.4564, 0.4137, 0.5005, 0.5463, 0.5500],
[ 0.6032, 0.3870, 0.8658, 0.4831, 0.3925, 0.4840, 0.5734, 0.5137],
[-0.0529, -0.0354, 0.7400, 0.2637, 0.3871, 0.2772, 0.4593, 0.5618],
[ 0.6284, 0.4051, 0.8570, 0.5077, 0.4325, 0.5167, 0.5824, 0.5051],
[ 0.6477, 0.4342, 0.8797, 0.3638, 0.3833, 0.2962, 0.6136, 0.5325],
[ 0.6533, 0.4331, 0.8344, 0.5550, 0.4074, 0.4584, 0.5385, 0.5828]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.6197, 0.3930, 0.8793, 0.4736, 0.4152, 0.5464, 0.6308, 0.5235],
[0.6197, 0.3986, 0.8800, 0.4617, 0.4187, 0.4783, 0.5688, 0.5550],
[0.6222, 0.3957, 0.8838, 0.5017, 0.3938, 0.4600, 0.5900, 0.5017],
[0.0000, 0.0000, 0.7553, 0.2722, 0.3875, 0.2550, 0.5125, 0.5633],
[0.6219, 0.3934, 0.8687, 0.5267, 0.4313, 0.4967, 0.5987, 0.4983],
[0.6277, 0.4117, 0.8988, 0.3833, 0.3950, 0.2650, 0.6290, 0.4938],
[0.6198, 0.4075, 0.8650, 0.5617, 0.4150, 0.4367, 0.5450, 0.5650]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.1281739636324346
step: 83
running loss: 0.0015442646220775254
Train Steps: 83/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6264, 0.4067, 0.9050, 0.4183, 0.3775, 0.4600, 0.6308, 0.4862],
[0.6164, 0.4119, 0.7913, 0.2650, 0.3538, 0.3500, 0.5614, 0.5038],
[0.6127, 0.4118, 0.8650, 0.5083, 0.4088, 0.5367, 0.5300, 0.5456],
[0.6231, 0.3973, 0.8650, 0.3950, 0.3625, 0.3183, 0.5837, 0.5167],
[0.6277, 0.4083, 0.8350, 0.2717, 0.4562, 0.1800, 0.5918, 0.4878],
[0.6199, 0.4065, 0.7598, 0.2385, 0.4317, 0.1981, 0.5933, 0.5221],
[0.6186, 0.4060, 0.8750, 0.5050, 0.3538, 0.4367, 0.5813, 0.6083],
[0.6279, 0.4008, 0.8600, 0.4883, 0.4325, 0.5283, 0.7010, 0.5378]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6597, 0.4264, 0.8902, 0.4278, 0.3658, 0.4644, 0.6411, 0.5222],
[0.5860, 0.3856, 0.7773, 0.2711, 0.3504, 0.3750, 0.5729, 0.5375],
[0.5656, 0.3925, 0.8694, 0.5230, 0.4260, 0.5606, 0.5162, 0.5660],
[0.6103, 0.3844, 0.8472, 0.4252, 0.3782, 0.3238, 0.5537, 0.5528],
[0.5067, 0.3293, 0.8092, 0.2659, 0.4708, 0.2124, 0.5685, 0.5118],
[0.5839, 0.3781, 0.7251, 0.2463, 0.4241, 0.2149, 0.5706, 0.5286],
[0.5335, 0.3611, 0.8560, 0.5066, 0.3550, 0.4511, 0.5697, 0.6224],
[0.5556, 0.3549, 0.8647, 0.5021, 0.4329, 0.5528, 0.6810, 0.5749]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6264, 0.4067, 0.9050, 0.4183, 0.3775, 0.4600, 0.6308, 0.4862],
[0.6164, 0.4119, 0.7912, 0.2650, 0.3537, 0.3500, 0.5614, 0.5038],
[0.6127, 0.4118, 0.8650, 0.5083, 0.4087, 0.5367, 0.5300, 0.5456],
[0.6231, 0.3973, 0.8650, 0.3950, 0.3625, 0.3183, 0.5838, 0.5167],
[0.6277, 0.4083, 0.8350, 0.2717, 0.4563, 0.1800, 0.5918, 0.4878],
[0.6199, 0.4065, 0.7598, 0.2385, 0.4317, 0.1981, 0.5933, 0.5221],
[0.6186, 0.4060, 0.8750, 0.5050, 0.3537, 0.4367, 0.5813, 0.6083],
[0.6279, 0.4008, 0.8600, 0.4883, 0.4325, 0.5283, 0.7010, 0.5378]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.12917014537379146
step: 84
running loss: 0.0015377398258784698
Train Steps: 84/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6250, 0.4054, 0.8770, 0.4723, 0.4662, 0.5367, 0.6162, 0.5433],
[0.6059, 0.4002, 0.7562, 0.2767, 0.3538, 0.3033, 0.5529, 0.5455],
[0.6145, 0.4007, 0.8775, 0.4533, 0.4562, 0.5533, 0.6088, 0.5533],
[0.6165, 0.4106, 0.7575, 0.1733, 0.3838, 0.2650, 0.5680, 0.5116],
[0.6250, 0.4013, 0.8525, 0.5417, 0.4037, 0.5117, 0.6325, 0.5017],
[0.6172, 0.4055, 0.8175, 0.2650, 0.3550, 0.3683, 0.5787, 0.5550],
[0.6202, 0.4053, 0.8638, 0.5283, 0.4546, 0.5108, 0.5900, 0.5133],
[0.6200, 0.4086, 0.8414, 0.2974, 0.4117, 0.2274, 0.5869, 0.5391]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6153, 0.4149, 0.8889, 0.4847, 0.4558, 0.5046, 0.6244, 0.5498],
[0.5586, 0.3738, 0.7486, 0.2882, 0.3541, 0.2953, 0.5606, 0.5527],
[0.6257, 0.4160, 0.8654, 0.4678, 0.4573, 0.5368, 0.5980, 0.5739],
[0.5703, 0.3918, 0.7460, 0.1940, 0.3798, 0.2339, 0.5797, 0.5188],
[0.5688, 0.3682, 0.8581, 0.5712, 0.4034, 0.4855, 0.6434, 0.5377],
[0.6166, 0.4107, 0.8232, 0.3031, 0.3427, 0.3449, 0.5720, 0.5591],
[0.6142, 0.3968, 0.8740, 0.5402, 0.4438, 0.4831, 0.6002, 0.5364],
[0.5238, 0.3544, 0.8481, 0.3092, 0.4216, 0.2158, 0.5670, 0.5483]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6250, 0.4054, 0.8770, 0.4723, 0.4663, 0.5367, 0.6162, 0.5433],
[0.6059, 0.4002, 0.7563, 0.2767, 0.3537, 0.3033, 0.5529, 0.5455],
[0.6145, 0.4007, 0.8775, 0.4533, 0.4563, 0.5533, 0.6087, 0.5533],
[0.6165, 0.4106, 0.7575, 0.1733, 0.3837, 0.2650, 0.5680, 0.5116],
[0.6250, 0.4013, 0.8525, 0.5417, 0.4038, 0.5117, 0.6325, 0.5017],
[0.6172, 0.4055, 0.8175, 0.2650, 0.3550, 0.3683, 0.5788, 0.5550],
[0.6202, 0.4053, 0.8637, 0.5283, 0.4546, 0.5108, 0.5900, 0.5133],
[0.6199, 0.4086, 0.8414, 0.2974, 0.4117, 0.2274, 0.5869, 0.5391]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.12972077063750476
step: 85
running loss: 0.001526126713382409
Train Steps: 85/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6204, 0.4013, 0.8075, 0.2400, 0.4313, 0.2050, 0.5800, 0.5150],
[ nan, nan, 0.8463, 0.2550, 0.5850, 0.2133, 0.7129, 0.6072],
[0.6269, 0.4073, 0.8900, 0.4933, 0.3625, 0.4183, 0.6288, 0.5150],
[0.6250, 0.4236, 0.8638, 0.3767, 0.4050, 0.3150, 0.5649, 0.5799],
[0.6038, 0.3946, 0.8413, 0.4883, 0.3563, 0.4550, 0.5266, 0.4693],
[0.6161, 0.4055, 0.8675, 0.3867, 0.3713, 0.4033, 0.5195, 0.5162],
[0.6169, 0.4108, 0.6821, 0.2722, 0.3825, 0.2550, 0.5550, 0.5717],
[0.6199, 0.4102, 0.8950, 0.4417, 0.4012, 0.5367, 0.6112, 0.5967]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6324, 0.4024, 0.7867, 0.2706, 0.4302, 0.1842, 0.5873, 0.5167],
[0.1120, 0.0905, 0.8614, 0.2757, 0.5323, 0.2532, 0.7227, 0.5899],
[0.6636, 0.4510, 0.8866, 0.5082, 0.3449, 0.4067, 0.6281, 0.5082],
[0.6678, 0.4606, 0.8678, 0.3985, 0.3912, 0.2996, 0.5728, 0.5700],
[0.6000, 0.4066, 0.8471, 0.5015, 0.3561, 0.4322, 0.5428, 0.5055],
[0.6050, 0.4145, 0.8732, 0.3977, 0.3691, 0.3673, 0.5318, 0.5119],
[0.5998, 0.4105, 0.6665, 0.2674, 0.3806, 0.2248, 0.5654, 0.5679],
[0.6570, 0.4326, 0.8951, 0.4556, 0.3951, 0.5170, 0.6160, 0.5746]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6204, 0.4013, 0.8075, 0.2400, 0.4313, 0.2050, 0.5800, 0.5150],
[0.0000, 0.0000, 0.8462, 0.2550, 0.5850, 0.2133, 0.7129, 0.6072],
[0.6269, 0.4073, 0.8900, 0.4933, 0.3625, 0.4183, 0.6288, 0.5150],
[0.6250, 0.4236, 0.8637, 0.3767, 0.4050, 0.3150, 0.5649, 0.5799],
[0.6038, 0.3946, 0.8413, 0.4883, 0.3562, 0.4550, 0.5266, 0.4693],
[0.6161, 0.4055, 0.8675, 0.3867, 0.3713, 0.4033, 0.5195, 0.5162],
[0.6169, 0.4108, 0.6821, 0.2722, 0.3825, 0.2550, 0.5550, 0.5717],
[0.6199, 0.4102, 0.8950, 0.4417, 0.4013, 0.5367, 0.6112, 0.5967]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.13042904192116112
step: 86
running loss: 0.0015166167665251293
Train Steps: 86/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6199, 0.4093, 0.7913, 0.2533, 0.4288, 0.2467, 0.5975, 0.5700],
[0.6332, 0.4165, 0.9100, 0.3350, 0.4188, 0.3683, 0.7438, 0.5528],
[0.6216, 0.4099, 0.7225, 0.2033, 0.4188, 0.2217, 0.5975, 0.5283],
[0.6307, 0.4029, 0.8988, 0.4817, 0.3937, 0.3500, 0.7311, 0.5378],
[0.6107, 0.4050, 0.8700, 0.4850, 0.4470, 0.4848, 0.5043, 0.5431],
[0.6200, 0.3993, 0.8519, 0.4923, 0.3962, 0.4717, 0.6013, 0.5433],
[0.6314, 0.4050, 0.8227, 0.5431, 0.4150, 0.5517, 0.7121, 0.5690],
[0.6060, 0.3924, 0.8450, 0.5717, 0.4200, 0.5217, 0.5253, 0.4752]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5883, 0.3915, 0.8001, 0.2407, 0.4200, 0.2433, 0.5929, 0.5700],
[0.6419, 0.4123, 0.9253, 0.3650, 0.4035, 0.3305, 0.7279, 0.5396],
[0.6671, 0.4461, 0.7152, 0.1981, 0.4120, 0.1980, 0.5596, 0.5310],
[0.6116, 0.4015, 0.9169, 0.4768, 0.3858, 0.3125, 0.7088, 0.5173],
[0.6014, 0.3990, 0.8853, 0.4906, 0.4388, 0.4627, 0.5007, 0.5111],
[0.5797, 0.3709, 0.8777, 0.5019, 0.3913, 0.4391, 0.5890, 0.5408],
[0.6075, 0.3936, 0.8572, 0.5368, 0.3973, 0.5263, 0.7019, 0.5504],
[0.6125, 0.3837, 0.8629, 0.5984, 0.4356, 0.4845, 0.5144, 0.4990]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6198, 0.4093, 0.7912, 0.2533, 0.4288, 0.2467, 0.5975, 0.5700],
[0.6332, 0.4165, 0.9100, 0.3350, 0.4187, 0.3683, 0.7438, 0.5528],
[0.6216, 0.4099, 0.7225, 0.2033, 0.4187, 0.2217, 0.5975, 0.5283],
[0.6307, 0.4029, 0.8988, 0.4817, 0.3938, 0.3500, 0.7311, 0.5378],
[0.6107, 0.4050, 0.8700, 0.4850, 0.4470, 0.4848, 0.5043, 0.5431],
[0.6200, 0.3993, 0.8519, 0.4923, 0.3963, 0.4717, 0.6012, 0.5433],
[0.6314, 0.4050, 0.8227, 0.5431, 0.4150, 0.5517, 0.7121, 0.5690],
[0.6060, 0.3924, 0.8450, 0.5717, 0.4200, 0.5217, 0.5253, 0.4752]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.13084795890608802
step: 87
running loss: 0.0015039995276561842
Train Steps: 87/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6218, 0.4098, 0.7238, 0.1850, 0.4238, 0.2517, 0.6288, 0.5350],
[0.6135, 0.3994, 0.7913, 0.3050, 0.3625, 0.3050, 0.5837, 0.5050],
[0.6284, 0.4093, 0.8900, 0.4700, 0.3650, 0.3850, 0.6212, 0.5167],
[0.6329, 0.4175, 0.8550, 0.2333, 0.5425, 0.2250, 0.7398, 0.5609],
[0.6064, 0.3953, 0.8738, 0.4417, 0.3663, 0.4683, 0.5511, 0.5416],
[0.6202, 0.4053, 0.8638, 0.5283, 0.4546, 0.5108, 0.5900, 0.5133],
[0.6203, 0.4076, 0.8611, 0.2878, 0.4050, 0.2554, 0.5907, 0.5496],
[0.6276, 0.4235, 0.8888, 0.5333, 0.3800, 0.3117, 0.5427, 0.6164]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6102, 0.4038, 0.7431, 0.1998, 0.4382, 0.2402, 0.6259, 0.5483],
[0.6186, 0.3994, 0.7977, 0.3072, 0.3726, 0.3181, 0.5868, 0.5125],
[0.5738, 0.3796, 0.9057, 0.4642, 0.3647, 0.3801, 0.6272, 0.5086],
[0.6229, 0.4183, 0.8687, 0.2433, 0.5416, 0.2083, 0.7472, 0.5412],
[0.5756, 0.3719, 0.8908, 0.4649, 0.3554, 0.4701, 0.5623, 0.5266],
[0.6130, 0.3902, 0.8879, 0.5309, 0.4536, 0.5069, 0.5984, 0.5160],
[0.6295, 0.4091, 0.8896, 0.2798, 0.4066, 0.2617, 0.6012, 0.5375],
[0.6980, 0.4612, 0.8706, 0.5554, 0.3980, 0.3224, 0.5773, 0.5992]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6218, 0.4098, 0.7237, 0.1850, 0.4238, 0.2517, 0.6288, 0.5350],
[0.6135, 0.3994, 0.7912, 0.3050, 0.3625, 0.3050, 0.5838, 0.5050],
[0.6284, 0.4092, 0.8900, 0.4700, 0.3650, 0.3850, 0.6212, 0.5167],
[0.6329, 0.4175, 0.8550, 0.2333, 0.5425, 0.2250, 0.7398, 0.5609],
[0.6064, 0.3952, 0.8737, 0.4417, 0.3663, 0.4683, 0.5511, 0.5416],
[0.6202, 0.4053, 0.8637, 0.5283, 0.4546, 0.5108, 0.5900, 0.5133],
[0.6203, 0.4076, 0.8611, 0.2878, 0.4050, 0.2554, 0.5907, 0.5496],
[0.6276, 0.4235, 0.8888, 0.5333, 0.3800, 0.3117, 0.5427, 0.6164]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.1311794207431376
step: 88
running loss: 0.0014906752357174728
Train Steps: 88/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6274, 0.4270, 0.8938, 0.4967, 0.3550, 0.4283, 0.5700, 0.5733],
[0.6274, 0.4117, 0.8100, 0.5801, 0.4000, 0.4583, 0.5582, 0.6118],
[0.6122, 0.4048, 0.7506, 0.3014, 0.3475, 0.3333, 0.5487, 0.5749],
[0.6163, 0.4006, 0.8788, 0.4683, 0.3663, 0.4883, 0.5887, 0.5017],
[0.6228, 0.4119, 0.7938, 0.2233, 0.4674, 0.1773, 0.6188, 0.5433],
[0.6207, 0.4110, 0.8738, 0.5000, 0.4800, 0.5633, 0.6300, 0.5433],
[0.6164, 0.3956, 0.8757, 0.5088, 0.4300, 0.5320, 0.6022, 0.5202],
[0.6030, 0.3969, 0.7988, 0.3917, 0.3450, 0.3667, 0.5266, 0.4700]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6583, 0.4411, 0.8900, 0.4753, 0.3661, 0.4107, 0.6070, 0.5610],
[0.7032, 0.4607, 0.8342, 0.5524, 0.4124, 0.4293, 0.6039, 0.6208],
[0.6121, 0.3993, 0.7666, 0.2818, 0.3541, 0.3070, 0.5600, 0.5471],
[0.6439, 0.4244, 0.8729, 0.4387, 0.3880, 0.4663, 0.5833, 0.5265],
[0.7073, 0.4632, 0.8083, 0.1969, 0.4801, 0.1462, 0.6399, 0.5277],
[0.6096, 0.3859, 0.9005, 0.4553, 0.4819, 0.5500, 0.6491, 0.5414],
[0.6181, 0.4030, 0.9020, 0.4781, 0.4361, 0.4963, 0.6299, 0.5102],
[0.6141, 0.4031, 0.8295, 0.3727, 0.3551, 0.3516, 0.5576, 0.4941]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6274, 0.4270, 0.8938, 0.4967, 0.3550, 0.4283, 0.5700, 0.5733],
[0.6274, 0.4117, 0.8100, 0.5801, 0.4000, 0.4583, 0.5582, 0.6118],
[0.6122, 0.4048, 0.7506, 0.3014, 0.3475, 0.3333, 0.5487, 0.5749],
[0.6163, 0.4006, 0.8788, 0.4683, 0.3663, 0.4883, 0.5888, 0.5017],
[0.6228, 0.4119, 0.7937, 0.2233, 0.4674, 0.1773, 0.6187, 0.5433],
[0.6207, 0.4110, 0.8737, 0.5000, 0.4800, 0.5633, 0.6300, 0.5433],
[0.6164, 0.3956, 0.8757, 0.5088, 0.4300, 0.5320, 0.6022, 0.5202],
[0.6030, 0.3969, 0.7987, 0.3917, 0.3450, 0.3667, 0.5266, 0.4700]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.13189973769476637
step: 89
running loss: 0.0014820195246602963
Train Steps: 89/90 Loss: 0.0015 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6271, 0.4081, 0.9081, 0.4894, 0.3700, 0.4283, 0.6661, 0.5274],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098],
[0.6198, 0.4114, 0.8263, 0.3283, 0.3550, 0.3583, 0.5813, 0.5667],
[0.6147, 0.4026, 0.6600, 0.2467, 0.4088, 0.2150, 0.5489, 0.5773],
[0.6357, 0.4118, 0.8400, 0.2500, 0.5413, 0.1633, 0.6725, 0.5586],
[0.6115, 0.3998, 0.7063, 0.2383, 0.4037, 0.1950, 0.5320, 0.4993],
[0.6261, 0.4045, 0.8865, 0.5369, 0.3895, 0.4859, 0.6683, 0.5249],
[0.6169, 0.4108, 0.6821, 0.2722, 0.3825, 0.2550, 0.5550, 0.5717]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6113, 0.4123, 0.9156, 0.4842, 0.3787, 0.4339, 0.6803, 0.5313],
[0.5968, 0.3982, 0.8830, 0.4667, 0.3824, 0.5372, 0.5866, 0.4975],
[0.6615, 0.4335, 0.8602, 0.3215, 0.3607, 0.3666, 0.5859, 0.5735],
[0.6616, 0.4508, 0.6859, 0.2386, 0.4228, 0.2136, 0.5463, 0.5839],
[0.6522, 0.4216, 0.8659, 0.2377, 0.5468, 0.1720, 0.6670, 0.5417],
[0.6198, 0.4215, 0.7188, 0.2078, 0.4245, 0.2021, 0.5389, 0.5014],
[0.5990, 0.3871, 0.9110, 0.5404, 0.3889, 0.4972, 0.6665, 0.5114],
[0.5953, 0.4015, 0.6792, 0.2568, 0.4020, 0.2465, 0.5699, 0.5747]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6271, 0.4081, 0.9081, 0.4894, 0.3700, 0.4283, 0.6661, 0.5274],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098],
[0.6198, 0.4114, 0.8263, 0.3283, 0.3550, 0.3583, 0.5813, 0.5667],
[0.6147, 0.4026, 0.6600, 0.2467, 0.4087, 0.2150, 0.5489, 0.5773],
[0.6357, 0.4118, 0.8400, 0.2500, 0.5412, 0.1633, 0.6725, 0.5586],
[0.6115, 0.3998, 0.7063, 0.2383, 0.4038, 0.1950, 0.5320, 0.4993],
[0.6261, 0.4045, 0.8865, 0.5369, 0.3895, 0.4859, 0.6683, 0.5249],
[0.6169, 0.4108, 0.6821, 0.2722, 0.3825, 0.2550, 0.5550, 0.5717]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.13218482348020189
step: 90
running loss: 0.001468720260891132
Valid Steps: 10/10 Loss: nan 15
--------------------------------------------------
Epoch: 7 Train Loss: 0.0015 Valid Loss: nan
--------------------------------------------------
size of train loader is: 90
torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6292, 0.4010, 0.8988, 0.4800, 0.3638, 0.3817, 0.6357, 0.5051],
[0.6268, 0.4094, 0.9038, 0.4300, 0.3700, 0.3483, 0.6262, 0.5167],
[0.6250, 0.4054, 0.8770, 0.4723, 0.4662, 0.5367, 0.6162, 0.5433],
[0.6269, 0.4073, 0.8900, 0.4933, 0.3625, 0.4183, 0.6288, 0.5150],
[0.6250, 0.4146, 0.8838, 0.3933, 0.3588, 0.4283, 0.6162, 0.5367],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3513, 0.4050, 0.6112, 0.5500],
[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150],
[0.6222, 0.4108, 0.8938, 0.4233, 0.3600, 0.3817, 0.5825, 0.5283]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6952, 0.4387, 0.8725, 0.4735, 0.3666, 0.3972, 0.6239, 0.5173],
[0.6620, 0.4335, 0.8837, 0.4076, 0.3828, 0.3460, 0.6416, 0.5286],
[0.6551, 0.4304, 0.8760, 0.4881, 0.4687, 0.5299, 0.6150, 0.5283],
[0.6975, 0.4636, 0.8789, 0.4989, 0.3623, 0.4215, 0.6250, 0.5132],
[0.6783, 0.4559, 0.8491, 0.3904, 0.3644, 0.3979, 0.6092, 0.5457],
[0.6325, 0.4093, 0.7707, 0.2715, 0.3652, 0.4031, 0.6094, 0.5560],
[0.6950, 0.4435, 0.8780, 0.4944, 0.4598, 0.6014, 0.6045, 0.5163],
[0.6692, 0.4511, 0.8783, 0.4058, 0.3701, 0.3708, 0.5801, 0.5369]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6292, 0.4010, 0.8988, 0.4800, 0.3638, 0.3817, 0.6357, 0.5051],
[0.6268, 0.4094, 0.9038, 0.4300, 0.3700, 0.3483, 0.6263, 0.5167],
[0.6250, 0.4054, 0.8770, 0.4723, 0.4663, 0.5367, 0.6162, 0.5433],
[0.6269, 0.4073, 0.8900, 0.4933, 0.3625, 0.4183, 0.6288, 0.5150],
[0.6250, 0.4146, 0.8838, 0.3933, 0.3587, 0.4283, 0.6162, 0.5367],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3512, 0.4050, 0.6112, 0.5500],
[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150],
[0.6222, 0.4108, 0.8938, 0.4233, 0.3600, 0.3817, 0.5825, 0.5283]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.000634737079963088
step: 1
running loss: 0.000634737079963088
Train Steps: 1/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6286, 0.4086, 0.8408, 0.2801, 0.4163, 0.2800, 0.6725, 0.5393],
[0.6115, 0.3998, 0.7063, 0.2383, 0.4037, 0.1950, 0.5320, 0.4993],
[0.6261, 0.4066, 0.8325, 0.2150, 0.4763, 0.2667, 0.7002, 0.5633],
[0.6153, 0.4119, 0.8463, 0.3833, 0.3600, 0.3200, 0.5106, 0.5563],
[0.6200, 0.4112, 0.8862, 0.4100, 0.3638, 0.4917, 0.6088, 0.6050],
[0.6135, 0.4115, 0.8838, 0.4667, 0.4288, 0.6050, 0.5778, 0.5097],
[0.6163, 0.4114, 0.7650, 0.2017, 0.3763, 0.2867, 0.5631, 0.5071],
[0.6361, 0.4165, 0.9038, 0.5017, 0.3750, 0.3783, 0.6448, 0.5309]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6766, 0.4289, 0.8286, 0.2968, 0.4127, 0.2863, 0.6748, 0.5418],
[0.6179, 0.4140, 0.6912, 0.2371, 0.4145, 0.2128, 0.5311, 0.5148],
[0.6247, 0.4153, 0.8053, 0.2420, 0.4797, 0.2715, 0.7081, 0.5556],
[0.5787, 0.3854, 0.8454, 0.4129, 0.3846, 0.3143, 0.5029, 0.5668],
[0.6452, 0.4174, 0.8559, 0.4356, 0.3796, 0.5023, 0.6076, 0.5970],
[0.6454, 0.4280, 0.8659, 0.4704, 0.4320, 0.6108, 0.5659, 0.5241],
[0.5738, 0.3689, 0.7364, 0.2182, 0.3825, 0.2897, 0.5679, 0.5108],
[0.6694, 0.4415, 0.8888, 0.4933, 0.3867, 0.3707, 0.6565, 0.5217]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6286, 0.4086, 0.8408, 0.2801, 0.4162, 0.2800, 0.6725, 0.5393],
[0.6115, 0.3998, 0.7063, 0.2383, 0.4038, 0.1950, 0.5320, 0.4993],
[0.6261, 0.4066, 0.8325, 0.2150, 0.4762, 0.2667, 0.7002, 0.5633],
[0.6153, 0.4119, 0.8462, 0.3833, 0.3600, 0.3200, 0.5106, 0.5563],
[0.6200, 0.4112, 0.8863, 0.4100, 0.3638, 0.4917, 0.6087, 0.6050],
[0.6135, 0.4115, 0.8838, 0.4667, 0.4288, 0.6050, 0.5778, 0.5097],
[0.6163, 0.4114, 0.7650, 0.2017, 0.3762, 0.2867, 0.5631, 0.5071],
[0.6361, 0.4165, 0.9038, 0.5017, 0.3750, 0.3783, 0.6448, 0.5309]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0009739936213009059
step: 2
running loss: 0.00048699681065045297
Train Steps: 2/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6307, 0.4029, 0.8650, 0.5200, 0.3763, 0.4017, 0.7311, 0.5366],
[0.6205, 0.4004, 0.8938, 0.4883, 0.3663, 0.5000, 0.6357, 0.4947],
[0.6200, 0.4059, 0.8700, 0.4900, 0.4163, 0.5000, 0.6162, 0.5467],
[0.6131, 0.4037, 0.6907, 0.2819, 0.3688, 0.2700, 0.5217, 0.5680],
[0.6199, 0.4112, 0.8475, 0.3717, 0.3550, 0.4350, 0.6063, 0.6083],
[0.6361, 0.4165, 0.9038, 0.5017, 0.3750, 0.3783, 0.6448, 0.5309],
[0.6118, 0.4052, 0.8463, 0.3917, 0.3538, 0.3450, 0.5053, 0.5593],
[0.6224, 0.4061, 0.8988, 0.4300, 0.3838, 0.4750, 0.6112, 0.5483]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6684, 0.4218, 0.8629, 0.5071, 0.3801, 0.4074, 0.7064, 0.5017],
[0.6440, 0.3897, 0.8907, 0.4888, 0.3580, 0.5210, 0.6386, 0.4876],
[0.6618, 0.4176, 0.8623, 0.4999, 0.4258, 0.5417, 0.5987, 0.5448],
[0.6504, 0.4116, 0.6684, 0.2818, 0.3705, 0.3098, 0.5226, 0.5757],
[0.6074, 0.4032, 0.8490, 0.3834, 0.3605, 0.4385, 0.6010, 0.6027],
[0.7068, 0.4541, 0.8974, 0.4816, 0.3890, 0.3849, 0.6512, 0.5143],
[0.6663, 0.4288, 0.8405, 0.3848, 0.3601, 0.3499, 0.4727, 0.5486],
[0.6665, 0.4204, 0.8850, 0.4391, 0.3886, 0.5139, 0.6090, 0.5330]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6307, 0.4029, 0.8650, 0.5200, 0.3762, 0.4017, 0.7311, 0.5366],
[0.6205, 0.4004, 0.8938, 0.4883, 0.3663, 0.5000, 0.6357, 0.4947],
[0.6199, 0.4059, 0.8700, 0.4900, 0.4162, 0.5000, 0.6162, 0.5467],
[0.6131, 0.4036, 0.6907, 0.2819, 0.3688, 0.2700, 0.5217, 0.5680],
[0.6199, 0.4112, 0.8475, 0.3717, 0.3550, 0.4350, 0.6062, 0.6083],
[0.6361, 0.4165, 0.9038, 0.5017, 0.3750, 0.3783, 0.6448, 0.5309],
[0.6118, 0.4052, 0.8462, 0.3917, 0.3537, 0.3450, 0.5053, 0.5593],
[0.6224, 0.4061, 0.8988, 0.4300, 0.3837, 0.4750, 0.6112, 0.5483]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0014395180041901767
step: 3
running loss: 0.0004798393347300589
Train Steps: 3/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6130, 0.4072, 0.8550, 0.4567, 0.3638, 0.3667, 0.5290, 0.5892],
[0.6193, 0.4050, 0.7313, 0.2433, 0.4075, 0.2117, 0.5649, 0.5656],
[0.6202, 0.4079, 0.8025, 0.2500, 0.3763, 0.3217, 0.6125, 0.5533],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5413, 0.5683],
[0.6200, 0.4086, 0.8414, 0.2974, 0.4117, 0.2274, 0.5869, 0.5391],
[0.6100, 0.4071, 0.7601, 0.3444, 0.3400, 0.4117, 0.5625, 0.5617],
[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383],
[0.6182, 0.4058, 0.8738, 0.4350, 0.3563, 0.3400, 0.5290, 0.5822]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6081, 0.3873, 0.8497, 0.4549, 0.3521, 0.3878, 0.5540, 0.5651],
[0.6429, 0.4091, 0.7206, 0.2405, 0.4152, 0.2421, 0.5812, 0.5704],
[0.6230, 0.3810, 0.7868, 0.2496, 0.3900, 0.3198, 0.6284, 0.5419],
[0.6585, 0.4105, 0.8837, 0.5345, 0.3681, 0.3895, 0.5702, 0.5555],
[0.6274, 0.3987, 0.8372, 0.3034, 0.4211, 0.2373, 0.6061, 0.5390],
[0.6069, 0.3815, 0.7686, 0.3443, 0.3403, 0.4284, 0.5813, 0.5239],
[0.6252, 0.3910, 0.8705, 0.4495, 0.4389, 0.6050, 0.6370, 0.5267],
[0.6166, 0.3865, 0.8532, 0.4427, 0.3593, 0.3599, 0.5404, 0.5638]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6130, 0.4072, 0.8550, 0.4567, 0.3638, 0.3667, 0.5290, 0.5892],
[0.6193, 0.4050, 0.7312, 0.2433, 0.4075, 0.2117, 0.5649, 0.5656],
[0.6202, 0.4079, 0.8025, 0.2500, 0.3762, 0.3217, 0.6125, 0.5533],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5412, 0.5683],
[0.6199, 0.4086, 0.8414, 0.2974, 0.4117, 0.2274, 0.5869, 0.5391],
[0.6100, 0.4071, 0.7601, 0.3444, 0.3400, 0.4117, 0.5625, 0.5617],
[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383],
[0.6182, 0.4058, 0.8737, 0.4350, 0.3562, 0.3400, 0.5290, 0.5822]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.001678855056525208
step: 4
running loss: 0.000419713764131302
Train Steps: 4/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6268, 0.4094, 0.9038, 0.4300, 0.3700, 0.3483, 0.6262, 0.5167],
[0.6138, 0.4054, 0.8750, 0.4750, 0.4363, 0.5017, 0.5086, 0.5822],
[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586],
[0.6300, 0.4013, 0.8938, 0.5350, 0.3675, 0.4600, 0.6456, 0.4973],
[ nan, nan, 0.6688, 0.2513, 0.4113, 0.2117, 0.5193, 0.5933],
[0.6211, 0.3993, 0.7650, 0.1933, 0.4575, 0.1550, 0.5965, 0.4895],
[0.6128, 0.4116, 0.8450, 0.4583, 0.3675, 0.4867, 0.5337, 0.5446],
[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6535, 0.4268, 0.9218, 0.4248, 0.3633, 0.3752, 0.6456, 0.5334],
[0.6299, 0.4239, 0.8814, 0.4930, 0.4228, 0.5131, 0.5455, 0.5724],
[0.6410, 0.4221, 0.8750, 0.2759, 0.4460, 0.2838, 0.7228, 0.5797],
[0.6569, 0.4039, 0.9135, 0.5521, 0.3506, 0.4886, 0.6536, 0.4932],
[0.0340, 0.0284, 0.6861, 0.2670, 0.4044, 0.2420, 0.5503, 0.6324],
[0.7165, 0.4682, 0.7702, 0.1931, 0.4608, 0.1776, 0.6070, 0.5090],
[0.6661, 0.4247, 0.8615, 0.4843, 0.3716, 0.5002, 0.5485, 0.5507],
[0.6522, 0.4341, 0.6852, 0.3236, 0.3517, 0.3098, 0.5355, 0.5977]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6268, 0.4094, 0.9038, 0.4300, 0.3700, 0.3483, 0.6263, 0.5167],
[0.6138, 0.4054, 0.8750, 0.4750, 0.4363, 0.5017, 0.5086, 0.5822],
[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586],
[0.6300, 0.4013, 0.8938, 0.5350, 0.3675, 0.4600, 0.6456, 0.4973],
[0.0000, 0.0000, 0.6688, 0.2513, 0.4112, 0.2117, 0.5193, 0.5933],
[0.6211, 0.3993, 0.7650, 0.1933, 0.4575, 0.1550, 0.5965, 0.4895],
[0.6128, 0.4116, 0.8450, 0.4583, 0.3675, 0.4867, 0.5337, 0.5446],
[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.002325661844224669
step: 5
running loss: 0.0004651323688449338
Train Steps: 5/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6239, 0.4206, 0.8750, 0.5400, 0.3688, 0.4850, 0.5737, 0.5700],
[0.6261, 0.3987, 0.8688, 0.4917, 0.4300, 0.5333, 0.7010, 0.5309],
[0.6282, 0.4029, 0.8988, 0.3000, 0.4250, 0.4183, 0.7042, 0.5575],
[0.6276, 0.4002, 0.8800, 0.5533, 0.3575, 0.4400, 0.6132, 0.4672],
[0.6206, 0.4123, 0.7175, 0.2400, 0.3887, 0.2933, 0.6225, 0.5750],
[0.6150, 0.3949, 0.8800, 0.4033, 0.3825, 0.4900, 0.5875, 0.5483],
[0.6177, 0.4086, 0.8738, 0.3950, 0.3775, 0.5600, 0.6225, 0.5700],
[0.6283, 0.4283, 0.7477, 0.3542, 0.5125, 0.1917, 0.5500, 0.6167]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6606, 0.4245, 0.8836, 0.5583, 0.3539, 0.4847, 0.5659, 0.5619],
[0.6123, 0.3990, 0.8744, 0.5123, 0.4089, 0.5486, 0.6709, 0.5649],
[0.5972, 0.3926, 0.8888, 0.3162, 0.3896, 0.4101, 0.6946, 0.5617],
[0.5883, 0.3712, 0.8911, 0.5428, 0.3359, 0.4267, 0.6049, 0.5045],
[0.6754, 0.4337, 0.7266, 0.2542, 0.3625, 0.2963, 0.5969, 0.5932],
[0.5790, 0.3739, 0.8706, 0.4205, 0.3542, 0.4721, 0.5582, 0.5324],
[0.5863, 0.3972, 0.8765, 0.4084, 0.3567, 0.5534, 0.6111, 0.5487],
[0.6434, 0.4218, 0.7339, 0.3618, 0.4775, 0.1961, 0.5330, 0.6443]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6239, 0.4206, 0.8750, 0.5400, 0.3688, 0.4850, 0.5738, 0.5700],
[0.6261, 0.3987, 0.8687, 0.4917, 0.4300, 0.5333, 0.7010, 0.5309],
[0.6282, 0.4029, 0.8988, 0.3000, 0.4250, 0.4183, 0.7042, 0.5575],
[0.6276, 0.4002, 0.8800, 0.5533, 0.3575, 0.4400, 0.6132, 0.4672],
[0.6206, 0.4123, 0.7175, 0.2400, 0.3887, 0.2933, 0.6225, 0.5750],
[0.6150, 0.3949, 0.8800, 0.4033, 0.3825, 0.4900, 0.5875, 0.5483],
[0.6177, 0.4085, 0.8737, 0.3950, 0.3775, 0.5600, 0.6225, 0.5700],
[0.6283, 0.4283, 0.7477, 0.3542, 0.5125, 0.1917, 0.5500, 0.6167]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0027636906161205843
step: 6
running loss: 0.00046061510268676403
Train Steps: 6/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6208, 0.4082, 0.8538, 0.3067, 0.3588, 0.3717, 0.6112, 0.5517],
[0.6277, 0.4118, 0.8988, 0.3833, 0.3950, 0.2650, 0.6290, 0.4938],
[0.6128, 0.4116, 0.8450, 0.4583, 0.3675, 0.4867, 0.5337, 0.5446],
[0.6203, 0.4096, 0.8862, 0.4267, 0.3538, 0.4117, 0.6025, 0.5650],
[ nan, nan, 0.7725, 0.2611, 0.3675, 0.2733, 0.5413, 0.5167],
[0.6203, 0.4073, 0.8189, 0.2398, 0.4400, 0.2054, 0.5929, 0.5501],
[0.6336, 0.4154, 0.8900, 0.2767, 0.4988, 0.2867, 0.7422, 0.5540],
[0.6058, 0.3978, 0.8287, 0.3600, 0.3400, 0.4050, 0.5529, 0.5461]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6093, 0.4016, 0.8455, 0.3136, 0.3467, 0.3746, 0.5997, 0.5630],
[0.6374, 0.4256, 0.8931, 0.3969, 0.3701, 0.2547, 0.6111, 0.5143],
[0.6286, 0.4087, 0.8342, 0.4794, 0.3684, 0.4703, 0.5179, 0.5471],
[0.6256, 0.4069, 0.8910, 0.4117, 0.3544, 0.4030, 0.5732, 0.5737],
[0.0518, 0.0447, 0.7377, 0.2758, 0.3662, 0.2630, 0.5332, 0.5880],
[0.6257, 0.4142, 0.7941, 0.2575, 0.4349, 0.1931, 0.5780, 0.5478],
[0.6132, 0.4034, 0.8644, 0.3036, 0.4870, 0.2848, 0.7201, 0.5546],
[0.6095, 0.4068, 0.8269, 0.3836, 0.3205, 0.4037, 0.5424, 0.5314]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6208, 0.4082, 0.8537, 0.3067, 0.3587, 0.3717, 0.6112, 0.5517],
[0.6277, 0.4117, 0.8988, 0.3833, 0.3950, 0.2650, 0.6290, 0.4938],
[0.6128, 0.4116, 0.8450, 0.4583, 0.3675, 0.4867, 0.5337, 0.5446],
[0.6203, 0.4096, 0.8863, 0.4267, 0.3537, 0.4117, 0.6025, 0.5650],
[0.0000, 0.0000, 0.7725, 0.2611, 0.3675, 0.2733, 0.5412, 0.5167],
[0.6203, 0.4073, 0.8189, 0.2398, 0.4400, 0.2054, 0.5929, 0.5501],
[0.6336, 0.4154, 0.8900, 0.2767, 0.4988, 0.2867, 0.7422, 0.5540],
[0.6058, 0.3978, 0.8288, 0.3600, 0.3400, 0.4050, 0.5529, 0.5461]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.003107938144239597
step: 7
running loss: 0.0004439911634627996
Train Steps: 7/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6095, 0.3970, 0.8688, 0.4767, 0.4860, 0.4879, 0.5191, 0.4940],
[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837],
[0.6211, 0.3993, 0.7650, 0.1933, 0.4575, 0.1550, 0.5965, 0.4895],
[0.6138, 0.4054, 0.8750, 0.4750, 0.4363, 0.5017, 0.5086, 0.5822],
[ nan, nan, 0.8750, 0.2467, 0.5138, 0.2617, 0.7382, 0.5552],
[0.6325, 0.4066, 0.8438, 0.5350, 0.3925, 0.5267, 0.7113, 0.5795],
[0.6211, 0.4069, 0.8750, 0.5117, 0.4150, 0.4900, 0.5875, 0.5167],
[0.6163, 0.4114, 0.7650, 0.2017, 0.3763, 0.2867, 0.5631, 0.5071]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6563, 0.4177, 0.8839, 0.4649, 0.4715, 0.4626, 0.5183, 0.5332],
[ 0.6144, 0.4091, 0.6869, 0.3082, 0.3530, 0.2762, 0.5134, 0.5890],
[ 0.6505, 0.4218, 0.7742, 0.1857, 0.4556, 0.1476, 0.5805, 0.5013],
[ 0.6151, 0.4132, 0.8729, 0.4727, 0.4237, 0.4703, 0.5191, 0.5730],
[-0.0467, -0.0208, 0.8933, 0.2386, 0.5126, 0.2212, 0.7333, 0.5870],
[ 0.6474, 0.4061, 0.8690, 0.5207, 0.3831, 0.5279, 0.6993, 0.5735],
[ 0.6017, 0.3957, 0.8910, 0.5184, 0.4018, 0.5002, 0.5945, 0.5251],
[ 0.6256, 0.4011, 0.7802, 0.1927, 0.3695, 0.2676, 0.5585, 0.5046]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6095, 0.3970, 0.8687, 0.4767, 0.4860, 0.4879, 0.5191, 0.4940],
[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837],
[0.6211, 0.3993, 0.7650, 0.1933, 0.4575, 0.1550, 0.5965, 0.4895],
[0.6138, 0.4054, 0.8750, 0.4750, 0.4363, 0.5017, 0.5086, 0.5822],
[0.0000, 0.0000, 0.8750, 0.2467, 0.5138, 0.2617, 0.7382, 0.5552],
[0.6325, 0.4066, 0.8438, 0.5350, 0.3925, 0.5267, 0.7113, 0.5795],
[0.6211, 0.4069, 0.8750, 0.5117, 0.4150, 0.4900, 0.5875, 0.5167],
[0.6163, 0.4114, 0.7650, 0.2017, 0.3762, 0.2867, 0.5631, 0.5071]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.003420340406592004
step: 8
running loss: 0.0004275425508240005
Train Steps: 8/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6055, 0.4015, 0.7425, 0.2033, 0.4113, 0.1883, 0.5217, 0.4823],
[0.6081, 0.3950, 0.8538, 0.4667, 0.3850, 0.4917, 0.5342, 0.4954],
[0.6250, 0.4013, 0.8525, 0.5417, 0.4037, 0.5117, 0.6325, 0.5017],
[0.6197, 0.4091, 0.8800, 0.4783, 0.3538, 0.4767, 0.5950, 0.5550],
[0.6227, 0.4193, 0.8838, 0.4933, 0.3663, 0.3733, 0.5637, 0.5633],
[ nan, nan, 0.8525, 0.2217, 0.5413, 0.2367, 0.7367, 0.5482],
[0.6202, 0.4054, 0.8892, 0.4428, 0.3642, 0.3249, 0.5840, 0.5426],
[0.6300, 0.4013, 0.8938, 0.5350, 0.3675, 0.4600, 0.6456, 0.4973]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5593, 0.3640, 0.7191, 0.2089, 0.4127, 0.1832, 0.5501, 0.5045],
[0.5864, 0.3865, 0.8691, 0.4170, 0.3943, 0.4823, 0.5247, 0.5135],
[0.6240, 0.3902, 0.8571, 0.5376, 0.4267, 0.5107, 0.6087, 0.5094],
[0.6303, 0.4107, 0.8826, 0.4569, 0.3914, 0.4682, 0.5766, 0.5644],
[0.6528, 0.4362, 0.8672, 0.4647, 0.3807, 0.3725, 0.5555, 0.5838],
[0.0477, 0.0448, 0.8623, 0.2045, 0.5571, 0.2246, 0.7361, 0.5878],
[0.5963, 0.4004, 0.9031, 0.4261, 0.3855, 0.3173, 0.5781, 0.5401],
[0.6139, 0.3800, 0.8932, 0.5163, 0.3783, 0.4553, 0.6279, 0.4962]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6055, 0.4015, 0.7425, 0.2033, 0.4112, 0.1883, 0.5217, 0.4823],
[0.6081, 0.3950, 0.8537, 0.4667, 0.3850, 0.4917, 0.5342, 0.4954],
[0.6250, 0.4013, 0.8525, 0.5417, 0.4038, 0.5117, 0.6325, 0.5017],
[0.6197, 0.4091, 0.8800, 0.4783, 0.3537, 0.4767, 0.5950, 0.5550],
[0.6227, 0.4193, 0.8838, 0.4933, 0.3663, 0.3733, 0.5638, 0.5633],
[0.0000, 0.0000, 0.8525, 0.2217, 0.5412, 0.2367, 0.7367, 0.5482],
[0.6202, 0.4054, 0.8892, 0.4428, 0.3642, 0.3249, 0.5840, 0.5426],
[0.6300, 0.4013, 0.8938, 0.5350, 0.3675, 0.4600, 0.6456, 0.4973]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0038243775634327903
step: 9
running loss: 0.00042493084038142115
Train Steps: 9/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6204, 0.4110, 0.7913, 0.2667, 0.4062, 0.2500, 0.6225, 0.5367],
[0.6200, 0.3993, 0.8519, 0.4923, 0.3962, 0.4717, 0.6013, 0.5433],
[0.6193, 0.4108, 0.7438, 0.2700, 0.3650, 0.3683, 0.6238, 0.5717],
[0.6168, 0.4029, 0.8523, 0.3417, 0.3588, 0.5000, 0.6125, 0.5400],
[0.6164, 0.3972, 0.7818, 0.3381, 0.3599, 0.3387, 0.5880, 0.5153],
[0.6279, 0.4050, 0.8025, 0.2200, 0.4313, 0.2733, 0.6820, 0.5320],
[0.6213, 0.4001, 0.7712, 0.2117, 0.4338, 0.1800, 0.5850, 0.5183],
[0.6178, 0.4059, 0.7525, 0.2250, 0.4313, 0.1783, 0.5404, 0.5240]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5691, 0.3796, 0.8062, 0.2591, 0.4247, 0.2604, 0.6077, 0.5386],
[0.5695, 0.3792, 0.8748, 0.5051, 0.4170, 0.4710, 0.6073, 0.5523],
[0.5765, 0.3793, 0.7552, 0.2764, 0.3750, 0.3704, 0.6181, 0.5690],
[0.5474, 0.3674, 0.8702, 0.3460, 0.3741, 0.4950, 0.6105, 0.5452],
[0.5676, 0.3823, 0.8079, 0.3202, 0.3746, 0.3489, 0.5917, 0.5139],
[0.5589, 0.3677, 0.8124, 0.2105, 0.4556, 0.2762, 0.6631, 0.5270],
[0.5715, 0.3594, 0.7832, 0.2142, 0.4573, 0.1787, 0.5668, 0.5262],
[0.3931, 0.2683, 0.7582, 0.2373, 0.4466, 0.1760, 0.5537, 0.5485]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6204, 0.4110, 0.7912, 0.2667, 0.4062, 0.2500, 0.6225, 0.5367],
[0.6200, 0.3993, 0.8519, 0.4923, 0.3963, 0.4717, 0.6012, 0.5433],
[0.6193, 0.4108, 0.7437, 0.2700, 0.3650, 0.3683, 0.6237, 0.5717],
[0.6168, 0.4029, 0.8523, 0.3417, 0.3587, 0.5000, 0.6125, 0.5400],
[0.6164, 0.3972, 0.7818, 0.3381, 0.3599, 0.3387, 0.5880, 0.5153],
[0.6279, 0.4050, 0.8025, 0.2200, 0.4313, 0.2733, 0.6820, 0.5320],
[0.6213, 0.4001, 0.7713, 0.2117, 0.4338, 0.1800, 0.5850, 0.5183],
[0.6178, 0.4059, 0.7525, 0.2250, 0.4313, 0.1783, 0.5404, 0.5240]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.005475856611155905
step: 10
running loss: 0.0005475856611155905
Train Steps: 10/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6211, 0.3935, 0.8636, 0.4841, 0.4417, 0.5126, 0.6331, 0.5268],
[0.6183, 0.4076, 0.8838, 0.4517, 0.3813, 0.4483, 0.5775, 0.5633],
[0.6186, 0.4060, 0.8750, 0.5050, 0.3538, 0.4367, 0.5813, 0.6083],
[0.6230, 0.4152, 0.7588, 0.2283, 0.4012, 0.2883, 0.6200, 0.5767],
[0.6107, 0.4050, 0.8700, 0.4850, 0.4470, 0.4848, 0.5043, 0.5431],
[0.6138, 0.4101, 0.8800, 0.5083, 0.4637, 0.5950, 0.5587, 0.5077],
[0.6257, 0.4034, 0.8287, 0.2333, 0.3925, 0.2717, 0.6330, 0.4901],
[0.6187, 0.4104, 0.7126, 0.2069, 0.3950, 0.2517, 0.5913, 0.5683]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5778, 0.3631, 0.8630, 0.4630, 0.4427, 0.4802, 0.6320, 0.5042],
[0.5571, 0.3702, 0.8847, 0.4294, 0.3884, 0.4266, 0.5899, 0.5506],
[0.5534, 0.3684, 0.8602, 0.4760, 0.3661, 0.4216, 0.5846, 0.5699],
[0.5960, 0.3879, 0.7611, 0.2382, 0.4183, 0.2803, 0.6296, 0.5309],
[0.5524, 0.3774, 0.8657, 0.4767, 0.4540, 0.4675, 0.5284, 0.4991],
[0.5111, 0.3414, 0.8815, 0.5135, 0.4777, 0.5534, 0.5801, 0.5005],
[0.6022, 0.3933, 0.8279, 0.2484, 0.3888, 0.2621, 0.6464, 0.4693],
[0.5504, 0.3655, 0.7145, 0.2024, 0.3990, 0.2294, 0.5790, 0.5200]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6211, 0.3935, 0.8636, 0.4841, 0.4417, 0.5126, 0.6331, 0.5268],
[0.6183, 0.4076, 0.8838, 0.4517, 0.3812, 0.4483, 0.5775, 0.5633],
[0.6186, 0.4060, 0.8750, 0.5050, 0.3537, 0.4367, 0.5813, 0.6083],
[0.6230, 0.4152, 0.7588, 0.2283, 0.4013, 0.2883, 0.6200, 0.5767],
[0.6107, 0.4050, 0.8700, 0.4850, 0.4470, 0.4848, 0.5043, 0.5431],
[0.6138, 0.4101, 0.8800, 0.5083, 0.4638, 0.5950, 0.5587, 0.5077],
[0.6257, 0.4034, 0.8288, 0.2333, 0.3925, 0.2717, 0.6330, 0.4901],
[0.6187, 0.4103, 0.7126, 0.2069, 0.3950, 0.2517, 0.5913, 0.5683]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.006415960393496789
step: 11
running loss: 0.0005832691266815262
Train Steps: 11/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6201, 0.4027, 0.8029, 0.2728, 0.4042, 0.2310, 0.5980, 0.5391],
[0.6143, 0.4055, 0.8150, 0.2767, 0.3825, 0.2567, 0.5173, 0.4901],
[0.6261, 0.3987, 0.8688, 0.4917, 0.4300, 0.5333, 0.7010, 0.5309],
[ nan, nan, 0.7525, 0.2291, 0.3838, 0.3017, 0.6050, 0.5667],
[0.6115, 0.4081, 0.6725, 0.2433, 0.4088, 0.1933, 0.5167, 0.5544],
[0.6095, 0.3970, 0.8688, 0.4767, 0.4860, 0.4879, 0.5191, 0.4940],
[0.6258, 0.4143, 0.8525, 0.2617, 0.4950, 0.1667, 0.6219, 0.4967],
[0.6084, 0.3981, 0.8588, 0.5233, 0.4600, 0.5367, 0.5680, 0.5006]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6073, 0.3913, 0.7963, 0.2558, 0.4119, 0.2415, 0.6013, 0.5137],
[0.5290, 0.3648, 0.7915, 0.2882, 0.3676, 0.2543, 0.5319, 0.4917],
[0.6104, 0.4107, 0.8586, 0.4751, 0.4234, 0.5301, 0.6855, 0.5266],
[0.0803, 0.0688, 0.7548, 0.2152, 0.3793, 0.2732, 0.5980, 0.5617],
[0.5532, 0.3812, 0.6788, 0.2455, 0.4015, 0.1991, 0.5203, 0.5415],
[0.5990, 0.3987, 0.8612, 0.4508, 0.4700, 0.4684, 0.5258, 0.5003],
[0.5285, 0.3691, 0.8373, 0.2425, 0.4806, 0.1649, 0.6189, 0.4771],
[0.6092, 0.4158, 0.8430, 0.5042, 0.4554, 0.5251, 0.5594, 0.4881]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6201, 0.4027, 0.8029, 0.2728, 0.4042, 0.2310, 0.5980, 0.5391],
[0.6143, 0.4055, 0.8150, 0.2767, 0.3825, 0.2567, 0.5173, 0.4901],
[0.6261, 0.3987, 0.8687, 0.4917, 0.4300, 0.5333, 0.7010, 0.5309],
[0.0000, 0.0000, 0.7525, 0.2291, 0.3837, 0.3017, 0.6050, 0.5667],
[0.6115, 0.4081, 0.6725, 0.2433, 0.4087, 0.1933, 0.5167, 0.5544],
[0.6095, 0.3970, 0.8687, 0.4767, 0.4860, 0.4879, 0.5191, 0.4940],
[0.6258, 0.4143, 0.8525, 0.2617, 0.4950, 0.1667, 0.6219, 0.4967],
[0.6084, 0.3981, 0.8587, 0.5233, 0.4600, 0.5367, 0.5680, 0.5006]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.007117415210814215
step: 12
running loss: 0.000593117934234518
Train Steps: 12/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6280, 0.4101, 0.9050, 0.4533, 0.3775, 0.3217, 0.6338, 0.4915],
[0.6154, 0.4048, 0.7100, 0.2067, 0.4338, 0.1667, 0.5413, 0.5220],
[0.6241, 0.4143, 0.8938, 0.4650, 0.4075, 0.5350, 0.6250, 0.5550],
[0.6122, 0.4006, 0.8850, 0.4217, 0.4088, 0.5517, 0.6063, 0.5517],
[0.6224, 0.3964, 0.8225, 0.5717, 0.4150, 0.4617, 0.5775, 0.5267],
[0.6081, 0.3950, 0.8538, 0.4667, 0.3850, 0.4917, 0.5342, 0.4954],
[0.6070, 0.3979, 0.8575, 0.5083, 0.4350, 0.5400, 0.5180, 0.5466],
[0.6201, 0.4098, 0.8575, 0.3617, 0.3700, 0.3550, 0.5988, 0.5667]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5904, 0.3898, 0.8998, 0.4425, 0.3572, 0.3174, 0.6593, 0.4781],
[0.5662, 0.3711, 0.6896, 0.1980, 0.4226, 0.1710, 0.5716, 0.4987],
[0.5754, 0.3873, 0.8808, 0.4244, 0.4162, 0.5290, 0.6554, 0.5356],
[0.5711, 0.3879, 0.8730, 0.4059, 0.4015, 0.5412, 0.6156, 0.5187],
[0.6003, 0.4078, 0.8135, 0.5540, 0.3982, 0.4318, 0.6006, 0.4987],
[0.5563, 0.3824, 0.8493, 0.4039, 0.3722, 0.4691, 0.5495, 0.4847],
[0.5480, 0.3759, 0.8244, 0.4778, 0.4327, 0.5286, 0.5453, 0.5120],
[0.5987, 0.4079, 0.8454, 0.3477, 0.3766, 0.3348, 0.6164, 0.5470]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6280, 0.4101, 0.9050, 0.4533, 0.3775, 0.3217, 0.6338, 0.4915],
[0.6154, 0.4048, 0.7100, 0.2067, 0.4338, 0.1667, 0.5413, 0.5220],
[0.6241, 0.4142, 0.8938, 0.4650, 0.4075, 0.5350, 0.6250, 0.5550],
[0.6122, 0.4006, 0.8850, 0.4217, 0.4087, 0.5517, 0.6062, 0.5517],
[0.6224, 0.3964, 0.8225, 0.5717, 0.4150, 0.4617, 0.5775, 0.5267],
[0.6081, 0.3950, 0.8537, 0.4667, 0.3850, 0.4917, 0.5342, 0.4954],
[0.6070, 0.3979, 0.8575, 0.5083, 0.4350, 0.5400, 0.5180, 0.5466],
[0.6201, 0.4098, 0.8575, 0.3617, 0.3700, 0.3550, 0.5987, 0.5667]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.007744449147139676
step: 13
running loss: 0.0005957268574722827
Train Steps: 13/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6204, 0.4049, 0.7975, 0.2700, 0.3937, 0.2567, 0.5700, 0.5183],
[0.6321, 0.4048, 0.8738, 0.5617, 0.3875, 0.4417, 0.6361, 0.4927],
[0.6075, 0.4000, 0.8513, 0.5183, 0.4510, 0.5329, 0.5180, 0.5280],
[0.6222, 0.3957, 0.8838, 0.5017, 0.3937, 0.4600, 0.5900, 0.5017],
[0.6150, 0.4097, 0.7468, 0.3194, 0.3825, 0.2633, 0.5463, 0.5800],
[0.6201, 0.4036, 0.8596, 0.3850, 0.3492, 0.3785, 0.5978, 0.5131],
[ nan, nan, 0.6992, 0.2791, 0.3950, 0.2383, 0.5483, 0.5819],
[0.6200, 0.4071, 0.7338, 0.1917, 0.4200, 0.2450, 0.6150, 0.5517]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6580, 0.4510, 0.7884, 0.2578, 0.3902, 0.2608, 0.5653, 0.5235],
[0.6374, 0.4277, 0.8697, 0.5432, 0.3760, 0.4533, 0.6301, 0.4782],
[0.6094, 0.4081, 0.8409, 0.5083, 0.4566, 0.5553, 0.5343, 0.5236],
[0.6468, 0.4245, 0.8740, 0.4897, 0.3949, 0.4702, 0.5960, 0.4987],
[0.6265, 0.4372, 0.7443, 0.2968, 0.3676, 0.2812, 0.5386, 0.5554],
[0.6135, 0.4098, 0.8615, 0.3593, 0.3455, 0.3919, 0.5960, 0.4974],
[0.1953, 0.1307, 0.6816, 0.2437, 0.3851, 0.2490, 0.5604, 0.5534],
[0.5964, 0.4031, 0.7323, 0.1757, 0.4227, 0.2616, 0.6200, 0.5441]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6204, 0.4049, 0.7975, 0.2700, 0.3938, 0.2567, 0.5700, 0.5183],
[0.6321, 0.4048, 0.8737, 0.5617, 0.3875, 0.4417, 0.6361, 0.4927],
[0.6075, 0.4000, 0.8512, 0.5183, 0.4510, 0.5329, 0.5180, 0.5280],
[0.6222, 0.3957, 0.8838, 0.5017, 0.3938, 0.4600, 0.5900, 0.5017],
[0.6150, 0.4097, 0.7468, 0.3194, 0.3825, 0.2633, 0.5462, 0.5800],
[0.6201, 0.4036, 0.8596, 0.3850, 0.3492, 0.3785, 0.5978, 0.5131],
[0.0000, 0.0000, 0.6992, 0.2791, 0.3950, 0.2383, 0.5483, 0.5819],
[0.6200, 0.4071, 0.7337, 0.1917, 0.4200, 0.2450, 0.6150, 0.5517]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.008856130370986648
step: 14
running loss: 0.0006325807407847606
Train Steps: 14/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6143, 0.4040, 0.8237, 0.3333, 0.4075, 0.2117, 0.5137, 0.4973],
[0.6113, 0.4006, 0.8700, 0.5350, 0.3638, 0.3767, 0.5097, 0.4882],
[0.6189, 0.4049, 0.8888, 0.4417, 0.4213, 0.5200, 0.5988, 0.5633],
[0.6203, 0.4056, 0.8942, 0.4086, 0.3643, 0.3617, 0.5917, 0.5482],
[ nan, nan, 0.6859, 0.2194, 0.4150, 0.1867, 0.5153, 0.5729],
[0.6246, 0.4090, 0.6964, 0.2027, 0.3925, 0.2683, 0.6088, 0.5583],
[0.6162, 0.3949, 0.8838, 0.4517, 0.4250, 0.5183, 0.5837, 0.5500],
[0.6197, 0.3930, 0.8793, 0.4736, 0.4152, 0.5464, 0.6308, 0.5235]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5724, 0.3819, 0.8246, 0.3438, 0.4118, 0.2549, 0.5484, 0.5102],
[0.6460, 0.4393, 0.8570, 0.5261, 0.3701, 0.4076, 0.5309, 0.5025],
[0.7027, 0.4749, 0.8744, 0.4550, 0.4139, 0.5604, 0.6192, 0.5783],
[0.6758, 0.4445, 0.8976, 0.4109, 0.3588, 0.3803, 0.5950, 0.5482],
[0.1091, 0.0646, 0.6863, 0.2242, 0.4313, 0.2017, 0.5191, 0.5573],
[0.6893, 0.4546, 0.7051, 0.2249, 0.3795, 0.2830, 0.6013, 0.5383],
[0.6455, 0.4368, 0.8594, 0.4563, 0.4097, 0.5432, 0.5876, 0.5352],
[0.6468, 0.4288, 0.8710, 0.4869, 0.4198, 0.5645, 0.6359, 0.5339]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6143, 0.4040, 0.8238, 0.3333, 0.4075, 0.2117, 0.5137, 0.4973],
[0.6113, 0.4006, 0.8700, 0.5350, 0.3638, 0.3767, 0.5097, 0.4882],
[0.6189, 0.4049, 0.8888, 0.4417, 0.4212, 0.5200, 0.5987, 0.5633],
[0.6203, 0.4056, 0.8942, 0.4086, 0.3643, 0.3617, 0.5917, 0.5482],
[0.0000, 0.0000, 0.6859, 0.2194, 0.4150, 0.1867, 0.5153, 0.5729],
[0.6246, 0.4090, 0.6964, 0.2027, 0.3925, 0.2683, 0.6087, 0.5583],
[0.6162, 0.3949, 0.8838, 0.4517, 0.4250, 0.5183, 0.5838, 0.5500],
[0.6197, 0.3930, 0.8793, 0.4736, 0.4152, 0.5464, 0.6308, 0.5235]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.00981652743939776
step: 15
running loss: 0.0006544351626265173
Train Steps: 15/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6260, 0.4106, 0.8025, 0.2583, 0.4550, 0.1867, 0.6281, 0.4869],
[0.6092, 0.4001, 0.8638, 0.4867, 0.4288, 0.5367, 0.5484, 0.5064],
[0.6213, 0.4131, 0.8438, 0.3550, 0.3513, 0.4400, 0.5716, 0.5123],
[0.6109, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117],
[0.6202, 0.4053, 0.8638, 0.5283, 0.4546, 0.5108, 0.5900, 0.5133],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098],
[0.6249, 0.4138, 0.9038, 0.4517, 0.3862, 0.4917, 0.6138, 0.5333],
[0.6128, 0.4084, 0.8738, 0.4683, 0.3613, 0.3700, 0.4960, 0.5397]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5996, 0.3768, 0.8086, 0.2620, 0.4501, 0.1922, 0.6225, 0.5224],
[0.6341, 0.4035, 0.8394, 0.4824, 0.4247, 0.5578, 0.5244, 0.5363],
[0.6212, 0.4082, 0.8375, 0.3579, 0.3429, 0.4226, 0.5650, 0.5385],
[0.6247, 0.4267, 0.8590, 0.4681, 0.3597, 0.4251, 0.5458, 0.5396],
[0.6561, 0.4138, 0.8484, 0.5444, 0.4495, 0.5152, 0.5933, 0.5391],
[0.6217, 0.4007, 0.8524, 0.4722, 0.3707, 0.5247, 0.6042, 0.5369],
[0.6051, 0.4039, 0.8702, 0.4627, 0.3706, 0.4843, 0.6178, 0.5528],
[0.6225, 0.3987, 0.8799, 0.4781, 0.3568, 0.3649, 0.5072, 0.5542]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6260, 0.4106, 0.8025, 0.2583, 0.4550, 0.1867, 0.6281, 0.4869],
[0.6092, 0.4001, 0.8637, 0.4867, 0.4288, 0.5367, 0.5484, 0.5064],
[0.6213, 0.4131, 0.8438, 0.3550, 0.3512, 0.4400, 0.5716, 0.5123],
[0.6108, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117],
[0.6202, 0.4053, 0.8637, 0.5283, 0.4546, 0.5108, 0.5900, 0.5133],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098],
[0.6249, 0.4138, 0.9038, 0.4517, 0.3862, 0.4917, 0.6137, 0.5333],
[0.6127, 0.4084, 0.8737, 0.4683, 0.3613, 0.3700, 0.4960, 0.5397]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.010077989150886424
step: 16
running loss: 0.0006298743219304015
Train Steps: 16/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6267, 0.4065, 0.8313, 0.2467, 0.4788, 0.1733, 0.6312, 0.5133],
[0.6339, 0.4081, 0.8425, 0.5417, 0.3850, 0.4833, 0.7335, 0.5760],
[0.6250, 0.4103, 0.8950, 0.4400, 0.3912, 0.5650, 0.6050, 0.5133],
[0.6132, 0.4037, 0.6963, 0.2217, 0.4100, 0.1950, 0.5395, 0.5175],
[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.6264, 0.4049, 0.8988, 0.4633, 0.3813, 0.4983, 0.6326, 0.4843],
[0.6083, 0.3957, 0.8638, 0.4950, 0.4363, 0.5083, 0.5346, 0.4980],
[0.6229, 0.4066, 0.7612, 0.2967, 0.4250, 0.2167, 0.5925, 0.5350]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5917, 0.3692, 0.8392, 0.2501, 0.4780, 0.1923, 0.6008, 0.5347],
[0.6336, 0.4016, 0.8444, 0.5631, 0.3798, 0.4912, 0.6907, 0.6007],
[0.6221, 0.3998, 0.8935, 0.4706, 0.3912, 0.5854, 0.5955, 0.5473],
[0.6236, 0.4051, 0.7214, 0.2565, 0.3991, 0.2110, 0.5162, 0.5318],
[0.6419, 0.4099, 0.8480, 0.5898, 0.3739, 0.4971, 0.6184, 0.5603],
[0.6154, 0.3999, 0.9063, 0.4833, 0.3787, 0.5135, 0.6094, 0.5174],
[0.6243, 0.3887, 0.8631, 0.5044, 0.4348, 0.5294, 0.5217, 0.5199],
[0.6385, 0.3931, 0.7728, 0.2902, 0.4140, 0.2608, 0.5593, 0.5696]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6266, 0.4065, 0.8313, 0.2467, 0.4787, 0.1733, 0.6313, 0.5133],
[0.6339, 0.4081, 0.8425, 0.5417, 0.3850, 0.4833, 0.7335, 0.5760],
[0.6250, 0.4103, 0.8950, 0.4400, 0.3913, 0.5650, 0.6050, 0.5133],
[0.6132, 0.4037, 0.6963, 0.2217, 0.4100, 0.1950, 0.5395, 0.5175],
[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.6264, 0.4049, 0.8988, 0.4633, 0.3812, 0.4983, 0.6326, 0.4843],
[0.6083, 0.3957, 0.8637, 0.4950, 0.4363, 0.5083, 0.5346, 0.4980],
[0.6229, 0.4066, 0.7613, 0.2967, 0.4250, 0.2167, 0.5925, 0.5350]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.01048219391668681
step: 17
running loss: 0.0006165996421580477
Train Steps: 17/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6197, 0.4091, 0.8800, 0.4783, 0.3538, 0.4767, 0.5950, 0.5550],
[0.6274, 0.4099, 0.8625, 0.3233, 0.4400, 0.1983, 0.5876, 0.4869],
[0.6200, 0.3961, 0.8461, 0.5497, 0.4142, 0.4577, 0.5892, 0.5402],
[0.6137, 0.4035, 0.8850, 0.4417, 0.3900, 0.4283, 0.5449, 0.5617],
[0.6339, 0.4123, 0.8638, 0.5367, 0.4075, 0.5467, 0.7517, 0.5436],
[0.6092, 0.4001, 0.8638, 0.4867, 0.4288, 0.5367, 0.5484, 0.5064],
[0.6246, 0.4028, 0.8738, 0.4867, 0.4088, 0.5667, 0.6362, 0.5200],
[ nan, nan, 0.6900, 0.1917, 0.3937, 0.2367, 0.5240, 0.5246]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[6.8750e-01, 4.4056e-01, 9.0004e-01, 4.9645e-01, 3.8054e-01, 4.6319e-01,
5.7499e-01, 5.7014e-01],
[7.5926e-01, 4.6508e-01, 8.8464e-01, 3.6296e-01, 4.5571e-01, 1.9916e-01,
5.7849e-01, 5.0027e-01],
[6.7550e-01, 4.1488e-01, 8.6852e-01, 5.8610e-01, 4.1434e-01, 4.5401e-01,
5.9690e-01, 5.4086e-01],
[6.8842e-01, 4.4305e-01, 8.9183e-01, 4.6133e-01, 3.9197e-01, 4.4541e-01,
5.1547e-01, 5.5174e-01],
[6.6559e-01, 4.2687e-01, 8.7362e-01, 5.4431e-01, 4.1048e-01, 5.4079e-01,
7.0992e-01, 5.4931e-01],
[6.8891e-01, 4.2708e-01, 8.7033e-01, 5.0001e-01, 4.3708e-01, 5.4782e-01,
5.0905e-01, 5.1298e-01],
[6.8797e-01, 4.2947e-01, 8.8706e-01, 5.1611e-01, 4.3128e-01, 5.7506e-01,
6.0441e-01, 5.3036e-01],
[5.4723e-02, 5.4600e-04, 7.2110e-01, 2.2487e-01, 4.1556e-01, 2.5140e-01,
5.0913e-01, 5.2042e-01]], device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6197, 0.4091, 0.8800, 0.4783, 0.3537, 0.4767, 0.5950, 0.5550],
[0.6274, 0.4099, 0.8625, 0.3233, 0.4400, 0.1983, 0.5876, 0.4869],
[0.6200, 0.3961, 0.8461, 0.5497, 0.4142, 0.4577, 0.5892, 0.5402],
[0.6137, 0.4035, 0.8850, 0.4417, 0.3900, 0.4283, 0.5449, 0.5617],
[0.6339, 0.4123, 0.8637, 0.5367, 0.4075, 0.5467, 0.7517, 0.5436],
[0.6092, 0.4001, 0.8637, 0.4867, 0.4288, 0.5367, 0.5484, 0.5064],
[0.6246, 0.4028, 0.8737, 0.4867, 0.4087, 0.5667, 0.6363, 0.5200],
[0.0000, 0.0000, 0.6900, 0.1917, 0.3938, 0.2367, 0.5240, 0.5246]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.011588190231123008
step: 18
running loss: 0.0006437883461735004
Train Steps: 18/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6189, 0.4049, 0.8888, 0.4417, 0.4213, 0.5200, 0.5988, 0.5633],
[0.6350, 0.4043, 0.8738, 0.5650, 0.3850, 0.4750, 0.6401, 0.4950],
[0.6197, 0.3986, 0.8800, 0.4617, 0.4188, 0.4783, 0.5687, 0.5550],
[0.6204, 0.4007, 0.7838, 0.2100, 0.4475, 0.1733, 0.5825, 0.5167],
[0.6022, 0.3994, 0.8025, 0.3350, 0.3350, 0.4400, 0.5565, 0.5025],
[0.6257, 0.4060, 0.8300, 0.2333, 0.4688, 0.2583, 0.7050, 0.5633],
[0.6156, 0.4125, 0.8850, 0.4833, 0.4550, 0.5817, 0.5765, 0.5084],
[0.6109, 0.3943, 0.8525, 0.4950, 0.4338, 0.4800, 0.5449, 0.5383]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6147, 0.3887, 0.8863, 0.4724, 0.4163, 0.5164, 0.5955, 0.5731],
[0.6220, 0.3836, 0.8847, 0.6055, 0.3916, 0.4640, 0.6227, 0.5119],
[0.6361, 0.4026, 0.8757, 0.4867, 0.4067, 0.4620, 0.5409, 0.5462],
[0.6163, 0.3732, 0.7845, 0.2437, 0.4469, 0.1474, 0.5833, 0.5044],
[0.6080, 0.3835, 0.8076, 0.3627, 0.3498, 0.4062, 0.5678, 0.5156],
[0.5851, 0.3613, 0.8399, 0.2569, 0.4622, 0.2293, 0.7007, 0.5473],
[0.6045, 0.3970, 0.8956, 0.5041, 0.4461, 0.5515, 0.5509, 0.5079],
[0.5926, 0.3736, 0.8545, 0.4993, 0.4274, 0.4609, 0.5187, 0.5249]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6189, 0.4049, 0.8888, 0.4417, 0.4212, 0.5200, 0.5987, 0.5633],
[0.6350, 0.4043, 0.8737, 0.5650, 0.3850, 0.4750, 0.6401, 0.4950],
[0.6197, 0.3986, 0.8800, 0.4617, 0.4187, 0.4783, 0.5688, 0.5550],
[0.6204, 0.4007, 0.7837, 0.2100, 0.4475, 0.1733, 0.5825, 0.5167],
[0.6022, 0.3994, 0.8025, 0.3350, 0.3350, 0.4400, 0.5565, 0.5025],
[0.6257, 0.4060, 0.8300, 0.2333, 0.4688, 0.2583, 0.7050, 0.5633],
[0.6155, 0.4124, 0.8850, 0.4833, 0.4550, 0.5817, 0.5765, 0.5084],
[0.6109, 0.3943, 0.8525, 0.4950, 0.4338, 0.4800, 0.5449, 0.5383]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.011935614966205321
step: 19
running loss: 0.0006281902613792274
Train Steps: 19/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6082, 0.4024, 0.8738, 0.4017, 0.3688, 0.3950, 0.5306, 0.5136],
[0.6183, 0.4076, 0.8838, 0.4517, 0.3813, 0.4483, 0.5775, 0.5633],
[0.6101, 0.3977, 0.8550, 0.5667, 0.3862, 0.4417, 0.5128, 0.4869],
[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.6133, 0.4094, 0.8495, 0.4028, 0.3588, 0.3200, 0.5003, 0.5407],
[0.6296, 0.3989, 0.9000, 0.4150, 0.3613, 0.3867, 0.6400, 0.5100],
[0.6202, 0.3983, 0.8555, 0.5429, 0.3842, 0.4370, 0.5866, 0.5398],
[0.6200, 0.3913, 0.8788, 0.5217, 0.4075, 0.5100, 0.6060, 0.4913]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6263, 0.3925, 0.8732, 0.3921, 0.3849, 0.3956, 0.5455, 0.4974],
[0.6533, 0.4087, 0.8859, 0.4419, 0.3958, 0.4445, 0.5874, 0.5733],
[0.6267, 0.3943, 0.8719, 0.5444, 0.4120, 0.4272, 0.5390, 0.4761],
[0.6193, 0.3927, 0.8507, 0.5603, 0.3943, 0.4842, 0.6691, 0.5243],
[0.5988, 0.3827, 0.8665, 0.3997, 0.3696, 0.3102, 0.5047, 0.5236],
[0.6087, 0.3742, 0.9097, 0.4067, 0.3816, 0.3709, 0.6709, 0.5170],
[0.6347, 0.3979, 0.8637, 0.5529, 0.3940, 0.4270, 0.6110, 0.5263],
[0.5986, 0.3606, 0.8703, 0.5145, 0.4212, 0.5126, 0.6077, 0.4776]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6082, 0.4024, 0.8737, 0.4017, 0.3688, 0.3950, 0.5306, 0.5136],
[0.6183, 0.4076, 0.8838, 0.4517, 0.3812, 0.4483, 0.5775, 0.5633],
[0.6101, 0.3977, 0.8550, 0.5667, 0.3862, 0.4417, 0.5128, 0.4869],
[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.6133, 0.4094, 0.8495, 0.4028, 0.3587, 0.3200, 0.5003, 0.5407],
[0.6296, 0.3989, 0.9000, 0.4150, 0.3613, 0.3867, 0.6400, 0.5100],
[0.6202, 0.3983, 0.8555, 0.5429, 0.3842, 0.4370, 0.5866, 0.5398],
[0.6199, 0.3913, 0.8788, 0.5217, 0.4075, 0.5100, 0.6060, 0.4913]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.012161795937572606
step: 20
running loss: 0.0006080897968786303
Train Steps: 20/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6259, 0.4133, 0.8200, 0.2317, 0.5025, 0.1533, 0.6250, 0.4947],
[0.6361, 0.4165, 0.9038, 0.5017, 0.3750, 0.3783, 0.6448, 0.5309],
[0.6205, 0.4081, 0.8950, 0.4017, 0.3788, 0.4700, 0.5963, 0.5667],
[0.6228, 0.4004, 0.8750, 0.5250, 0.3825, 0.5233, 0.6362, 0.5000],
[0.6224, 0.3964, 0.8225, 0.5717, 0.4150, 0.4617, 0.5775, 0.5267],
[0.6113, 0.4104, 0.8650, 0.4250, 0.3925, 0.5967, 0.5787, 0.5116],
[0.6346, 0.4165, 0.9138, 0.3983, 0.3875, 0.4317, 0.7469, 0.5471],
[0.6126, 0.4067, 0.8638, 0.5383, 0.4188, 0.4850, 0.5016, 0.5392]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5987, 0.3954, 0.8173, 0.2192, 0.4885, 0.1446, 0.6238, 0.4868],
[0.5582, 0.3632, 0.8971, 0.4730, 0.3848, 0.3590, 0.6402, 0.5108],
[0.6092, 0.3868, 0.8781, 0.3871, 0.3858, 0.4487, 0.6047, 0.5587],
[0.5910, 0.3785, 0.8639, 0.5020, 0.3823, 0.4878, 0.6334, 0.5027],
[0.5871, 0.3863, 0.8189, 0.5730, 0.4102, 0.4278, 0.5889, 0.5085],
[0.5511, 0.3794, 0.8619, 0.4024, 0.4057, 0.5856, 0.5989, 0.5047],
[0.6610, 0.4281, 0.9137, 0.3863, 0.4046, 0.4023, 0.7138, 0.5366],
[0.6162, 0.4093, 0.8579, 0.5548, 0.4164, 0.4813, 0.5180, 0.5221]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6259, 0.4132, 0.8200, 0.2317, 0.5025, 0.1533, 0.6250, 0.4947],
[0.6361, 0.4165, 0.9038, 0.5017, 0.3750, 0.3783, 0.6448, 0.5309],
[0.6205, 0.4081, 0.8950, 0.4017, 0.3787, 0.4700, 0.5962, 0.5667],
[0.6228, 0.4004, 0.8750, 0.5250, 0.3825, 0.5233, 0.6363, 0.5000],
[0.6224, 0.3964, 0.8225, 0.5717, 0.4150, 0.4617, 0.5775, 0.5267],
[0.6113, 0.4104, 0.8650, 0.4250, 0.3925, 0.5967, 0.5787, 0.5116],
[0.6346, 0.4165, 0.9137, 0.3983, 0.3875, 0.4317, 0.7469, 0.5471],
[0.6126, 0.4067, 0.8637, 0.5383, 0.4187, 0.4850, 0.5016, 0.5392]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.012637686988455243
step: 21
running loss: 0.0006017946184978687
Train Steps: 21/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6263, 0.4065, 0.9038, 0.4317, 0.3588, 0.4550, 0.6325, 0.5250],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3788, 0.4900, 0.7121, 0.5864],
[0.6260, 0.4106, 0.8025, 0.2583, 0.4550, 0.1867, 0.6281, 0.4869],
[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758],
[0.6186, 0.4154, 0.6825, 0.2633, 0.4150, 0.2300, 0.5713, 0.5517],
[ nan, nan, 0.6412, 0.1900, 0.4238, 0.1883, 0.5487, 0.5700],
[0.6266, 0.4070, 0.8712, 0.5600, 0.3713, 0.4783, 0.5775, 0.6100],
[0.6128, 0.4116, 0.8450, 0.4583, 0.3675, 0.4867, 0.5337, 0.5446]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6649, 0.4329, 0.9265, 0.4418, 0.3756, 0.4570, 0.6535, 0.5047],
[0.6515, 0.4245, 0.8946, 0.5157, 0.3987, 0.5116, 0.7217, 0.5745],
[0.6301, 0.4162, 0.8319, 0.2472, 0.4605, 0.1993, 0.6361, 0.4867],
[0.6229, 0.3967, 0.9096, 0.5021, 0.4142, 0.5424, 0.6717, 0.4770],
[0.6070, 0.4140, 0.7183, 0.2585, 0.4197, 0.2502, 0.5961, 0.5439],
[0.1898, 0.1257, 0.6954, 0.2147, 0.4328, 0.2136, 0.5403, 0.5564],
[0.6513, 0.4347, 0.8825, 0.5707, 0.3661, 0.5091, 0.6079, 0.5719],
[0.6652, 0.4476, 0.8582, 0.4722, 0.3887, 0.4969, 0.5615, 0.5470]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6263, 0.4065, 0.9038, 0.4317, 0.3587, 0.4550, 0.6325, 0.5250],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3787, 0.4900, 0.7121, 0.5864],
[0.6260, 0.4106, 0.8025, 0.2583, 0.4550, 0.1867, 0.6281, 0.4869],
[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758],
[0.6186, 0.4154, 0.6825, 0.2633, 0.4150, 0.2300, 0.5713, 0.5517],
[0.0000, 0.0000, 0.6413, 0.1900, 0.4238, 0.1883, 0.5487, 0.5700],
[0.6266, 0.4070, 0.8712, 0.5600, 0.3713, 0.4783, 0.5775, 0.6100],
[0.6128, 0.4116, 0.8450, 0.4583, 0.3675, 0.4867, 0.5337, 0.5446]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.013873206989956088
step: 22
running loss: 0.0006306003177252768
Train Steps: 22/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6124, 0.4069, 0.8314, 0.5001, 0.3738, 0.4650, 0.5167, 0.5402],
[0.6175, 0.3997, 0.6737, 0.2500, 0.4313, 0.1933, 0.5513, 0.5750],
[0.6277, 0.4057, 0.8300, 0.2650, 0.4363, 0.1850, 0.6140, 0.4823],
[0.6275, 0.4008, 0.8047, 0.2484, 0.4037, 0.2777, 0.6506, 0.5212],
[0.6203, 0.4076, 0.8611, 0.2878, 0.4050, 0.2554, 0.5907, 0.5496],
[ nan, nan, 0.7335, 0.2569, 0.3788, 0.2667, 0.5066, 0.5578],
[0.6250, 0.3993, 0.9138, 0.4333, 0.3763, 0.5217, 0.6995, 0.5320],
[0.6179, 0.4082, 0.6688, 0.2667, 0.3588, 0.3317, 0.5750, 0.5783]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6789, 0.4531, 0.8366, 0.5151, 0.3868, 0.4881, 0.5628, 0.5444],
[ 0.5932, 0.3999, 0.6746, 0.2478, 0.4322, 0.2141, 0.5409, 0.5745],
[ 0.6355, 0.4195, 0.8298, 0.2498, 0.4403, 0.2101, 0.6484, 0.4799],
[ 0.6366, 0.4174, 0.8163, 0.2554, 0.3985, 0.2939, 0.6574, 0.5077],
[ 0.6709, 0.4485, 0.8697, 0.2799, 0.4090, 0.2833, 0.6203, 0.5327],
[-0.0907, -0.0473, 0.7337, 0.2581, 0.3986, 0.2763, 0.5389, 0.5449],
[ 0.6507, 0.4282, 0.9220, 0.4580, 0.3847, 0.5605, 0.7420, 0.5411],
[ 0.6149, 0.4125, 0.6879, 0.2764, 0.3574, 0.3549, 0.5735, 0.5754]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6123, 0.4069, 0.8314, 0.5001, 0.3738, 0.4650, 0.5167, 0.5402],
[0.6175, 0.3997, 0.6737, 0.2500, 0.4313, 0.1933, 0.5512, 0.5750],
[0.6277, 0.4056, 0.8300, 0.2650, 0.4363, 0.1850, 0.6140, 0.4823],
[0.6275, 0.4008, 0.8047, 0.2484, 0.4037, 0.2777, 0.6506, 0.5212],
[0.6203, 0.4076, 0.8611, 0.2878, 0.4050, 0.2554, 0.5907, 0.5496],
[0.0000, 0.0000, 0.7335, 0.2569, 0.3787, 0.2667, 0.5066, 0.5578],
[0.6250, 0.3993, 0.9137, 0.4333, 0.3762, 0.5217, 0.6995, 0.5320],
[0.6179, 0.4082, 0.6687, 0.2667, 0.3587, 0.3317, 0.5750, 0.5783]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.014488388042082079
step: 23
running loss: 0.0006299299148731338
Train Steps: 23/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6198, 0.4076, 0.7945, 0.2453, 0.4475, 0.1871, 0.5897, 0.5350],
[0.6165, 0.4106, 0.7575, 0.1733, 0.3838, 0.2650, 0.5680, 0.5116],
[0.6262, 0.4052, 0.8888, 0.4700, 0.3675, 0.5117, 0.6350, 0.5233],
[0.6137, 0.4035, 0.8850, 0.4417, 0.3900, 0.4283, 0.5449, 0.5617],
[0.6055, 0.4015, 0.7425, 0.2033, 0.4113, 0.1883, 0.5217, 0.4823],
[0.6263, 0.4233, 0.7924, 0.4626, 0.3788, 0.2883, 0.5573, 0.6047],
[0.6265, 0.4251, 0.7113, 0.3550, 0.4375, 0.2117, 0.5587, 0.6118],
[0.6289, 0.4032, 0.8419, 0.5446, 0.4075, 0.5017, 0.6312, 0.5117]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6425, 0.4334, 0.7857, 0.2444, 0.4534, 0.2241, 0.6116, 0.5370],
[0.5337, 0.3651, 0.7608, 0.1682, 0.3684, 0.2772, 0.5912, 0.5040],
[0.6076, 0.4188, 0.9171, 0.4704, 0.3646, 0.5334, 0.6596, 0.5171],
[0.5587, 0.3836, 0.8954, 0.4398, 0.3733, 0.4680, 0.5639, 0.5459],
[0.4811, 0.3287, 0.7080, 0.1976, 0.3847, 0.2021, 0.5528, 0.4906],
[0.5850, 0.4175, 0.8096, 0.4730, 0.3751, 0.3225, 0.5790, 0.6054],
[0.5410, 0.3818, 0.7291, 0.3556, 0.4151, 0.2339, 0.5605, 0.6092],
[0.6152, 0.3929, 0.8487, 0.5331, 0.3923, 0.5295, 0.6696, 0.5108]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6198, 0.4076, 0.7945, 0.2453, 0.4475, 0.1871, 0.5897, 0.5350],
[0.6165, 0.4106, 0.7575, 0.1733, 0.3837, 0.2650, 0.5680, 0.5116],
[0.6262, 0.4052, 0.8888, 0.4700, 0.3675, 0.5117, 0.6350, 0.5233],
[0.6137, 0.4035, 0.8850, 0.4417, 0.3900, 0.4283, 0.5449, 0.5617],
[0.6055, 0.4015, 0.7425, 0.2033, 0.4112, 0.1883, 0.5217, 0.4823],
[0.6263, 0.4232, 0.7924, 0.4626, 0.3787, 0.2883, 0.5573, 0.6047],
[0.6265, 0.4251, 0.7113, 0.3550, 0.4375, 0.2117, 0.5587, 0.6118],
[0.6289, 0.4031, 0.8419, 0.5446, 0.4075, 0.5017, 0.6313, 0.5117]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.015468385492567904
step: 24
running loss: 0.0006445160621903293
Train Steps: 24/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6284, 0.4093, 0.8900, 0.4700, 0.3650, 0.3850, 0.6212, 0.5167],
[0.6113, 0.4006, 0.8700, 0.5350, 0.3638, 0.3767, 0.5097, 0.4882],
[0.6086, 0.3940, 0.8712, 0.4783, 0.4025, 0.4900, 0.5498, 0.5390],
[0.6201, 0.4116, 0.8725, 0.4733, 0.3700, 0.3217, 0.5386, 0.5767],
[0.6307, 0.4029, 0.8650, 0.5200, 0.3763, 0.4017, 0.7311, 0.5366],
[0.6197, 0.3986, 0.8800, 0.4617, 0.4188, 0.4783, 0.5687, 0.5550],
[0.6300, 0.4013, 0.8938, 0.5350, 0.3675, 0.4600, 0.6456, 0.4973],
[0.6162, 0.4014, 0.8800, 0.5333, 0.3750, 0.4817, 0.5988, 0.5283]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6276, 0.4176, 0.8725, 0.4386, 0.3636, 0.3857, 0.6137, 0.5281],
[0.5841, 0.3924, 0.8455, 0.4871, 0.3654, 0.3801, 0.5033, 0.5044],
[0.5597, 0.3609, 0.8477, 0.4645, 0.4077, 0.4724, 0.5645, 0.5286],
[0.5953, 0.3937, 0.8515, 0.4216, 0.3513, 0.3099, 0.5330, 0.5782],
[0.6220, 0.4098, 0.8538, 0.4849, 0.3751, 0.3998, 0.7113, 0.5320],
[0.6160, 0.4092, 0.8647, 0.4288, 0.4002, 0.4723, 0.5555, 0.5552],
[0.6098, 0.3939, 0.8777, 0.4970, 0.3560, 0.4419, 0.6439, 0.5046],
[0.5940, 0.3962, 0.8593, 0.5128, 0.3781, 0.4755, 0.5813, 0.5490]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6284, 0.4092, 0.8900, 0.4700, 0.3650, 0.3850, 0.6212, 0.5167],
[0.6113, 0.4006, 0.8700, 0.5350, 0.3638, 0.3767, 0.5097, 0.4882],
[0.6086, 0.3940, 0.8712, 0.4783, 0.4025, 0.4900, 0.5498, 0.5390],
[0.6201, 0.4116, 0.8725, 0.4733, 0.3700, 0.3217, 0.5386, 0.5767],
[0.6307, 0.4029, 0.8650, 0.5200, 0.3762, 0.4017, 0.7311, 0.5366],
[0.6197, 0.3986, 0.8800, 0.4617, 0.4187, 0.4783, 0.5688, 0.5550],
[0.6300, 0.4013, 0.8938, 0.5350, 0.3675, 0.4600, 0.6456, 0.4973],
[0.6162, 0.4014, 0.8800, 0.5333, 0.3750, 0.4817, 0.5987, 0.5283]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.015839603831409477
step: 25
running loss: 0.000633584153256379
Train Steps: 25/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6300, 0.4133, 0.8538, 0.2167, 0.5587, 0.2250, 0.7390, 0.5413],
[0.6083, 0.3957, 0.8638, 0.4950, 0.4363, 0.5083, 0.5346, 0.4980],
[0.6075, 0.4000, 0.8513, 0.5183, 0.4510, 0.5329, 0.5180, 0.5280],
[0.6271, 0.4040, 0.9138, 0.3750, 0.4625, 0.2617, 0.7232, 0.5413],
[0.6260, 0.4153, 0.9000, 0.4533, 0.4025, 0.2633, 0.6223, 0.4967],
[0.6275, 0.4111, 0.8463, 0.2617, 0.4487, 0.1983, 0.6211, 0.4904],
[0.6264, 0.4067, 0.9050, 0.4183, 0.3775, 0.4600, 0.6308, 0.4862],
[0.6257, 0.4167, 0.8775, 0.3433, 0.3563, 0.4133, 0.6200, 0.5667]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5226, 0.3504, 0.8105, 0.2154, 0.5130, 0.2438, 0.6988, 0.5625],
[0.5402, 0.3682, 0.8372, 0.4816, 0.4074, 0.4962, 0.5079, 0.5018],
[0.5685, 0.3850, 0.8234, 0.5167, 0.4233, 0.5160, 0.4992, 0.5361],
[0.5714, 0.3812, 0.8884, 0.3620, 0.4291, 0.2457, 0.6756, 0.5418],
[0.6046, 0.4120, 0.8562, 0.4381, 0.3657, 0.2545, 0.5891, 0.5079],
[0.5323, 0.3624, 0.7989, 0.2456, 0.4330, 0.1772, 0.5702, 0.5084],
[0.5645, 0.3777, 0.8732, 0.3930, 0.3376, 0.4368, 0.5953, 0.5110],
[0.5504, 0.3856, 0.8446, 0.3207, 0.3229, 0.3875, 0.5939, 0.5799]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6300, 0.4133, 0.8537, 0.2167, 0.5587, 0.2250, 0.7390, 0.5413],
[0.6083, 0.3957, 0.8637, 0.4950, 0.4363, 0.5083, 0.5346, 0.4980],
[0.6075, 0.4000, 0.8512, 0.5183, 0.4510, 0.5329, 0.5180, 0.5280],
[0.6271, 0.4040, 0.9137, 0.3750, 0.4625, 0.2617, 0.7232, 0.5413],
[0.6260, 0.4153, 0.9000, 0.4533, 0.4025, 0.2633, 0.6223, 0.4967],
[0.6275, 0.4111, 0.8462, 0.2617, 0.4487, 0.1983, 0.6211, 0.4904],
[0.6264, 0.4067, 0.9050, 0.4183, 0.3775, 0.4600, 0.6308, 0.4862],
[0.6257, 0.4167, 0.8775, 0.3433, 0.3562, 0.4133, 0.6200, 0.5667]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.01718238960893359
step: 26
running loss: 0.0006608611388051381
Train Steps: 26/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6076, 0.3953, 0.8125, 0.3917, 0.3525, 0.4083, 0.5346, 0.4954],
[ nan, nan, 0.6935, 0.1930, 0.4150, 0.2250, 0.5450, 0.5650],
[0.6091, 0.3997, 0.8314, 0.4334, 0.3788, 0.4550, 0.5213, 0.5656],
[0.6193, 0.4079, 0.7288, 0.2500, 0.4250, 0.2550, 0.5989, 0.6266],
[0.6055, 0.4015, 0.7425, 0.2033, 0.4113, 0.1883, 0.5217, 0.4823],
[0.6254, 0.3993, 0.8988, 0.4767, 0.3987, 0.5517, 0.6955, 0.5285],
[0.6259, 0.4156, 0.8812, 0.3183, 0.4775, 0.1867, 0.6219, 0.4960],
[0.6114, 0.4018, 0.7213, 0.1967, 0.3763, 0.2700, 0.5875, 0.5533]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6554, 0.4223, 0.8275, 0.4110, 0.3327, 0.3789, 0.5315, 0.5074],
[-0.0383, -0.0347, 0.6959, 0.2131, 0.4342, 0.2363, 0.5394, 0.5475],
[ 0.7011, 0.4454, 0.8374, 0.4684, 0.3629, 0.4386, 0.5320, 0.5673],
[ 0.6363, 0.4132, 0.7260, 0.2594, 0.4300, 0.2263, 0.5920, 0.6204],
[ 0.6163, 0.4085, 0.7112, 0.2127, 0.3985, 0.1573, 0.5243, 0.5062],
[ 0.5961, 0.3852, 0.9198, 0.5011, 0.4065, 0.5625, 0.6961, 0.5370],
[ 0.7267, 0.4630, 0.8801, 0.3093, 0.4681, 0.1737, 0.6029, 0.5127],
[ 0.5984, 0.3974, 0.7103, 0.1963, 0.3715, 0.2508, 0.5763, 0.5615]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6076, 0.3952, 0.8125, 0.3917, 0.3525, 0.4083, 0.5346, 0.4954],
[0.0000, 0.0000, 0.6935, 0.1930, 0.4150, 0.2250, 0.5450, 0.5650],
[0.6091, 0.3997, 0.8314, 0.4334, 0.3787, 0.4550, 0.5213, 0.5656],
[0.6193, 0.4078, 0.7287, 0.2500, 0.4250, 0.2550, 0.5989, 0.6266],
[0.6055, 0.4015, 0.7425, 0.2033, 0.4112, 0.1883, 0.5217, 0.4823],
[0.6254, 0.3993, 0.8988, 0.4767, 0.3988, 0.5517, 0.6955, 0.5285],
[0.6259, 0.4156, 0.8813, 0.3183, 0.4775, 0.1867, 0.6219, 0.4960],
[0.6114, 0.4018, 0.7212, 0.1967, 0.3762, 0.2700, 0.5875, 0.5533]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.01784341588790994
step: 27
running loss: 0.0006608672551077756
Train Steps: 27/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6286, 0.4078, 0.8063, 0.2267, 0.4788, 0.1533, 0.5953, 0.4913],
[ nan, nan, 0.6935, 0.1930, 0.4150, 0.2250, 0.5450, 0.5650],
[0.6085, 0.4008, 0.8588, 0.5200, 0.4959, 0.4977, 0.5175, 0.5283],
[0.6276, 0.4235, 0.8888, 0.5333, 0.3800, 0.3117, 0.5427, 0.6164],
[0.6198, 0.4076, 0.7945, 0.2453, 0.4475, 0.1871, 0.5897, 0.5350],
[0.6180, 0.4064, 0.7200, 0.2467, 0.4275, 0.2367, 0.5963, 0.6217],
[ nan, nan, 0.6688, 0.2513, 0.4113, 0.2117, 0.5193, 0.5933],
[0.6296, 0.4060, 0.9100, 0.3267, 0.4726, 0.3367, 0.7446, 0.5355]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.7125, 0.4531, 0.7847, 0.2330, 0.4667, 0.1434, 0.5637, 0.4987],
[ 0.0361, 0.0144, 0.6946, 0.1977, 0.4312, 0.2426, 0.5346, 0.5346],
[ 0.7027, 0.4471, 0.8598, 0.5141, 0.4767, 0.4845, 0.5079, 0.5195],
[ 0.6661, 0.4406, 0.8856, 0.5504, 0.3870, 0.3181, 0.5491, 0.5983],
[ 0.7124, 0.4633, 0.7861, 0.2478, 0.4556, 0.1856, 0.5815, 0.5314],
[ 0.7486, 0.4859, 0.7194, 0.2394, 0.4215, 0.1986, 0.5841, 0.6084],
[-0.0305, -0.0297, 0.6597, 0.2384, 0.4110, 0.2072, 0.5175, 0.5639],
[ 0.6786, 0.4400, 0.8910, 0.3322, 0.4522, 0.3354, 0.7192, 0.5160]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6286, 0.4078, 0.8062, 0.2267, 0.4787, 0.1533, 0.5953, 0.4913],
[0.0000, 0.0000, 0.6935, 0.1930, 0.4150, 0.2250, 0.5450, 0.5650],
[0.6084, 0.4008, 0.8587, 0.5200, 0.4959, 0.4977, 0.5175, 0.5283],
[0.6276, 0.4235, 0.8888, 0.5333, 0.3800, 0.3117, 0.5427, 0.6164],
[0.6198, 0.4076, 0.7945, 0.2453, 0.4475, 0.1871, 0.5897, 0.5350],
[0.6180, 0.4064, 0.7200, 0.2467, 0.4275, 0.2367, 0.5962, 0.6217],
[0.0000, 0.0000, 0.6688, 0.2513, 0.4112, 0.2117, 0.5193, 0.5933],
[0.6296, 0.4060, 0.9100, 0.3267, 0.4726, 0.3367, 0.7446, 0.5355]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.018996318729477935
step: 28
running loss: 0.0006784399546242119
Train Steps: 28/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6072, 0.4029, 0.7037, 0.2150, 0.3912, 0.2267, 0.5516, 0.5507],
[0.6277, 0.4083, 0.8350, 0.2717, 0.4562, 0.1800, 0.5918, 0.4878],
[0.6200, 0.3993, 0.8639, 0.3687, 0.3658, 0.3139, 0.6002, 0.5374],
[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334],
[0.6192, 0.4128, 0.8513, 0.5617, 0.4200, 0.5267, 0.5850, 0.5633],
[0.6346, 0.4165, 0.9138, 0.3983, 0.3875, 0.4317, 0.7469, 0.5471],
[0.6259, 0.4133, 0.8200, 0.2317, 0.5025, 0.1533, 0.6250, 0.4947],
[0.6224, 0.4061, 0.8988, 0.4300, 0.3838, 0.4750, 0.6112, 0.5483]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5747, 0.3813, 0.6918, 0.2215, 0.3995, 0.2139, 0.5478, 0.5785],
[0.6207, 0.4144, 0.8046, 0.2775, 0.4792, 0.1880, 0.5633, 0.5005],
[0.5985, 0.3829, 0.8660, 0.3888, 0.3766, 0.3070, 0.5694, 0.5266],
[0.5662, 0.3804, 0.7525, 0.2375, 0.3794, 0.3052, 0.6041, 0.5262],
[0.5694, 0.3678, 0.8466, 0.5783, 0.4286, 0.4979, 0.5485, 0.5595],
[0.6115, 0.4068, 0.9104, 0.4118, 0.4048, 0.4170, 0.7017, 0.5510],
[0.6342, 0.4301, 0.8145, 0.2441, 0.5075, 0.1358, 0.6096, 0.5103],
[0.5751, 0.3817, 0.8953, 0.4413, 0.3908, 0.4685, 0.5948, 0.5521]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6072, 0.4029, 0.7038, 0.2150, 0.3913, 0.2267, 0.5516, 0.5507],
[0.6277, 0.4083, 0.8350, 0.2717, 0.4563, 0.1800, 0.5918, 0.4878],
[0.6200, 0.3993, 0.8639, 0.3687, 0.3658, 0.3139, 0.6002, 0.5374],
[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334],
[0.6192, 0.4128, 0.8512, 0.5617, 0.4200, 0.5267, 0.5850, 0.5633],
[0.6346, 0.4165, 0.9137, 0.3983, 0.3875, 0.4317, 0.7469, 0.5471],
[0.6259, 0.4132, 0.8200, 0.2317, 0.5025, 0.1533, 0.6250, 0.4947],
[0.6224, 0.4061, 0.8988, 0.4300, 0.3837, 0.4750, 0.6112, 0.5483]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.019415606089751236
step: 29
running loss: 0.000669503658267284
Train Steps: 29/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6117, 0.4018, 0.6562, 0.1967, 0.3738, 0.2550, 0.5280, 0.5103],
[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[ nan, nan, 0.8625, 0.2550, 0.5487, 0.2200, 0.7335, 0.5737],
[0.6175, 0.3997, 0.6737, 0.2500, 0.4313, 0.1933, 0.5513, 0.5750],
[ nan, nan, 0.8675, 0.2833, 0.5350, 0.1983, 0.6678, 0.5621],
[0.6193, 0.4108, 0.7438, 0.2700, 0.3650, 0.3683, 0.6238, 0.5717],
[0.6228, 0.4004, 0.8750, 0.5250, 0.3825, 0.5233, 0.6362, 0.5000],
[0.6162, 0.4134, 0.6700, 0.2467, 0.3962, 0.2533, 0.5737, 0.5467]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6897, 0.4506, 0.6948, 0.2281, 0.4008, 0.2410, 0.5203, 0.5133],
[0.7451, 0.4733, 0.8854, 0.5929, 0.4019, 0.4944, 0.6341, 0.5262],
[0.0708, 0.0346, 0.8714, 0.2453, 0.5403, 0.2397, 0.7223, 0.5470],
[0.6919, 0.4506, 0.7064, 0.2530, 0.4442, 0.1918, 0.5331, 0.5808],
[0.0642, 0.0430, 0.8695, 0.2792, 0.5340, 0.2003, 0.6744, 0.5507],
[0.6989, 0.4623, 0.7750, 0.2946, 0.3784, 0.3741, 0.6267, 0.5688],
[0.7815, 0.4923, 0.9183, 0.5498, 0.4017, 0.5253, 0.6147, 0.5207],
[0.7112, 0.4725, 0.7207, 0.2791, 0.4066, 0.2466, 0.5596, 0.5634]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6116, 0.4018, 0.6562, 0.1967, 0.3738, 0.2550, 0.5280, 0.5103],
[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.0000, 0.0000, 0.8625, 0.2550, 0.5487, 0.2200, 0.7335, 0.5737],
[0.6175, 0.3997, 0.6737, 0.2500, 0.4313, 0.1933, 0.5512, 0.5750],
[0.0000, 0.0000, 0.8675, 0.2833, 0.5350, 0.1983, 0.6678, 0.5621],
[0.6193, 0.4108, 0.7437, 0.2700, 0.3650, 0.3683, 0.6237, 0.5717],
[0.6228, 0.4004, 0.8750, 0.5250, 0.3825, 0.5233, 0.6363, 0.5000],
[0.6162, 0.4134, 0.6700, 0.2467, 0.3963, 0.2533, 0.5738, 0.5467]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.021278868938679807
step: 30
running loss: 0.0007092956312893269
Train Steps: 30/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6357, 0.4159, 0.8788, 0.5583, 0.3638, 0.4433, 0.6488, 0.5297],
[0.6212, 0.4171, 0.7875, 0.3633, 0.3813, 0.2933, 0.5675, 0.5700],
[0.6081, 0.3950, 0.8538, 0.4667, 0.3850, 0.4917, 0.5342, 0.4954],
[0.6136, 0.4117, 0.8700, 0.5167, 0.4188, 0.5083, 0.5147, 0.5495],
[0.6164, 0.4076, 0.8838, 0.4117, 0.3713, 0.5550, 0.6238, 0.5350],
[0.6284, 0.4093, 0.8900, 0.4700, 0.3650, 0.3850, 0.6212, 0.5167],
[0.6058, 0.3978, 0.8287, 0.3600, 0.3400, 0.4050, 0.5529, 0.5461],
[0.6284, 0.4127, 0.8538, 0.5867, 0.4363, 0.5083, 0.6038, 0.5433]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5884, 0.3731, 0.8906, 0.5048, 0.3881, 0.4043, 0.6788, 0.5305],
[0.6297, 0.4199, 0.7994, 0.3490, 0.3894, 0.2737, 0.6291, 0.5945],
[0.6037, 0.3834, 0.8661, 0.4282, 0.3997, 0.4526, 0.5736, 0.4915],
[0.5989, 0.3808, 0.8840, 0.5084, 0.4319, 0.4836, 0.5536, 0.5220],
[0.6533, 0.4188, 0.8890, 0.3762, 0.3981, 0.5358, 0.6787, 0.5290],
[0.6001, 0.3861, 0.8929, 0.4558, 0.3773, 0.3699, 0.6534, 0.5160],
[0.6126, 0.4025, 0.8269, 0.3528, 0.3623, 0.3757, 0.5925, 0.5358],
[0.6032, 0.3817, 0.8537, 0.5689, 0.4503, 0.4667, 0.6179, 0.5194]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6357, 0.4159, 0.8788, 0.5583, 0.3638, 0.4433, 0.6488, 0.5297],
[0.6212, 0.4171, 0.7875, 0.3633, 0.3812, 0.2933, 0.5675, 0.5700],
[0.6081, 0.3950, 0.8537, 0.4667, 0.3850, 0.4917, 0.5342, 0.4954],
[0.6136, 0.4117, 0.8700, 0.5167, 0.4187, 0.5083, 0.5147, 0.5495],
[0.6164, 0.4076, 0.8838, 0.4117, 0.3713, 0.5550, 0.6237, 0.5350],
[0.6284, 0.4092, 0.8900, 0.4700, 0.3650, 0.3850, 0.6212, 0.5167],
[0.6058, 0.3978, 0.8288, 0.3600, 0.3400, 0.4050, 0.5529, 0.5461],
[0.6284, 0.4127, 0.8537, 0.5867, 0.4363, 0.5083, 0.6037, 0.5433]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.021944493215414695
step: 31
running loss: 0.000707886877916603
Train Steps: 31/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6268, 0.4061, 0.8350, 0.2433, 0.4575, 0.2283, 0.6350, 0.5300],
[0.6161, 0.4024, 0.8838, 0.4583, 0.3688, 0.3733, 0.5311, 0.5344],
[0.6325, 0.4066, 0.8438, 0.5350, 0.3925, 0.5267, 0.7113, 0.5795],
[0.6199, 0.4071, 0.7600, 0.2117, 0.4037, 0.2767, 0.6138, 0.5550],
[0.6153, 0.4117, 0.8688, 0.5167, 0.4895, 0.5647, 0.5524, 0.5136],
[0.6199, 0.3952, 0.8573, 0.5374, 0.4075, 0.4687, 0.5942, 0.5377],
[0.6161, 0.4055, 0.8675, 0.3867, 0.3713, 0.4033, 0.5195, 0.5162],
[0.6261, 0.4066, 0.8325, 0.2150, 0.4763, 0.2667, 0.7002, 0.5633]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6376, 0.4051, 0.8445, 0.2461, 0.4565, 0.1849, 0.6426, 0.5119],
[0.5506, 0.3638, 0.8830, 0.4665, 0.3697, 0.3586, 0.5518, 0.5292],
[0.5575, 0.3506, 0.8518, 0.5144, 0.3972, 0.5224, 0.7341, 0.5738],
[0.5898, 0.3928, 0.7805, 0.2062, 0.4126, 0.2712, 0.6223, 0.5467],
[0.5837, 0.3926, 0.8823, 0.5018, 0.4803, 0.5185, 0.5774, 0.5102],
[0.5228, 0.3175, 0.8610, 0.5440, 0.4067, 0.4438, 0.6141, 0.5258],
[0.5061, 0.3396, 0.8566, 0.3850, 0.3814, 0.3897, 0.5234, 0.5217],
[0.6307, 0.4236, 0.8495, 0.2266, 0.4794, 0.2508, 0.7256, 0.5409]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6268, 0.4060, 0.8350, 0.2433, 0.4575, 0.2283, 0.6350, 0.5300],
[0.6161, 0.4024, 0.8838, 0.4583, 0.3688, 0.3733, 0.5311, 0.5344],
[0.6325, 0.4066, 0.8438, 0.5350, 0.3925, 0.5267, 0.7113, 0.5795],
[0.6199, 0.4071, 0.7600, 0.2117, 0.4038, 0.2767, 0.6137, 0.5550],
[0.6154, 0.4117, 0.8687, 0.5167, 0.4895, 0.5647, 0.5524, 0.5136],
[0.6199, 0.3952, 0.8573, 0.5374, 0.4075, 0.4687, 0.5942, 0.5377],
[0.6161, 0.4055, 0.8675, 0.3867, 0.3713, 0.4033, 0.5195, 0.5162],
[0.6261, 0.4066, 0.8325, 0.2150, 0.4762, 0.2667, 0.7002, 0.5633]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.022897559145349078
step: 32
running loss: 0.0007155487232921587
Train Steps: 32/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6223, 0.3990, 0.8037, 0.2800, 0.4000, 0.2283, 0.5864, 0.5208],
[0.6182, 0.3998, 0.8793, 0.4191, 0.3552, 0.4285, 0.6038, 0.5312],
[0.6156, 0.4125, 0.8850, 0.4833, 0.4550, 0.5817, 0.5765, 0.5084],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4012, 0.4633, 0.5338, 0.5767],
[0.6277, 0.4036, 0.8688, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742],
[0.6286, 0.4034, 0.8191, 0.2414, 0.4262, 0.2393, 0.6365, 0.5356],
[0.6296, 0.3989, 0.9000, 0.4150, 0.3613, 0.3867, 0.6400, 0.5100],
[0.6058, 0.3978, 0.8287, 0.3600, 0.3400, 0.4050, 0.5529, 0.5461]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6576, 0.4233, 0.7940, 0.2923, 0.3964, 0.2534, 0.6247, 0.5410],
[0.5724, 0.3634, 0.8504, 0.4078, 0.3608, 0.4618, 0.6095, 0.5409],
[0.6195, 0.4325, 0.8775, 0.4804, 0.4494, 0.5989, 0.6058, 0.5275],
[0.5582, 0.3695, 0.8496, 0.5030, 0.4034, 0.4863, 0.5666, 0.5961],
[0.5600, 0.3584, 0.8529, 0.3570, 0.3881, 0.2920, 0.6447, 0.4917],
[0.6144, 0.3968, 0.8115, 0.2539, 0.4409, 0.2646, 0.6695, 0.5365],
[0.5736, 0.3816, 0.8761, 0.4166, 0.3680, 0.4029, 0.6566, 0.5264],
[0.5960, 0.3976, 0.8047, 0.3775, 0.3493, 0.4274, 0.5664, 0.5595]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6223, 0.3990, 0.8037, 0.2800, 0.4000, 0.2283, 0.5864, 0.5208],
[0.6182, 0.3998, 0.8793, 0.4191, 0.3552, 0.4285, 0.6038, 0.5312],
[0.6155, 0.4124, 0.8850, 0.4833, 0.4550, 0.5817, 0.5765, 0.5084],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4013, 0.4633, 0.5337, 0.5767],
[0.6277, 0.4036, 0.8687, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742],
[0.6286, 0.4034, 0.8191, 0.2414, 0.4262, 0.2393, 0.6365, 0.5356],
[0.6296, 0.3989, 0.9000, 0.4150, 0.3613, 0.3867, 0.6400, 0.5100],
[0.6058, 0.3978, 0.8288, 0.3600, 0.3400, 0.4050, 0.5529, 0.5461]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.023489262952352874
step: 33
running loss: 0.0007117958470409961
Train Steps: 33/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6272, 0.4071, 0.8738, 0.5600, 0.3675, 0.3783, 0.5926, 0.4742],
[0.6293, 0.4024, 0.8750, 0.5000, 0.4012, 0.5733, 0.7121, 0.5633],
[0.6257, 0.4024, 0.8612, 0.5352, 0.4361, 0.5253, 0.6680, 0.5166],
[ nan, nan, 0.8488, 0.2300, 0.5563, 0.2100, 0.7390, 0.5679],
[0.6246, 0.4126, 0.8850, 0.4833, 0.4200, 0.5350, 0.6112, 0.5250],
[0.6186, 0.4060, 0.8750, 0.5050, 0.3538, 0.4367, 0.5813, 0.6083],
[0.6199, 0.3952, 0.8573, 0.5374, 0.4075, 0.4687, 0.5942, 0.5377],
[0.6265, 0.4088, 0.8025, 0.1850, 0.4163, 0.2500, 0.6290, 0.4947]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6593, 0.4331, 0.8618, 0.5456, 0.3639, 0.4010, 0.5979, 0.4803],
[0.6536, 0.4266, 0.8628, 0.4762, 0.3945, 0.5987, 0.6864, 0.5626],
[0.6165, 0.3938, 0.8499, 0.5151, 0.4208, 0.5274, 0.6455, 0.5208],
[0.1122, 0.0747, 0.8574, 0.2338, 0.5162, 0.2554, 0.7275, 0.5477],
[0.6545, 0.4259, 0.8812, 0.4674, 0.4134, 0.5498, 0.5881, 0.5204],
[0.6227, 0.4213, 0.8596, 0.4772, 0.3509, 0.4564, 0.5783, 0.6005],
[0.6466, 0.4088, 0.8482, 0.5273, 0.3951, 0.4719, 0.5904, 0.5376],
[0.6413, 0.4213, 0.8073, 0.1971, 0.4224, 0.2603, 0.6283, 0.5116]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6272, 0.4071, 0.8737, 0.5600, 0.3675, 0.3783, 0.5926, 0.4742],
[0.6293, 0.4024, 0.8750, 0.5000, 0.4013, 0.5733, 0.7121, 0.5633],
[0.6257, 0.4024, 0.8612, 0.5352, 0.4361, 0.5253, 0.6680, 0.5166],
[0.0000, 0.0000, 0.8487, 0.2300, 0.5562, 0.2100, 0.7390, 0.5679],
[0.6246, 0.4126, 0.8850, 0.4833, 0.4200, 0.5350, 0.6112, 0.5250],
[0.6186, 0.4060, 0.8750, 0.5050, 0.3537, 0.4367, 0.5813, 0.6083],
[0.6199, 0.3952, 0.8573, 0.5374, 0.4075, 0.4687, 0.5942, 0.5377],
[0.6265, 0.4088, 0.8025, 0.1850, 0.4162, 0.2500, 0.6290, 0.4947]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.02405052950780373
step: 34
running loss: 0.0007073685149354039
Train Steps: 34/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6081, 0.3950, 0.8538, 0.4667, 0.3850, 0.4917, 0.5342, 0.4954],
[ nan, nan, 0.8037, 0.2483, 0.3975, 0.2517, 0.5575, 0.5600],
[0.6202, 0.4054, 0.8892, 0.4428, 0.3642, 0.3249, 0.5840, 0.5426],
[0.6115, 0.4005, 0.8838, 0.3867, 0.3763, 0.4700, 0.5800, 0.5550],
[0.6234, 0.4023, 0.8888, 0.4633, 0.3975, 0.5767, 0.6400, 0.5183],
[0.6262, 0.4052, 0.8888, 0.4700, 0.3675, 0.5117, 0.6350, 0.5233],
[0.6239, 0.4206, 0.8750, 0.5400, 0.3688, 0.4850, 0.5737, 0.5700],
[0.6250, 0.4008, 0.8950, 0.4183, 0.3550, 0.4383, 0.6361, 0.4927]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6548, 0.4210, 0.8627, 0.4514, 0.3951, 0.4915, 0.5448, 0.4980],
[0.1056, 0.0795, 0.7924, 0.3010, 0.4140, 0.2797, 0.5885, 0.5713],
[0.6397, 0.4316, 0.8833, 0.4366, 0.3750, 0.3403, 0.6105, 0.5304],
[0.6451, 0.4234, 0.8708, 0.4025, 0.3790, 0.4824, 0.5783, 0.5597],
[0.6710, 0.4289, 0.8743, 0.4705, 0.4077, 0.5930, 0.6590, 0.5049],
[0.6303, 0.4196, 0.8991, 0.4671, 0.3868, 0.5141, 0.6538, 0.5146],
[0.6531, 0.4207, 0.8667, 0.5391, 0.3833, 0.5041, 0.6007, 0.5643],
[0.6968, 0.4398, 0.8925, 0.4197, 0.3636, 0.4451, 0.6342, 0.5185]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6081, 0.3950, 0.8537, 0.4667, 0.3850, 0.4917, 0.5342, 0.4954],
[0.0000, 0.0000, 0.8037, 0.2483, 0.3975, 0.2517, 0.5575, 0.5600],
[0.6202, 0.4054, 0.8892, 0.4428, 0.3642, 0.3249, 0.5840, 0.5426],
[0.6115, 0.4005, 0.8838, 0.3867, 0.3762, 0.4700, 0.5800, 0.5550],
[0.6234, 0.4023, 0.8888, 0.4633, 0.3975, 0.5767, 0.6400, 0.5183],
[0.6262, 0.4052, 0.8888, 0.4700, 0.3675, 0.5117, 0.6350, 0.5233],
[0.6239, 0.4206, 0.8750, 0.5400, 0.3688, 0.4850, 0.5738, 0.5700],
[0.6250, 0.4008, 0.8950, 0.4183, 0.3550, 0.4383, 0.6361, 0.4927]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0247619836445665
step: 35
running loss: 0.0007074852469876143
Train Steps: 35/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6199, 0.4071, 0.7600, 0.2117, 0.4037, 0.2767, 0.6138, 0.5550],
[0.6156, 0.4125, 0.8850, 0.4833, 0.4550, 0.5817, 0.5765, 0.5084],
[0.6275, 0.4111, 0.8463, 0.2617, 0.4487, 0.1983, 0.6211, 0.4904],
[0.6267, 0.4065, 0.8313, 0.2467, 0.4788, 0.1733, 0.6312, 0.5133],
[0.6124, 0.4075, 0.7696, 0.4153, 0.3475, 0.3767, 0.5157, 0.5427],
[0.6154, 0.4048, 0.7100, 0.2067, 0.4338, 0.1667, 0.5413, 0.5220],
[0.6249, 0.4138, 0.9038, 0.4517, 0.3862, 0.4917, 0.6138, 0.5333],
[0.6201, 0.4004, 0.8786, 0.5043, 0.3833, 0.5138, 0.5997, 0.5092]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5583, 0.3769, 0.7909, 0.2271, 0.3903, 0.3063, 0.6082, 0.5704],
[0.5810, 0.4007, 0.9030, 0.4943, 0.4276, 0.6022, 0.5849, 0.5148],
[0.5632, 0.3702, 0.8655, 0.2920, 0.4494, 0.2302, 0.6230, 0.5132],
[0.6146, 0.4037, 0.8404, 0.2668, 0.4663, 0.2104, 0.6326, 0.5392],
[0.5761, 0.3819, 0.8072, 0.4148, 0.3366, 0.4056, 0.5089, 0.5536],
[0.5267, 0.3407, 0.7181, 0.2295, 0.4272, 0.1918, 0.5570, 0.5498],
[0.5548, 0.3801, 0.8961, 0.4657, 0.3552, 0.5163, 0.6202, 0.5391],
[0.5590, 0.3516, 0.8754, 0.5194, 0.3642, 0.5391, 0.5913, 0.5152]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6199, 0.4071, 0.7600, 0.2117, 0.4038, 0.2767, 0.6137, 0.5550],
[0.6155, 0.4124, 0.8850, 0.4833, 0.4550, 0.5817, 0.5765, 0.5084],
[0.6275, 0.4111, 0.8462, 0.2617, 0.4487, 0.1983, 0.6211, 0.4904],
[0.6266, 0.4065, 0.8313, 0.2467, 0.4787, 0.1733, 0.6313, 0.5133],
[0.6124, 0.4075, 0.7696, 0.4153, 0.3475, 0.3767, 0.5157, 0.5427],
[0.6154, 0.4048, 0.7100, 0.2067, 0.4338, 0.1667, 0.5413, 0.5220],
[0.6249, 0.4138, 0.9038, 0.4517, 0.3862, 0.4917, 0.6137, 0.5333],
[0.6201, 0.4004, 0.8786, 0.5043, 0.3833, 0.5138, 0.5997, 0.5092]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.025636436403146945
step: 36
running loss: 0.0007121232334207485
Train Steps: 36/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6260, 0.4214, 0.8538, 0.5500, 0.3663, 0.3767, 0.5587, 0.5983],
[0.6226, 0.4098, 0.8912, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367],
[0.6111, 0.3995, 0.8788, 0.4567, 0.3813, 0.4833, 0.5450, 0.5700],
[0.6201, 0.4017, 0.8871, 0.4621, 0.3517, 0.4675, 0.5999, 0.5106],
[0.6206, 0.4123, 0.7175, 0.2400, 0.3887, 0.2933, 0.6225, 0.5750],
[0.6189, 0.3911, 0.8800, 0.4917, 0.3713, 0.4800, 0.6038, 0.4833],
[0.6339, 0.4102, 0.8588, 0.3133, 0.4425, 0.2117, 0.6417, 0.5089],
[0.6179, 0.3998, 0.8396, 0.3505, 0.3552, 0.3768, 0.6064, 0.5329]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5802, 0.3709, 0.8561, 0.5348, 0.3591, 0.4219, 0.5316, 0.5887],
[0.5363, 0.3499, 0.8974, 0.4331, 0.4099, 0.2639, 0.5611, 0.5330],
[0.5620, 0.3608, 0.8742, 0.4556, 0.3872, 0.5100, 0.5308, 0.5577],
[0.5790, 0.3515, 0.8831, 0.4553, 0.3560, 0.4888, 0.5747, 0.5238],
[0.5446, 0.3546, 0.7188, 0.2502, 0.3910, 0.3107, 0.6053, 0.5817],
[0.6499, 0.4162, 0.8837, 0.5015, 0.3725, 0.5004, 0.5665, 0.4842],
[0.6564, 0.4173, 0.8841, 0.3146, 0.4628, 0.2244, 0.6416, 0.4986],
[0.6285, 0.4154, 0.8605, 0.3613, 0.3461, 0.3816, 0.5735, 0.5304]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6260, 0.4214, 0.8537, 0.5500, 0.3663, 0.3767, 0.5587, 0.5983],
[0.6226, 0.4098, 0.8913, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367],
[0.6111, 0.3995, 0.8788, 0.4567, 0.3812, 0.4833, 0.5450, 0.5700],
[0.6201, 0.4017, 0.8871, 0.4621, 0.3517, 0.4675, 0.5999, 0.5106],
[0.6206, 0.4123, 0.7175, 0.2400, 0.3887, 0.2933, 0.6225, 0.5750],
[0.6189, 0.3911, 0.8800, 0.4917, 0.3713, 0.4800, 0.6037, 0.4833],
[0.6339, 0.4102, 0.8587, 0.3133, 0.4425, 0.2117, 0.6417, 0.5089],
[0.6179, 0.3998, 0.8396, 0.3505, 0.3552, 0.3768, 0.6064, 0.5329]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0263910611247411
step: 37
running loss: 0.0007132719222903
Train Steps: 37/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6263, 0.4065, 0.9038, 0.4317, 0.3588, 0.4550, 0.6325, 0.5250],
[0.6125, 0.3983, 0.8750, 0.4867, 0.4275, 0.4783, 0.5413, 0.5717],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4012, 0.4633, 0.5338, 0.5767],
[0.6236, 0.4081, 0.8575, 0.3000, 0.3713, 0.3033, 0.5550, 0.5633],
[0.6250, 0.4236, 0.8638, 0.3767, 0.4050, 0.3150, 0.5649, 0.5799],
[0.6109, 0.4036, 0.7188, 0.1750, 0.3850, 0.2550, 0.5863, 0.5567],
[0.6079, 0.3964, 0.7420, 0.2958, 0.3563, 0.2917, 0.5351, 0.4980],
[0.6136, 0.4085, 0.6688, 0.2317, 0.3862, 0.2367, 0.5517, 0.5783]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5990, 0.3769, 0.9140, 0.4488, 0.3714, 0.4375, 0.6351, 0.5066],
[0.6271, 0.3925, 0.8840, 0.5031, 0.4382, 0.4743, 0.5681, 0.5371],
[0.6133, 0.3925, 0.8837, 0.5092, 0.4141, 0.4641, 0.5364, 0.5583],
[0.5439, 0.3584, 0.8692, 0.3327, 0.3847, 0.2954, 0.5554, 0.5394],
[0.5175, 0.3475, 0.8748, 0.4092, 0.3998, 0.3059, 0.5479, 0.5673],
[0.5929, 0.3816, 0.7363, 0.2116, 0.3944, 0.2486, 0.5592, 0.5466],
[0.5964, 0.3888, 0.7736, 0.3105, 0.3548, 0.2785, 0.5229, 0.4887],
[0.5833, 0.3863, 0.6853, 0.2263, 0.3996, 0.2373, 0.5364, 0.5512]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6263, 0.4065, 0.9038, 0.4317, 0.3587, 0.4550, 0.6325, 0.5250],
[0.6125, 0.3983, 0.8750, 0.4867, 0.4275, 0.4783, 0.5412, 0.5717],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4013, 0.4633, 0.5337, 0.5767],
[0.6236, 0.4081, 0.8575, 0.3000, 0.3713, 0.3033, 0.5550, 0.5633],
[0.6250, 0.4236, 0.8637, 0.3767, 0.4050, 0.3150, 0.5649, 0.5799],
[0.6108, 0.4036, 0.7188, 0.1750, 0.3850, 0.2550, 0.5863, 0.5567],
[0.6079, 0.3964, 0.7420, 0.2958, 0.3562, 0.2917, 0.5351, 0.4980],
[0.6136, 0.4085, 0.6687, 0.2317, 0.3862, 0.2367, 0.5517, 0.5783]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.027080467421910726
step: 38
running loss: 0.0007126438795239665
Train Steps: 38/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6264, 0.4069, 0.7900, 0.1650, 0.4275, 0.2267, 0.6290, 0.4947],
[0.6289, 0.4081, 0.8720, 0.3487, 0.3900, 0.3183, 0.6703, 0.5376],
[0.6289, 0.4032, 0.8419, 0.5446, 0.4075, 0.5017, 0.6312, 0.5117],
[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383],
[0.6112, 0.4029, 0.8638, 0.4800, 0.4875, 0.5083, 0.5763, 0.5567],
[0.6257, 0.4060, 0.8300, 0.2333, 0.4688, 0.2583, 0.7050, 0.5633],
[0.6226, 0.4125, 0.8800, 0.4900, 0.4512, 0.5600, 0.6275, 0.5517],
[0.6115, 0.3998, 0.7063, 0.2383, 0.4037, 0.1950, 0.5320, 0.4993]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5684, 0.3738, 0.7840, 0.1812, 0.4079, 0.1931, 0.6037, 0.5029],
[0.5567, 0.3666, 0.8722, 0.3481, 0.3623, 0.2860, 0.6309, 0.5371],
[0.5954, 0.3750, 0.8283, 0.5332, 0.3828, 0.4742, 0.5910, 0.4946],
[0.5968, 0.3983, 0.8844, 0.4523, 0.4209, 0.5508, 0.5773, 0.5281],
[0.5925, 0.3815, 0.8645, 0.4634, 0.4638, 0.4607, 0.5284, 0.5370],
[0.6031, 0.3976, 0.8330, 0.2334, 0.4379, 0.1981, 0.6606, 0.5579],
[0.5907, 0.3900, 0.8811, 0.4777, 0.4345, 0.5356, 0.5625, 0.5505],
[0.5687, 0.3794, 0.7224, 0.2112, 0.3896, 0.1612, 0.4978, 0.4984]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6264, 0.4069, 0.7900, 0.1650, 0.4275, 0.2267, 0.6290, 0.4947],
[0.6289, 0.4081, 0.8720, 0.3487, 0.3900, 0.3183, 0.6703, 0.5376],
[0.6289, 0.4031, 0.8419, 0.5446, 0.4075, 0.5017, 0.6313, 0.5117],
[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383],
[0.6112, 0.4029, 0.8637, 0.4800, 0.4875, 0.5083, 0.5763, 0.5567],
[0.6257, 0.4060, 0.8300, 0.2333, 0.4688, 0.2583, 0.7050, 0.5633],
[0.6226, 0.4125, 0.8800, 0.4900, 0.4512, 0.5600, 0.6275, 0.5517],
[0.6115, 0.3998, 0.7063, 0.2383, 0.4038, 0.1950, 0.5320, 0.4993]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.027903765891096555
step: 39
running loss: 0.0007154811766947835
Train Steps: 39/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6207, 0.4110, 0.8738, 0.5000, 0.4800, 0.5633, 0.6300, 0.5433],
[0.6125, 0.3974, 0.7725, 0.2517, 0.3538, 0.3317, 0.5887, 0.5500],
[0.6214, 0.4175, 0.7300, 0.2883, 0.4338, 0.2167, 0.5698, 0.5773],
[0.6329, 0.4196, 0.9238, 0.4583, 0.4263, 0.2933, 0.7343, 0.5748],
[0.6276, 0.4235, 0.8888, 0.5333, 0.3800, 0.3117, 0.5427, 0.6164],
[0.6234, 0.4023, 0.8888, 0.4633, 0.3975, 0.5767, 0.6400, 0.5183],
[0.6185, 0.4080, 0.8625, 0.3483, 0.3788, 0.2650, 0.5320, 0.5272],
[0.6226, 0.4001, 0.8438, 0.5733, 0.3862, 0.4250, 0.5750, 0.5283]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6086, 0.3948, 0.8793, 0.4601, 0.4524, 0.5521, 0.5810, 0.5304],
[0.6241, 0.4068, 0.7623, 0.2233, 0.3301, 0.3224, 0.5753, 0.5376],
[0.5699, 0.3948, 0.7303, 0.2490, 0.4237, 0.1971, 0.5398, 0.5759],
[0.5910, 0.3813, 0.9273, 0.4244, 0.4138, 0.2584, 0.7003, 0.5499],
[0.6257, 0.4145, 0.8526, 0.4932, 0.3787, 0.3170, 0.5312, 0.5960],
[0.6313, 0.4051, 0.8683, 0.4292, 0.3831, 0.5610, 0.6172, 0.4978],
[0.6149, 0.4161, 0.8498, 0.3317, 0.3739, 0.2650, 0.5100, 0.5272],
[0.6453, 0.4217, 0.8295, 0.5290, 0.3750, 0.4164, 0.5556, 0.5208]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6207, 0.4110, 0.8737, 0.5000, 0.4800, 0.5633, 0.6300, 0.5433],
[0.6125, 0.3974, 0.7725, 0.2517, 0.3537, 0.3317, 0.5888, 0.5500],
[0.6214, 0.4175, 0.7300, 0.2883, 0.4338, 0.2167, 0.5698, 0.5773],
[0.6329, 0.4196, 0.9237, 0.4583, 0.4263, 0.2933, 0.7343, 0.5748],
[0.6276, 0.4235, 0.8888, 0.5333, 0.3800, 0.3117, 0.5427, 0.6164],
[0.6234, 0.4023, 0.8888, 0.4633, 0.3975, 0.5767, 0.6400, 0.5183],
[0.6186, 0.4080, 0.8625, 0.3483, 0.3787, 0.2650, 0.5320, 0.5272],
[0.6226, 0.4001, 0.8438, 0.5733, 0.3862, 0.4250, 0.5750, 0.5283]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.028414304062607698
step: 40
running loss: 0.0007103576015651924
Train Steps: 40/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6200, 0.4112, 0.8862, 0.4100, 0.3638, 0.4917, 0.6088, 0.6050],
[0.6277, 0.4029, 0.8250, 0.2433, 0.4325, 0.2100, 0.6366, 0.5207],
[0.6091, 0.3997, 0.8314, 0.4334, 0.3788, 0.4550, 0.5213, 0.5656],
[ nan, nan, 0.7612, 0.3250, 0.4037, 0.2533, 0.5438, 0.5767],
[0.6226, 0.4001, 0.8438, 0.5733, 0.3862, 0.4250, 0.5750, 0.5283],
[0.6085, 0.4005, 0.8400, 0.4317, 0.3763, 0.4750, 0.5476, 0.5058],
[0.6136, 0.4060, 0.8025, 0.3217, 0.3650, 0.3000, 0.5060, 0.5646],
[0.6132, 0.4118, 0.8200, 0.3633, 0.3563, 0.5400, 0.5787, 0.5136]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6467, 0.4431, 0.8648, 0.3886, 0.3671, 0.4597, 0.6357, 0.5992],
[0.6807, 0.4511, 0.8120, 0.2432, 0.4405, 0.1834, 0.6839, 0.5110],
[0.6613, 0.4373, 0.8320, 0.4391, 0.3748, 0.4331, 0.5437, 0.5581],
[0.2648, 0.1831, 0.7805, 0.2907, 0.4217, 0.2114, 0.5688, 0.5838],
[0.7139, 0.4862, 0.8317, 0.5578, 0.3945, 0.4067, 0.6070, 0.5315],
[0.6573, 0.4524, 0.8424, 0.4128, 0.3647, 0.4494, 0.5517, 0.5118],
[0.6732, 0.4647, 0.8023, 0.3019, 0.3642, 0.2834, 0.5257, 0.5534],
[0.6547, 0.4513, 0.8251, 0.3458, 0.3673, 0.4919, 0.6024, 0.5175]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6200, 0.4112, 0.8863, 0.4100, 0.3638, 0.4917, 0.6087, 0.6050],
[0.6277, 0.4029, 0.8250, 0.2433, 0.4325, 0.2100, 0.6366, 0.5207],
[0.6091, 0.3997, 0.8314, 0.4334, 0.3787, 0.4550, 0.5213, 0.5656],
[0.0000, 0.0000, 0.7613, 0.3250, 0.4038, 0.2533, 0.5437, 0.5767],
[0.6226, 0.4001, 0.8438, 0.5733, 0.3862, 0.4250, 0.5750, 0.5283],
[0.6084, 0.4005, 0.8400, 0.4317, 0.3762, 0.4750, 0.5476, 0.5058],
[0.6136, 0.4060, 0.8025, 0.3217, 0.3650, 0.3000, 0.5060, 0.5646],
[0.6132, 0.4118, 0.8200, 0.3633, 0.3562, 0.5400, 0.5787, 0.5136]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0026, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0026, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03098702679562848
step: 41
running loss: 0.0007557811413567922
Train Steps: 41/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6113, 0.4104, 0.8650, 0.4250, 0.3925, 0.5967, 0.5787, 0.5116],
[0.6205, 0.4004, 0.8938, 0.4883, 0.3663, 0.5000, 0.6357, 0.4947],
[0.6307, 0.4029, 0.8650, 0.5200, 0.3763, 0.4017, 0.7311, 0.5366],
[0.6204, 0.4007, 0.7838, 0.2100, 0.4475, 0.1733, 0.5825, 0.5167],
[ nan, nan, 0.8363, 0.3317, 0.3563, 0.3367, 0.5329, 0.5142],
[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466],
[0.6126, 0.3954, 0.8538, 0.4983, 0.4250, 0.4700, 0.5355, 0.5350],
[0.6193, 0.4165, 0.8838, 0.4700, 0.4150, 0.4867, 0.5427, 0.5261]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7133, 0.4949, 0.8636, 0.4180, 0.4097, 0.5950, 0.5953, 0.5434],
[0.7292, 0.4689, 0.8951, 0.4901, 0.3736, 0.5000, 0.6631, 0.5112],
[0.6799, 0.4530, 0.8630, 0.5163, 0.3925, 0.4040, 0.7449, 0.5381],
[0.6545, 0.4295, 0.7728, 0.1951, 0.4598, 0.1320, 0.6202, 0.5347],
[0.1823, 0.1531, 0.8082, 0.3131, 0.3363, 0.3036, 0.5638, 0.5512],
[0.6235, 0.4221, 0.7693, 0.3914, 0.3424, 0.4040, 0.5297, 0.5574],
[0.7180, 0.4684, 0.8529, 0.5158, 0.4348, 0.4772, 0.5545, 0.5509],
[0.6849, 0.4614, 0.8755, 0.4868, 0.4155, 0.4720, 0.5656, 0.5568]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6113, 0.4104, 0.8650, 0.4250, 0.3925, 0.5967, 0.5787, 0.5116],
[0.6205, 0.4004, 0.8938, 0.4883, 0.3663, 0.5000, 0.6357, 0.4947],
[0.6307, 0.4029, 0.8650, 0.5200, 0.3762, 0.4017, 0.7311, 0.5366],
[0.6204, 0.4007, 0.7837, 0.2100, 0.4475, 0.1733, 0.5825, 0.5167],
[0.0000, 0.0000, 0.8363, 0.3317, 0.3562, 0.3367, 0.5329, 0.5142],
[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466],
[0.6126, 0.3954, 0.8537, 0.4983, 0.4250, 0.4700, 0.5355, 0.5350],
[0.6193, 0.4165, 0.8838, 0.4700, 0.4150, 0.4867, 0.5427, 0.5261]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0021, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0021, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.033130172334495
step: 42
running loss: 0.0007888136270117858
Train Steps: 42/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6040, 0.4002, 0.7338, 0.2267, 0.3975, 0.2100, 0.5231, 0.4778],
[0.6223, 0.3990, 0.8037, 0.2800, 0.4000, 0.2283, 0.5864, 0.5208],
[0.6245, 0.4100, 0.7762, 0.2583, 0.4963, 0.1517, 0.5875, 0.5417],
[0.6254, 0.3993, 0.8988, 0.4767, 0.3987, 0.5517, 0.6955, 0.5285],
[0.6209, 0.3920, 0.8650, 0.5367, 0.4400, 0.5067, 0.6025, 0.4950],
[0.6175, 0.4013, 0.7734, 0.2783, 0.4475, 0.1786, 0.5790, 0.5351],
[0.6275, 0.4157, 0.8337, 0.5800, 0.3763, 0.4200, 0.5547, 0.6125],
[0.6203, 0.4073, 0.8189, 0.2398, 0.4400, 0.2054, 0.5929, 0.5501]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6053, 0.3980, 0.7228, 0.2082, 0.3935, 0.2359, 0.5442, 0.5130],
[0.5986, 0.3876, 0.7927, 0.2864, 0.3970, 0.2688, 0.5976, 0.5458],
[0.5661, 0.3729, 0.7679, 0.2413, 0.4758, 0.1661, 0.5989, 0.5626],
[0.6387, 0.4324, 0.9024, 0.4804, 0.4105, 0.5948, 0.7053, 0.5499],
[0.6400, 0.4180, 0.8542, 0.5340, 0.4257, 0.5459, 0.5904, 0.5136],
[0.6048, 0.4021, 0.7705, 0.2558, 0.4410, 0.1949, 0.5803, 0.5480],
[0.6067, 0.4071, 0.8136, 0.5844, 0.3786, 0.4786, 0.5582, 0.6415],
[0.5370, 0.3652, 0.8080, 0.2506, 0.4418, 0.2339, 0.6032, 0.5683]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6040, 0.4002, 0.7337, 0.2267, 0.3975, 0.2100, 0.5231, 0.4778],
[0.6223, 0.3990, 0.8037, 0.2800, 0.4000, 0.2283, 0.5864, 0.5208],
[0.6245, 0.4100, 0.7763, 0.2583, 0.4963, 0.1517, 0.5875, 0.5417],
[0.6254, 0.3993, 0.8988, 0.4767, 0.3988, 0.5517, 0.6955, 0.5285],
[0.6209, 0.3920, 0.8650, 0.5367, 0.4400, 0.5067, 0.6025, 0.4950],
[0.6175, 0.4013, 0.7734, 0.2783, 0.4475, 0.1786, 0.5790, 0.5351],
[0.6275, 0.4157, 0.8338, 0.5800, 0.3762, 0.4200, 0.5547, 0.6125],
[0.6203, 0.4073, 0.8189, 0.2398, 0.4400, 0.2054, 0.5929, 0.5501]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.033696947430144064
step: 43
running loss: 0.0007836499402359084
Train Steps: 43/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6263, 0.4057, 0.8800, 0.3833, 0.3650, 0.3717, 0.6375, 0.4804],
[0.6268, 0.4029, 0.8500, 0.2683, 0.3937, 0.3500, 0.6860, 0.5297],
[0.6336, 0.4086, 0.8900, 0.3950, 0.3900, 0.2950, 0.6504, 0.5066],
[0.6234, 0.4179, 0.7825, 0.3450, 0.3813, 0.2867, 0.5675, 0.5617],
[ nan, nan, 0.8850, 0.3000, 0.5363, 0.2250, 0.7343, 0.5771],
[0.6064, 0.4019, 0.8650, 0.4517, 0.4037, 0.5367, 0.5703, 0.5609],
[0.6350, 0.4144, 0.9250, 0.4100, 0.4125, 0.3750, 0.7129, 0.5945],
[0.6206, 0.4001, 0.8900, 0.3933, 0.3588, 0.3567, 0.5837, 0.5083]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6887, 0.4348, 0.8442, 0.4089, 0.3687, 0.3939, 0.6161, 0.4755],
[ 0.6412, 0.4167, 0.8052, 0.2971, 0.3953, 0.3711, 0.6636, 0.5303],
[ 0.7081, 0.4484, 0.8750, 0.4183, 0.4020, 0.3306, 0.6459, 0.5059],
[ 0.5995, 0.4066, 0.7609, 0.3685, 0.3983, 0.3026, 0.5671, 0.5638],
[-0.0731, -0.0399, 0.8660, 0.2882, 0.5323, 0.2049, 0.7043, 0.6052],
[ 0.6184, 0.4114, 0.8384, 0.4840, 0.4189, 0.5765, 0.5598, 0.5455],
[ 0.7184, 0.4611, 0.8971, 0.4411, 0.4320, 0.4057, 0.7127, 0.5755],
[ 0.6672, 0.4277, 0.8704, 0.4425, 0.3659, 0.3813, 0.5603, 0.5099]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6263, 0.4057, 0.8800, 0.3833, 0.3650, 0.3717, 0.6375, 0.4804],
[0.6268, 0.4029, 0.8500, 0.2683, 0.3938, 0.3500, 0.6860, 0.5297],
[0.6336, 0.4086, 0.8900, 0.3950, 0.3900, 0.2950, 0.6504, 0.5066],
[0.6234, 0.4179, 0.7825, 0.3450, 0.3812, 0.2867, 0.5675, 0.5617],
[0.0000, 0.0000, 0.8850, 0.3000, 0.5362, 0.2250, 0.7343, 0.5771],
[0.6064, 0.4019, 0.8650, 0.4517, 0.4038, 0.5367, 0.5703, 0.5609],
[0.6350, 0.4144, 0.9250, 0.4100, 0.4125, 0.3750, 0.7129, 0.5945],
[0.6206, 0.4001, 0.8900, 0.3933, 0.3587, 0.3567, 0.5838, 0.5083]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0345825739641441
step: 44
running loss: 0.0007859675900941842
Train Steps: 44/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.6311, 0.3998, 0.7975, 0.5767, 0.3838, 0.4850, 0.7327, 0.5343],
[0.6277, 0.4103, 0.8087, 0.5717, 0.4188, 0.4750, 0.5663, 0.6083],
[ nan, nan, 0.7625, 0.2433, 0.3713, 0.2867, 0.5235, 0.5220],
[0.6203, 0.4096, 0.8862, 0.4267, 0.3538, 0.4117, 0.6025, 0.5650],
[0.6180, 0.4064, 0.7200, 0.2467, 0.4275, 0.2367, 0.5963, 0.6217],
[0.6299, 0.4303, 0.7963, 0.3933, 0.4850, 0.2283, 0.5480, 0.6222],
[0.6193, 0.4108, 0.7425, 0.2350, 0.3887, 0.2750, 0.5900, 0.5717]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6366, 0.4079, 0.8650, 0.5747, 0.3955, 0.5086, 0.6662, 0.5088],
[0.6423, 0.4086, 0.8256, 0.5419, 0.3860, 0.4891, 0.7217, 0.5036],
[0.6544, 0.4121, 0.8499, 0.5703, 0.4315, 0.4819, 0.5847, 0.5896],
[0.1003, 0.0558, 0.7747, 0.2473, 0.3955, 0.2725, 0.5176, 0.5151],
[0.5841, 0.3731, 0.9133, 0.4263, 0.3761, 0.4109, 0.6111, 0.5613],
[0.5823, 0.3797, 0.7245, 0.2530, 0.4314, 0.2382, 0.6005, 0.5880],
[0.6369, 0.4191, 0.8270, 0.3852, 0.4887, 0.2643, 0.5677, 0.5828],
[0.6239, 0.3974, 0.7727, 0.2497, 0.3892, 0.2870, 0.6044, 0.5587]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.6311, 0.3998, 0.7975, 0.5767, 0.3837, 0.4850, 0.7327, 0.5343],
[0.6277, 0.4103, 0.8087, 0.5717, 0.4187, 0.4750, 0.5663, 0.6083],
[0.0000, 0.0000, 0.7625, 0.2433, 0.3713, 0.2867, 0.5235, 0.5220],
[0.6203, 0.4096, 0.8863, 0.4267, 0.3537, 0.4117, 0.6025, 0.5650],
[0.6180, 0.4064, 0.7200, 0.2467, 0.4275, 0.2367, 0.5962, 0.6217],
[0.6299, 0.4303, 0.7962, 0.3933, 0.4850, 0.2283, 0.5480, 0.6222],
[0.6193, 0.4108, 0.7425, 0.2350, 0.3887, 0.2750, 0.5900, 0.5717]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03513337757613044
step: 45
running loss: 0.0007807417239140098
Train Steps: 45/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6179, 0.4040, 0.7412, 0.1850, 0.3825, 0.2783, 0.5837, 0.5600],
[ nan, nan, 0.7335, 0.2569, 0.3788, 0.2667, 0.5066, 0.5578],
[0.6300, 0.4013, 0.8938, 0.5350, 0.3675, 0.4600, 0.6456, 0.4973],
[0.6277, 0.4083, 0.8350, 0.2717, 0.4562, 0.1800, 0.5918, 0.4878],
[0.6201, 0.4102, 0.7288, 0.2417, 0.4150, 0.2383, 0.6100, 0.5500],
[0.6260, 0.4253, 0.8938, 0.4400, 0.3675, 0.3650, 0.5675, 0.5767],
[0.6254, 0.4076, 0.8700, 0.3267, 0.4150, 0.3083, 0.7050, 0.5609],
[0.6193, 0.4108, 0.7438, 0.2700, 0.3650, 0.3683, 0.6238, 0.5717]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6316, 0.4101, 0.7578, 0.2223, 0.4062, 0.2772, 0.5956, 0.5518],
[0.0738, 0.0471, 0.7439, 0.2771, 0.4110, 0.2470, 0.5182, 0.5831],
[0.6456, 0.3919, 0.9053, 0.5674, 0.3980, 0.4672, 0.6566, 0.4862],
[0.5411, 0.3353, 0.8373, 0.2930, 0.4931, 0.2127, 0.6068, 0.4882],
[0.6293, 0.3939, 0.7605, 0.2568, 0.4241, 0.2575, 0.6009, 0.5605],
[0.6253, 0.3865, 0.9118, 0.4759, 0.4028, 0.3663, 0.5960, 0.5789],
[0.6018, 0.3726, 0.8972, 0.3387, 0.4325, 0.2984, 0.7147, 0.5485],
[0.5627, 0.3518, 0.7641, 0.2984, 0.3925, 0.3745, 0.6367, 0.5628]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6179, 0.4040, 0.7412, 0.1850, 0.3825, 0.2783, 0.5838, 0.5600],
[0.0000, 0.0000, 0.7335, 0.2569, 0.3787, 0.2667, 0.5066, 0.5578],
[0.6300, 0.4013, 0.8938, 0.5350, 0.3675, 0.4600, 0.6456, 0.4973],
[0.6277, 0.4083, 0.8350, 0.2717, 0.4563, 0.1800, 0.5918, 0.4878],
[0.6201, 0.4102, 0.7287, 0.2417, 0.4150, 0.2383, 0.6100, 0.5500],
[0.6260, 0.4253, 0.8938, 0.4400, 0.3675, 0.3650, 0.5675, 0.5767],
[0.6254, 0.4076, 0.8700, 0.3267, 0.4150, 0.3083, 0.7050, 0.5609],
[0.6193, 0.4108, 0.7437, 0.2700, 0.3650, 0.3683, 0.6237, 0.5717]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03593642565829214
step: 46
running loss: 0.0007812266447454813
Train Steps: 46/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5413, 0.5683],
[0.6086, 0.3940, 0.8712, 0.4783, 0.4025, 0.4900, 0.5498, 0.5390],
[0.6229, 0.4066, 0.7612, 0.2967, 0.4250, 0.2167, 0.5925, 0.5350],
[0.6151, 0.4125, 0.8738, 0.4417, 0.3575, 0.3783, 0.5138, 0.5483],
[0.6187, 0.4104, 0.7126, 0.2069, 0.3950, 0.2517, 0.5913, 0.5683],
[0.6275, 0.4013, 0.8850, 0.2833, 0.4975, 0.2233, 0.7058, 0.5343],
[0.6197, 0.4091, 0.8800, 0.4783, 0.3538, 0.4767, 0.5950, 0.5550],
[0.6043, 0.4022, 0.6887, 0.1983, 0.3775, 0.2483, 0.5480, 0.5136]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5747, 0.3567, 0.8971, 0.5689, 0.3822, 0.3893, 0.5378, 0.5800],
[0.6002, 0.3645, 0.8841, 0.5117, 0.4197, 0.4937, 0.5724, 0.5320],
[0.5817, 0.3587, 0.7647, 0.2957, 0.4275, 0.2383, 0.5902, 0.5493],
[0.5815, 0.3735, 0.8794, 0.4650, 0.3519, 0.4093, 0.5114, 0.5625],
[0.5597, 0.3534, 0.7042, 0.2082, 0.3968, 0.2579, 0.5914, 0.5546],
[0.5851, 0.3438, 0.8778, 0.2913, 0.5018, 0.2339, 0.7276, 0.5327],
[0.5661, 0.3607, 0.9040, 0.5104, 0.3726, 0.4870, 0.6096, 0.5701],
[0.5549, 0.3462, 0.6927, 0.2035, 0.3760, 0.2776, 0.5572, 0.5165]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5412, 0.5683],
[0.6086, 0.3940, 0.8712, 0.4783, 0.4025, 0.4900, 0.5498, 0.5390],
[0.6229, 0.4066, 0.7613, 0.2967, 0.4250, 0.2167, 0.5925, 0.5350],
[0.6151, 0.4125, 0.8737, 0.4417, 0.3575, 0.3783, 0.5138, 0.5483],
[0.6187, 0.4103, 0.7126, 0.2069, 0.3950, 0.2517, 0.5913, 0.5683],
[0.6275, 0.4013, 0.8850, 0.2833, 0.4975, 0.2233, 0.7058, 0.5343],
[0.6197, 0.4091, 0.8800, 0.4783, 0.3537, 0.4767, 0.5950, 0.5550],
[0.6043, 0.4022, 0.6888, 0.1983, 0.3775, 0.2483, 0.5480, 0.5136]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03665601489774417
step: 47
running loss: 0.0007799152105903015
Train Steps: 47/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6286, 0.4086, 0.8408, 0.2801, 0.4163, 0.2800, 0.6725, 0.5393],
[0.6357, 0.4159, 0.8788, 0.5583, 0.3638, 0.4433, 0.6488, 0.5297],
[ nan, nan, 0.7515, 0.2708, 0.3987, 0.2267, 0.5162, 0.5567],
[0.6258, 0.4038, 0.8750, 0.4883, 0.3900, 0.5500, 0.6375, 0.5217],
[0.6169, 0.4052, 0.8742, 0.4779, 0.4288, 0.4917, 0.5763, 0.5617],
[0.6132, 0.4118, 0.8200, 0.3633, 0.3563, 0.5400, 0.5787, 0.5136],
[0.6364, 0.4165, 0.9088, 0.4367, 0.4075, 0.3150, 0.6448, 0.5297],
[0.6101, 0.4042, 0.7775, 0.2617, 0.3713, 0.2817, 0.5440, 0.5650]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6047, 0.3709, 0.8453, 0.2752, 0.4076, 0.2719, 0.6861, 0.5352],
[ 0.6716, 0.4370, 0.8774, 0.5461, 0.3600, 0.4168, 0.6446, 0.5402],
[-0.0229, -0.0220, 0.7496, 0.2566, 0.3989, 0.2077, 0.5066, 0.5667],
[ 0.5969, 0.3846, 0.8858, 0.5054, 0.4045, 0.5154, 0.6771, 0.5271],
[ 0.6160, 0.4008, 0.8757, 0.4793, 0.4367, 0.4673, 0.5788, 0.5784],
[ 0.6028, 0.3947, 0.8308, 0.3613, 0.3697, 0.4870, 0.5969, 0.5300],
[ 0.6021, 0.3922, 0.9019, 0.4375, 0.4062, 0.2941, 0.6574, 0.5230],
[ 0.5390, 0.3624, 0.7708, 0.2638, 0.3830, 0.2645, 0.5742, 0.5576]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6286, 0.4086, 0.8408, 0.2801, 0.4162, 0.2800, 0.6725, 0.5393],
[0.6357, 0.4159, 0.8788, 0.5583, 0.3638, 0.4433, 0.6488, 0.5297],
[0.0000, 0.0000, 0.7515, 0.2708, 0.3988, 0.2267, 0.5163, 0.5567],
[0.6258, 0.4038, 0.8750, 0.4883, 0.3900, 0.5500, 0.6375, 0.5217],
[0.6169, 0.4052, 0.8742, 0.4779, 0.4288, 0.4917, 0.5763, 0.5617],
[0.6132, 0.4118, 0.8200, 0.3633, 0.3562, 0.5400, 0.5787, 0.5136],
[0.6364, 0.4165, 0.9087, 0.4367, 0.4075, 0.3150, 0.6448, 0.5297],
[0.6101, 0.4042, 0.7775, 0.2617, 0.3713, 0.2817, 0.5440, 0.5650]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03708239090337884
step: 48
running loss: 0.0007725498104870591
Train Steps: 48/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6197, 0.3930, 0.8793, 0.4736, 0.4152, 0.5464, 0.6308, 0.5235],
[0.6109, 0.4041, 0.6975, 0.3167, 0.3513, 0.3383, 0.5153, 0.5319],
[0.6239, 0.4107, 0.8162, 0.2763, 0.3625, 0.3600, 0.5988, 0.5700],
[0.6307, 0.4045, 0.8025, 0.5833, 0.3775, 0.4867, 0.6892, 0.5459],
[0.6286, 0.3977, 0.9038, 0.4733, 0.3900, 0.4150, 0.7074, 0.5320],
[0.6275, 0.4013, 0.8850, 0.2833, 0.4975, 0.2233, 0.7058, 0.5343],
[0.6201, 0.4027, 0.8029, 0.2728, 0.4042, 0.2310, 0.5980, 0.5391],
[0.6204, 0.4049, 0.7975, 0.2700, 0.3937, 0.2567, 0.5700, 0.5183]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5392, 0.3393, 0.8966, 0.4762, 0.4050, 0.5081, 0.6086, 0.5354],
[0.5919, 0.4023, 0.7150, 0.2929, 0.3263, 0.3258, 0.4798, 0.5289],
[0.4935, 0.3126, 0.7921, 0.2691, 0.3399, 0.3424, 0.5831, 0.5745],
[0.6140, 0.4021, 0.8272, 0.5483, 0.3646, 0.4634, 0.6519, 0.5380],
[0.5755, 0.3592, 0.9023, 0.4503, 0.3514, 0.4043, 0.6516, 0.5154],
[0.5746, 0.3584, 0.8680, 0.2639, 0.4762, 0.2027, 0.6777, 0.5342],
[0.5433, 0.3501, 0.8058, 0.2698, 0.3872, 0.2175, 0.5622, 0.5379],
[0.6003, 0.4070, 0.7896, 0.2489, 0.3604, 0.2387, 0.5386, 0.5305]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6197, 0.3930, 0.8793, 0.4736, 0.4152, 0.5464, 0.6308, 0.5235],
[0.6109, 0.4041, 0.6975, 0.3167, 0.3512, 0.3383, 0.5153, 0.5319],
[0.6239, 0.4107, 0.8162, 0.2763, 0.3625, 0.3600, 0.5987, 0.5700],
[0.6307, 0.4045, 0.8025, 0.5833, 0.3775, 0.4867, 0.6892, 0.5459],
[0.6286, 0.3977, 0.9038, 0.4733, 0.3900, 0.4150, 0.7074, 0.5320],
[0.6275, 0.4013, 0.8850, 0.2833, 0.4975, 0.2233, 0.7058, 0.5343],
[0.6201, 0.4027, 0.8029, 0.2728, 0.4042, 0.2310, 0.5980, 0.5391],
[0.6204, 0.4049, 0.7975, 0.2700, 0.3938, 0.2567, 0.5700, 0.5183]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03830938627652358
step: 49
running loss: 0.0007818242097249711
Train Steps: 49/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6199, 0.4102, 0.8950, 0.4417, 0.4012, 0.5367, 0.6112, 0.5967],
[0.6210, 0.4164, 0.7202, 0.2930, 0.4025, 0.2483, 0.5687, 0.5567],
[0.6346, 0.4144, 0.9088, 0.4667, 0.3850, 0.4333, 0.7121, 0.5899],
[0.6236, 0.4081, 0.8575, 0.3000, 0.3713, 0.3033, 0.5550, 0.5633],
[ nan, nan, 0.7850, 0.2700, 0.4288, 0.1717, 0.5199, 0.4999],
[0.6283, 0.4283, 0.7477, 0.3542, 0.5125, 0.1917, 0.5500, 0.6167],
[0.6178, 0.4012, 0.8900, 0.4495, 0.3891, 0.5617, 0.5972, 0.4879],
[0.6228, 0.4119, 0.7938, 0.2233, 0.4674, 0.1773, 0.6188, 0.5433]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6319, 0.4052, 0.9060, 0.4367, 0.3820, 0.5091, 0.6136, 0.5904],
[0.5923, 0.3935, 0.7427, 0.2612, 0.3888, 0.2576, 0.5829, 0.5510],
[0.6742, 0.4459, 0.9098, 0.4459, 0.3704, 0.4277, 0.7321, 0.5875],
[0.6198, 0.4075, 0.8555, 0.2908, 0.3433, 0.2992, 0.5808, 0.5473],
[0.0068, 0.0069, 0.7769, 0.2453, 0.4023, 0.1820, 0.5361, 0.5231],
[0.5984, 0.4031, 0.7380, 0.3369, 0.4850, 0.1821, 0.5506, 0.6082],
[0.6052, 0.4033, 0.8811, 0.4277, 0.3689, 0.5446, 0.6375, 0.4999],
[0.5963, 0.3933, 0.7923, 0.1988, 0.4512, 0.1713, 0.6343, 0.5319]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6199, 0.4102, 0.8950, 0.4417, 0.4013, 0.5367, 0.6112, 0.5967],
[0.6210, 0.4164, 0.7202, 0.2930, 0.4025, 0.2483, 0.5688, 0.5567],
[0.6346, 0.4144, 0.9087, 0.4667, 0.3850, 0.4333, 0.7121, 0.5899],
[0.6236, 0.4081, 0.8575, 0.3000, 0.3713, 0.3033, 0.5550, 0.5633],
[0.0000, 0.0000, 0.7850, 0.2700, 0.4288, 0.1717, 0.5199, 0.4999],
[0.6283, 0.4283, 0.7477, 0.3542, 0.5125, 0.1917, 0.5500, 0.6167],
[0.6178, 0.4012, 0.8900, 0.4495, 0.3891, 0.5617, 0.5972, 0.4879],
[0.6228, 0.4119, 0.7937, 0.2233, 0.4674, 0.1773, 0.6187, 0.5433]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03863833627838176
step: 50
running loss: 0.0007727667255676352
Train Steps: 50/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6173, 0.4114, 0.7325, 0.2500, 0.4213, 0.1917, 0.5338, 0.5700],
[0.6164, 0.4066, 0.6625, 0.3033, 0.3775, 0.2967, 0.5725, 0.5833],
[ nan, nan, 0.8850, 0.2817, 0.5112, 0.2183, 0.7184, 0.5436],
[0.6257, 0.4167, 0.8775, 0.3433, 0.3563, 0.4133, 0.6200, 0.5667],
[0.6211, 0.3993, 0.7650, 0.1933, 0.4575, 0.1550, 0.5965, 0.4895],
[0.6284, 0.4127, 0.8538, 0.5867, 0.4363, 0.5083, 0.6038, 0.5433],
[0.6196, 0.4094, 0.7562, 0.2817, 0.3937, 0.3183, 0.6013, 0.6183],
[0.6201, 0.4098, 0.8575, 0.3617, 0.3700, 0.3550, 0.5988, 0.5667]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6040, 0.4282, 0.7308, 0.2059, 0.4077, 0.2071, 0.5314, 0.5556],
[ 0.6273, 0.4338, 0.6940, 0.2815, 0.3589, 0.2807, 0.5497, 0.5789],
[-0.0056, -0.0037, 0.8923, 0.2670, 0.4995, 0.2198, 0.7089, 0.5389],
[ 0.6117, 0.4112, 0.8859, 0.3281, 0.3341, 0.4142, 0.6316, 0.5609],
[ 0.6467, 0.4352, 0.7644, 0.1785, 0.4511, 0.1633, 0.5915, 0.4808],
[ 0.6760, 0.4614, 0.8418, 0.5814, 0.4076, 0.4921, 0.5650, 0.5409],
[ 0.6194, 0.4256, 0.7702, 0.2751, 0.3781, 0.3243, 0.6166, 0.6052],
[ 0.5795, 0.4023, 0.8600, 0.3549, 0.3603, 0.3462, 0.6070, 0.5654]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6173, 0.4114, 0.7325, 0.2500, 0.4212, 0.1917, 0.5337, 0.5700],
[0.6164, 0.4066, 0.6625, 0.3033, 0.3775, 0.2967, 0.5725, 0.5833],
[0.0000, 0.0000, 0.8850, 0.2817, 0.5113, 0.2183, 0.7184, 0.5436],
[0.6257, 0.4167, 0.8775, 0.3433, 0.3562, 0.4133, 0.6200, 0.5667],
[0.6211, 0.3993, 0.7650, 0.1933, 0.4575, 0.1550, 0.5965, 0.4895],
[0.6284, 0.4127, 0.8537, 0.5867, 0.4363, 0.5083, 0.6037, 0.5433],
[0.6196, 0.4094, 0.7563, 0.2817, 0.3938, 0.3183, 0.6012, 0.6183],
[0.6201, 0.4098, 0.8575, 0.3617, 0.3700, 0.3550, 0.5987, 0.5667]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03896989063650835
step: 51
running loss: 0.0007641155026766344
Train Steps: 51/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6214, 0.3982, 0.8938, 0.4517, 0.3663, 0.4083, 0.5863, 0.5050],
[0.6160, 0.4093, 0.8314, 0.4417, 0.3675, 0.4583, 0.5250, 0.5808],
[0.6279, 0.4050, 0.8025, 0.2200, 0.4313, 0.2733, 0.6820, 0.5320],
[0.6069, 0.3975, 0.8625, 0.5083, 0.4388, 0.5483, 0.5650, 0.4967],
[0.6256, 0.4199, 0.8638, 0.5800, 0.3987, 0.4383, 0.5600, 0.5950],
[0.6230, 0.4113, 0.7213, 0.1983, 0.4325, 0.2367, 0.6262, 0.5400],
[0.6270, 0.4267, 0.7150, 0.3317, 0.4900, 0.1817, 0.5560, 0.6183],
[0.6361, 0.4071, 0.9100, 0.4783, 0.3738, 0.3967, 0.6670, 0.5332]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6073, 0.4136, 0.8816, 0.4450, 0.3556, 0.4199, 0.5715, 0.5052],
[0.6147, 0.4262, 0.8284, 0.4442, 0.3397, 0.4541, 0.5100, 0.5697],
[0.6346, 0.4331, 0.7867, 0.2099, 0.4025, 0.2692, 0.6605, 0.5185],
[0.5712, 0.4087, 0.8530, 0.5211, 0.4311, 0.5627, 0.5652, 0.5148],
[0.5833, 0.4068, 0.8546, 0.5685, 0.3776, 0.4327, 0.5370, 0.6009],
[0.5960, 0.4159, 0.7190, 0.1794, 0.4325, 0.2432, 0.6347, 0.5452],
[0.5953, 0.4253, 0.6915, 0.2885, 0.4620, 0.1969, 0.5367, 0.5910],
[0.5961, 0.4056, 0.8904, 0.4810, 0.3547, 0.4024, 0.6478, 0.5261]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6214, 0.3982, 0.8938, 0.4517, 0.3663, 0.4083, 0.5863, 0.5050],
[0.6160, 0.4092, 0.8314, 0.4417, 0.3675, 0.4583, 0.5250, 0.5808],
[0.6279, 0.4050, 0.8025, 0.2200, 0.4313, 0.2733, 0.6820, 0.5320],
[0.6069, 0.3975, 0.8625, 0.5083, 0.4387, 0.5483, 0.5650, 0.4967],
[0.6256, 0.4199, 0.8637, 0.5800, 0.3988, 0.4383, 0.5600, 0.5950],
[0.6230, 0.4113, 0.7212, 0.1983, 0.4325, 0.2367, 0.6263, 0.5400],
[0.6270, 0.4266, 0.7150, 0.3317, 0.4900, 0.1817, 0.5560, 0.6183],
[0.6361, 0.4071, 0.9100, 0.4783, 0.3738, 0.3967, 0.6670, 0.5332]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03928698522213381
step: 52
running loss: 0.0007555189465794963
Train Steps: 52/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6307, 0.4060, 0.8950, 0.5183, 0.3750, 0.3850, 0.6338, 0.4938],
[0.6186, 0.3967, 0.7337, 0.1992, 0.4120, 0.2508, 0.6105, 0.5395],
[0.6075, 0.4000, 0.8513, 0.5183, 0.4510, 0.5329, 0.5180, 0.5280],
[0.6149, 0.4054, 0.6713, 0.2333, 0.4025, 0.2017, 0.5213, 0.5695],
[0.6211, 0.3993, 0.7650, 0.1933, 0.4575, 0.1550, 0.5965, 0.4895],
[0.6275, 0.4071, 0.8075, 0.2100, 0.4700, 0.1533, 0.6148, 0.4834],
[0.6161, 0.4099, 0.8738, 0.4383, 0.3788, 0.5483, 0.5605, 0.5019],
[ nan, nan, 0.7240, 0.2722, 0.3900, 0.2567, 0.5168, 0.5933]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6855, 0.4642, 0.8893, 0.5334, 0.3714, 0.3921, 0.6544, 0.5189],
[0.7078, 0.4839, 0.7207, 0.2155, 0.4106, 0.2417, 0.6140, 0.5604],
[0.5593, 0.3895, 0.8413, 0.5402, 0.4644, 0.5556, 0.5571, 0.5589],
[0.6221, 0.4285, 0.6530, 0.2349, 0.4115, 0.2204, 0.5106, 0.5732],
[0.6814, 0.4617, 0.7495, 0.1913, 0.4757, 0.1683, 0.6202, 0.5073],
[0.6239, 0.4233, 0.7985, 0.2182, 0.5043, 0.1667, 0.6382, 0.5138],
[0.6505, 0.4486, 0.8450, 0.4286, 0.3794, 0.5564, 0.5866, 0.5351],
[0.0618, 0.0508, 0.6994, 0.2725, 0.3897, 0.2711, 0.5051, 0.5950]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6307, 0.4060, 0.8950, 0.5183, 0.3750, 0.3850, 0.6338, 0.4938],
[0.6186, 0.3967, 0.7337, 0.1992, 0.4120, 0.2508, 0.6105, 0.5395],
[0.6075, 0.4000, 0.8512, 0.5183, 0.4510, 0.5329, 0.5180, 0.5280],
[0.6149, 0.4054, 0.6712, 0.2333, 0.4025, 0.2017, 0.5213, 0.5695],
[0.6211, 0.3993, 0.7650, 0.1933, 0.4575, 0.1550, 0.5965, 0.4895],
[0.6275, 0.4071, 0.8075, 0.2100, 0.4700, 0.1533, 0.6148, 0.4834],
[0.6161, 0.4099, 0.8737, 0.4383, 0.3787, 0.5483, 0.5605, 0.5019],
[0.0000, 0.0000, 0.7240, 0.2722, 0.3900, 0.2567, 0.5168, 0.5933]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.040181065662181936
step: 53
running loss: 0.0007581333143807913
Train Steps: 53/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6229, 0.4086, 0.7538, 0.2600, 0.4775, 0.1617, 0.5900, 0.5383],
[0.6265, 0.4091, 0.8950, 0.3533, 0.3600, 0.3967, 0.6295, 0.4901],
[0.6201, 0.4098, 0.8575, 0.3617, 0.3700, 0.3550, 0.5988, 0.5667],
[0.6216, 0.4167, 0.8588, 0.5583, 0.3975, 0.5167, 0.5775, 0.5667],
[0.6277, 0.4036, 0.8688, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742],
[0.6203, 0.4021, 0.8780, 0.5031, 0.3667, 0.3882, 0.5842, 0.5405],
[ nan, nan, 0.7612, 0.3250, 0.4037, 0.2533, 0.5438, 0.5767],
[0.6152, 0.4131, 0.6863, 0.2567, 0.3625, 0.3300, 0.5765, 0.5305]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7365, 0.4962, 0.7534, 0.2470, 0.4813, 0.1644, 0.5918, 0.5210],
[0.6629, 0.4288, 0.8927, 0.3460, 0.3785, 0.3965, 0.6518, 0.5165],
[0.6685, 0.4532, 0.8460, 0.3589, 0.3941, 0.3674, 0.6022, 0.5691],
[0.6363, 0.4391, 0.8478, 0.5446, 0.4133, 0.5225, 0.5803, 0.5728],
[0.6585, 0.4363, 0.8502, 0.3563, 0.4291, 0.2718, 0.6160, 0.4798],
[0.6618, 0.4396, 0.8653, 0.5108, 0.3825, 0.4054, 0.5755, 0.5395],
[0.0434, 0.0198, 0.7778, 0.3281, 0.4289, 0.2592, 0.5454, 0.5704],
[0.6542, 0.4441, 0.6695, 0.2451, 0.3776, 0.3397, 0.5739, 0.5523]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6229, 0.4086, 0.7538, 0.2600, 0.4775, 0.1617, 0.5900, 0.5383],
[0.6265, 0.4091, 0.8950, 0.3533, 0.3600, 0.3967, 0.6295, 0.4901],
[0.6201, 0.4098, 0.8575, 0.3617, 0.3700, 0.3550, 0.5987, 0.5667],
[0.6216, 0.4167, 0.8587, 0.5583, 0.3975, 0.5167, 0.5775, 0.5667],
[0.6277, 0.4036, 0.8687, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742],
[0.6203, 0.4020, 0.8780, 0.5031, 0.3667, 0.3882, 0.5842, 0.5405],
[0.0000, 0.0000, 0.7613, 0.3250, 0.4038, 0.2533, 0.5437, 0.5767],
[0.6152, 0.4131, 0.6862, 0.2567, 0.3625, 0.3300, 0.5765, 0.5305]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04089540946006309
step: 54
running loss: 0.0007573223974085758
Train Steps: 54/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6265, 0.4091, 0.8950, 0.3533, 0.3600, 0.3967, 0.6295, 0.4901],
[0.6246, 0.4028, 0.8738, 0.4867, 0.4088, 0.5667, 0.6362, 0.5200],
[ nan, nan, 0.7192, 0.2346, 0.4037, 0.2050, 0.5138, 0.5650],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3513, 0.4050, 0.6112, 0.5500],
[0.6250, 0.4110, 0.7238, 0.2067, 0.4263, 0.1883, 0.5625, 0.5633],
[0.6263, 0.4057, 0.8800, 0.3833, 0.3650, 0.3717, 0.6375, 0.4804],
[0.6133, 0.4094, 0.8495, 0.4028, 0.3588, 0.3200, 0.5003, 0.5407],
[0.6165, 0.4106, 0.7575, 0.1733, 0.3838, 0.2650, 0.5680, 0.5116]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6796, 0.4268, 0.9074, 0.3819, 0.3924, 0.3890, 0.6588, 0.5231],
[0.6585, 0.4226, 0.8758, 0.5104, 0.4502, 0.5876, 0.6470, 0.5290],
[0.0220, 0.0207, 0.7197, 0.2960, 0.4424, 0.2298, 0.4976, 0.5429],
[0.6749, 0.4446, 0.7745, 0.2926, 0.3850, 0.4026, 0.6171, 0.5571],
[0.6448, 0.4231, 0.7123, 0.2585, 0.4646, 0.1773, 0.5542, 0.5607],
[0.6679, 0.4259, 0.8739, 0.3943, 0.3975, 0.3687, 0.6295, 0.4941],
[0.6708, 0.4429, 0.8537, 0.4344, 0.3786, 0.3161, 0.5023, 0.5432],
[0.7364, 0.4848, 0.7535, 0.2071, 0.4139, 0.2637, 0.5635, 0.5158]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6265, 0.4091, 0.8950, 0.3533, 0.3600, 0.3967, 0.6295, 0.4901],
[0.6246, 0.4028, 0.8737, 0.4867, 0.4087, 0.5667, 0.6363, 0.5200],
[0.0000, 0.0000, 0.7192, 0.2346, 0.4038, 0.2050, 0.5138, 0.5650],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3512, 0.4050, 0.6112, 0.5500],
[0.6250, 0.4110, 0.7237, 0.2067, 0.4263, 0.1883, 0.5625, 0.5633],
[0.6263, 0.4057, 0.8800, 0.3833, 0.3650, 0.3717, 0.6375, 0.4804],
[0.6133, 0.4094, 0.8495, 0.4028, 0.3587, 0.3200, 0.5003, 0.5407],
[0.6165, 0.4106, 0.7575, 0.1733, 0.3837, 0.2650, 0.5680, 0.5116]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04186867403041106
step: 55
running loss: 0.0007612486187347464
Train Steps: 55/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6277, 0.4083, 0.8350, 0.2717, 0.4562, 0.1800, 0.5918, 0.4878],
[0.6210, 0.4164, 0.7202, 0.2930, 0.4025, 0.2483, 0.5687, 0.5567],
[0.6193, 0.4034, 0.7757, 0.2347, 0.3733, 0.2919, 0.5930, 0.4926],
[0.6198, 0.4075, 0.8650, 0.5617, 0.4150, 0.4367, 0.5450, 0.5650],
[0.6231, 0.3973, 0.8650, 0.3950, 0.3625, 0.3183, 0.5837, 0.5167],
[0.6223, 0.4028, 0.8988, 0.4200, 0.3763, 0.5733, 0.6375, 0.5167],
[0.6185, 0.4098, 0.8838, 0.4900, 0.4537, 0.5800, 0.6288, 0.5400],
[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6891, 0.4279, 0.8262, 0.2814, 0.4698, 0.1748, 0.5825, 0.4751],
[0.6379, 0.4060, 0.7332, 0.2904, 0.4166, 0.2478, 0.5579, 0.5494],
[0.5869, 0.3768, 0.7651, 0.2341, 0.3812, 0.2749, 0.5775, 0.4873],
[0.5375, 0.3461, 0.8667, 0.5664, 0.4084, 0.4206, 0.5235, 0.5708],
[0.6034, 0.3690, 0.8506, 0.3974, 0.3891, 0.2989, 0.5728, 0.5234],
[0.5709, 0.3539, 0.8911, 0.4125, 0.3997, 0.5595, 0.6092, 0.5050],
[0.5394, 0.3326, 0.8761, 0.5040, 0.4639, 0.5729, 0.6081, 0.5213],
[0.6028, 0.3882, 0.8502, 0.2723, 0.4557, 0.2620, 0.7067, 0.5437]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6277, 0.4083, 0.8350, 0.2717, 0.4563, 0.1800, 0.5918, 0.4878],
[0.6210, 0.4164, 0.7202, 0.2930, 0.4025, 0.2483, 0.5688, 0.5567],
[0.6193, 0.4034, 0.7757, 0.2347, 0.3733, 0.2919, 0.5930, 0.4926],
[0.6198, 0.4075, 0.8650, 0.5617, 0.4150, 0.4367, 0.5450, 0.5650],
[0.6231, 0.3973, 0.8650, 0.3950, 0.3625, 0.3183, 0.5838, 0.5167],
[0.6223, 0.4028, 0.8988, 0.4200, 0.3762, 0.5733, 0.6375, 0.5167],
[0.6185, 0.4098, 0.8838, 0.4900, 0.4538, 0.5800, 0.6288, 0.5400],
[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04255643083888572
step: 56
running loss: 0.0007599362649801021
Train Steps: 56/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6224, 0.4061, 0.8988, 0.4300, 0.3838, 0.4750, 0.6112, 0.5483],
[0.6184, 0.4079, 0.8350, 0.3700, 0.3675, 0.2883, 0.5312, 0.5783],
[0.6257, 0.4167, 0.8775, 0.3433, 0.3563, 0.4133, 0.6200, 0.5667],
[ nan, nan, 0.7612, 0.3250, 0.4037, 0.2533, 0.5438, 0.5767],
[0.6250, 0.4008, 0.8950, 0.4183, 0.3550, 0.4383, 0.6361, 0.4927],
[0.6234, 0.4179, 0.7825, 0.3450, 0.3813, 0.2867, 0.5675, 0.5617],
[0.6128, 0.4022, 0.8738, 0.5067, 0.4983, 0.5231, 0.5364, 0.5064],
[0.6275, 0.4024, 0.8600, 0.2283, 0.5350, 0.1800, 0.7074, 0.5413]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6451, 0.3948, 0.8907, 0.4315, 0.3767, 0.4683, 0.6095, 0.5213],
[ 0.6609, 0.4179, 0.8393, 0.3767, 0.3521, 0.2983, 0.5139, 0.5342],
[ 0.6633, 0.4080, 0.8775, 0.3444, 0.3452, 0.4230, 0.6186, 0.5333],
[ 0.0151, -0.0232, 0.7885, 0.3428, 0.4042, 0.2410, 0.5492, 0.5479],
[ 0.6191, 0.3628, 0.8780, 0.4186, 0.3605, 0.4454, 0.6142, 0.4847],
[ 0.7265, 0.4772, 0.7809, 0.3525, 0.3794, 0.2705, 0.5712, 0.5360],
[ 0.6252, 0.4042, 0.8688, 0.5054, 0.4890, 0.5129, 0.5313, 0.4892],
[ 0.5614, 0.3362, 0.8642, 0.2500, 0.5491, 0.1969, 0.7115, 0.5232]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6224, 0.4061, 0.8988, 0.4300, 0.3837, 0.4750, 0.6112, 0.5483],
[0.6184, 0.4079, 0.8350, 0.3700, 0.3675, 0.2883, 0.5312, 0.5783],
[0.6257, 0.4167, 0.8775, 0.3433, 0.3562, 0.4133, 0.6200, 0.5667],
[0.0000, 0.0000, 0.7613, 0.3250, 0.4038, 0.2533, 0.5437, 0.5767],
[0.6250, 0.4008, 0.8950, 0.4183, 0.3550, 0.4383, 0.6361, 0.4927],
[0.6234, 0.4179, 0.7825, 0.3450, 0.3812, 0.2867, 0.5675, 0.5617],
[0.6128, 0.4022, 0.8737, 0.5067, 0.4983, 0.5231, 0.5364, 0.5064],
[0.6275, 0.4024, 0.8600, 0.2283, 0.5350, 0.1800, 0.7074, 0.5413]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04318221162247937
step: 57
running loss: 0.0007575826600434977
Train Steps: 57/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.6859, 0.2194, 0.4150, 0.1867, 0.5153, 0.5729],
[0.6204, 0.4013, 0.8075, 0.2400, 0.4313, 0.2050, 0.5800, 0.5150],
[0.6229, 0.4086, 0.7538, 0.2600, 0.4775, 0.1617, 0.5900, 0.5383],
[0.6201, 0.4055, 0.7717, 0.1919, 0.4250, 0.2079, 0.5871, 0.5044],
[0.6135, 0.3994, 0.7913, 0.3050, 0.3625, 0.3050, 0.5837, 0.5050],
[0.6339, 0.4102, 0.9088, 0.4767, 0.3925, 0.5283, 0.7509, 0.5390],
[0.6274, 0.4087, 0.8375, 0.5700, 0.4025, 0.4800, 0.5700, 0.6117],
[0.6213, 0.4001, 0.7712, 0.2117, 0.4338, 0.1800, 0.5850, 0.5183]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.0021, -0.0080, 0.7031, 0.2469, 0.4050, 0.1991, 0.5280, 0.5715],
[ 0.6362, 0.3893, 0.8048, 0.2570, 0.4196, 0.2289, 0.5890, 0.5236],
[ 0.6615, 0.4203, 0.7796, 0.2559, 0.4539, 0.1697, 0.5960, 0.5247],
[ 0.7031, 0.4374, 0.7803, 0.1934, 0.4075, 0.2273, 0.5867, 0.4858],
[ 0.6264, 0.3888, 0.7986, 0.3021, 0.3568, 0.3290, 0.5865, 0.5070],
[ 0.6252, 0.3895, 0.9177, 0.4737, 0.3849, 0.5662, 0.7386, 0.5326],
[ 0.6240, 0.3859, 0.8420, 0.5800, 0.3921, 0.5099, 0.5730, 0.6145],
[ 0.6473, 0.3830, 0.7823, 0.2062, 0.4194, 0.1886, 0.5721, 0.5217]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.6859, 0.2194, 0.4150, 0.1867, 0.5153, 0.5729],
[0.6204, 0.4013, 0.8075, 0.2400, 0.4313, 0.2050, 0.5800, 0.5150],
[0.6229, 0.4086, 0.7538, 0.2600, 0.4775, 0.1617, 0.5900, 0.5383],
[0.6202, 0.4055, 0.7717, 0.1919, 0.4250, 0.2079, 0.5871, 0.5044],
[0.6135, 0.3994, 0.7912, 0.3050, 0.3625, 0.3050, 0.5838, 0.5050],
[0.6339, 0.4102, 0.9087, 0.4767, 0.3925, 0.5283, 0.7509, 0.5390],
[0.6274, 0.4087, 0.8375, 0.5700, 0.4025, 0.4800, 0.5700, 0.6117],
[0.6213, 0.4001, 0.7713, 0.2117, 0.4338, 0.1800, 0.5850, 0.5183]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04352180591376964
step: 58
running loss: 0.0007503759640305111
Train Steps: 58/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6133, 0.4094, 0.8495, 0.4028, 0.3588, 0.3200, 0.5003, 0.5407],
[0.6274, 0.4117, 0.8100, 0.5801, 0.4000, 0.4583, 0.5582, 0.6118],
[0.6176, 0.4017, 0.8788, 0.5100, 0.4075, 0.5250, 0.5913, 0.5033],
[0.6136, 0.4117, 0.8700, 0.5167, 0.4188, 0.5083, 0.5147, 0.5495],
[0.6189, 0.4033, 0.8650, 0.5267, 0.4487, 0.5150, 0.5925, 0.5050],
[0.6111, 0.3995, 0.8788, 0.4567, 0.3813, 0.4833, 0.5450, 0.5700],
[0.6245, 0.4100, 0.7762, 0.2583, 0.4963, 0.1517, 0.5875, 0.5417],
[0.6153, 0.4119, 0.8463, 0.3833, 0.3600, 0.3200, 0.5106, 0.5563]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5926, 0.3791, 0.8699, 0.3925, 0.3340, 0.3080, 0.5218, 0.5129],
[0.5920, 0.3798, 0.8317, 0.5436, 0.3708, 0.4394, 0.5764, 0.5986],
[0.5888, 0.3719, 0.8841, 0.4800, 0.3814, 0.5299, 0.6021, 0.5108],
[0.6247, 0.3948, 0.8895, 0.5144, 0.4037, 0.5002, 0.5442, 0.5280],
[0.5756, 0.3660, 0.8945, 0.4966, 0.4299, 0.5158, 0.6156, 0.5064],
[0.5044, 0.3224, 0.8838, 0.4386, 0.3716, 0.4736, 0.5628, 0.5452],
[0.6710, 0.4162, 0.7985, 0.2600, 0.4690, 0.1384, 0.5956, 0.5194],
[0.6026, 0.3820, 0.8637, 0.3745, 0.3446, 0.3149, 0.5279, 0.5321]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6133, 0.4094, 0.8495, 0.4028, 0.3587, 0.3200, 0.5003, 0.5407],
[0.6274, 0.4117, 0.8100, 0.5801, 0.4000, 0.4583, 0.5582, 0.6118],
[0.6176, 0.4017, 0.8788, 0.5100, 0.4075, 0.5250, 0.5913, 0.5033],
[0.6136, 0.4117, 0.8700, 0.5167, 0.4187, 0.5083, 0.5147, 0.5495],
[0.6189, 0.4033, 0.8650, 0.5267, 0.4487, 0.5150, 0.5925, 0.5050],
[0.6111, 0.3995, 0.8788, 0.4567, 0.3812, 0.4833, 0.5450, 0.5700],
[0.6245, 0.4100, 0.7763, 0.2583, 0.4963, 0.1517, 0.5875, 0.5417],
[0.6153, 0.4119, 0.8462, 0.3833, 0.3600, 0.3200, 0.5106, 0.5563]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04425763736071531
step: 59
running loss: 0.0007501294467917849
Train Steps: 59/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6161, 0.4055, 0.8675, 0.3867, 0.3713, 0.4033, 0.5195, 0.5162],
[0.6228, 0.4004, 0.8750, 0.5250, 0.3825, 0.5233, 0.6362, 0.5000],
[0.6087, 0.3951, 0.8387, 0.5833, 0.4188, 0.4933, 0.5146, 0.4830],
[0.6218, 0.4185, 0.7338, 0.2650, 0.4625, 0.1950, 0.5687, 0.5800],
[0.6167, 0.4048, 0.6831, 0.3639, 0.3763, 0.3017, 0.5700, 0.5883],
[0.6137, 0.4084, 0.8076, 0.3889, 0.3650, 0.3150, 0.5356, 0.5896],
[0.6286, 0.4078, 0.8063, 0.2267, 0.4788, 0.1533, 0.5953, 0.4913],
[ nan, nan, 0.6992, 0.2791, 0.3950, 0.2383, 0.5483, 0.5819]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6232, 0.4094, 0.9060, 0.3644, 0.3718, 0.3913, 0.5427, 0.5234],
[0.5923, 0.3678, 0.8974, 0.4886, 0.3832, 0.5251, 0.6586, 0.5065],
[0.5933, 0.3822, 0.8689, 0.5705, 0.4047, 0.4963, 0.5346, 0.5147],
[0.6270, 0.4227, 0.7658, 0.2528, 0.4602, 0.1894, 0.5709, 0.5945],
[0.5592, 0.3721, 0.7411, 0.3281, 0.3730, 0.3106, 0.5833, 0.5873],
[0.6357, 0.4168, 0.8609, 0.3741, 0.3467, 0.3067, 0.5425, 0.5905],
[0.6143, 0.3925, 0.8168, 0.2518, 0.4762, 0.1560, 0.5998, 0.5089],
[0.0199, 0.0254, 0.7184, 0.2600, 0.3754, 0.2183, 0.5676, 0.5825]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6161, 0.4055, 0.8675, 0.3867, 0.3713, 0.4033, 0.5195, 0.5162],
[0.6228, 0.4004, 0.8750, 0.5250, 0.3825, 0.5233, 0.6363, 0.5000],
[0.6087, 0.3951, 0.8388, 0.5833, 0.4187, 0.4933, 0.5146, 0.4830],
[0.6218, 0.4185, 0.7337, 0.2650, 0.4625, 0.1950, 0.5688, 0.5800],
[0.6167, 0.4048, 0.6831, 0.3639, 0.3762, 0.3017, 0.5700, 0.5883],
[0.6137, 0.4084, 0.8076, 0.3889, 0.3650, 0.3150, 0.5356, 0.5896],
[0.6286, 0.4078, 0.8062, 0.2267, 0.4787, 0.1533, 0.5953, 0.4913],
[0.0000, 0.0000, 0.6992, 0.2791, 0.3950, 0.2383, 0.5483, 0.5819]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0447188821999589
step: 60
running loss: 0.0007453147033326483
Train Steps: 60/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6043, 0.4022, 0.6887, 0.1983, 0.3775, 0.2483, 0.5480, 0.5136],
[0.6111, 0.3995, 0.8788, 0.4567, 0.3813, 0.4833, 0.5450, 0.5700],
[0.6214, 0.4112, 0.7838, 0.2117, 0.3650, 0.3133, 0.5675, 0.5083],
[0.6198, 0.4105, 0.7950, 0.3267, 0.3675, 0.3767, 0.6038, 0.6167],
[0.6127, 0.4118, 0.8650, 0.5083, 0.4088, 0.5367, 0.5300, 0.5456],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098],
[0.6321, 0.4048, 0.8738, 0.5617, 0.3875, 0.4417, 0.6361, 0.4927],
[0.6267, 0.4065, 0.8313, 0.2467, 0.4788, 0.1733, 0.6312, 0.5133]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5633, 0.3762, 0.6976, 0.2267, 0.3762, 0.2533, 0.5589, 0.5271],
[0.5295, 0.3590, 0.8761, 0.4640, 0.3860, 0.4623, 0.5525, 0.5737],
[0.5826, 0.3891, 0.7838, 0.2237, 0.3603, 0.2857, 0.5810, 0.5268],
[0.6006, 0.4065, 0.8024, 0.3331, 0.3506, 0.3795, 0.6129, 0.6237],
[0.6266, 0.4274, 0.8681, 0.4975, 0.4155, 0.5203, 0.5503, 0.5702],
[0.5805, 0.3821, 0.8804, 0.4771, 0.3678, 0.5073, 0.6005, 0.5190],
[0.5910, 0.3802, 0.8822, 0.5528, 0.3864, 0.4164, 0.6233, 0.4992],
[0.5723, 0.3710, 0.8342, 0.2592, 0.4869, 0.1630, 0.6223, 0.5278]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6043, 0.4022, 0.6888, 0.1983, 0.3775, 0.2483, 0.5480, 0.5136],
[0.6111, 0.3995, 0.8788, 0.4567, 0.3812, 0.4833, 0.5450, 0.5700],
[0.6214, 0.4112, 0.7837, 0.2117, 0.3650, 0.3133, 0.5675, 0.5083],
[0.6198, 0.4105, 0.7950, 0.3267, 0.3675, 0.3767, 0.6037, 0.6167],
[0.6127, 0.4118, 0.8650, 0.5083, 0.4087, 0.5367, 0.5300, 0.5456],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098],
[0.6321, 0.4048, 0.8737, 0.5617, 0.3875, 0.4417, 0.6361, 0.4927],
[0.6266, 0.4065, 0.8313, 0.2467, 0.4787, 0.1733, 0.6313, 0.5133]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04516495233110618
step: 61
running loss: 0.0007404090546082981
Train Steps: 61/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6223, 0.3990, 0.8037, 0.2800, 0.4000, 0.2283, 0.5864, 0.5208],
[0.6176, 0.3911, 0.8738, 0.4217, 0.3488, 0.4033, 0.6025, 0.4817],
[0.6276, 0.4095, 0.8237, 0.2250, 0.4662, 0.1783, 0.6171, 0.4869],
[0.6204, 0.4091, 0.8950, 0.4783, 0.3613, 0.4617, 0.6063, 0.5617],
[0.6229, 0.4107, 0.8137, 0.2883, 0.4750, 0.1717, 0.5813, 0.5400],
[0.6147, 0.4107, 0.8137, 0.3333, 0.3750, 0.2683, 0.5006, 0.5412],
[0.6200, 0.3978, 0.8900, 0.4550, 0.3775, 0.5200, 0.6150, 0.5367],
[0.6193, 0.3930, 0.8949, 0.4437, 0.3852, 0.5435, 0.6263, 0.5263]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5905, 0.3962, 0.7859, 0.2966, 0.4024, 0.2382, 0.5886, 0.5458],
[0.5662, 0.3733, 0.8546, 0.4214, 0.3753, 0.3908, 0.5882, 0.5191],
[0.5349, 0.3653, 0.8111, 0.2279, 0.4760, 0.1968, 0.6072, 0.5061],
[0.6284, 0.4320, 0.8794, 0.4852, 0.3632, 0.4742, 0.5870, 0.5755],
[0.5406, 0.3842, 0.7860, 0.2888, 0.4766, 0.1790, 0.5583, 0.5668],
[0.5116, 0.3594, 0.7696, 0.3321, 0.3682, 0.2809, 0.4983, 0.5764],
[0.6265, 0.4087, 0.8644, 0.4585, 0.3857, 0.5276, 0.5999, 0.5688],
[0.5494, 0.3629, 0.8488, 0.4420, 0.3872, 0.5560, 0.6158, 0.5347]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6223, 0.3990, 0.8037, 0.2800, 0.4000, 0.2283, 0.5864, 0.5208],
[0.6176, 0.3911, 0.8737, 0.4217, 0.3487, 0.4033, 0.6025, 0.4817],
[0.6276, 0.4095, 0.8238, 0.2250, 0.4663, 0.1783, 0.6171, 0.4869],
[0.6204, 0.4091, 0.8950, 0.4783, 0.3613, 0.4617, 0.6062, 0.5617],
[0.6229, 0.4107, 0.8138, 0.2883, 0.4750, 0.1717, 0.5813, 0.5400],
[0.6147, 0.4107, 0.8138, 0.3333, 0.3750, 0.2683, 0.5006, 0.5412],
[0.6199, 0.3978, 0.8900, 0.4550, 0.3775, 0.5200, 0.6150, 0.5367],
[0.6193, 0.3930, 0.8949, 0.4437, 0.3852, 0.5435, 0.6263, 0.5263]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04607175434648525
step: 62
running loss: 0.0007430928120400847
Train Steps: 62/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6260, 0.4253, 0.8938, 0.4400, 0.3675, 0.3650, 0.5675, 0.5767],
[0.6179, 0.3998, 0.8396, 0.3505, 0.3552, 0.3768, 0.6064, 0.5329],
[0.6182, 0.3982, 0.7541, 0.2379, 0.3959, 0.2792, 0.6079, 0.5389],
[0.6129, 0.4063, 0.8738, 0.5250, 0.4313, 0.4733, 0.5230, 0.5874],
[0.6136, 0.4060, 0.8025, 0.3217, 0.3650, 0.3000, 0.5060, 0.5646],
[ nan, nan, 0.6900, 0.1917, 0.3937, 0.2367, 0.5240, 0.5246],
[0.6095, 0.4002, 0.8533, 0.5168, 0.5031, 0.5094, 0.5125, 0.5433],
[0.6361, 0.4076, 0.8862, 0.5350, 0.3713, 0.4650, 0.6654, 0.5297]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6707, 0.4670, 0.8677, 0.4491, 0.3788, 0.3431, 0.5712, 0.5661],
[0.6315, 0.4356, 0.8234, 0.3544, 0.3526, 0.3590, 0.5785, 0.5125],
[0.5871, 0.4064, 0.7431, 0.2339, 0.3850, 0.2712, 0.6034, 0.5493],
[0.6304, 0.4422, 0.8382, 0.5349, 0.4207, 0.4679, 0.5292, 0.5819],
[0.5833, 0.4111, 0.7829, 0.3156, 0.3633, 0.2995, 0.4954, 0.5502],
[0.0056, 0.0311, 0.6748, 0.2038, 0.3992, 0.2276, 0.5228, 0.5308],
[0.6268, 0.4436, 0.8411, 0.5354, 0.4784, 0.4864, 0.5279, 0.5470],
[0.6584, 0.4570, 0.8667, 0.5405, 0.3740, 0.4484, 0.6698, 0.5254]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6260, 0.4253, 0.8938, 0.4400, 0.3675, 0.3650, 0.5675, 0.5767],
[0.6179, 0.3998, 0.8396, 0.3505, 0.3552, 0.3768, 0.6064, 0.5329],
[0.6182, 0.3982, 0.7541, 0.2379, 0.3959, 0.2792, 0.6079, 0.5389],
[0.6130, 0.4063, 0.8737, 0.5250, 0.4313, 0.4733, 0.5230, 0.5874],
[0.6136, 0.4060, 0.8025, 0.3217, 0.3650, 0.3000, 0.5060, 0.5646],
[0.0000, 0.0000, 0.6900, 0.1917, 0.3938, 0.2367, 0.5240, 0.5246],
[0.6095, 0.4002, 0.8533, 0.5168, 0.5031, 0.5094, 0.5125, 0.5433],
[0.6361, 0.4076, 0.8863, 0.5350, 0.3713, 0.4650, 0.6654, 0.5297]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04644800083769951
step: 63
running loss: 0.0007372698545666589
Train Steps: 63/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6147, 0.4026, 0.6600, 0.2467, 0.4088, 0.2150, 0.5489, 0.5773],
[0.6182, 0.3987, 0.7878, 0.2889, 0.3699, 0.3260, 0.6086, 0.5367],
[0.6228, 0.4119, 0.7938, 0.2233, 0.4674, 0.1773, 0.6188, 0.5433],
[0.6073, 0.3932, 0.8363, 0.5817, 0.4425, 0.5117, 0.5204, 0.4817],
[0.6168, 0.4029, 0.8523, 0.3417, 0.3588, 0.5000, 0.6125, 0.5400],
[0.6182, 0.3998, 0.8793, 0.4191, 0.3552, 0.4285, 0.6038, 0.5312],
[0.6179, 0.4118, 0.7278, 0.4237, 0.3588, 0.3400, 0.5675, 0.5917],
[0.6262, 0.4163, 0.8850, 0.5183, 0.3763, 0.4150, 0.6025, 0.5500]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5616, 0.3987, 0.6612, 0.2353, 0.4208, 0.1947, 0.5107, 0.5745],
[0.5573, 0.3817, 0.7776, 0.2782, 0.3594, 0.3186, 0.5920, 0.5305],
[0.5528, 0.3848, 0.7682, 0.2134, 0.4712, 0.1687, 0.5880, 0.5412],
[0.5727, 0.3796, 0.8123, 0.5452, 0.4452, 0.4979, 0.5041, 0.4830],
[0.6293, 0.4308, 0.8392, 0.3437, 0.3631, 0.4830, 0.5959, 0.5178],
[0.6417, 0.4228, 0.8615, 0.4075, 0.3550, 0.4194, 0.5687, 0.5197],
[0.5581, 0.3868, 0.7555, 0.3847, 0.3587, 0.3180, 0.5133, 0.5807],
[0.6269, 0.4197, 0.8552, 0.4713, 0.3764, 0.3860, 0.5693, 0.5327]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6147, 0.4026, 0.6600, 0.2467, 0.4087, 0.2150, 0.5489, 0.5773],
[0.6182, 0.3987, 0.7878, 0.2889, 0.3699, 0.3260, 0.6086, 0.5367],
[0.6228, 0.4119, 0.7937, 0.2233, 0.4674, 0.1773, 0.6187, 0.5433],
[0.6073, 0.3932, 0.8363, 0.5817, 0.4425, 0.5117, 0.5204, 0.4817],
[0.6168, 0.4029, 0.8523, 0.3417, 0.3587, 0.5000, 0.6125, 0.5400],
[0.6182, 0.3998, 0.8793, 0.4191, 0.3552, 0.4285, 0.6038, 0.5312],
[0.6179, 0.4118, 0.7278, 0.4237, 0.3587, 0.3400, 0.5675, 0.5917],
[0.6262, 0.4163, 0.8850, 0.5183, 0.3762, 0.4150, 0.6025, 0.5500]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0470950579183409
step: 64
running loss: 0.0007358602799740765
Train Steps: 64/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6085, 0.4005, 0.8400, 0.4317, 0.3763, 0.4750, 0.5476, 0.5058],
[0.6343, 0.4097, 0.9287, 0.4367, 0.4313, 0.3600, 0.7248, 0.5841],
[0.6137, 0.4084, 0.8076, 0.3889, 0.3650, 0.3150, 0.5356, 0.5896],
[0.6202, 0.4079, 0.8025, 0.2500, 0.3763, 0.3217, 0.6125, 0.5533],
[0.6271, 0.4081, 0.9081, 0.4894, 0.3700, 0.4283, 0.6661, 0.5274],
[0.6346, 0.4086, 0.7938, 0.5500, 0.3962, 0.4867, 0.7343, 0.5702],
[0.6222, 0.3937, 0.8350, 0.5617, 0.4138, 0.4600, 0.5800, 0.5233],
[0.6164, 0.4076, 0.8838, 0.4117, 0.3713, 0.5550, 0.6238, 0.5350]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6138, 0.4214, 0.8354, 0.4241, 0.3648, 0.4590, 0.5131, 0.4924],
[0.6428, 0.4388, 0.8917, 0.4322, 0.4117, 0.3551, 0.6836, 0.5497],
[0.5849, 0.4031, 0.7995, 0.3712, 0.3463, 0.3027, 0.4893, 0.5656],
[0.6113, 0.4225, 0.7709, 0.2444, 0.3745, 0.3282, 0.5668, 0.5318],
[0.6188, 0.4291, 0.8725, 0.4718, 0.3644, 0.4302, 0.6124, 0.5090],
[0.6344, 0.4364, 0.7759, 0.5476, 0.3937, 0.4836, 0.6670, 0.5534],
[0.6023, 0.3985, 0.8128, 0.5589, 0.4047, 0.4458, 0.5374, 0.5205],
[0.6651, 0.4503, 0.8545, 0.4076, 0.3714, 0.5456, 0.5912, 0.5054]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6084, 0.4005, 0.8400, 0.4317, 0.3762, 0.4750, 0.5476, 0.5058],
[0.6343, 0.4097, 0.9287, 0.4367, 0.4313, 0.3600, 0.7248, 0.5841],
[0.6137, 0.4084, 0.8076, 0.3889, 0.3650, 0.3150, 0.5356, 0.5896],
[0.6202, 0.4079, 0.8025, 0.2500, 0.3762, 0.3217, 0.6125, 0.5533],
[0.6271, 0.4081, 0.9081, 0.4894, 0.3700, 0.4283, 0.6661, 0.5274],
[0.6346, 0.4086, 0.7937, 0.5500, 0.3963, 0.4867, 0.7343, 0.5702],
[0.6222, 0.3937, 0.8350, 0.5617, 0.4137, 0.4600, 0.5800, 0.5233],
[0.6164, 0.4076, 0.8838, 0.4117, 0.3713, 0.5550, 0.6237, 0.5350]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04768331356171984
step: 65
running loss: 0.0007335894394110745
Train Steps: 65/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6076, 0.3958, 0.8700, 0.4667, 0.4546, 0.5046, 0.5231, 0.4960],
[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150],
[0.6147, 0.4112, 0.7988, 0.3200, 0.3775, 0.2767, 0.5150, 0.5550],
[0.6120, 0.4014, 0.6863, 0.2817, 0.3700, 0.2783, 0.5513, 0.5667],
[0.6260, 0.4120, 0.8013, 0.2350, 0.4888, 0.1533, 0.6281, 0.4895],
[0.6272, 0.4045, 0.8538, 0.5900, 0.3750, 0.4417, 0.5989, 0.4649],
[0.6205, 0.4016, 0.8350, 0.2717, 0.3987, 0.2550, 0.5787, 0.5133],
[0.6264, 0.4071, 0.9038, 0.3867, 0.3663, 0.3917, 0.6338, 0.5283]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6108, 0.4151, 0.8757, 0.4770, 0.4467, 0.4963, 0.5417, 0.5156],
[0.6673, 0.4383, 0.8964, 0.4764, 0.4516, 0.5921, 0.6215, 0.5118],
[0.5872, 0.3994, 0.7957, 0.3206, 0.3719, 0.3037, 0.5088, 0.5784],
[0.5984, 0.3938, 0.6967, 0.2951, 0.3714, 0.3026, 0.5459, 0.5644],
[0.5771, 0.3856, 0.8076, 0.2430, 0.4911, 0.1712, 0.6498, 0.5274],
[0.5973, 0.4015, 0.8380, 0.5838, 0.3782, 0.4484, 0.5942, 0.4922],
[0.5895, 0.3874, 0.8228, 0.2661, 0.4062, 0.2829, 0.5728, 0.5299],
[0.6101, 0.4115, 0.8977, 0.3835, 0.3710, 0.4011, 0.6480, 0.5377]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6076, 0.3958, 0.8700, 0.4667, 0.4546, 0.5046, 0.5231, 0.4960],
[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150],
[0.6147, 0.4112, 0.7987, 0.3200, 0.3775, 0.2767, 0.5150, 0.5550],
[0.6120, 0.4013, 0.6862, 0.2817, 0.3700, 0.2783, 0.5512, 0.5667],
[0.6259, 0.4120, 0.8012, 0.2350, 0.4888, 0.1533, 0.6281, 0.4895],
[0.6271, 0.4045, 0.8537, 0.5900, 0.3750, 0.4417, 0.5989, 0.4649],
[0.6205, 0.4015, 0.8350, 0.2717, 0.3988, 0.2550, 0.5788, 0.5133],
[0.6264, 0.4071, 0.9038, 0.3867, 0.3663, 0.3917, 0.6338, 0.5283]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04797610554669518
step: 66
running loss: 0.0007269106901014421
Train Steps: 66/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6264, 0.3972, 0.8853, 0.4771, 0.3853, 0.4511, 0.6293, 0.5334],
[0.6300, 0.4133, 0.8538, 0.2167, 0.5587, 0.2250, 0.7390, 0.5413],
[0.6204, 0.4007, 0.7838, 0.2100, 0.4475, 0.1733, 0.5825, 0.5167],
[0.6211, 0.3993, 0.7650, 0.1933, 0.4575, 0.1550, 0.5965, 0.4895],
[0.6122, 0.4006, 0.8850, 0.4217, 0.4088, 0.5517, 0.6063, 0.5517],
[0.6212, 0.4033, 0.8938, 0.4167, 0.3813, 0.4267, 0.5613, 0.5583],
[0.6201, 0.4050, 0.7757, 0.2234, 0.4459, 0.1798, 0.5975, 0.5426],
[0.6279, 0.4008, 0.8600, 0.4883, 0.4325, 0.5283, 0.7010, 0.5378]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6038, 0.3741, 0.9009, 0.5030, 0.3543, 0.5153, 0.6121, 0.5218],
[0.6826, 0.4435, 0.8553, 0.2553, 0.5435, 0.2630, 0.7351, 0.5675],
[0.6452, 0.4126, 0.7562, 0.2424, 0.4441, 0.2027, 0.5805, 0.5247],
[0.5573, 0.3575, 0.7552, 0.2212, 0.4434, 0.2005, 0.5919, 0.5020],
[0.6784, 0.4411, 0.8808, 0.4649, 0.4005, 0.5945, 0.5945, 0.5313],
[0.6025, 0.4080, 0.8856, 0.4498, 0.3573, 0.4614, 0.5600, 0.5423],
[0.6007, 0.3935, 0.7706, 0.2596, 0.4448, 0.2150, 0.5805, 0.5448],
[0.6657, 0.4195, 0.8535, 0.5146, 0.4174, 0.5708, 0.7015, 0.5428]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6264, 0.3972, 0.8853, 0.4771, 0.3853, 0.4511, 0.6293, 0.5334],
[0.6300, 0.4133, 0.8537, 0.2167, 0.5587, 0.2250, 0.7390, 0.5413],
[0.6204, 0.4007, 0.7837, 0.2100, 0.4475, 0.1733, 0.5825, 0.5167],
[0.6211, 0.3993, 0.7650, 0.1933, 0.4575, 0.1550, 0.5965, 0.4895],
[0.6122, 0.4006, 0.8850, 0.4217, 0.4087, 0.5517, 0.6062, 0.5517],
[0.6212, 0.4033, 0.8938, 0.4167, 0.3812, 0.4267, 0.5612, 0.5583],
[0.6201, 0.4050, 0.7757, 0.2234, 0.4459, 0.1798, 0.5975, 0.5426],
[0.6279, 0.4008, 0.8600, 0.4883, 0.4325, 0.5283, 0.7010, 0.5378]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.048750259753433056
step: 67
running loss: 0.0007276158172154187
Train Steps: 67/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6201, 0.4029, 0.8776, 0.4602, 0.3683, 0.4203, 0.5938, 0.5450],
[0.6176, 0.4017, 0.8788, 0.5100, 0.4075, 0.5250, 0.5913, 0.5033],
[0.6201, 0.4116, 0.8725, 0.4733, 0.3700, 0.3217, 0.5386, 0.5767],
[0.6110, 0.4047, 0.8700, 0.4483, 0.3713, 0.3967, 0.5088, 0.5517],
[0.6178, 0.4012, 0.8900, 0.4495, 0.3891, 0.5617, 0.5972, 0.4879],
[0.6271, 0.4040, 0.9000, 0.3250, 0.4938, 0.2300, 0.7192, 0.5413],
[0.6201, 0.4050, 0.7757, 0.2234, 0.4459, 0.1798, 0.5975, 0.5426],
[0.6275, 0.4024, 0.7722, 0.2080, 0.4392, 0.2234, 0.6435, 0.5290]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6498, 0.4061, 0.8830, 0.4685, 0.3808, 0.4473, 0.6150, 0.5376],
[0.6717, 0.4231, 0.8865, 0.5102, 0.4039, 0.5551, 0.6107, 0.5116],
[0.6743, 0.4255, 0.8788, 0.4651, 0.3708, 0.3492, 0.5595, 0.5616],
[0.6536, 0.4194, 0.8888, 0.4669, 0.3753, 0.4371, 0.5224, 0.5394],
[0.7025, 0.4403, 0.8933, 0.4476, 0.3991, 0.5874, 0.6223, 0.4826],
[0.6191, 0.3752, 0.9168, 0.3248, 0.5109, 0.2552, 0.7435, 0.5421],
[0.6457, 0.3986, 0.7897, 0.2415, 0.4592, 0.1989, 0.6085, 0.5358],
[0.6341, 0.3853, 0.7629, 0.2232, 0.4380, 0.2254, 0.6620, 0.5276]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6201, 0.4029, 0.8776, 0.4602, 0.3683, 0.4203, 0.5938, 0.5450],
[0.6176, 0.4017, 0.8788, 0.5100, 0.4075, 0.5250, 0.5913, 0.5033],
[0.6201, 0.4116, 0.8725, 0.4733, 0.3700, 0.3217, 0.5386, 0.5767],
[0.6110, 0.4047, 0.8700, 0.4483, 0.3713, 0.3967, 0.5088, 0.5517],
[0.6178, 0.4012, 0.8900, 0.4495, 0.3891, 0.5617, 0.5972, 0.4879],
[0.6271, 0.4040, 0.9000, 0.3250, 0.4938, 0.2300, 0.7192, 0.5413],
[0.6201, 0.4050, 0.7757, 0.2234, 0.4459, 0.1798, 0.5975, 0.5426],
[0.6275, 0.4024, 0.7722, 0.2080, 0.4392, 0.2234, 0.6435, 0.5290]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.049255486417678185
step: 68
running loss: 0.0007243453884952675
Train Steps: 68/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6204, 0.4049, 0.7975, 0.2700, 0.3937, 0.2567, 0.5700, 0.5183],
[0.6168, 0.4029, 0.8523, 0.3417, 0.3588, 0.5000, 0.6125, 0.5400],
[0.6101, 0.4042, 0.7775, 0.2617, 0.3713, 0.2817, 0.5440, 0.5650],
[0.6271, 0.4040, 0.9138, 0.3750, 0.4625, 0.2617, 0.7232, 0.5413],
[0.6236, 0.3966, 0.8850, 0.4967, 0.3638, 0.4017, 0.5850, 0.5183],
[0.6216, 0.4100, 0.7350, 0.2067, 0.4325, 0.2050, 0.5950, 0.5333],
[0.6307, 0.4045, 0.8025, 0.5833, 0.3775, 0.4867, 0.6892, 0.5459],
[0.6329, 0.4196, 0.9238, 0.4583, 0.4263, 0.2933, 0.7343, 0.5748]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6066, 0.3856, 0.8011, 0.2484, 0.4016, 0.2708, 0.5804, 0.5224],
[0.6193, 0.3879, 0.8731, 0.3425, 0.3602, 0.5105, 0.6248, 0.5186],
[0.6137, 0.3860, 0.7856, 0.2496, 0.3973, 0.2793, 0.5676, 0.5596],
[0.6431, 0.3960, 0.9349, 0.3631, 0.4764, 0.2546, 0.7226, 0.5344],
[0.6240, 0.3707, 0.9125, 0.4803, 0.3718, 0.4266, 0.6152, 0.5204],
[0.6428, 0.3944, 0.7469, 0.2015, 0.4372, 0.2012, 0.6081, 0.5121],
[0.6284, 0.3823, 0.8317, 0.5589, 0.4057, 0.4849, 0.6951, 0.5196],
[0.6600, 0.4035, 0.9298, 0.4591, 0.4420, 0.2887, 0.7233, 0.5457]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6204, 0.4049, 0.7975, 0.2700, 0.3938, 0.2567, 0.5700, 0.5183],
[0.6168, 0.4029, 0.8523, 0.3417, 0.3587, 0.5000, 0.6125, 0.5400],
[0.6101, 0.4042, 0.7775, 0.2617, 0.3713, 0.2817, 0.5440, 0.5650],
[0.6271, 0.4040, 0.9137, 0.3750, 0.4625, 0.2617, 0.7232, 0.5413],
[0.6236, 0.3965, 0.8850, 0.4967, 0.3638, 0.4017, 0.5850, 0.5183],
[0.6216, 0.4100, 0.7350, 0.2067, 0.4325, 0.2050, 0.5950, 0.5333],
[0.6307, 0.4045, 0.8025, 0.5833, 0.3775, 0.4867, 0.6892, 0.5459],
[0.6329, 0.4196, 0.9237, 0.4583, 0.4263, 0.2933, 0.7343, 0.5748]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04951172370056156
step: 69
running loss: 0.0007175612130516168
Train Steps: 69/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6271, 0.4081, 0.9081, 0.4894, 0.3700, 0.4283, 0.6661, 0.5274],
[0.6203, 0.4056, 0.8942, 0.4086, 0.3643, 0.3617, 0.5917, 0.5482],
[0.6099, 0.4030, 0.8638, 0.5117, 0.4983, 0.4965, 0.5086, 0.5388],
[0.6198, 0.4101, 0.8838, 0.5283, 0.3763, 0.5267, 0.5913, 0.5567],
[0.6034, 0.4011, 0.7350, 0.2533, 0.3438, 0.3367, 0.5516, 0.5084],
[0.6202, 0.4066, 0.8398, 0.2648, 0.3925, 0.2627, 0.5845, 0.5124],
[0.6364, 0.4165, 0.9088, 0.4367, 0.4075, 0.3150, 0.6448, 0.5297],
[0.6125, 0.4076, 0.8488, 0.3883, 0.3700, 0.3683, 0.5026, 0.5505]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6369, 0.4063, 0.9166, 0.4760, 0.3783, 0.4141, 0.6935, 0.5250],
[0.6562, 0.3967, 0.9160, 0.4163, 0.3726, 0.3441, 0.6424, 0.5450],
[0.6723, 0.4198, 0.8920, 0.5082, 0.5132, 0.4629, 0.5744, 0.5426],
[0.6825, 0.4162, 0.9109, 0.5298, 0.3909, 0.5015, 0.6304, 0.5498],
[0.6299, 0.3838, 0.7454, 0.2568, 0.3605, 0.3079, 0.6139, 0.5104],
[0.6160, 0.3820, 0.8326, 0.2532, 0.4049, 0.2346, 0.6360, 0.5246],
[0.6479, 0.4071, 0.9284, 0.4265, 0.4301, 0.2949, 0.6847, 0.5333],
[0.6430, 0.3917, 0.8725, 0.3664, 0.3732, 0.3443, 0.5314, 0.5447]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6271, 0.4081, 0.9081, 0.4894, 0.3700, 0.4283, 0.6661, 0.5274],
[0.6203, 0.4056, 0.8942, 0.4086, 0.3643, 0.3617, 0.5917, 0.5482],
[0.6098, 0.4030, 0.8637, 0.5117, 0.4983, 0.4965, 0.5086, 0.5388],
[0.6198, 0.4101, 0.8838, 0.5283, 0.3762, 0.5267, 0.5913, 0.5567],
[0.6033, 0.4011, 0.7350, 0.2533, 0.3438, 0.3367, 0.5516, 0.5084],
[0.6202, 0.4066, 0.8398, 0.2648, 0.3925, 0.2627, 0.5845, 0.5124],
[0.6364, 0.4165, 0.9087, 0.4367, 0.4075, 0.3150, 0.6448, 0.5297],
[0.6125, 0.4076, 0.8487, 0.3883, 0.3700, 0.3683, 0.5026, 0.5505]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05016214041097555
step: 70
running loss: 0.0007166020058710793
Train Steps: 70/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.7268, 0.2333, 0.4125, 0.1933, 0.5112, 0.5383],
[0.6200, 0.4112, 0.8862, 0.4100, 0.3638, 0.4917, 0.6088, 0.6050],
[0.6182, 0.3967, 0.8263, 0.3065, 0.3526, 0.4161, 0.6192, 0.5290],
[0.6302, 0.4007, 0.8850, 0.5500, 0.3613, 0.4517, 0.6335, 0.5012],
[0.6135, 0.3994, 0.7913, 0.3050, 0.3625, 0.3050, 0.5837, 0.5050],
[0.6137, 0.4038, 0.8563, 0.4050, 0.3813, 0.2550, 0.5106, 0.4954],
[0.6102, 0.4020, 0.8638, 0.3717, 0.3625, 0.5017, 0.6038, 0.5500],
[0.6248, 0.4185, 0.8500, 0.5767, 0.4463, 0.4550, 0.5613, 0.5917]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.2846, 0.1741, 0.7245, 0.1989, 0.4228, 0.1664, 0.5666, 0.5444],
[0.7737, 0.4870, 0.8862, 0.4056, 0.3876, 0.4681, 0.6411, 0.6069],
[0.6626, 0.4021, 0.8599, 0.2900, 0.3500, 0.3739, 0.6576, 0.5374],
[0.6829, 0.4202, 0.8933, 0.5592, 0.3822, 0.4282, 0.6746, 0.5033],
[0.6728, 0.4183, 0.8102, 0.3008, 0.3831, 0.2867, 0.6244, 0.5226],
[0.7139, 0.4413, 0.8702, 0.4020, 0.4185, 0.2396, 0.5509, 0.5229],
[0.6474, 0.4059, 0.8866, 0.3840, 0.3860, 0.4751, 0.6363, 0.5533],
[0.7377, 0.4589, 0.8799, 0.5809, 0.4689, 0.4086, 0.5932, 0.6058]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.7268, 0.2333, 0.4125, 0.1933, 0.5113, 0.5383],
[0.6200, 0.4112, 0.8863, 0.4100, 0.3638, 0.4917, 0.6087, 0.6050],
[0.6182, 0.3967, 0.8263, 0.3065, 0.3526, 0.4161, 0.6192, 0.5290],
[0.6302, 0.4007, 0.8850, 0.5500, 0.3613, 0.4517, 0.6335, 0.5012],
[0.6135, 0.3994, 0.7912, 0.3050, 0.3625, 0.3050, 0.5838, 0.5050],
[0.6137, 0.4038, 0.8562, 0.4050, 0.3812, 0.2550, 0.5106, 0.4954],
[0.6102, 0.4020, 0.8637, 0.3717, 0.3625, 0.5017, 0.6037, 0.5500],
[0.6248, 0.4185, 0.8500, 0.5767, 0.4462, 0.4550, 0.5612, 0.5917]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0032, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0032, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.053396602292195894
step: 71
running loss: 0.0007520648210168436
Train Steps: 71/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.8213, 0.2700, 0.3775, 0.2817, 0.5425, 0.5533],
[0.6184, 0.4079, 0.8350, 0.3700, 0.3675, 0.2883, 0.5312, 0.5783],
[0.6277, 0.4118, 0.8988, 0.3833, 0.3950, 0.2650, 0.6290, 0.4938],
[0.6329, 0.4196, 0.9238, 0.4583, 0.4263, 0.2933, 0.7343, 0.5748],
[0.6336, 0.4191, 0.8938, 0.5167, 0.3937, 0.3517, 0.7343, 0.5748],
[0.6307, 0.4029, 0.8988, 0.4817, 0.3937, 0.3500, 0.7311, 0.5378],
[0.6250, 0.4116, 0.8700, 0.4850, 0.4650, 0.5567, 0.6088, 0.5183],
[0.6168, 0.4029, 0.8523, 0.3417, 0.3588, 0.5000, 0.6125, 0.5400]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.1801, 0.1107, 0.7775, 0.2522, 0.3755, 0.2760, 0.5482, 0.5658],
[0.6555, 0.4322, 0.8262, 0.3429, 0.3661, 0.2883, 0.5107, 0.5873],
[0.6422, 0.4133, 0.8809, 0.3643, 0.3938, 0.2512, 0.6069, 0.5259],
[0.6714, 0.4308, 0.9102, 0.4524, 0.4319, 0.2764, 0.7034, 0.5672],
[0.6379, 0.4200, 0.8942, 0.5023, 0.4042, 0.3349, 0.7128, 0.5673],
[0.6437, 0.4143, 0.8999, 0.4609, 0.3997, 0.3374, 0.7002, 0.5466],
[0.6936, 0.4358, 0.8862, 0.4660, 0.4581, 0.5420, 0.6077, 0.5310],
[0.6167, 0.4021, 0.8470, 0.3338, 0.3548, 0.4915, 0.5990, 0.5446]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.8213, 0.2700, 0.3775, 0.2817, 0.5425, 0.5533],
[0.6184, 0.4079, 0.8350, 0.3700, 0.3675, 0.2883, 0.5312, 0.5783],
[0.6277, 0.4117, 0.8988, 0.3833, 0.3950, 0.2650, 0.6290, 0.4938],
[0.6329, 0.4196, 0.9237, 0.4583, 0.4263, 0.2933, 0.7343, 0.5748],
[0.6336, 0.4191, 0.8938, 0.5167, 0.3938, 0.3517, 0.7343, 0.5748],
[0.6307, 0.4029, 0.8988, 0.4817, 0.3938, 0.3500, 0.7311, 0.5378],
[0.6251, 0.4116, 0.8700, 0.4850, 0.4650, 0.5567, 0.6087, 0.5183],
[0.6168, 0.4029, 0.8523, 0.3417, 0.3587, 0.5000, 0.6125, 0.5400]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05442776322888676
step: 72
running loss: 0.0007559411559567605
Train Steps: 72/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6185, 0.4080, 0.8625, 0.3483, 0.3788, 0.2650, 0.5320, 0.5272],
[0.6257, 0.4060, 0.8300, 0.2333, 0.4688, 0.2583, 0.7050, 0.5633],
[ nan, nan, 0.7553, 0.2722, 0.3875, 0.2550, 0.5125, 0.5633],
[0.6304, 0.4024, 0.8925, 0.4800, 0.3937, 0.4817, 0.7485, 0.5297],
[0.6157, 0.4102, 0.8513, 0.3817, 0.3613, 0.3667, 0.5096, 0.5890],
[0.6175, 0.3957, 0.8700, 0.4817, 0.4662, 0.5133, 0.5800, 0.5517],
[0.6135, 0.3994, 0.7913, 0.3050, 0.3625, 0.3050, 0.5837, 0.5050],
[0.6259, 0.4156, 0.8812, 0.3183, 0.4775, 0.1867, 0.6219, 0.4960]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6175, 0.4065, 0.8519, 0.3611, 0.3844, 0.2618, 0.5318, 0.5447],
[0.6762, 0.4368, 0.8453, 0.2408, 0.4535, 0.2396, 0.6948, 0.5665],
[0.1374, 0.0842, 0.7511, 0.2508, 0.3693, 0.2625, 0.5106, 0.5620],
[0.6211, 0.3957, 0.8926, 0.4968, 0.3888, 0.4682, 0.6999, 0.5258],
[0.6164, 0.4151, 0.8564, 0.3892, 0.3551, 0.3569, 0.5156, 0.5850],
[0.6030, 0.4068, 0.8657, 0.4823, 0.4596, 0.5002, 0.5685, 0.5478],
[0.6145, 0.3968, 0.7989, 0.3191, 0.3619, 0.3048, 0.5876, 0.5153],
[0.6064, 0.3935, 0.8939, 0.3244, 0.4601, 0.1780, 0.6137, 0.5080]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6186, 0.4080, 0.8625, 0.3483, 0.3787, 0.2650, 0.5320, 0.5272],
[0.6257, 0.4060, 0.8300, 0.2333, 0.4688, 0.2583, 0.7050, 0.5633],
[0.0000, 0.0000, 0.7553, 0.2722, 0.3875, 0.2550, 0.5125, 0.5633],
[0.6304, 0.4024, 0.8925, 0.4800, 0.3938, 0.4817, 0.7485, 0.5297],
[0.6157, 0.4102, 0.8512, 0.3817, 0.3613, 0.3667, 0.5096, 0.5890],
[0.6175, 0.3957, 0.8700, 0.4817, 0.4663, 0.5133, 0.5800, 0.5517],
[0.6135, 0.3994, 0.7912, 0.3050, 0.3625, 0.3050, 0.5838, 0.5050],
[0.6259, 0.4156, 0.8813, 0.3183, 0.4775, 0.1867, 0.6219, 0.4960]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05502122991310898
step: 73
running loss: 0.0007537154782617668
Train Steps: 73/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6205, 0.4004, 0.8938, 0.4883, 0.3663, 0.5000, 0.6357, 0.4947],
[0.6182, 0.3972, 0.8552, 0.5914, 0.3683, 0.4181, 0.5688, 0.5378],
[0.6225, 0.4196, 0.8788, 0.3467, 0.3750, 0.3400, 0.5413, 0.5433],
[0.6185, 0.4079, 0.8838, 0.4617, 0.4838, 0.5650, 0.6175, 0.5850],
[0.6339, 0.4102, 0.8588, 0.3133, 0.4425, 0.2117, 0.6417, 0.5089],
[0.6201, 0.4151, 0.8588, 0.5467, 0.3700, 0.3950, 0.5637, 0.5933],
[ nan, nan, 0.9088, 0.3783, 0.4562, 0.2617, 0.6741, 0.5575],
[0.6260, 0.4161, 0.9000, 0.3833, 0.4450, 0.2133, 0.6237, 0.4986]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5918, 0.3869, 0.8965, 0.4814, 0.3500, 0.4986, 0.6200, 0.5045],
[0.6109, 0.3999, 0.8538, 0.5933, 0.3659, 0.4532, 0.5646, 0.5465],
[0.6070, 0.4145, 0.8305, 0.3525, 0.3421, 0.3375, 0.5324, 0.5634],
[0.6302, 0.4250, 0.8856, 0.4422, 0.4552, 0.5652, 0.6061, 0.5706],
[0.6146, 0.4082, 0.8555, 0.3182, 0.4298, 0.2219, 0.6388, 0.5193],
[0.6136, 0.4235, 0.8473, 0.5513, 0.3558, 0.4063, 0.5634, 0.5982],
[0.2057, 0.1608, 0.9028, 0.3820, 0.4332, 0.2708, 0.6609, 0.5754],
[0.6079, 0.4167, 0.8930, 0.3856, 0.4246, 0.2257, 0.6196, 0.5225]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6205, 0.4004, 0.8938, 0.4883, 0.3663, 0.5000, 0.6357, 0.4947],
[0.6182, 0.3972, 0.8552, 0.5914, 0.3683, 0.4181, 0.5688, 0.5378],
[0.6225, 0.4196, 0.8788, 0.3467, 0.3750, 0.3400, 0.5412, 0.5433],
[0.6184, 0.4079, 0.8838, 0.4617, 0.4837, 0.5650, 0.6175, 0.5850],
[0.6339, 0.4102, 0.8587, 0.3133, 0.4425, 0.2117, 0.6417, 0.5089],
[0.6202, 0.4151, 0.8587, 0.5467, 0.3700, 0.3950, 0.5638, 0.5933],
[0.0000, 0.0000, 0.9087, 0.3783, 0.4563, 0.2617, 0.6741, 0.5575],
[0.6260, 0.4161, 0.9000, 0.3833, 0.4450, 0.2133, 0.6237, 0.4986]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05629452761786524
step: 74
running loss: 0.0007607368597008817
Train Steps: 74/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6182, 0.3998, 0.8793, 0.4191, 0.3552, 0.4285, 0.6038, 0.5312],
[0.6249, 0.4138, 0.9038, 0.4517, 0.3862, 0.4917, 0.6138, 0.5333],
[ nan, nan, 0.7612, 0.3250, 0.4037, 0.2533, 0.5438, 0.5767],
[0.6229, 0.4107, 0.8137, 0.2883, 0.4750, 0.1717, 0.5813, 0.5400],
[0.6241, 0.4143, 0.8938, 0.4650, 0.4075, 0.5350, 0.6250, 0.5550],
[0.6177, 0.4086, 0.8738, 0.3950, 0.3775, 0.5600, 0.6225, 0.5700],
[0.6201, 0.4151, 0.8588, 0.5467, 0.3700, 0.3950, 0.5637, 0.5933],
[0.6199, 0.4093, 0.7913, 0.2533, 0.4288, 0.2467, 0.5975, 0.5700]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.5973, 0.3953, 0.8694, 0.4266, 0.3525, 0.4234, 0.5897, 0.5375],
[ 0.5847, 0.4172, 0.8889, 0.4558, 0.3766, 0.4846, 0.6057, 0.5288],
[-0.0367, -0.0179, 0.7660, 0.3021, 0.4063, 0.2443, 0.5496, 0.5709],
[ 0.5803, 0.4091, 0.8079, 0.2855, 0.4667, 0.1643, 0.5777, 0.5374],
[ 0.6129, 0.4125, 0.8918, 0.4804, 0.4105, 0.5255, 0.6131, 0.5526],
[ 0.6146, 0.4240, 0.8785, 0.4078, 0.3761, 0.5326, 0.6223, 0.5452],
[ 0.6074, 0.4237, 0.8493, 0.5601, 0.3660, 0.3887, 0.5702, 0.5769],
[ 0.5856, 0.4142, 0.7920, 0.2483, 0.4149, 0.2620, 0.5998, 0.5645]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6182, 0.3998, 0.8793, 0.4191, 0.3552, 0.4285, 0.6038, 0.5312],
[0.6249, 0.4138, 0.9038, 0.4517, 0.3862, 0.4917, 0.6137, 0.5333],
[0.0000, 0.0000, 0.7613, 0.3250, 0.4038, 0.2533, 0.5437, 0.5767],
[0.6229, 0.4107, 0.8138, 0.2883, 0.4750, 0.1717, 0.5813, 0.5400],
[0.6241, 0.4142, 0.8938, 0.4650, 0.4075, 0.5350, 0.6250, 0.5550],
[0.6177, 0.4085, 0.8737, 0.3950, 0.3775, 0.5600, 0.6225, 0.5700],
[0.6202, 0.4151, 0.8587, 0.5467, 0.3700, 0.3950, 0.5638, 0.5933],
[0.6198, 0.4093, 0.7912, 0.2533, 0.4288, 0.2467, 0.5975, 0.5700]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05648698155710008
step: 75
running loss: 0.0007531597540946678
Train Steps: 75/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6208, 0.4082, 0.8538, 0.3067, 0.3588, 0.3717, 0.6112, 0.5517],
[0.6275, 0.4024, 0.8600, 0.2283, 0.5350, 0.1800, 0.7074, 0.5413],
[0.6284, 0.4127, 0.8538, 0.5867, 0.4363, 0.5083, 0.6038, 0.5433],
[0.6200, 0.3993, 0.8519, 0.4923, 0.3962, 0.4717, 0.6013, 0.5433],
[0.6196, 0.4090, 0.8450, 0.3900, 0.3575, 0.3933, 0.5975, 0.5583],
[0.6168, 0.4055, 0.7575, 0.2950, 0.4050, 0.2717, 0.5938, 0.6167],
[ nan, nan, 0.8488, 0.2300, 0.5563, 0.2100, 0.7390, 0.5679],
[0.6109, 0.3943, 0.8525, 0.4950, 0.4338, 0.4800, 0.5449, 0.5383]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.5860, 0.3923, 0.8425, 0.3362, 0.3515, 0.3928, 0.5738, 0.5406],
[ 0.6200, 0.4110, 0.8593, 0.2493, 0.5200, 0.1874, 0.6884, 0.5160],
[ 0.5664, 0.3781, 0.8495, 0.6168, 0.4182, 0.5069, 0.5700, 0.5070],
[ 0.5546, 0.3733, 0.8446, 0.5169, 0.3833, 0.4792, 0.5760, 0.5295],
[ 0.6115, 0.4124, 0.8515, 0.4124, 0.3485, 0.3957, 0.5713, 0.5496],
[ 0.5548, 0.3851, 0.7570, 0.3027, 0.3813, 0.2792, 0.5600, 0.6106],
[-0.0340, -0.0110, 0.8601, 0.2618, 0.5085, 0.2280, 0.7064, 0.5195],
[ 0.5388, 0.3658, 0.8529, 0.5009, 0.4163, 0.4864, 0.5184, 0.5185]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6208, 0.4082, 0.8537, 0.3067, 0.3587, 0.3717, 0.6112, 0.5517],
[0.6275, 0.4024, 0.8600, 0.2283, 0.5350, 0.1800, 0.7074, 0.5413],
[0.6284, 0.4127, 0.8537, 0.5867, 0.4363, 0.5083, 0.6037, 0.5433],
[0.6200, 0.3993, 0.8519, 0.4923, 0.3963, 0.4717, 0.6012, 0.5433],
[0.6196, 0.4090, 0.8450, 0.3900, 0.3575, 0.3933, 0.5975, 0.5583],
[0.6168, 0.4055, 0.7575, 0.2950, 0.4050, 0.2717, 0.5938, 0.6167],
[0.0000, 0.0000, 0.8487, 0.2300, 0.5562, 0.2100, 0.7390, 0.5679],
[0.6109, 0.3943, 0.8525, 0.4950, 0.4338, 0.4800, 0.5449, 0.5383]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05719406365824398
step: 76
running loss: 0.0007525534691874208
Train Steps: 76/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6361, 0.4076, 0.8862, 0.5350, 0.3713, 0.4650, 0.6654, 0.5297],
[0.6185, 0.4042, 0.7700, 0.2250, 0.4062, 0.2117, 0.5763, 0.5150],
[0.6038, 0.3946, 0.8413, 0.4883, 0.3563, 0.4550, 0.5266, 0.4693],
[0.6250, 0.4106, 0.8700, 0.3717, 0.3588, 0.4967, 0.6038, 0.5167],
[0.6142, 0.3982, 0.8650, 0.4883, 0.3912, 0.4317, 0.5315, 0.5350],
[0.6175, 0.3957, 0.8700, 0.4817, 0.4662, 0.5133, 0.5800, 0.5517],
[0.6100, 0.4016, 0.8600, 0.5067, 0.4612, 0.5233, 0.5086, 0.5519],
[0.6120, 0.4014, 0.6863, 0.2817, 0.3700, 0.2783, 0.5513, 0.5667]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5419, 0.3606, 0.9036, 0.5570, 0.3769, 0.4674, 0.6729, 0.5537],
[0.5144, 0.3454, 0.7958, 0.2320, 0.4242, 0.1981, 0.5915, 0.5206],
[0.5326, 0.3526, 0.8689, 0.5011, 0.3797, 0.4656, 0.5266, 0.5109],
[0.5822, 0.3942, 0.8984, 0.3880, 0.3711, 0.5033, 0.6150, 0.5528],
[0.5335, 0.3495, 0.8842, 0.5127, 0.3977, 0.4380, 0.5443, 0.5262],
[0.5281, 0.3587, 0.8922, 0.4874, 0.4806, 0.4987, 0.5777, 0.5571],
[0.5011, 0.3317, 0.8862, 0.5422, 0.4830, 0.5021, 0.5015, 0.5560],
[0.5466, 0.3579, 0.7138, 0.2882, 0.3758, 0.2871, 0.5510, 0.5647]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6361, 0.4076, 0.8863, 0.5350, 0.3713, 0.4650, 0.6654, 0.5297],
[0.6184, 0.4042, 0.7700, 0.2250, 0.4062, 0.2117, 0.5763, 0.5150],
[0.6038, 0.3946, 0.8413, 0.4883, 0.3562, 0.4550, 0.5266, 0.4693],
[0.6250, 0.4105, 0.8700, 0.3717, 0.3587, 0.4967, 0.6037, 0.5167],
[0.6143, 0.3982, 0.8650, 0.4883, 0.3913, 0.4317, 0.5315, 0.5350],
[0.6175, 0.3957, 0.8700, 0.4817, 0.4663, 0.5133, 0.5800, 0.5517],
[0.6100, 0.4016, 0.8600, 0.5067, 0.4613, 0.5233, 0.5086, 0.5519],
[0.6120, 0.4013, 0.6862, 0.2817, 0.3700, 0.2783, 0.5512, 0.5667]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05860871459299233
step: 77
running loss: 0.000761152137571329
Train Steps: 77/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6031, 0.3986, 0.7462, 0.2833, 0.3638, 0.2717, 0.5253, 0.4726],
[0.6196, 0.4094, 0.7562, 0.2817, 0.3937, 0.3183, 0.6013, 0.6183],
[0.6201, 0.4036, 0.8596, 0.3850, 0.3492, 0.3785, 0.5978, 0.5131],
[0.6200, 0.3913, 0.8788, 0.5217, 0.4075, 0.5100, 0.6060, 0.4913],
[0.6107, 0.4013, 0.8700, 0.4650, 0.5049, 0.5176, 0.5850, 0.5550],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3788, 0.4900, 0.7121, 0.5864],
[0.6197, 0.4091, 0.8800, 0.4783, 0.3538, 0.4767, 0.5950, 0.5550],
[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6068, 0.3924, 0.7669, 0.2712, 0.3886, 0.2821, 0.5187, 0.4813],
[0.5069, 0.3377, 0.7737, 0.2816, 0.4305, 0.3110, 0.6087, 0.6188],
[0.5604, 0.3725, 0.8664, 0.3686, 0.3614, 0.3860, 0.5699, 0.5144],
[0.4626, 0.2921, 0.8657, 0.5072, 0.4164, 0.4981, 0.5736, 0.4907],
[0.5271, 0.3523, 0.8900, 0.4604, 0.5042, 0.4929, 0.5649, 0.5500],
[0.5475, 0.3650, 0.8750, 0.4847, 0.3954, 0.4822, 0.7045, 0.5844],
[0.5740, 0.3863, 0.8746, 0.4546, 0.3666, 0.4736, 0.5707, 0.5636],
[0.4890, 0.3238, 0.8717, 0.5288, 0.3855, 0.3552, 0.5640, 0.5294]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6031, 0.3986, 0.7462, 0.2833, 0.3638, 0.2717, 0.5253, 0.4726],
[0.6196, 0.4094, 0.7563, 0.2817, 0.3938, 0.3183, 0.6012, 0.6183],
[0.6201, 0.4036, 0.8596, 0.3850, 0.3492, 0.3785, 0.5978, 0.5131],
[0.6199, 0.3913, 0.8788, 0.5217, 0.4075, 0.5100, 0.6060, 0.4913],
[0.6107, 0.4013, 0.8700, 0.4650, 0.5049, 0.5176, 0.5850, 0.5550],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3787, 0.4900, 0.7121, 0.5864],
[0.6197, 0.4091, 0.8800, 0.4783, 0.3537, 0.4767, 0.5950, 0.5550],
[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.060351279433234595
step: 78
running loss: 0.0007737343517081358
Train Steps: 78/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.8363, 0.3317, 0.3563, 0.3367, 0.5329, 0.5142],
[0.6224, 0.4179, 0.8700, 0.5683, 0.4037, 0.4683, 0.5650, 0.5600],
[0.6125, 0.4035, 0.7825, 0.3100, 0.3463, 0.4900, 0.5832, 0.5637],
[0.6200, 0.4059, 0.8700, 0.4900, 0.4163, 0.5000, 0.6162, 0.5467],
[0.6233, 0.4091, 0.8100, 0.2950, 0.3563, 0.3883, 0.6013, 0.5200],
[0.6146, 0.4124, 0.8800, 0.4867, 0.3800, 0.4500, 0.5106, 0.5524],
[ nan, nan, 0.8750, 0.2467, 0.5138, 0.2617, 0.7382, 0.5552],
[0.6189, 0.4049, 0.8888, 0.4417, 0.4213, 0.5200, 0.5988, 0.5633]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[-0.0143, -0.0024, 0.8038, 0.3344, 0.3643, 0.3234, 0.5648, 0.5117],
[ 0.6862, 0.4534, 0.8565, 0.5897, 0.4113, 0.4675, 0.5926, 0.5485],
[ 0.6735, 0.4393, 0.7570, 0.3208, 0.3560, 0.4950, 0.5838, 0.5183],
[ 0.6936, 0.4571, 0.8300, 0.4819, 0.4362, 0.5289, 0.6201, 0.5342],
[ 0.6809, 0.4478, 0.7915, 0.3032, 0.3672, 0.4096, 0.6177, 0.5297],
[ 0.6235, 0.4041, 0.8658, 0.5046, 0.3969, 0.4643, 0.5237, 0.5457],
[-0.0387, -0.0200, 0.8594, 0.2558, 0.5169, 0.2219, 0.7540, 0.5521],
[ 0.6800, 0.4418, 0.8547, 0.4494, 0.4336, 0.5273, 0.6129, 0.5608]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.8363, 0.3317, 0.3562, 0.3367, 0.5329, 0.5142],
[0.6224, 0.4179, 0.8700, 0.5683, 0.4038, 0.4683, 0.5650, 0.5600],
[0.6125, 0.4035, 0.7825, 0.3100, 0.3462, 0.4900, 0.5832, 0.5637],
[0.6199, 0.4059, 0.8700, 0.4900, 0.4162, 0.5000, 0.6162, 0.5467],
[0.6233, 0.4091, 0.8100, 0.2950, 0.3562, 0.3883, 0.6012, 0.5200],
[0.6146, 0.4124, 0.8800, 0.4867, 0.3800, 0.4500, 0.5106, 0.5524],
[0.0000, 0.0000, 0.8750, 0.2467, 0.5138, 0.2617, 0.7382, 0.5552],
[0.6189, 0.4049, 0.8888, 0.4417, 0.4212, 0.5200, 0.5987, 0.5633]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06108348035195377
step: 79
running loss: 0.0007732086120500476
Train Steps: 79/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6201, 0.4055, 0.7717, 0.1919, 0.4250, 0.2079, 0.5871, 0.5044],
[0.6296, 0.4008, 0.9150, 0.4317, 0.4263, 0.3050, 0.7256, 0.5413],
[0.6177, 0.4086, 0.8738, 0.3950, 0.3775, 0.5600, 0.6225, 0.5700],
[0.6168, 0.4081, 0.8438, 0.3367, 0.3500, 0.4667, 0.6212, 0.5400],
[0.6200, 0.4070, 0.8938, 0.4183, 0.3538, 0.4567, 0.6175, 0.5400],
[0.6261, 0.4131, 0.8938, 0.3550, 0.4000, 0.2683, 0.6188, 0.5283],
[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150],
[0.6249, 0.4142, 0.8350, 0.3283, 0.3613, 0.3700, 0.6188, 0.5400]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5224, 0.3419, 0.7550, 0.2004, 0.4276, 0.2089, 0.5920, 0.4913],
[0.5525, 0.3680, 0.9134, 0.4232, 0.4112, 0.3087, 0.7105, 0.5515],
[0.5902, 0.4045, 0.8558, 0.3962, 0.3823, 0.5594, 0.6005, 0.5678],
[0.5608, 0.3880, 0.8351, 0.3319, 0.3604, 0.4914, 0.5836, 0.5657],
[0.6617, 0.4348, 0.8837, 0.4245, 0.3588, 0.4808, 0.6075, 0.5278],
[0.5215, 0.3512, 0.8832, 0.3702, 0.4036, 0.2688, 0.6154, 0.5268],
[0.5126, 0.3345, 0.8717, 0.4826, 0.4417, 0.5923, 0.5912, 0.5300],
[0.5494, 0.3744, 0.8171, 0.3323, 0.3662, 0.3569, 0.6079, 0.5482]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6202, 0.4055, 0.7717, 0.1919, 0.4250, 0.2079, 0.5871, 0.5044],
[0.6296, 0.4008, 0.9150, 0.4317, 0.4263, 0.3050, 0.7256, 0.5413],
[0.6177, 0.4085, 0.8737, 0.3950, 0.3775, 0.5600, 0.6225, 0.5700],
[0.6168, 0.4081, 0.8438, 0.3367, 0.3500, 0.4667, 0.6212, 0.5400],
[0.6200, 0.4070, 0.8938, 0.4183, 0.3537, 0.4567, 0.6175, 0.5400],
[0.6261, 0.4131, 0.8938, 0.3550, 0.4000, 0.2683, 0.6187, 0.5283],
[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150],
[0.6249, 0.4142, 0.8350, 0.3283, 0.3613, 0.3700, 0.6187, 0.5400]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06227331746777054
step: 80
running loss: 0.0007784164683471318
Train Steps: 80/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6185, 0.4042, 0.7700, 0.2250, 0.4062, 0.2117, 0.5763, 0.5150],
[0.6258, 0.4143, 0.8525, 0.2617, 0.4950, 0.1667, 0.6219, 0.4967],
[0.6203, 0.4056, 0.8942, 0.4086, 0.3643, 0.3617, 0.5917, 0.5482],
[0.6350, 0.4043, 0.8738, 0.5650, 0.3850, 0.4750, 0.6401, 0.4950],
[0.6280, 0.4055, 0.8600, 0.5317, 0.3800, 0.4700, 0.6275, 0.5133],
[0.6296, 0.4008, 0.9150, 0.4317, 0.4263, 0.3050, 0.7256, 0.5413],
[0.6286, 0.4055, 0.9000, 0.4717, 0.3763, 0.4683, 0.7018, 0.5494],
[0.6211, 0.3935, 0.8636, 0.4841, 0.4417, 0.5126, 0.6331, 0.5268]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5728, 0.3780, 0.7630, 0.2122, 0.4002, 0.2459, 0.5436, 0.5268],
[0.5629, 0.3804, 0.8455, 0.2477, 0.4786, 0.1995, 0.5931, 0.5053],
[0.5817, 0.3744, 0.8778, 0.3963, 0.3435, 0.3911, 0.5819, 0.5604],
[0.6186, 0.3939, 0.8592, 0.5448, 0.3678, 0.5465, 0.6132, 0.5131],
[0.6066, 0.3892, 0.8570, 0.5147, 0.3561, 0.5063, 0.6153, 0.5325],
[0.5814, 0.3799, 0.9132, 0.3978, 0.3947, 0.3442, 0.6963, 0.5596],
[0.5945, 0.3818, 0.8924, 0.4424, 0.3485, 0.5178, 0.6996, 0.5596],
[0.5771, 0.3658, 0.8505, 0.4618, 0.4108, 0.5537, 0.5980, 0.5515]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6184, 0.4042, 0.7700, 0.2250, 0.4062, 0.2117, 0.5763, 0.5150],
[0.6258, 0.4143, 0.8525, 0.2617, 0.4950, 0.1667, 0.6219, 0.4967],
[0.6203, 0.4056, 0.8942, 0.4086, 0.3643, 0.3617, 0.5917, 0.5482],
[0.6350, 0.4043, 0.8737, 0.5650, 0.3850, 0.4750, 0.6401, 0.4950],
[0.6280, 0.4055, 0.8600, 0.5317, 0.3800, 0.4700, 0.6275, 0.5133],
[0.6296, 0.4008, 0.9150, 0.4317, 0.4263, 0.3050, 0.7256, 0.5413],
[0.6286, 0.4055, 0.9000, 0.4717, 0.3762, 0.4683, 0.7018, 0.5494],
[0.6211, 0.3935, 0.8636, 0.4841, 0.4417, 0.5126, 0.6331, 0.5268]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06305107554362621
step: 81
running loss: 0.000778408340044768
Train Steps: 81/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6154, 0.4112, 0.7037, 0.2317, 0.4238, 0.1833, 0.5350, 0.5600],
[0.6249, 0.4138, 0.9038, 0.4517, 0.3862, 0.4917, 0.6138, 0.5333],
[0.6196, 0.4094, 0.7562, 0.2817, 0.3937, 0.3183, 0.6013, 0.6183],
[0.6090, 0.4045, 0.7250, 0.2100, 0.4075, 0.2300, 0.5476, 0.5663],
[0.6117, 0.4018, 0.6562, 0.1967, 0.3738, 0.2550, 0.5280, 0.5103],
[0.6216, 0.4100, 0.7350, 0.2067, 0.4325, 0.2050, 0.5950, 0.5333],
[0.6185, 0.4067, 0.8838, 0.4450, 0.4037, 0.4733, 0.5213, 0.5142],
[0.6219, 0.4114, 0.8175, 0.2817, 0.3925, 0.2783, 0.5900, 0.5350]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5925, 0.3868, 0.7185, 0.2207, 0.4239, 0.1918, 0.5743, 0.5804],
[0.5980, 0.3963, 0.9158, 0.4424, 0.3656, 0.5126, 0.6424, 0.5339],
[0.6732, 0.4341, 0.7695, 0.2681, 0.3920, 0.3232, 0.6471, 0.6118],
[0.4580, 0.2868, 0.7231, 0.2085, 0.4095, 0.2476, 0.5547, 0.5508],
[0.5601, 0.3514, 0.6649, 0.2035, 0.3818, 0.2585, 0.5571, 0.5226],
[0.5739, 0.3568, 0.7445, 0.1915, 0.4272, 0.2050, 0.6112, 0.5174],
[0.5811, 0.3766, 0.8925, 0.4364, 0.3828, 0.4687, 0.5463, 0.5253],
[0.5821, 0.3855, 0.8140, 0.2603, 0.3948, 0.2667, 0.6166, 0.5354]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6154, 0.4112, 0.7038, 0.2317, 0.4238, 0.1833, 0.5350, 0.5600],
[0.6249, 0.4138, 0.9038, 0.4517, 0.3862, 0.4917, 0.6137, 0.5333],
[0.6196, 0.4094, 0.7563, 0.2817, 0.3938, 0.3183, 0.6012, 0.6183],
[0.6090, 0.4045, 0.7250, 0.2100, 0.4075, 0.2300, 0.5476, 0.5663],
[0.6116, 0.4018, 0.6562, 0.1967, 0.3738, 0.2550, 0.5280, 0.5103],
[0.6216, 0.4100, 0.7350, 0.2067, 0.4325, 0.2050, 0.5950, 0.5333],
[0.6185, 0.4067, 0.8838, 0.4450, 0.4038, 0.4733, 0.5213, 0.5142],
[0.6219, 0.4114, 0.8175, 0.2817, 0.3925, 0.2783, 0.5900, 0.5350]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06413436621369328
step: 82
running loss: 0.000782126417240162
Train Steps: 82/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6249, 0.4138, 0.9038, 0.4517, 0.3862, 0.4917, 0.6138, 0.5333],
[0.6161, 0.4076, 0.8900, 0.4667, 0.4125, 0.5917, 0.6262, 0.5367],
[0.6216, 0.4167, 0.8588, 0.5583, 0.3975, 0.5167, 0.5775, 0.5667],
[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466],
[0.6195, 0.4101, 0.8650, 0.3917, 0.3575, 0.4033, 0.5800, 0.5650],
[0.6156, 0.4125, 0.8850, 0.4833, 0.4550, 0.5817, 0.5765, 0.5084],
[0.6175, 0.4013, 0.7734, 0.2783, 0.4475, 0.1786, 0.5790, 0.5351],
[0.6127, 0.4118, 0.8650, 0.5083, 0.4088, 0.5367, 0.5300, 0.5456]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6515, 0.4266, 0.8918, 0.4172, 0.3766, 0.4620, 0.6430, 0.5268],
[0.6456, 0.4085, 0.8798, 0.4478, 0.4039, 0.5626, 0.6127, 0.5239],
[0.7003, 0.4583, 0.8623, 0.5334, 0.3712, 0.4893, 0.6281, 0.5466],
[0.6903, 0.4388, 0.7631, 0.3358, 0.3392, 0.3826, 0.5472, 0.5373],
[0.6365, 0.4038, 0.8620, 0.3614, 0.3483, 0.3893, 0.6020, 0.5475],
[0.6166, 0.4032, 0.8847, 0.4609, 0.4272, 0.5328, 0.6282, 0.5048],
[0.7030, 0.4594, 0.7801, 0.2450, 0.4328, 0.1511, 0.6083, 0.5073],
[0.6425, 0.4281, 0.8641, 0.4693, 0.4036, 0.5050, 0.5713, 0.5506]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6249, 0.4138, 0.9038, 0.4517, 0.3862, 0.4917, 0.6137, 0.5333],
[0.6161, 0.4076, 0.8900, 0.4667, 0.4125, 0.5917, 0.6263, 0.5367],
[0.6216, 0.4167, 0.8587, 0.5583, 0.3975, 0.5167, 0.5775, 0.5667],
[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466],
[0.6195, 0.4101, 0.8650, 0.3917, 0.3575, 0.4033, 0.5800, 0.5650],
[0.6155, 0.4124, 0.8850, 0.4833, 0.4550, 0.5817, 0.5765, 0.5084],
[0.6175, 0.4013, 0.7734, 0.2783, 0.4475, 0.1786, 0.5790, 0.5351],
[0.6127, 0.4118, 0.8650, 0.5083, 0.4087, 0.5367, 0.5300, 0.5456]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06510589212120976
step: 83
running loss: 0.0007844083388097562
Train Steps: 83/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.7525, 0.2291, 0.3838, 0.3017, 0.6050, 0.5667],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4012, 0.4633, 0.5338, 0.5767],
[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758],
[0.6229, 0.4066, 0.8513, 0.5717, 0.4500, 0.5050, 0.6025, 0.5350],
[0.6286, 0.4086, 0.8408, 0.2801, 0.4163, 0.2800, 0.6725, 0.5393],
[0.6076, 0.3958, 0.8700, 0.4667, 0.4546, 0.5046, 0.5231, 0.4960],
[0.6236, 0.3966, 0.8850, 0.4967, 0.3638, 0.4017, 0.5850, 0.5183],
[0.6200, 0.4055, 0.8011, 0.2988, 0.3842, 0.2798, 0.5949, 0.5183]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.1093, 0.0623, 0.7614, 0.2376, 0.4039, 0.2795, 0.6019, 0.5619],
[0.6374, 0.4181, 0.8749, 0.4911, 0.3949, 0.4465, 0.5443, 0.5621],
[0.7407, 0.4638, 0.8816, 0.4757, 0.3898, 0.5048, 0.6563, 0.4767],
[0.7346, 0.4880, 0.8432, 0.5665, 0.4289, 0.4709, 0.6206, 0.5230],
[0.7766, 0.4909, 0.8456, 0.2801, 0.4178, 0.2757, 0.6832, 0.5210],
[0.6897, 0.4571, 0.8626, 0.4530, 0.4290, 0.4688, 0.5380, 0.4883],
[0.6902, 0.4332, 0.8677, 0.4743, 0.3426, 0.3980, 0.5872, 0.5126],
[0.7270, 0.4772, 0.8036, 0.2919, 0.3839, 0.2818, 0.6136, 0.5013]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.7525, 0.2291, 0.3837, 0.3017, 0.6050, 0.5667],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4013, 0.4633, 0.5337, 0.5767],
[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758],
[0.6229, 0.4066, 0.8512, 0.5717, 0.4500, 0.5050, 0.6025, 0.5350],
[0.6286, 0.4086, 0.8408, 0.2801, 0.4162, 0.2800, 0.6725, 0.5393],
[0.6076, 0.3958, 0.8700, 0.4667, 0.4546, 0.5046, 0.5231, 0.4960],
[0.6236, 0.3965, 0.8850, 0.4967, 0.3638, 0.4017, 0.5850, 0.5183],
[0.6201, 0.4055, 0.8011, 0.2988, 0.3842, 0.2798, 0.5949, 0.5183]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06704556952172425
step: 84
running loss: 0.0007981615419252886
Train Steps: 84/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6273, 0.4143, 0.8750, 0.5700, 0.3987, 0.4717, 0.6013, 0.5467],
[0.6263, 0.4030, 0.9000, 0.4767, 0.3800, 0.5167, 0.6415, 0.4771],
[0.6267, 0.4080, 0.8438, 0.2633, 0.4763, 0.1800, 0.6259, 0.5240],
[ nan, nan, 0.8900, 0.3217, 0.5038, 0.2233, 0.6694, 0.5609],
[0.6114, 0.4018, 0.7213, 0.1967, 0.3763, 0.2700, 0.5875, 0.5533],
[0.6185, 0.4079, 0.8838, 0.4617, 0.4838, 0.5650, 0.6175, 0.5850],
[0.6234, 0.4023, 0.8888, 0.4633, 0.3975, 0.5767, 0.6400, 0.5183],
[0.6202, 0.4053, 0.8638, 0.5283, 0.4546, 0.5108, 0.5900, 0.5133]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7320, 0.4737, 0.8611, 0.5556, 0.3902, 0.4397, 0.5956, 0.5358],
[0.7077, 0.4610, 0.8938, 0.4741, 0.3591, 0.5033, 0.6193, 0.4845],
[0.7522, 0.4808, 0.8343, 0.2710, 0.4589, 0.1764, 0.6038, 0.5168],
[0.0814, 0.0406, 0.8817, 0.3188, 0.4925, 0.2216, 0.6584, 0.5543],
[0.6683, 0.4413, 0.7192, 0.2160, 0.3753, 0.2583, 0.5710, 0.5413],
[0.7060, 0.4613, 0.8823, 0.4435, 0.4619, 0.5227, 0.6069, 0.5665],
[0.6551, 0.4286, 0.8835, 0.4538, 0.3918, 0.5613, 0.6043, 0.5227],
[0.7188, 0.4664, 0.8615, 0.5288, 0.4406, 0.4852, 0.5693, 0.5099]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6273, 0.4143, 0.8750, 0.5700, 0.3988, 0.4717, 0.6012, 0.5467],
[0.6263, 0.4029, 0.9000, 0.4767, 0.3800, 0.5167, 0.6415, 0.4771],
[0.6267, 0.4080, 0.8438, 0.2633, 0.4762, 0.1800, 0.6259, 0.5240],
[0.0000, 0.0000, 0.8900, 0.3217, 0.5038, 0.2233, 0.6694, 0.5609],
[0.6114, 0.4018, 0.7212, 0.1967, 0.3762, 0.2700, 0.5875, 0.5533],
[0.6184, 0.4079, 0.8838, 0.4617, 0.4837, 0.5650, 0.6175, 0.5850],
[0.6234, 0.4023, 0.8888, 0.4633, 0.3975, 0.5767, 0.6400, 0.5183],
[0.6202, 0.4053, 0.8637, 0.5283, 0.4546, 0.5108, 0.5900, 0.5133]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0015, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06853765701816883
step: 85
running loss: 0.0008063253766843392
Train Steps: 85/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586],
[0.6202, 0.4064, 0.7879, 0.2179, 0.4567, 0.1725, 0.5955, 0.5478],
[0.6286, 0.3977, 0.9038, 0.4733, 0.3900, 0.4150, 0.7074, 0.5320],
[0.6200, 0.3913, 0.8788, 0.5217, 0.4075, 0.5100, 0.6060, 0.4913],
[0.6100, 0.4016, 0.8600, 0.5067, 0.4612, 0.5233, 0.5086, 0.5519],
[0.6173, 0.4114, 0.7325, 0.2500, 0.4213, 0.1917, 0.5338, 0.5700],
[0.6058, 0.3978, 0.8287, 0.3600, 0.3400, 0.4050, 0.5529, 0.5461],
[0.6308, 0.3990, 0.8688, 0.5183, 0.3950, 0.4983, 0.6388, 0.5133]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6508, 0.4336, 0.8535, 0.2768, 0.4638, 0.2824, 0.6922, 0.5507],
[0.6845, 0.4468, 0.7882, 0.2625, 0.4845, 0.1763, 0.5718, 0.5383],
[0.6801, 0.4236, 0.9062, 0.4683, 0.3671, 0.4290, 0.6874, 0.5161],
[0.6959, 0.4352, 0.8825, 0.5497, 0.4140, 0.4984, 0.5772, 0.4890],
[0.6354, 0.4205, 0.8702, 0.5328, 0.4810, 0.5111, 0.4839, 0.5492],
[0.5374, 0.3567, 0.7500, 0.2449, 0.4344, 0.2038, 0.5264, 0.5679],
[0.6251, 0.4128, 0.8308, 0.3663, 0.3539, 0.4017, 0.5425, 0.5324],
[0.6461, 0.3940, 0.8751, 0.5405, 0.4116, 0.4967, 0.6169, 0.5035]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586],
[0.6202, 0.4064, 0.7879, 0.2179, 0.4567, 0.1725, 0.5955, 0.5478],
[0.6286, 0.3977, 0.9038, 0.4733, 0.3900, 0.4150, 0.7074, 0.5320],
[0.6199, 0.3913, 0.8788, 0.5217, 0.4075, 0.5100, 0.6060, 0.4913],
[0.6100, 0.4016, 0.8600, 0.5067, 0.4613, 0.5233, 0.5086, 0.5519],
[0.6173, 0.4114, 0.7325, 0.2500, 0.4212, 0.1917, 0.5337, 0.5700],
[0.6058, 0.3978, 0.8288, 0.3600, 0.3400, 0.4050, 0.5529, 0.5461],
[0.6308, 0.3990, 0.8687, 0.5183, 0.3950, 0.4983, 0.6388, 0.5133]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06918519355531316
step: 86
running loss: 0.0008044789948292229
Train Steps: 86/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6353, 0.4128, 0.9138, 0.3533, 0.4688, 0.3250, 0.7145, 0.5991],
[0.6203, 0.4056, 0.8942, 0.4086, 0.3643, 0.3617, 0.5917, 0.5482],
[0.6156, 0.4125, 0.8850, 0.4833, 0.4550, 0.5817, 0.5765, 0.5084],
[0.6336, 0.4154, 0.8900, 0.2767, 0.4988, 0.2867, 0.7422, 0.5540],
[0.6127, 0.4084, 0.8700, 0.4467, 0.3987, 0.4317, 0.5013, 0.5471],
[0.6211, 0.3993, 0.7650, 0.1933, 0.4575, 0.1550, 0.5965, 0.4895],
[0.6263, 0.4030, 0.9000, 0.4767, 0.3800, 0.5167, 0.6415, 0.4771],
[ nan, nan, 0.7553, 0.2722, 0.3875, 0.2550, 0.5125, 0.5633]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6749, 0.4588, 0.8992, 0.3963, 0.4897, 0.3346, 0.7159, 0.6081],
[ 0.6886, 0.4441, 0.8908, 0.4452, 0.3752, 0.3636, 0.5976, 0.5500],
[ 0.6656, 0.4560, 0.8947, 0.5214, 0.4696, 0.5912, 0.5820, 0.5216],
[ 0.6618, 0.4416, 0.8677, 0.3127, 0.5169, 0.3047, 0.7389, 0.5555],
[ 0.6127, 0.4198, 0.8645, 0.4757, 0.4118, 0.4427, 0.4806, 0.5549],
[ 0.6725, 0.4273, 0.7533, 0.2409, 0.4704, 0.1748, 0.5897, 0.4989],
[ 0.6451, 0.4203, 0.8935, 0.5194, 0.3952, 0.5392, 0.6293, 0.4988],
[-0.0591, -0.0411, 0.7639, 0.3055, 0.4165, 0.2820, 0.4991, 0.5784]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6353, 0.4128, 0.9137, 0.3533, 0.4688, 0.3250, 0.7145, 0.5991],
[0.6203, 0.4056, 0.8942, 0.4086, 0.3643, 0.3617, 0.5917, 0.5482],
[0.6155, 0.4124, 0.8850, 0.4833, 0.4550, 0.5817, 0.5765, 0.5084],
[0.6336, 0.4154, 0.8900, 0.2767, 0.4988, 0.2867, 0.7422, 0.5540],
[0.6127, 0.4084, 0.8700, 0.4467, 0.3988, 0.4317, 0.5013, 0.5471],
[0.6211, 0.3993, 0.7650, 0.1933, 0.4575, 0.1550, 0.5965, 0.4895],
[0.6263, 0.4029, 0.9000, 0.4767, 0.3800, 0.5167, 0.6415, 0.4771],
[0.0000, 0.0000, 0.7553, 0.2722, 0.3875, 0.2550, 0.5125, 0.5633]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.06988749319862109
step: 87
running loss: 0.0008033045195243803
Train Steps: 87/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6274, 0.4003, 0.8638, 0.5967, 0.3688, 0.4900, 0.6108, 0.4661],
[0.6293, 0.4024, 0.8750, 0.5000, 0.4012, 0.5733, 0.7121, 0.5633],
[0.6186, 0.4154, 0.6825, 0.2633, 0.4150, 0.2300, 0.5713, 0.5517],
[0.6332, 0.4165, 0.9100, 0.3350, 0.4188, 0.3683, 0.7438, 0.5528],
[0.6179, 0.3961, 0.8347, 0.6020, 0.3887, 0.4624, 0.5714, 0.5373],
[0.6260, 0.4253, 0.8938, 0.4400, 0.3675, 0.3650, 0.5675, 0.5767],
[0.6339, 0.4081, 0.8425, 0.5417, 0.3850, 0.4833, 0.7335, 0.5760],
[0.6143, 0.4055, 0.8150, 0.2767, 0.3825, 0.2567, 0.5173, 0.4901]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6093, 0.3767, 0.8861, 0.6041, 0.4109, 0.4834, 0.6146, 0.5040],
[0.5823, 0.3717, 0.9175, 0.5160, 0.4458, 0.5912, 0.6775, 0.5757],
[0.6102, 0.4081, 0.7195, 0.2583, 0.4323, 0.2579, 0.5604, 0.5746],
[0.5733, 0.3835, 0.9435, 0.3738, 0.4507, 0.3760, 0.7062, 0.5696],
[0.6482, 0.4254, 0.8759, 0.5979, 0.4299, 0.4589, 0.5743, 0.5528],
[0.6330, 0.4260, 0.9245, 0.4645, 0.4103, 0.3689, 0.5681, 0.5909],
[0.6020, 0.3900, 0.8795, 0.5706, 0.4186, 0.5017, 0.7201, 0.5703],
[0.5623, 0.3640, 0.8323, 0.2971, 0.4104, 0.2730, 0.5071, 0.5186]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6274, 0.4003, 0.8637, 0.5967, 0.3688, 0.4900, 0.6108, 0.4661],
[0.6293, 0.4024, 0.8750, 0.5000, 0.4013, 0.5733, 0.7121, 0.5633],
[0.6186, 0.4154, 0.6825, 0.2633, 0.4150, 0.2300, 0.5713, 0.5517],
[0.6332, 0.4165, 0.9100, 0.3350, 0.4187, 0.3683, 0.7438, 0.5528],
[0.6179, 0.3961, 0.8347, 0.6020, 0.3887, 0.4624, 0.5714, 0.5373],
[0.6260, 0.4253, 0.8938, 0.4400, 0.3675, 0.3650, 0.5675, 0.5767],
[0.6339, 0.4081, 0.8425, 0.5417, 0.3850, 0.4833, 0.7335, 0.5760],
[0.6143, 0.4055, 0.8150, 0.2767, 0.3825, 0.2567, 0.5173, 0.4901]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0706424161180621
step: 88
running loss: 0.0008027547286143421
Train Steps: 88/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6265, 0.4251, 0.7113, 0.3550, 0.4375, 0.2117, 0.5587, 0.6118],
[ nan, nan, 0.8675, 0.2833, 0.5350, 0.1983, 0.6678, 0.5621],
[ nan, nan, 0.7525, 0.2291, 0.3838, 0.3017, 0.6050, 0.5667],
[0.6226, 0.4185, 0.8850, 0.5500, 0.3800, 0.4250, 0.5625, 0.5617],
[0.6132, 0.4066, 0.7259, 0.2402, 0.3588, 0.3300, 0.6000, 0.5600],
[0.6206, 0.4123, 0.7175, 0.2400, 0.3887, 0.2933, 0.6225, 0.5750],
[0.6102, 0.4005, 0.8688, 0.5100, 0.4813, 0.5400, 0.5404, 0.5064],
[0.6200, 0.4112, 0.8862, 0.4100, 0.3638, 0.4917, 0.6088, 0.6050]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7329, 0.4968, 0.7483, 0.3786, 0.4358, 0.2171, 0.5631, 0.5937],
[0.0535, 0.0381, 0.8644, 0.2943, 0.5412, 0.2195, 0.6699, 0.5556],
[0.1255, 0.0737, 0.7721, 0.2515, 0.4036, 0.3109, 0.5987, 0.5628],
[0.7190, 0.4711, 0.9182, 0.5764, 0.3963, 0.4302, 0.5831, 0.5388],
[0.6366, 0.4122, 0.7466, 0.2615, 0.3732, 0.3417, 0.6117, 0.5708],
[0.6869, 0.4533, 0.7324, 0.2783, 0.3922, 0.2976, 0.6281, 0.5651],
[0.6615, 0.4455, 0.8908, 0.5147, 0.4825, 0.5266, 0.5687, 0.4876],
[0.6953, 0.4555, 0.9070, 0.4323, 0.3842, 0.5011, 0.6273, 0.5798]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6265, 0.4251, 0.7113, 0.3550, 0.4375, 0.2117, 0.5587, 0.6118],
[0.0000, 0.0000, 0.8675, 0.2833, 0.5350, 0.1983, 0.6678, 0.5621],
[0.0000, 0.0000, 0.7525, 0.2291, 0.3837, 0.3017, 0.6050, 0.5667],
[0.6226, 0.4185, 0.8850, 0.5500, 0.3800, 0.4250, 0.5625, 0.5617],
[0.6132, 0.4066, 0.7259, 0.2402, 0.3587, 0.3300, 0.6000, 0.5600],
[0.6206, 0.4123, 0.7175, 0.2400, 0.3887, 0.2933, 0.6225, 0.5750],
[0.6102, 0.4005, 0.8687, 0.5100, 0.4812, 0.5400, 0.5404, 0.5064],
[0.6200, 0.4112, 0.8863, 0.4100, 0.3638, 0.4917, 0.6087, 0.6050]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.07201781774347182
step: 89
running loss: 0.0008091889634097958
Train Steps: 89/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837],
[ nan, nan, 0.8625, 0.2550, 0.5487, 0.2200, 0.7335, 0.5737],
[0.6131, 0.4037, 0.6907, 0.2819, 0.3688, 0.2700, 0.5217, 0.5680],
[0.6034, 0.4011, 0.7350, 0.2533, 0.3438, 0.3367, 0.5516, 0.5084],
[0.6296, 0.4008, 0.9150, 0.4317, 0.4263, 0.3050, 0.7256, 0.5413],
[0.6160, 0.4086, 0.8775, 0.3983, 0.3750, 0.3783, 0.5128, 0.4882],
[0.6127, 0.4084, 0.8700, 0.4467, 0.3987, 0.4317, 0.5013, 0.5471],
[0.6222, 0.4172, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6060, 0.3917, 0.6771, 0.3172, 0.3757, 0.2812, 0.5570, 0.5812],
[-0.0581, -0.0375, 0.8625, 0.2447, 0.5502, 0.2356, 0.7400, 0.5764],
[ 0.5796, 0.3699, 0.6941, 0.2917, 0.3760, 0.2843, 0.5499, 0.5678],
[ 0.5950, 0.3760, 0.7373, 0.2582, 0.3706, 0.3330, 0.5954, 0.5064],
[ 0.6301, 0.3950, 0.9330, 0.4419, 0.4240, 0.3126, 0.7530, 0.5388],
[ 0.6633, 0.4413, 0.8922, 0.4290, 0.3791, 0.3910, 0.5547, 0.5141],
[ 0.5718, 0.3831, 0.8884, 0.4709, 0.4058, 0.4407, 0.5156, 0.5442],
[ 0.5806, 0.3847, 0.9144, 0.5505, 0.3841, 0.4862, 0.5937, 0.5728]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837],
[0.0000, 0.0000, 0.8625, 0.2550, 0.5487, 0.2200, 0.7335, 0.5737],
[0.6131, 0.4036, 0.6907, 0.2819, 0.3688, 0.2700, 0.5217, 0.5680],
[0.6033, 0.4011, 0.7350, 0.2533, 0.3438, 0.3367, 0.5516, 0.5084],
[0.6296, 0.4008, 0.9150, 0.4317, 0.4263, 0.3050, 0.7256, 0.5413],
[0.6160, 0.4086, 0.8775, 0.3983, 0.3750, 0.3783, 0.5128, 0.4882],
[0.6127, 0.4084, 0.8700, 0.4467, 0.3988, 0.4317, 0.5013, 0.5471],
[0.6222, 0.4171, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0725348553241929
step: 90
running loss: 0.0008059428369354767
Valid Steps: 10/10 Loss: nan 6.2924
--------------------------------------------------
Epoch: 8 Train Loss: 0.0008 Valid Loss: nan
--------------------------------------------------
size of train loader is: 90
torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6222, 0.4172, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633],
[0.6266, 0.4067, 0.8588, 0.2867, 0.4300, 0.2850, 0.6325, 0.5267],
[ nan, nan, 0.8675, 0.2833, 0.5350, 0.1983, 0.6678, 0.5621],
[0.6201, 0.3970, 0.8413, 0.4950, 0.4413, 0.5183, 0.6088, 0.5400],
[0.6092, 0.4001, 0.8638, 0.4867, 0.4288, 0.5367, 0.5484, 0.5064],
[0.6179, 0.3998, 0.8396, 0.3505, 0.3552, 0.3768, 0.6064, 0.5329],
[0.6091, 0.3997, 0.8314, 0.4334, 0.3788, 0.4550, 0.5213, 0.5656],
[0.6211, 0.4069, 0.8750, 0.5117, 0.4150, 0.4900, 0.5875, 0.5167]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.5809, 0.3892, 0.8763, 0.5048, 0.3556, 0.4534, 0.5933, 0.5725],
[ 0.5585, 0.3613, 0.8566, 0.2598, 0.4254, 0.2554, 0.6410, 0.5312],
[-0.0281, -0.0072, 0.8385, 0.2609, 0.5153, 0.1945, 0.6909, 0.5716],
[ 0.6296, 0.4013, 0.8372, 0.4857, 0.4138, 0.5036, 0.6315, 0.5534],
[ 0.5775, 0.3675, 0.8493, 0.4625, 0.4122, 0.5282, 0.5725, 0.5064],
[ 0.6405, 0.4147, 0.8342, 0.3335, 0.3355, 0.3601, 0.6054, 0.5336],
[ 0.5747, 0.3587, 0.8181, 0.4326, 0.3595, 0.4352, 0.5605, 0.5659],
[ 0.5893, 0.3826, 0.8734, 0.4997, 0.3901, 0.4934, 0.6083, 0.5265]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6222, 0.4171, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633],
[0.6266, 0.4067, 0.8587, 0.2867, 0.4300, 0.2850, 0.6325, 0.5267],
[0.0000, 0.0000, 0.8675, 0.2833, 0.5350, 0.1983, 0.6678, 0.5621],
[0.6201, 0.3970, 0.8413, 0.4950, 0.4412, 0.5183, 0.6087, 0.5400],
[0.6092, 0.4001, 0.8637, 0.4867, 0.4288, 0.5367, 0.5484, 0.5064],
[0.6179, 0.3998, 0.8396, 0.3505, 0.3552, 0.3768, 0.6064, 0.5329],
[0.6091, 0.3997, 0.8314, 0.4334, 0.3787, 0.4550, 0.5213, 0.5656],
[0.6211, 0.4069, 0.8750, 0.5117, 0.4150, 0.4900, 0.5875, 0.5167]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0004860513436142355
step: 1
running loss: 0.0004860513436142355
Train Steps: 1/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6127, 0.4115, 0.7163, 0.2883, 0.3625, 0.2950, 0.5327, 0.5495],
[0.6228, 0.4119, 0.7938, 0.2233, 0.4674, 0.1773, 0.6188, 0.5433],
[0.6248, 0.4032, 0.7738, 0.1900, 0.4813, 0.1400, 0.5941, 0.4904],
[0.6145, 0.3983, 0.8700, 0.5017, 0.4400, 0.4800, 0.5375, 0.5750],
[0.6093, 0.3990, 0.8400, 0.4333, 0.3688, 0.4633, 0.5560, 0.5656],
[0.6199, 0.4071, 0.7600, 0.2117, 0.4037, 0.2767, 0.6138, 0.5550],
[0.6339, 0.4118, 0.7988, 0.5800, 0.3912, 0.4583, 0.7343, 0.5760],
[0.6115, 0.3998, 0.7063, 0.2383, 0.4037, 0.1950, 0.5320, 0.4993]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4761, 0.3098, 0.7138, 0.2520, 0.3472, 0.2872, 0.5280, 0.5661],
[0.5404, 0.3577, 0.7892, 0.2008, 0.4592, 0.1701, 0.6062, 0.5569],
[0.5778, 0.3732, 0.7722, 0.2057, 0.4636, 0.1201, 0.5917, 0.4919],
[0.5289, 0.3369, 0.8543, 0.4854, 0.4132, 0.4918, 0.5679, 0.5458],
[0.4861, 0.3146, 0.8276, 0.4051, 0.3561, 0.4725, 0.5445, 0.5689],
[0.5397, 0.3539, 0.7541, 0.1826, 0.4015, 0.2716, 0.5978, 0.5660],
[0.5419, 0.3511, 0.7921, 0.5433, 0.3567, 0.4557, 0.6956, 0.5577],
[0.5144, 0.3353, 0.7089, 0.2007, 0.3883, 0.1958, 0.5168, 0.5069]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6127, 0.4114, 0.7163, 0.2883, 0.3625, 0.2950, 0.5327, 0.5495],
[0.6228, 0.4119, 0.7937, 0.2233, 0.4674, 0.1773, 0.6187, 0.5433],
[0.6248, 0.4032, 0.7738, 0.1900, 0.4812, 0.1400, 0.5941, 0.4904],
[0.6145, 0.3983, 0.8700, 0.5017, 0.4400, 0.4800, 0.5375, 0.5750],
[0.6093, 0.3990, 0.8400, 0.4333, 0.3688, 0.4633, 0.5560, 0.5656],
[0.6199, 0.4071, 0.7600, 0.2117, 0.4038, 0.2767, 0.6137, 0.5550],
[0.6339, 0.4118, 0.7987, 0.5800, 0.3913, 0.4583, 0.7343, 0.5760],
[0.6115, 0.3998, 0.7063, 0.2383, 0.4038, 0.1950, 0.5320, 0.4993]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0020, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0020, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.00245886217453517
step: 2
running loss: 0.001229431087267585
Train Steps: 2/90 Loss: 0.0012 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6215, 0.4119, 0.7688, 0.2300, 0.4200, 0.2283, 0.5925, 0.5317],
[0.6200, 0.4118, 0.8287, 0.4017, 0.3775, 0.2833, 0.5391, 0.5799],
[ nan, nan, 0.6412, 0.1900, 0.4238, 0.1883, 0.5487, 0.5700],
[0.6201, 0.4017, 0.8871, 0.4621, 0.3517, 0.4675, 0.5999, 0.5106],
[0.6258, 0.4038, 0.8750, 0.4883, 0.3900, 0.5500, 0.6375, 0.5217],
[0.6214, 0.3982, 0.8938, 0.4517, 0.3663, 0.4083, 0.5863, 0.5050],
[0.6176, 0.4030, 0.8850, 0.4850, 0.3688, 0.4050, 0.5312, 0.5783],
[0.6304, 0.4024, 0.8925, 0.4800, 0.3937, 0.4817, 0.7485, 0.5297]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.4858, 0.3245, 0.7570, 0.2105, 0.4402, 0.2475, 0.5965, 0.5613],
[0.5709, 0.3834, 0.7998, 0.3829, 0.3771, 0.2972, 0.5274, 0.5805],
[0.0874, 0.0654, 0.6780, 0.1980, 0.4254, 0.2052, 0.5490, 0.5937],
[0.5820, 0.3664, 0.8662, 0.4281, 0.3647, 0.4916, 0.5814, 0.5280],
[0.5865, 0.3777, 0.8605, 0.4721, 0.3877, 0.5724, 0.6234, 0.5273],
[0.6304, 0.4000, 0.8916, 0.4334, 0.3792, 0.4218, 0.5842, 0.5127],
[0.5845, 0.3798, 0.8789, 0.4629, 0.3794, 0.4046, 0.5080, 0.5814],
[0.6068, 0.3876, 0.8614, 0.4630, 0.4006, 0.4813, 0.7141, 0.5286]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6215, 0.4119, 0.7688, 0.2300, 0.4200, 0.2283, 0.5925, 0.5317],
[0.6200, 0.4118, 0.8288, 0.4017, 0.3775, 0.2833, 0.5391, 0.5799],
[0.0000, 0.0000, 0.6413, 0.1900, 0.4238, 0.1883, 0.5487, 0.5700],
[0.6201, 0.4017, 0.8871, 0.4621, 0.3517, 0.4675, 0.5999, 0.5106],
[0.6258, 0.4038, 0.8750, 0.4883, 0.3900, 0.5500, 0.6375, 0.5217],
[0.6214, 0.3982, 0.8938, 0.4517, 0.3663, 0.4083, 0.5863, 0.5050],
[0.6176, 0.4030, 0.8850, 0.4850, 0.3688, 0.4050, 0.5312, 0.5783],
[0.6304, 0.4024, 0.8925, 0.4800, 0.3938, 0.4817, 0.7485, 0.5297]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0034466659708414227
step: 3
running loss: 0.0011488886569471408
Train Steps: 3/90 Loss: 0.0011 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6205, 0.4012, 0.8675, 0.3283, 0.3713, 0.3050, 0.5813, 0.5117],
[0.6175, 0.4091, 0.7863, 0.2800, 0.3638, 0.3583, 0.6188, 0.5433],
[ nan, nan, 0.8525, 0.2217, 0.5413, 0.2367, 0.7367, 0.5482],
[0.6145, 0.3983, 0.8700, 0.5017, 0.4400, 0.4800, 0.5375, 0.5750],
[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758],
[0.6279, 0.4008, 0.8600, 0.4883, 0.4325, 0.5283, 0.7010, 0.5378],
[0.6293, 0.4097, 0.8800, 0.2517, 0.5262, 0.2600, 0.7430, 0.5378],
[0.6214, 0.4116, 0.7750, 0.2317, 0.4487, 0.1883, 0.6200, 0.5400]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5710, 0.3786, 0.8432, 0.3172, 0.3542, 0.2946, 0.5317, 0.5189],
[0.5667, 0.3979, 0.7542, 0.2634, 0.3320, 0.3626, 0.5838, 0.5578],
[0.0320, 0.0410, 0.8086, 0.2045, 0.5000, 0.2239, 0.6892, 0.5512],
[0.6161, 0.4025, 0.8187, 0.4901, 0.4073, 0.4758, 0.5308, 0.5540],
[0.5866, 0.3672, 0.8515, 0.4788, 0.3924, 0.5120, 0.6089, 0.4946],
[0.5726, 0.3708, 0.8269, 0.4869, 0.4068, 0.5184, 0.6734, 0.5451],
[0.6295, 0.4060, 0.8382, 0.2308, 0.4869, 0.2442, 0.6998, 0.5377],
[0.5761, 0.3858, 0.7478, 0.2148, 0.4222, 0.1888, 0.5715, 0.5357]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6205, 0.4012, 0.8675, 0.3283, 0.3713, 0.3050, 0.5813, 0.5117],
[0.6175, 0.4091, 0.7862, 0.2800, 0.3638, 0.3583, 0.6187, 0.5433],
[0.0000, 0.0000, 0.8525, 0.2217, 0.5412, 0.2367, 0.7367, 0.5482],
[0.6145, 0.3983, 0.8700, 0.5017, 0.4400, 0.4800, 0.5375, 0.5750],
[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758],
[0.6279, 0.4008, 0.8600, 0.4883, 0.4325, 0.5283, 0.7010, 0.5378],
[0.6293, 0.4097, 0.8800, 0.2517, 0.5263, 0.2600, 0.7430, 0.5378],
[0.6214, 0.4116, 0.7750, 0.2317, 0.4487, 0.1883, 0.6200, 0.5400]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.004258358589140698
step: 4
running loss: 0.0010645896472851746
Train Steps: 4/90 Loss: 0.0011 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6252, 0.4158, 0.8988, 0.4083, 0.3788, 0.4783, 0.6225, 0.5633],
[0.6129, 0.3930, 0.8769, 0.5105, 0.4146, 0.5642, 0.6000, 0.5082],
[0.6200, 0.4070, 0.8938, 0.4183, 0.3538, 0.4567, 0.6175, 0.5400],
[0.6346, 0.4092, 0.7712, 0.5917, 0.4037, 0.4767, 0.7343, 0.5725],
[0.6193, 0.4165, 0.8838, 0.4700, 0.4150, 0.4867, 0.5427, 0.5261],
[0.6211, 0.3935, 0.8636, 0.4841, 0.4417, 0.5126, 0.6331, 0.5268],
[0.6329, 0.4175, 0.8550, 0.2333, 0.5425, 0.2250, 0.7398, 0.5609],
[0.6361, 0.4076, 0.8862, 0.5350, 0.3713, 0.4650, 0.6654, 0.5297]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6286, 0.4358, 0.8769, 0.3787, 0.3642, 0.4453, 0.5894, 0.5461],
[0.5941, 0.4048, 0.8591, 0.4995, 0.4092, 0.5502, 0.5732, 0.5008],
[0.4940, 0.3278, 0.8859, 0.3949, 0.3396, 0.4385, 0.5975, 0.5139],
[0.6161, 0.4102, 0.7761, 0.5220, 0.3656, 0.4566, 0.6900, 0.5708],
[0.5571, 0.3729, 0.8705, 0.4630, 0.3933, 0.4678, 0.5163, 0.5224],
[0.5966, 0.3890, 0.8608, 0.4651, 0.4166, 0.4937, 0.6023, 0.5137],
[0.5856, 0.3920, 0.8522, 0.2076, 0.5237, 0.1951, 0.7348, 0.5356],
[0.5518, 0.3843, 0.8716, 0.5228, 0.3479, 0.4377, 0.6359, 0.5273]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6252, 0.4158, 0.8988, 0.4083, 0.3787, 0.4783, 0.6225, 0.5633],
[0.6129, 0.3930, 0.8769, 0.5105, 0.4146, 0.5642, 0.6000, 0.5082],
[0.6200, 0.4070, 0.8938, 0.4183, 0.3537, 0.4567, 0.6175, 0.5400],
[0.6346, 0.4092, 0.7713, 0.5917, 0.4038, 0.4767, 0.7343, 0.5725],
[0.6193, 0.4165, 0.8838, 0.4700, 0.4150, 0.4867, 0.5427, 0.5261],
[0.6211, 0.3935, 0.8636, 0.4841, 0.4417, 0.5126, 0.6331, 0.5268],
[0.6329, 0.4175, 0.8550, 0.2333, 0.5425, 0.2250, 0.7398, 0.5609],
[0.6361, 0.4076, 0.8863, 0.5350, 0.3713, 0.4650, 0.6654, 0.5297]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.005290690081892535
step: 5
running loss: 0.001058138016378507
Train Steps: 5/90 Loss: 0.0011 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6223, 0.4028, 0.8988, 0.4200, 0.3763, 0.5733, 0.6375, 0.5167],
[ nan, nan, 0.6488, 0.1817, 0.4325, 0.1867, 0.5475, 0.5733],
[0.6339, 0.4112, 0.8838, 0.5067, 0.4000, 0.5433, 0.7549, 0.5378],
[0.6230, 0.4113, 0.7213, 0.1983, 0.4325, 0.2367, 0.6262, 0.5400],
[0.6136, 0.4060, 0.8025, 0.3217, 0.3650, 0.3000, 0.5060, 0.5646],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098],
[0.6115, 0.3998, 0.7063, 0.2383, 0.4037, 0.1950, 0.5320, 0.4993],
[0.6182, 0.3967, 0.8263, 0.3065, 0.3526, 0.4161, 0.6192, 0.5290]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5628, 0.3675, 0.9012, 0.4321, 0.4039, 0.5772, 0.6425, 0.5173],
[0.1123, 0.0837, 0.6882, 0.2115, 0.4484, 0.1851, 0.5827, 0.5779],
[0.6376, 0.4141, 0.8935, 0.5407, 0.4235, 0.5582, 0.7549, 0.5473],
[0.6193, 0.4202, 0.7262, 0.2125, 0.4546, 0.2231, 0.6338, 0.5522],
[0.6757, 0.4559, 0.7992, 0.3261, 0.3754, 0.2913, 0.5048, 0.5636],
[0.6086, 0.4059, 0.8714, 0.4880, 0.3842, 0.5257, 0.6139, 0.5058],
[0.6429, 0.4291, 0.7146, 0.2307, 0.4096, 0.1962, 0.5411, 0.4932],
[0.5703, 0.3764, 0.8226, 0.3077, 0.3508, 0.3935, 0.6427, 0.5397]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6223, 0.4028, 0.8988, 0.4200, 0.3762, 0.5733, 0.6375, 0.5167],
[0.0000, 0.0000, 0.6488, 0.1817, 0.4325, 0.1867, 0.5475, 0.5733],
[0.6339, 0.4112, 0.8838, 0.5067, 0.4000, 0.5433, 0.7549, 0.5378],
[0.6230, 0.4113, 0.7212, 0.1983, 0.4325, 0.2367, 0.6263, 0.5400],
[0.6136, 0.4060, 0.8025, 0.3217, 0.3650, 0.3000, 0.5060, 0.5646],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098],
[0.6115, 0.3998, 0.7063, 0.2383, 0.4038, 0.1950, 0.5320, 0.4993],
[0.6182, 0.3967, 0.8263, 0.3065, 0.3526, 0.4161, 0.6192, 0.5290]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.006010964134475216
step: 6
running loss: 0.0010018273557458695
Train Steps: 6/90 Loss: 0.0010 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6125, 0.4010, 0.8650, 0.4567, 0.3663, 0.3900, 0.5600, 0.5567],
[0.6300, 0.4013, 0.8938, 0.5350, 0.3675, 0.4600, 0.6456, 0.4973],
[0.6133, 0.4066, 0.6787, 0.2617, 0.3800, 0.2433, 0.5147, 0.5358],
[0.6091, 0.3997, 0.8314, 0.4334, 0.3788, 0.4550, 0.5213, 0.5656],
[0.6197, 0.4090, 0.7825, 0.2500, 0.4200, 0.2483, 0.5988, 0.5667],
[0.6246, 0.4028, 0.8738, 0.4867, 0.4088, 0.5667, 0.6362, 0.5200],
[0.6201, 0.4065, 0.7300, 0.1933, 0.4075, 0.2533, 0.6162, 0.5483],
[0.6113, 0.4104, 0.8650, 0.4250, 0.3925, 0.5967, 0.5787, 0.5116]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6033, 0.3968, 0.8633, 0.4681, 0.3756, 0.3958, 0.5996, 0.5504],
[0.6511, 0.4366, 0.8907, 0.5408, 0.3869, 0.4642, 0.6706, 0.4991],
[0.6189, 0.4157, 0.7080, 0.2688, 0.3831, 0.2361, 0.5732, 0.5136],
[0.6097, 0.4049, 0.8417, 0.4520, 0.3871, 0.4563, 0.5520, 0.5556],
[0.6564, 0.4354, 0.7826, 0.2350, 0.4024, 0.2438, 0.6246, 0.5608],
[0.6491, 0.4279, 0.8879, 0.4915, 0.4421, 0.5618, 0.6730, 0.5224],
[0.6068, 0.4018, 0.7448, 0.1839, 0.4090, 0.2412, 0.6519, 0.5410],
[0.5664, 0.3761, 0.8622, 0.4227, 0.4177, 0.5919, 0.6115, 0.5155]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6125, 0.4010, 0.8650, 0.4567, 0.3663, 0.3900, 0.5600, 0.5567],
[0.6300, 0.4013, 0.8938, 0.5350, 0.3675, 0.4600, 0.6456, 0.4973],
[0.6133, 0.4065, 0.6787, 0.2617, 0.3800, 0.2433, 0.5147, 0.5358],
[0.6091, 0.3997, 0.8314, 0.4334, 0.3787, 0.4550, 0.5213, 0.5656],
[0.6197, 0.4090, 0.7825, 0.2500, 0.4200, 0.2483, 0.5987, 0.5667],
[0.6246, 0.4028, 0.8737, 0.4867, 0.4087, 0.5667, 0.6363, 0.5200],
[0.6201, 0.4065, 0.7300, 0.1933, 0.4075, 0.2533, 0.6162, 0.5483],
[0.6113, 0.4104, 0.8650, 0.4250, 0.3925, 0.5967, 0.5787, 0.5116]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.006409419496776536
step: 7
running loss: 0.0009156313566823623
Train Steps: 7/90 Loss: 0.0009 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6277, 0.4036, 0.8688, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742],
[0.6275, 0.4111, 0.8463, 0.2617, 0.4487, 0.1983, 0.6211, 0.4904],
[0.6274, 0.4117, 0.8100, 0.5801, 0.4000, 0.4583, 0.5582, 0.6118],
[0.6185, 0.4129, 0.8900, 0.4567, 0.3937, 0.5417, 0.5734, 0.5110],
[0.6196, 0.4088, 0.8888, 0.4583, 0.4500, 0.5683, 0.6138, 0.5883],
[0.6284, 0.4127, 0.8538, 0.5867, 0.4363, 0.5083, 0.6038, 0.5433],
[0.6167, 0.4048, 0.6831, 0.3639, 0.3763, 0.3017, 0.5700, 0.5883],
[0.6201, 0.4029, 0.8776, 0.4602, 0.3683, 0.4203, 0.5938, 0.5450]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6184, 0.3991, 0.8760, 0.3445, 0.3885, 0.2568, 0.6579, 0.4637],
[0.6569, 0.4371, 0.8507, 0.2505, 0.4504, 0.2141, 0.6291, 0.4659],
[0.6265, 0.4320, 0.8225, 0.5594, 0.4027, 0.4503, 0.5940, 0.5949],
[0.6272, 0.4296, 0.8969, 0.4458, 0.3914, 0.5446, 0.5957, 0.4927],
[0.6098, 0.4292, 0.8974, 0.4494, 0.4426, 0.5651, 0.6509, 0.5711],
[0.5869, 0.3878, 0.8679, 0.5695, 0.4349, 0.5059, 0.6164, 0.5257],
[0.5942, 0.3922, 0.7184, 0.3401, 0.3705, 0.3252, 0.5932, 0.5651],
[0.6090, 0.4050, 0.8767, 0.4538, 0.3760, 0.4140, 0.6232, 0.5329]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6277, 0.4036, 0.8687, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742],
[0.6275, 0.4111, 0.8462, 0.2617, 0.4487, 0.1983, 0.6211, 0.4904],
[0.6274, 0.4117, 0.8100, 0.5801, 0.4000, 0.4583, 0.5582, 0.6118],
[0.6186, 0.4129, 0.8900, 0.4567, 0.3938, 0.5417, 0.5734, 0.5110],
[0.6196, 0.4088, 0.8888, 0.4583, 0.4500, 0.5683, 0.6137, 0.5883],
[0.6284, 0.4127, 0.8537, 0.5867, 0.4363, 0.5083, 0.6037, 0.5433],
[0.6167, 0.4048, 0.6831, 0.3639, 0.3762, 0.3017, 0.5700, 0.5883],
[0.6201, 0.4029, 0.8776, 0.4602, 0.3683, 0.4203, 0.5938, 0.5450]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.006727247644448653
step: 8
running loss: 0.0008409059555560816
Train Steps: 8/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6122, 0.4048, 0.7506, 0.3014, 0.3475, 0.3333, 0.5487, 0.5749],
[0.6275, 0.4111, 0.8463, 0.2617, 0.4487, 0.1983, 0.6211, 0.4904],
[0.6196, 0.4088, 0.8888, 0.4583, 0.4500, 0.5683, 0.6138, 0.5883],
[0.6300, 0.4102, 0.9088, 0.4433, 0.4088, 0.3067, 0.6820, 0.5540],
[0.6154, 0.4112, 0.7037, 0.2317, 0.4238, 0.1833, 0.5350, 0.5600],
[0.6182, 0.3982, 0.7541, 0.2379, 0.3959, 0.2792, 0.6079, 0.5389],
[0.6037, 0.4020, 0.8300, 0.4033, 0.3575, 0.4883, 0.5647, 0.5631],
[0.6223, 0.4171, 0.8750, 0.5500, 0.4050, 0.4817, 0.5675, 0.5600]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6183, 0.4030, 0.7435, 0.3145, 0.3552, 0.3331, 0.5759, 0.5422],
[0.6342, 0.4077, 0.8421, 0.2665, 0.4672, 0.2127, 0.6182, 0.4593],
[0.6046, 0.4084, 0.8912, 0.4746, 0.4667, 0.5795, 0.6430, 0.5635],
[0.5526, 0.3554, 0.9060, 0.4546, 0.4237, 0.3305, 0.6833, 0.5396],
[0.6539, 0.4260, 0.7077, 0.2388, 0.4306, 0.1791, 0.5493, 0.5390],
[0.6156, 0.4022, 0.7569, 0.2314, 0.3848, 0.2848, 0.6123, 0.5242],
[0.6136, 0.4001, 0.8375, 0.4258, 0.3736, 0.5034, 0.6086, 0.5390],
[0.6474, 0.4279, 0.8735, 0.5599, 0.4168, 0.5013, 0.5937, 0.5653]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6122, 0.4048, 0.7506, 0.3014, 0.3475, 0.3333, 0.5487, 0.5749],
[0.6275, 0.4111, 0.8462, 0.2617, 0.4487, 0.1983, 0.6211, 0.4904],
[0.6196, 0.4088, 0.8888, 0.4583, 0.4500, 0.5683, 0.6137, 0.5883],
[0.6300, 0.4102, 0.9087, 0.4433, 0.4087, 0.3067, 0.6820, 0.5540],
[0.6154, 0.4112, 0.7038, 0.2317, 0.4238, 0.1833, 0.5350, 0.5600],
[0.6182, 0.3982, 0.7541, 0.2379, 0.3959, 0.2792, 0.6079, 0.5389],
[0.6037, 0.4020, 0.8300, 0.4033, 0.3575, 0.4883, 0.5647, 0.5631],
[0.6223, 0.4171, 0.8750, 0.5500, 0.4050, 0.4817, 0.5675, 0.5600]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0071166820416692644
step: 9
running loss: 0.0007907424490743628
Train Steps: 9/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6064, 0.3953, 0.8738, 0.4417, 0.3663, 0.4683, 0.5511, 0.5416],
[0.6292, 0.4010, 0.8988, 0.4800, 0.3638, 0.3817, 0.6357, 0.5051],
[0.6250, 0.4110, 0.7238, 0.2067, 0.4263, 0.1883, 0.5625, 0.5633],
[0.6150, 0.4097, 0.7468, 0.3194, 0.3825, 0.2633, 0.5463, 0.5800],
[0.6201, 0.4064, 0.8688, 0.5050, 0.4225, 0.5100, 0.6138, 0.5500],
[0.6214, 0.4175, 0.7300, 0.2883, 0.4338, 0.2167, 0.5698, 0.5773],
[0.6179, 0.3961, 0.8347, 0.6020, 0.3887, 0.4624, 0.5714, 0.5373],
[0.6264, 0.4069, 0.7900, 0.1650, 0.4275, 0.2267, 0.6290, 0.4947]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6942, 0.4339, 0.8907, 0.4814, 0.3835, 0.5011, 0.5572, 0.5364],
[0.6969, 0.4367, 0.8986, 0.5011, 0.3749, 0.4080, 0.6448, 0.5017],
[0.5561, 0.3609, 0.7203, 0.2376, 0.4244, 0.2072, 0.5682, 0.5440],
[0.6394, 0.4293, 0.7587, 0.3248, 0.3745, 0.2947, 0.5382, 0.5660],
[0.6396, 0.4080, 0.8953, 0.5133, 0.4375, 0.5452, 0.6052, 0.5679],
[0.5969, 0.4074, 0.7429, 0.3088, 0.4482, 0.2296, 0.5628, 0.5750],
[0.6409, 0.4072, 0.8550, 0.6127, 0.4090, 0.4920, 0.5700, 0.5451],
[0.6599, 0.4126, 0.7889, 0.1861, 0.4329, 0.2702, 0.6305, 0.5054]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6064, 0.3952, 0.8737, 0.4417, 0.3663, 0.4683, 0.5511, 0.5416],
[0.6292, 0.4010, 0.8988, 0.4800, 0.3638, 0.3817, 0.6357, 0.5051],
[0.6250, 0.4110, 0.7237, 0.2067, 0.4263, 0.1883, 0.5625, 0.5633],
[0.6150, 0.4097, 0.7468, 0.3194, 0.3825, 0.2633, 0.5462, 0.5800],
[0.6201, 0.4064, 0.8687, 0.5050, 0.4225, 0.5100, 0.6137, 0.5500],
[0.6214, 0.4175, 0.7300, 0.2883, 0.4338, 0.2167, 0.5698, 0.5773],
[0.6179, 0.3961, 0.8347, 0.6020, 0.3887, 0.4624, 0.5714, 0.5373],
[0.6264, 0.4069, 0.7900, 0.1650, 0.4275, 0.2267, 0.6290, 0.4947]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.007774444384267554
step: 10
running loss: 0.0007774444384267554
Train Steps: 10/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6057, 0.4011, 0.8750, 0.4267, 0.4400, 0.5800, 0.5845, 0.5585],
[0.6202, 0.3983, 0.8555, 0.5429, 0.3842, 0.4370, 0.5866, 0.5398],
[0.6282, 0.4034, 0.7830, 0.2080, 0.4532, 0.2080, 0.6404, 0.5323],
[0.6146, 0.4124, 0.8800, 0.4867, 0.3800, 0.4500, 0.5106, 0.5524],
[0.6068, 0.3963, 0.8650, 0.4317, 0.4037, 0.5083, 0.5253, 0.4999],
[0.6182, 0.4099, 0.7812, 0.3000, 0.3937, 0.2367, 0.5325, 0.5750],
[0.6076, 0.3958, 0.8700, 0.4667, 0.4546, 0.5046, 0.5231, 0.4960],
[0.6122, 0.4048, 0.7506, 0.3014, 0.3475, 0.3333, 0.5487, 0.5749]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6385, 0.4033, 0.8655, 0.4518, 0.4351, 0.5511, 0.6074, 0.5391],
[0.6870, 0.4239, 0.8564, 0.5643, 0.3862, 0.4419, 0.5884, 0.5476],
[0.5826, 0.3651, 0.7670, 0.2289, 0.4291, 0.1928, 0.6284, 0.5399],
[0.6836, 0.4302, 0.8857, 0.5144, 0.3720, 0.4463, 0.5233, 0.5645],
[0.6096, 0.3817, 0.8424, 0.4521, 0.3899, 0.4873, 0.5573, 0.5129],
[0.6418, 0.4088, 0.7759, 0.3049, 0.4048, 0.2246, 0.5228, 0.5798],
[0.6431, 0.4098, 0.8683, 0.4738, 0.4422, 0.4891, 0.5520, 0.5079],
[0.6509, 0.4179, 0.7390, 0.3151, 0.3359, 0.3168, 0.5603, 0.5707]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6057, 0.4011, 0.8750, 0.4267, 0.4400, 0.5800, 0.5845, 0.5585],
[0.6202, 0.3983, 0.8555, 0.5429, 0.3842, 0.4370, 0.5866, 0.5398],
[0.6282, 0.4034, 0.7830, 0.2080, 0.4532, 0.2080, 0.6404, 0.5323],
[0.6146, 0.4124, 0.8800, 0.4867, 0.3800, 0.4500, 0.5106, 0.5524],
[0.6068, 0.3963, 0.8650, 0.4317, 0.4038, 0.5083, 0.5253, 0.4999],
[0.6182, 0.4099, 0.7812, 0.3000, 0.3938, 0.2367, 0.5325, 0.5750],
[0.6076, 0.3958, 0.8700, 0.4667, 0.4546, 0.5046, 0.5231, 0.4960],
[0.6122, 0.4048, 0.7506, 0.3014, 0.3475, 0.3333, 0.5487, 0.5749]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.008245526551036164
step: 11
running loss: 0.0007495933228214694
Train Steps: 11/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6199, 0.4015, 0.8716, 0.5228, 0.3833, 0.4772, 0.5883, 0.5148],
[0.6299, 0.4303, 0.7963, 0.3933, 0.4850, 0.2283, 0.5480, 0.6222],
[0.6179, 0.3961, 0.8347, 0.6020, 0.3887, 0.4624, 0.5714, 0.5373],
[0.6250, 0.4131, 0.8688, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367],
[0.6275, 0.4003, 0.9100, 0.3783, 0.4388, 0.3133, 0.7058, 0.5343],
[ nan, nan, 0.7525, 0.2291, 0.3838, 0.3017, 0.6050, 0.5667],
[0.6187, 0.4104, 0.7126, 0.2069, 0.3950, 0.2517, 0.5913, 0.5683],
[0.6186, 0.4060, 0.8750, 0.5050, 0.3538, 0.4367, 0.5813, 0.6083]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6789, 0.4254, 0.8802, 0.5339, 0.3951, 0.4785, 0.5689, 0.5207],
[0.6904, 0.4412, 0.7863, 0.3883, 0.4789, 0.2596, 0.4998, 0.6308],
[0.6794, 0.4258, 0.8299, 0.5935, 0.3994, 0.4723, 0.5408, 0.5457],
[0.6904, 0.4317, 0.8464, 0.3005, 0.4299, 0.2478, 0.5632, 0.5375],
[0.6913, 0.4495, 0.8708, 0.3862, 0.4187, 0.3195, 0.6650, 0.5311],
[0.0830, 0.0339, 0.7411, 0.2390, 0.3734, 0.2989, 0.5673, 0.5606],
[0.6843, 0.4467, 0.6902, 0.2188, 0.3999, 0.2534, 0.5375, 0.5657],
[0.7003, 0.4519, 0.8651, 0.5073, 0.3672, 0.4434, 0.5544, 0.6115]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6199, 0.4015, 0.8716, 0.5228, 0.3833, 0.4772, 0.5883, 0.5148],
[0.6299, 0.4303, 0.7962, 0.3933, 0.4850, 0.2283, 0.5480, 0.6222],
[0.6179, 0.3961, 0.8347, 0.6020, 0.3887, 0.4624, 0.5714, 0.5373],
[0.6250, 0.4131, 0.8687, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367],
[0.6275, 0.4003, 0.9100, 0.3783, 0.4387, 0.3133, 0.7058, 0.5343],
[0.0000, 0.0000, 0.7525, 0.2291, 0.3837, 0.3017, 0.6050, 0.5667],
[0.6187, 0.4103, 0.7126, 0.2069, 0.3950, 0.2517, 0.5913, 0.5683],
[0.6186, 0.4060, 0.8750, 0.5050, 0.3537, 0.4367, 0.5813, 0.6083]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.009264791355235502
step: 12
running loss: 0.0007720659462696252
Train Steps: 12/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6249, 0.4142, 0.8350, 0.3283, 0.3613, 0.3700, 0.6188, 0.5400],
[0.6113, 0.4088, 0.6859, 0.2208, 0.4363, 0.1700, 0.5188, 0.5533],
[0.6250, 0.4131, 0.8688, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367],
[0.6040, 0.4002, 0.7338, 0.2267, 0.3975, 0.2100, 0.5231, 0.4778],
[0.6211, 0.3935, 0.8636, 0.4841, 0.4417, 0.5126, 0.6331, 0.5268],
[0.6304, 0.4029, 0.8413, 0.5217, 0.4125, 0.5617, 0.7089, 0.5679],
[0.6198, 0.4114, 0.8263, 0.3283, 0.3550, 0.3583, 0.5813, 0.5667],
[0.6286, 0.3977, 0.9038, 0.4733, 0.3900, 0.4150, 0.7074, 0.5320]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6438, 0.4170, 0.8441, 0.3354, 0.3635, 0.3598, 0.5761, 0.5718],
[0.5178, 0.3205, 0.6909, 0.2413, 0.4453, 0.1691, 0.4824, 0.5813],
[0.6444, 0.4104, 0.8591, 0.3085, 0.4397, 0.2368, 0.5545, 0.5576],
[0.6467, 0.4118, 0.7465, 0.2338, 0.4028, 0.2046, 0.5104, 0.5042],
[0.6424, 0.4062, 0.8770, 0.4743, 0.4497, 0.5087, 0.5798, 0.5563],
[0.6998, 0.4514, 0.8549, 0.5256, 0.4192, 0.5506, 0.6577, 0.6106],
[0.5969, 0.3950, 0.8450, 0.3362, 0.3615, 0.3658, 0.5247, 0.6014],
[0.6412, 0.4060, 0.8985, 0.4726, 0.3843, 0.4225, 0.6617, 0.5409]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6249, 0.4142, 0.8350, 0.3283, 0.3613, 0.3700, 0.6187, 0.5400],
[0.6113, 0.4088, 0.6859, 0.2208, 0.4363, 0.1700, 0.5188, 0.5533],
[0.6250, 0.4131, 0.8687, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367],
[0.6040, 0.4002, 0.7337, 0.2267, 0.3975, 0.2100, 0.5231, 0.4778],
[0.6211, 0.3935, 0.8636, 0.4841, 0.4417, 0.5126, 0.6331, 0.5268],
[0.6304, 0.4029, 0.8413, 0.5217, 0.4125, 0.5617, 0.7089, 0.5679],
[0.6198, 0.4114, 0.8263, 0.3283, 0.3550, 0.3583, 0.5813, 0.5667],
[0.6286, 0.3977, 0.9038, 0.4733, 0.3900, 0.4150, 0.7074, 0.5320]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.010133300122106448
step: 13
running loss: 0.000779484624777419
Train Steps: 13/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6265, 0.4091, 0.8950, 0.3533, 0.3600, 0.3967, 0.6295, 0.4901],
[0.6168, 0.4029, 0.8523, 0.3417, 0.3588, 0.5000, 0.6125, 0.5400],
[0.6193, 0.4050, 0.7313, 0.2433, 0.4075, 0.2117, 0.5649, 0.5656],
[0.6082, 0.4024, 0.8738, 0.4017, 0.3688, 0.3950, 0.5306, 0.5136],
[0.6154, 0.4048, 0.7100, 0.2067, 0.4338, 0.1667, 0.5413, 0.5220],
[0.6164, 0.4076, 0.8838, 0.4117, 0.3713, 0.5550, 0.6238, 0.5350],
[0.6209, 0.3920, 0.8650, 0.5367, 0.4400, 0.5067, 0.6025, 0.4950],
[0.6211, 0.4069, 0.8750, 0.5117, 0.4150, 0.4900, 0.5875, 0.5167]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6662, 0.4234, 0.9031, 0.3694, 0.3580, 0.3724, 0.6157, 0.5550],
[0.6267, 0.4100, 0.8555, 0.3439, 0.3576, 0.4699, 0.6097, 0.5852],
[0.6212, 0.4056, 0.7296, 0.2370, 0.4127, 0.2023, 0.5632, 0.5981],
[0.5978, 0.3986, 0.8732, 0.4130, 0.3557, 0.3778, 0.5035, 0.5433],
[0.6166, 0.4000, 0.6922, 0.2149, 0.4322, 0.1552, 0.5333, 0.5524],
[0.6210, 0.3970, 0.8759, 0.4106, 0.3713, 0.5390, 0.6254, 0.5757],
[0.6666, 0.4193, 0.8550, 0.5351, 0.4326, 0.4919, 0.5749, 0.5434],
[0.6432, 0.4139, 0.8767, 0.5163, 0.4053, 0.4915, 0.5790, 0.5741]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6265, 0.4091, 0.8950, 0.3533, 0.3600, 0.3967, 0.6295, 0.4901],
[0.6168, 0.4029, 0.8523, 0.3417, 0.3587, 0.5000, 0.6125, 0.5400],
[0.6193, 0.4050, 0.7312, 0.2433, 0.4075, 0.2117, 0.5649, 0.5656],
[0.6082, 0.4024, 0.8737, 0.4017, 0.3688, 0.3950, 0.5306, 0.5136],
[0.6154, 0.4048, 0.7100, 0.2067, 0.4338, 0.1667, 0.5413, 0.5220],
[0.6164, 0.4076, 0.8838, 0.4117, 0.3713, 0.5550, 0.6237, 0.5350],
[0.6209, 0.3920, 0.8650, 0.5367, 0.4400, 0.5067, 0.6025, 0.4950],
[0.6211, 0.4069, 0.8750, 0.5117, 0.4150, 0.4900, 0.5875, 0.5167]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.010566788056166843
step: 14
running loss: 0.0007547705754404888
Train Steps: 14/90 Loss: 0.0008 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6150, 0.3935, 0.8696, 0.5158, 0.4647, 0.5329, 0.6041, 0.5153],
[0.6169, 0.4052, 0.8742, 0.4779, 0.4288, 0.4917, 0.5763, 0.5617],
[0.6267, 0.4080, 0.8438, 0.2633, 0.4763, 0.1800, 0.6259, 0.5240],
[0.6203, 0.4076, 0.8611, 0.2878, 0.4050, 0.2554, 0.5907, 0.5496],
[0.6086, 0.3998, 0.8788, 0.4450, 0.4025, 0.4650, 0.5306, 0.5103],
[0.6176, 0.4030, 0.8850, 0.4850, 0.3688, 0.4050, 0.5312, 0.5783],
[0.6259, 0.4133, 0.8200, 0.2317, 0.5025, 0.1533, 0.6250, 0.4947],
[0.6300, 0.4102, 0.9088, 0.4433, 0.4088, 0.3067, 0.6820, 0.5540]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6224, 0.4058, 0.8545, 0.4940, 0.4377, 0.5267, 0.6175, 0.5340],
[0.5924, 0.3953, 0.8547, 0.4568, 0.4137, 0.4933, 0.5830, 0.5806],
[0.5722, 0.3748, 0.8269, 0.2542, 0.4515, 0.2007, 0.6299, 0.5232],
[0.5919, 0.3963, 0.8611, 0.2738, 0.3905, 0.2842, 0.5890, 0.5384],
[0.5859, 0.3965, 0.8591, 0.4376, 0.3848, 0.4553, 0.5460, 0.5158],
[0.6042, 0.4017, 0.8832, 0.4621, 0.3735, 0.4036, 0.5302, 0.5805],
[0.5670, 0.3899, 0.8042, 0.2198, 0.4908, 0.1637, 0.6256, 0.5006],
[0.6143, 0.4162, 0.8901, 0.4287, 0.3958, 0.3150, 0.6744, 0.5654]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6150, 0.3935, 0.8696, 0.5158, 0.4647, 0.5329, 0.6041, 0.5153],
[0.6169, 0.4052, 0.8742, 0.4779, 0.4288, 0.4917, 0.5763, 0.5617],
[0.6267, 0.4080, 0.8438, 0.2633, 0.4762, 0.1800, 0.6259, 0.5240],
[0.6203, 0.4076, 0.8611, 0.2878, 0.4050, 0.2554, 0.5907, 0.5496],
[0.6086, 0.3998, 0.8788, 0.4450, 0.4025, 0.4650, 0.5306, 0.5103],
[0.6176, 0.4030, 0.8850, 0.4850, 0.3688, 0.4050, 0.5312, 0.5783],
[0.6259, 0.4132, 0.8200, 0.2317, 0.5025, 0.1533, 0.6250, 0.4947],
[0.6300, 0.4102, 0.9087, 0.4433, 0.4087, 0.3067, 0.6820, 0.5540]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0108872129349038
step: 15
running loss: 0.0007258141956602534
Train Steps: 15/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6193, 0.4079, 0.7288, 0.2500, 0.4250, 0.2550, 0.5989, 0.6266],
[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150],
[ nan, nan, 0.8888, 0.3100, 0.5262, 0.2817, 0.7145, 0.6003],
[0.6259, 0.4133, 0.8200, 0.2317, 0.5025, 0.1533, 0.6250, 0.4947],
[0.6277, 0.4057, 0.8300, 0.2650, 0.4363, 0.1850, 0.6140, 0.4823],
[0.6098, 0.3991, 0.8638, 0.4717, 0.4263, 0.4967, 0.5212, 0.5650],
[0.6182, 0.3930, 0.8841, 0.3892, 0.3556, 0.4967, 0.6222, 0.5279],
[0.6353, 0.4128, 0.9138, 0.3533, 0.4688, 0.3250, 0.7145, 0.5991]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6015, 0.4170, 0.7197, 0.2435, 0.4179, 0.2499, 0.5913, 0.6008],
[0.6438, 0.4261, 0.8888, 0.4595, 0.4274, 0.5851, 0.6316, 0.5029],
[0.0754, 0.0515, 0.8658, 0.2984, 0.4927, 0.2718, 0.7197, 0.5535],
[0.6106, 0.4292, 0.8134, 0.2247, 0.4864, 0.1641, 0.6272, 0.4792],
[0.6354, 0.4273, 0.8239, 0.2510, 0.4067, 0.1870, 0.6059, 0.4785],
[0.6247, 0.4177, 0.8501, 0.4693, 0.4100, 0.5023, 0.5431, 0.5304],
[0.6193, 0.3932, 0.8688, 0.3921, 0.3346, 0.4652, 0.6326, 0.5106],
[0.6273, 0.4316, 0.8989, 0.3456, 0.4486, 0.3181, 0.7250, 0.5764]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6193, 0.4078, 0.7287, 0.2500, 0.4250, 0.2550, 0.5989, 0.6266],
[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150],
[0.0000, 0.0000, 0.8888, 0.3100, 0.5263, 0.2817, 0.7145, 0.6003],
[0.6259, 0.4132, 0.8200, 0.2317, 0.5025, 0.1533, 0.6250, 0.4947],
[0.6277, 0.4056, 0.8300, 0.2650, 0.4363, 0.1850, 0.6140, 0.4823],
[0.6098, 0.3991, 0.8637, 0.4717, 0.4263, 0.4967, 0.5213, 0.5650],
[0.6182, 0.3930, 0.8841, 0.3892, 0.3556, 0.4967, 0.6222, 0.5279],
[0.6353, 0.4128, 0.9137, 0.3533, 0.4688, 0.3250, 0.7145, 0.5991]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.011273512180196121
step: 16
running loss: 0.0007045945112622576
Train Steps: 16/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6161, 0.4076, 0.8900, 0.4667, 0.4125, 0.5917, 0.6262, 0.5367],
[0.6150, 0.3949, 0.8800, 0.4033, 0.3825, 0.4900, 0.5875, 0.5483],
[0.6261, 0.4045, 0.8865, 0.5369, 0.3895, 0.4859, 0.6683, 0.5249],
[0.6101, 0.4042, 0.7775, 0.2617, 0.3713, 0.2817, 0.5440, 0.5650],
[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459],
[0.6128, 0.4022, 0.8738, 0.5067, 0.4983, 0.5231, 0.5364, 0.5064],
[0.6167, 0.4048, 0.6831, 0.3639, 0.3763, 0.3017, 0.5700, 0.5883],
[0.6179, 0.4082, 0.6688, 0.2667, 0.3588, 0.3317, 0.5750, 0.5783]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5943, 0.3980, 0.9217, 0.4521, 0.4279, 0.5748, 0.6315, 0.5061],
[0.5945, 0.3896, 0.8918, 0.3888, 0.3856, 0.4484, 0.6115, 0.5012],
[0.5628, 0.3809, 0.9031, 0.5169, 0.3854, 0.4670, 0.6718, 0.5036],
[0.5827, 0.3990, 0.7920, 0.2506, 0.3870, 0.2685, 0.5760, 0.5261],
[0.5897, 0.4110, 0.8753, 0.2631, 0.4937, 0.1924, 0.6866, 0.5137],
[0.5579, 0.3951, 0.8914, 0.4911, 0.5017, 0.4916, 0.5551, 0.4862],
[0.5632, 0.3852, 0.7218, 0.3323, 0.3831, 0.2869, 0.6009, 0.5554],
[0.6234, 0.4210, 0.6913, 0.2689, 0.3568, 0.2974, 0.5792, 0.5452]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6161, 0.4076, 0.8900, 0.4667, 0.4125, 0.5917, 0.6263, 0.5367],
[0.6150, 0.3949, 0.8800, 0.4033, 0.3825, 0.4900, 0.5875, 0.5483],
[0.6261, 0.4045, 0.8865, 0.5369, 0.3895, 0.4859, 0.6683, 0.5249],
[0.6101, 0.4042, 0.7775, 0.2617, 0.3713, 0.2817, 0.5440, 0.5650],
[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459],
[0.6128, 0.4022, 0.8737, 0.5067, 0.4983, 0.5231, 0.5364, 0.5064],
[0.6167, 0.4048, 0.6831, 0.3639, 0.3762, 0.3017, 0.5700, 0.5883],
[0.6179, 0.4082, 0.6687, 0.2667, 0.3587, 0.3317, 0.5750, 0.5783]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.011899679695488885
step: 17
running loss: 0.0006999811585581698
Train Steps: 17/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6357, 0.4159, 0.8788, 0.5583, 0.3638, 0.4433, 0.6488, 0.5297],
[0.6214, 0.4040, 0.8838, 0.3500, 0.3600, 0.5183, 0.6362, 0.5200],
[0.6257, 0.4024, 0.8612, 0.5352, 0.4361, 0.5253, 0.6680, 0.5166],
[0.6164, 0.3972, 0.7818, 0.3381, 0.3599, 0.3387, 0.5880, 0.5153],
[0.6160, 0.4093, 0.8314, 0.4417, 0.3675, 0.4583, 0.5250, 0.5808],
[0.6109, 0.3943, 0.8525, 0.4950, 0.4338, 0.4800, 0.5449, 0.5383],
[0.6275, 0.4024, 0.7722, 0.2080, 0.4392, 0.2234, 0.6435, 0.5290],
[0.6296, 0.4076, 0.8400, 0.5583, 0.3700, 0.4367, 0.6876, 0.5494]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5759, 0.3881, 0.8742, 0.5237, 0.3796, 0.4402, 0.6483, 0.5152],
[0.5830, 0.3891, 0.8870, 0.3364, 0.3729, 0.5032, 0.6474, 0.4874],
[0.6178, 0.4078, 0.8628, 0.5105, 0.4526, 0.5175, 0.6762, 0.5152],
[0.6367, 0.4283, 0.8008, 0.3185, 0.3739, 0.3252, 0.6114, 0.4945],
[0.5898, 0.3955, 0.8429, 0.4416, 0.3837, 0.4432, 0.5401, 0.5572],
[0.5827, 0.3843, 0.8635, 0.4610, 0.4559, 0.4643, 0.5379, 0.5216],
[0.6468, 0.4418, 0.7687, 0.1860, 0.4526, 0.1878, 0.6652, 0.5080],
[0.6178, 0.4185, 0.8519, 0.5210, 0.3906, 0.4284, 0.6882, 0.5288]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6357, 0.4159, 0.8788, 0.5583, 0.3638, 0.4433, 0.6488, 0.5297],
[0.6214, 0.4040, 0.8838, 0.3500, 0.3600, 0.5183, 0.6363, 0.5200],
[0.6257, 0.4024, 0.8612, 0.5352, 0.4361, 0.5253, 0.6680, 0.5166],
[0.6164, 0.3972, 0.7818, 0.3381, 0.3599, 0.3387, 0.5880, 0.5153],
[0.6160, 0.4092, 0.8314, 0.4417, 0.3675, 0.4583, 0.5250, 0.5808],
[0.6109, 0.3943, 0.8525, 0.4950, 0.4338, 0.4800, 0.5449, 0.5383],
[0.6275, 0.4024, 0.7722, 0.2080, 0.4392, 0.2234, 0.6435, 0.5290],
[0.6296, 0.4076, 0.8400, 0.5583, 0.3700, 0.4367, 0.6876, 0.5494]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.012323376664426178
step: 18
running loss: 0.0006846320369125655
Train Steps: 18/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6286, 0.4078, 0.8063, 0.2267, 0.4788, 0.1533, 0.5953, 0.4913],
[0.6224, 0.3964, 0.8225, 0.5717, 0.4150, 0.4617, 0.5775, 0.5267],
[0.6275, 0.4024, 0.8500, 0.5383, 0.3912, 0.4883, 0.6288, 0.5100],
[0.6275, 0.4024, 0.7722, 0.2080, 0.4392, 0.2234, 0.6435, 0.5290],
[ nan, nan, 0.8488, 0.2300, 0.5563, 0.2100, 0.7390, 0.5679],
[0.6201, 0.4065, 0.7300, 0.1933, 0.4075, 0.2533, 0.6162, 0.5483],
[0.6203, 0.4072, 0.8892, 0.3523, 0.3783, 0.3017, 0.5898, 0.5478],
[0.6300, 0.4102, 0.9088, 0.4433, 0.4088, 0.3067, 0.6820, 0.5540]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5797, 0.3699, 0.8009, 0.2417, 0.4690, 0.1885, 0.6042, 0.4845],
[0.5711, 0.3744, 0.8285, 0.5885, 0.4178, 0.4771, 0.5702, 0.5147],
[0.6353, 0.3908, 0.8537, 0.5339, 0.4054, 0.5166, 0.6063, 0.4817],
[0.6587, 0.4327, 0.7637, 0.2214, 0.4382, 0.2271, 0.6492, 0.5154],
[0.0846, 0.0291, 0.8546, 0.2416, 0.5450, 0.2666, 0.7472, 0.5351],
[0.6410, 0.4245, 0.7340, 0.1888, 0.4015, 0.2636, 0.6165, 0.5394],
[0.6169, 0.4116, 0.8886, 0.3509, 0.3904, 0.3113, 0.5855, 0.5371],
[0.6510, 0.4297, 0.9147, 0.4437, 0.4104, 0.3270, 0.6731, 0.5441]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6286, 0.4078, 0.8062, 0.2267, 0.4787, 0.1533, 0.5953, 0.4913],
[0.6224, 0.3964, 0.8225, 0.5717, 0.4150, 0.4617, 0.5775, 0.5267],
[0.6275, 0.4024, 0.8500, 0.5383, 0.3913, 0.4883, 0.6288, 0.5100],
[0.6275, 0.4024, 0.7722, 0.2080, 0.4392, 0.2234, 0.6435, 0.5290],
[0.0000, 0.0000, 0.8487, 0.2300, 0.5562, 0.2100, 0.7390, 0.5679],
[0.6201, 0.4065, 0.7300, 0.1933, 0.4075, 0.2533, 0.6162, 0.5483],
[0.6203, 0.4072, 0.8892, 0.3523, 0.3783, 0.3017, 0.5898, 0.5478],
[0.6300, 0.4102, 0.9087, 0.4433, 0.4087, 0.3067, 0.6820, 0.5540]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.012789542262908071
step: 19
running loss: 0.0006731338033109511
Train Steps: 19/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6213, 0.4131, 0.8438, 0.3550, 0.3513, 0.4400, 0.5716, 0.5123],
[0.6346, 0.4086, 0.7938, 0.5500, 0.3962, 0.4867, 0.7343, 0.5702],
[0.6266, 0.4067, 0.8588, 0.2867, 0.4300, 0.2850, 0.6325, 0.5267],
[ nan, nan, 0.8463, 0.2550, 0.5850, 0.2133, 0.7129, 0.6072],
[0.6201, 0.4098, 0.8575, 0.3617, 0.3700, 0.3550, 0.5988, 0.5667],
[0.6064, 0.3953, 0.8738, 0.4417, 0.3663, 0.4683, 0.5511, 0.5416],
[0.6271, 0.4024, 0.9000, 0.3517, 0.3700, 0.4517, 0.6931, 0.5285],
[0.6260, 0.4133, 0.8800, 0.5117, 0.3713, 0.3283, 0.6223, 0.4967]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6144, 0.4006, 0.8502, 0.3668, 0.3638, 0.4422, 0.5844, 0.4963],
[0.6249, 0.4046, 0.8022, 0.5589, 0.3946, 0.4815, 0.7036, 0.5593],
[0.6223, 0.4128, 0.8770, 0.2965, 0.4358, 0.2833, 0.6508, 0.5138],
[0.0960, 0.0492, 0.8665, 0.2693, 0.5726, 0.2490, 0.7453, 0.5857],
[0.6294, 0.4175, 0.8569, 0.3660, 0.3810, 0.3529, 0.6021, 0.5679],
[0.6125, 0.3823, 0.8703, 0.4571, 0.3776, 0.4691, 0.5518, 0.5235],
[0.6238, 0.4022, 0.8976, 0.3624, 0.3795, 0.4454, 0.6836, 0.5143],
[0.6391, 0.4209, 0.8698, 0.5133, 0.3780, 0.3417, 0.6381, 0.5009]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6213, 0.4131, 0.8438, 0.3550, 0.3512, 0.4400, 0.5716, 0.5123],
[0.6346, 0.4086, 0.7937, 0.5500, 0.3963, 0.4867, 0.7343, 0.5702],
[0.6266, 0.4067, 0.8587, 0.2867, 0.4300, 0.2850, 0.6325, 0.5267],
[0.0000, 0.0000, 0.8462, 0.2550, 0.5850, 0.2133, 0.7129, 0.6072],
[0.6201, 0.4098, 0.8575, 0.3617, 0.3700, 0.3550, 0.5987, 0.5667],
[0.6064, 0.3952, 0.8737, 0.4417, 0.3663, 0.4683, 0.5511, 0.5416],
[0.6271, 0.4024, 0.9000, 0.3517, 0.3700, 0.4517, 0.6931, 0.5285],
[0.6260, 0.4133, 0.8800, 0.5117, 0.3713, 0.3283, 0.6223, 0.4967]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.013119590788846835
step: 20
running loss: 0.0006559795394423418
Train Steps: 20/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6250, 0.4131, 0.8688, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367],
[0.6272, 0.4045, 0.8538, 0.5900, 0.3750, 0.4417, 0.5989, 0.4649],
[0.6200, 0.4059, 0.8700, 0.4900, 0.4163, 0.5000, 0.6162, 0.5467],
[0.6255, 0.4017, 0.8688, 0.3217, 0.3638, 0.3550, 0.6344, 0.4901],
[0.6124, 0.4083, 0.6954, 0.3069, 0.3650, 0.2750, 0.5163, 0.5485],
[0.6200, 0.4118, 0.8287, 0.4017, 0.3775, 0.2833, 0.5391, 0.5799],
[0.6308, 0.3990, 0.8688, 0.5183, 0.3950, 0.4983, 0.6388, 0.5133],
[0.6147, 0.4026, 0.6600, 0.2467, 0.4088, 0.2150, 0.5489, 0.5773]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6296, 0.4074, 0.8948, 0.3214, 0.4477, 0.2529, 0.6697, 0.5555],
[0.6054, 0.3959, 0.8685, 0.5957, 0.3754, 0.4682, 0.6372, 0.4977],
[0.5450, 0.3340, 0.8945, 0.4939, 0.4314, 0.5339, 0.6315, 0.5598],
[0.5763, 0.3613, 0.8921, 0.3362, 0.3809, 0.3682, 0.6608, 0.5188],
[0.6269, 0.4156, 0.7311, 0.3101, 0.3836, 0.3070, 0.5511, 0.5822],
[0.5670, 0.3752, 0.8318, 0.4177, 0.3885, 0.3006, 0.5604, 0.5971],
[0.6255, 0.3709, 0.8807, 0.5453, 0.3992, 0.5174, 0.6570, 0.5380],
[0.5794, 0.3761, 0.6974, 0.2540, 0.4204, 0.2369, 0.5726, 0.6080]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6250, 0.4131, 0.8687, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367],
[0.6271, 0.4045, 0.8537, 0.5900, 0.3750, 0.4417, 0.5989, 0.4649],
[0.6199, 0.4059, 0.8700, 0.4900, 0.4162, 0.5000, 0.6162, 0.5467],
[0.6255, 0.4017, 0.8687, 0.3217, 0.3638, 0.3550, 0.6344, 0.4901],
[0.6123, 0.4083, 0.6954, 0.3069, 0.3650, 0.2750, 0.5163, 0.5485],
[0.6200, 0.4118, 0.8288, 0.4017, 0.3775, 0.2833, 0.5391, 0.5799],
[0.6308, 0.3990, 0.8687, 0.5183, 0.3950, 0.4983, 0.6388, 0.5133],
[0.6147, 0.4026, 0.6600, 0.2467, 0.4087, 0.2150, 0.5489, 0.5773]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.013877765712095425
step: 21
running loss: 0.0006608459862902583
Train Steps: 21/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6176, 0.4017, 0.8788, 0.5100, 0.4075, 0.5250, 0.5913, 0.5033],
[0.6364, 0.4154, 0.8938, 0.3717, 0.4500, 0.2583, 0.6448, 0.5285],
[0.6241, 0.4143, 0.8938, 0.4650, 0.4075, 0.5350, 0.6250, 0.5550],
[0.6189, 0.4033, 0.8650, 0.5267, 0.4487, 0.5150, 0.5925, 0.5050],
[0.6193, 0.4108, 0.7425, 0.2350, 0.3887, 0.2750, 0.5900, 0.5717],
[0.6325, 0.4165, 0.9000, 0.4617, 0.3813, 0.4900, 0.7485, 0.5447],
[0.6275, 0.4024, 0.8500, 0.5383, 0.3912, 0.4883, 0.6288, 0.5100],
[0.6178, 0.4059, 0.7525, 0.2250, 0.4313, 0.1783, 0.5404, 0.5240]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5650, 0.3551, 0.8819, 0.5313, 0.4009, 0.5310, 0.5723, 0.5404],
[0.5824, 0.3737, 0.9007, 0.3910, 0.4633, 0.2645, 0.6485, 0.5586],
[0.6109, 0.3947, 0.8851, 0.4863, 0.3972, 0.5470, 0.6387, 0.5904],
[0.5914, 0.3826, 0.8671, 0.5249, 0.4320, 0.5236, 0.5967, 0.5469],
[0.6290, 0.4103, 0.7343, 0.2679, 0.3852, 0.2887, 0.5911, 0.6182],
[0.5890, 0.3860, 0.9081, 0.4825, 0.3769, 0.5022, 0.7166, 0.5768],
[0.6258, 0.3809, 0.8503, 0.5562, 0.3911, 0.5099, 0.6123, 0.5244],
[0.5949, 0.3755, 0.7443, 0.2458, 0.4314, 0.1738, 0.5385, 0.5607]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6176, 0.4017, 0.8788, 0.5100, 0.4075, 0.5250, 0.5913, 0.5033],
[0.6364, 0.4154, 0.8938, 0.3717, 0.4500, 0.2583, 0.6448, 0.5285],
[0.6241, 0.4142, 0.8938, 0.4650, 0.4075, 0.5350, 0.6250, 0.5550],
[0.6189, 0.4033, 0.8650, 0.5267, 0.4487, 0.5150, 0.5925, 0.5050],
[0.6193, 0.4108, 0.7425, 0.2350, 0.3887, 0.2750, 0.5900, 0.5717],
[0.6325, 0.4165, 0.9000, 0.4617, 0.3812, 0.4900, 0.7485, 0.5447],
[0.6275, 0.4024, 0.8500, 0.5383, 0.3913, 0.4883, 0.6288, 0.5100],
[0.6178, 0.4059, 0.7525, 0.2250, 0.4313, 0.1783, 0.5404, 0.5240]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.014404586370801553
step: 22
running loss: 0.0006547539259455251
Train Steps: 22/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6289, 0.4032, 0.8419, 0.5446, 0.4075, 0.5017, 0.6312, 0.5117],
[0.6266, 0.4067, 0.8588, 0.2867, 0.4300, 0.2850, 0.6325, 0.5267],
[0.6124, 0.4083, 0.6954, 0.3069, 0.3650, 0.2750, 0.5163, 0.5485],
[0.6125, 0.3999, 0.8750, 0.4883, 0.4750, 0.4700, 0.5533, 0.5617],
[0.6090, 0.4010, 0.7838, 0.3483, 0.3538, 0.3783, 0.5462, 0.5077],
[0.6250, 0.4236, 0.8638, 0.3767, 0.4050, 0.3150, 0.5649, 0.5799],
[ nan, nan, 0.8850, 0.3000, 0.5363, 0.2250, 0.7343, 0.5771],
[0.6159, 0.4085, 0.6900, 0.2283, 0.4088, 0.1950, 0.5123, 0.5397]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6460, 0.3959, 0.8257, 0.5581, 0.3873, 0.4902, 0.6624, 0.5208],
[0.6283, 0.4119, 0.8619, 0.2948, 0.4182, 0.2608, 0.6523, 0.5370],
[0.6427, 0.4274, 0.6905, 0.2963, 0.3651, 0.2692, 0.5266, 0.5680],
[0.6403, 0.4086, 0.8583, 0.4989, 0.4620, 0.4748, 0.5454, 0.5695],
[0.6413, 0.4226, 0.7729, 0.3604, 0.3415, 0.3635, 0.5549, 0.5128],
[0.6557, 0.4392, 0.8538, 0.3977, 0.3870, 0.3068, 0.5797, 0.5940],
[0.0340, 0.0126, 0.8629, 0.2940, 0.5285, 0.2054, 0.7630, 0.5743],
[0.5121, 0.3272, 0.6654, 0.2389, 0.4041, 0.1704, 0.5190, 0.5577]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6289, 0.4031, 0.8419, 0.5446, 0.4075, 0.5017, 0.6313, 0.5117],
[0.6266, 0.4067, 0.8587, 0.2867, 0.4300, 0.2850, 0.6325, 0.5267],
[0.6123, 0.4083, 0.6954, 0.3069, 0.3650, 0.2750, 0.5163, 0.5485],
[0.6125, 0.3999, 0.8750, 0.4883, 0.4750, 0.4700, 0.5533, 0.5617],
[0.6090, 0.4010, 0.7837, 0.3483, 0.3537, 0.3783, 0.5462, 0.5077],
[0.6250, 0.4236, 0.8637, 0.3767, 0.4050, 0.3150, 0.5649, 0.5799],
[0.0000, 0.0000, 0.8850, 0.3000, 0.5362, 0.2250, 0.7343, 0.5771],
[0.6159, 0.4085, 0.6900, 0.2283, 0.4087, 0.1950, 0.5123, 0.5397]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.014939425949705765
step: 23
running loss: 0.0006495402586828593
Train Steps: 23/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6144, 0.4032, 0.8563, 0.3283, 0.3525, 0.4200, 0.5775, 0.5583],
[0.6185, 0.4079, 0.8838, 0.4617, 0.4838, 0.5650, 0.6175, 0.5850],
[0.6188, 0.4099, 0.7400, 0.2433, 0.3962, 0.2750, 0.6162, 0.5467],
[0.6246, 0.4126, 0.8850, 0.4833, 0.4200, 0.5350, 0.6112, 0.5250],
[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758],
[0.6175, 0.3957, 0.8700, 0.4817, 0.4662, 0.5133, 0.5800, 0.5517],
[0.6198, 0.4101, 0.8838, 0.5283, 0.3763, 0.5267, 0.5913, 0.5567],
[0.6201, 0.4027, 0.8029, 0.2728, 0.4042, 0.2310, 0.5980, 0.5391]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6195, 0.3847, 0.8599, 0.3413, 0.3459, 0.3976, 0.5567, 0.5486],
[0.6105, 0.3927, 0.8786, 0.4613, 0.4847, 0.5375, 0.6117, 0.5935],
[0.6538, 0.4311, 0.7202, 0.2353, 0.3908, 0.2772, 0.5970, 0.5718],
[0.6367, 0.4093, 0.8734, 0.4899, 0.4099, 0.5058, 0.6015, 0.5389],
[0.6352, 0.3884, 0.8787, 0.5097, 0.3985, 0.4984, 0.6342, 0.4904],
[0.6424, 0.4127, 0.8495, 0.4789, 0.4571, 0.4931, 0.5678, 0.5521],
[0.6069, 0.3848, 0.8498, 0.5368, 0.3684, 0.4988, 0.5818, 0.5520],
[0.6352, 0.3954, 0.8017, 0.2887, 0.4095, 0.2181, 0.5965, 0.5479]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6144, 0.4032, 0.8562, 0.3283, 0.3525, 0.4200, 0.5775, 0.5583],
[0.6184, 0.4079, 0.8838, 0.4617, 0.4837, 0.5650, 0.6175, 0.5850],
[0.6188, 0.4099, 0.7400, 0.2433, 0.3963, 0.2750, 0.6162, 0.5467],
[0.6246, 0.4126, 0.8850, 0.4833, 0.4200, 0.5350, 0.6112, 0.5250],
[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758],
[0.6175, 0.3957, 0.8700, 0.4817, 0.4663, 0.5133, 0.5800, 0.5517],
[0.6198, 0.4101, 0.8838, 0.5283, 0.3762, 0.5267, 0.5913, 0.5567],
[0.6201, 0.4027, 0.8029, 0.2728, 0.4042, 0.2310, 0.5980, 0.5391]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.015169626043643802
step: 24
running loss: 0.0006320677518184917
Train Steps: 24/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6163, 0.4006, 0.8788, 0.4683, 0.3663, 0.4883, 0.5887, 0.5017],
[0.6304, 0.4029, 0.8413, 0.5217, 0.4125, 0.5617, 0.7089, 0.5679],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3788, 0.4900, 0.7121, 0.5864],
[0.6075, 0.4000, 0.8513, 0.5183, 0.4510, 0.5329, 0.5180, 0.5280],
[0.6136, 0.4029, 0.8263, 0.3350, 0.3625, 0.3067, 0.5675, 0.5167],
[0.6239, 0.4107, 0.8162, 0.2763, 0.3625, 0.3600, 0.5988, 0.5700],
[0.6161, 0.4099, 0.8738, 0.4383, 0.3788, 0.5483, 0.5605, 0.5019],
[0.6115, 0.4081, 0.6725, 0.2433, 0.4088, 0.1933, 0.5167, 0.5544]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5821, 0.3851, 0.8686, 0.4562, 0.3777, 0.4854, 0.5571, 0.5129],
[0.5867, 0.3747, 0.8297, 0.5226, 0.4066, 0.5395, 0.6983, 0.5600],
[0.6231, 0.4036, 0.8612, 0.5096, 0.3793, 0.4699, 0.6989, 0.5680],
[0.6329, 0.3993, 0.8323, 0.5190, 0.4639, 0.5174, 0.5098, 0.4993],
[0.6596, 0.4292, 0.8100, 0.3271, 0.3733, 0.2925, 0.5534, 0.5063],
[0.6017, 0.3856, 0.7856, 0.2735, 0.3719, 0.3316, 0.5911, 0.5630],
[0.6342, 0.4121, 0.8748, 0.4167, 0.3754, 0.5315, 0.5385, 0.4856],
[0.6165, 0.3957, 0.6680, 0.2330, 0.4212, 0.1719, 0.5023, 0.5374]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6163, 0.4006, 0.8788, 0.4683, 0.3663, 0.4883, 0.5888, 0.5017],
[0.6304, 0.4029, 0.8413, 0.5217, 0.4125, 0.5617, 0.7089, 0.5679],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3787, 0.4900, 0.7121, 0.5864],
[0.6075, 0.4000, 0.8512, 0.5183, 0.4510, 0.5329, 0.5180, 0.5280],
[0.6136, 0.4029, 0.8263, 0.3350, 0.3625, 0.3067, 0.5675, 0.5167],
[0.6239, 0.4107, 0.8162, 0.2763, 0.3625, 0.3600, 0.5987, 0.5700],
[0.6161, 0.4099, 0.8737, 0.4383, 0.3787, 0.5483, 0.5605, 0.5019],
[0.6115, 0.4081, 0.6725, 0.2433, 0.4087, 0.1933, 0.5167, 0.5544]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.015483570605283603
step: 25
running loss: 0.0006193428242113441
Train Steps: 25/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6236, 0.4081, 0.8575, 0.3000, 0.3713, 0.3033, 0.5550, 0.5633],
[0.6126, 0.4073, 0.8750, 0.5133, 0.3800, 0.4333, 0.4986, 0.5378],
[0.6339, 0.4118, 0.7988, 0.5800, 0.3912, 0.4583, 0.7343, 0.5760],
[0.6250, 0.4008, 0.8950, 0.4183, 0.3550, 0.4383, 0.6361, 0.4927],
[ nan, nan, 0.6488, 0.1817, 0.4325, 0.1867, 0.5475, 0.5733],
[0.6222, 0.3937, 0.8350, 0.5617, 0.4138, 0.4600, 0.5800, 0.5233],
[0.6284, 0.4029, 0.8838, 0.3783, 0.3975, 0.2850, 0.6335, 0.5090],
[0.6260, 0.4253, 0.8938, 0.4400, 0.3675, 0.3650, 0.5675, 0.5767]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6852, 0.4632, 0.8482, 0.2990, 0.3883, 0.3077, 0.5581, 0.5466],
[ 0.6258, 0.4264, 0.8568, 0.5108, 0.3806, 0.4525, 0.5085, 0.5110],
[ 0.6581, 0.4255, 0.7901, 0.5492, 0.3743, 0.4760, 0.7085, 0.5539],
[ 0.7054, 0.4497, 0.8871, 0.4031, 0.3478, 0.4665, 0.5962, 0.4949],
[-0.0766, -0.0439, 0.6816, 0.1964, 0.4734, 0.1699, 0.5512, 0.5810],
[ 0.6778, 0.4353, 0.8170, 0.5715, 0.4026, 0.4640, 0.5526, 0.5143],
[ 0.6876, 0.4435, 0.8741, 0.3700, 0.3973, 0.3027, 0.6253, 0.4798],
[ 0.6833, 0.4596, 0.8834, 0.4272, 0.3690, 0.3819, 0.5770, 0.5657]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6236, 0.4081, 0.8575, 0.3000, 0.3713, 0.3033, 0.5550, 0.5633],
[0.6126, 0.4073, 0.8750, 0.5133, 0.3800, 0.4333, 0.4986, 0.5378],
[0.6339, 0.4118, 0.7987, 0.5800, 0.3913, 0.4583, 0.7343, 0.5760],
[0.6250, 0.4008, 0.8950, 0.4183, 0.3550, 0.4383, 0.6361, 0.4927],
[0.0000, 0.0000, 0.6488, 0.1817, 0.4325, 0.1867, 0.5475, 0.5733],
[0.6222, 0.3937, 0.8350, 0.5617, 0.4137, 0.4600, 0.5800, 0.5233],
[0.6284, 0.4029, 0.8838, 0.3783, 0.3975, 0.2850, 0.6335, 0.5090],
[0.6260, 0.4253, 0.8938, 0.4400, 0.3675, 0.3650, 0.5675, 0.5767]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.016324585973052308
step: 26
running loss: 0.0006278686912712426
Train Steps: 26/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6286, 0.3977, 0.9038, 0.4733, 0.3900, 0.4150, 0.7074, 0.5320],
[0.6271, 0.4005, 0.8450, 0.6067, 0.3850, 0.4983, 0.6069, 0.4649],
[0.6275, 0.4157, 0.8337, 0.5800, 0.3763, 0.4200, 0.5547, 0.6125],
[0.6305, 0.3983, 0.8950, 0.4833, 0.3688, 0.4683, 0.6375, 0.5117],
[0.6097, 0.4024, 0.8488, 0.3717, 0.3875, 0.5517, 0.5836, 0.5591],
[0.6129, 0.4069, 0.8750, 0.5067, 0.3875, 0.4233, 0.5235, 0.5881],
[0.6222, 0.4172, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633],
[0.6197, 0.4091, 0.8800, 0.4783, 0.3538, 0.4767, 0.5950, 0.5550]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6205, 0.3967, 0.9026, 0.4544, 0.3932, 0.4375, 0.6945, 0.5092],
[0.6907, 0.4562, 0.8337, 0.5767, 0.3931, 0.5079, 0.6054, 0.4719],
[0.6233, 0.4279, 0.8179, 0.5471, 0.3836, 0.4258, 0.5543, 0.6103],
[0.6515, 0.4255, 0.8997, 0.4725, 0.3777, 0.4727, 0.6153, 0.5013],
[0.6181, 0.4017, 0.8575, 0.3643, 0.4084, 0.5700, 0.5951, 0.5194],
[0.6669, 0.4463, 0.8475, 0.5062, 0.3903, 0.4386, 0.4891, 0.5614],
[0.6693, 0.4533, 0.8795, 0.4952, 0.3682, 0.4686, 0.5514, 0.5426],
[0.6131, 0.4099, 0.8660, 0.4607, 0.3811, 0.4951, 0.5762, 0.5430]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6286, 0.3977, 0.9038, 0.4733, 0.3900, 0.4150, 0.7074, 0.5320],
[0.6271, 0.4005, 0.8450, 0.6067, 0.3850, 0.4983, 0.6069, 0.4649],
[0.6275, 0.4157, 0.8338, 0.5800, 0.3762, 0.4200, 0.5547, 0.6125],
[0.6305, 0.3983, 0.8950, 0.4833, 0.3688, 0.4683, 0.6375, 0.5117],
[0.6097, 0.4024, 0.8487, 0.3717, 0.3875, 0.5517, 0.5836, 0.5591],
[0.6129, 0.4069, 0.8750, 0.5067, 0.3875, 0.4233, 0.5235, 0.5881],
[0.6222, 0.4171, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633],
[0.6197, 0.4091, 0.8800, 0.4783, 0.3537, 0.4767, 0.5950, 0.5550]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.016808000102173537
step: 27
running loss: 0.0006225185223027236
Train Steps: 27/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6072, 0.4029, 0.7037, 0.2150, 0.3912, 0.2267, 0.5516, 0.5507],
[0.6187, 0.4104, 0.7126, 0.2069, 0.3950, 0.2517, 0.5913, 0.5683],
[0.6124, 0.4075, 0.7696, 0.4153, 0.3475, 0.3767, 0.5157, 0.5427],
[0.6145, 0.4008, 0.8750, 0.5383, 0.3975, 0.4650, 0.5563, 0.5533],
[ nan, nan, 0.8888, 0.3100, 0.5262, 0.2817, 0.7145, 0.6003],
[0.6113, 0.4088, 0.6859, 0.2208, 0.4363, 0.1700, 0.5188, 0.5533],
[0.6222, 0.4169, 0.8638, 0.5650, 0.4313, 0.4783, 0.5637, 0.5633],
[0.6223, 0.4130, 0.8100, 0.2983, 0.3525, 0.3900, 0.5694, 0.5103]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6678, 0.4515, 0.6983, 0.1999, 0.3860, 0.2305, 0.5475, 0.5385],
[ 0.6567, 0.4500, 0.7093, 0.2060, 0.3911, 0.2487, 0.5784, 0.5428],
[ 0.6494, 0.4381, 0.7825, 0.4043, 0.3370, 0.3878, 0.5269, 0.5209],
[ 0.5652, 0.3896, 0.8628, 0.5309, 0.3852, 0.4684, 0.5787, 0.5374],
[-0.0491, -0.0215, 0.9024, 0.3033, 0.5342, 0.2410, 0.7110, 0.5998],
[ 0.7045, 0.4607, 0.7032, 0.2196, 0.4323, 0.1755, 0.5227, 0.5387],
[ 0.6341, 0.4296, 0.8694, 0.5635, 0.4121, 0.4887, 0.5844, 0.5403],
[ 0.6351, 0.4425, 0.8114, 0.2984, 0.3520, 0.3987, 0.5705, 0.5170]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6072, 0.4029, 0.7038, 0.2150, 0.3913, 0.2267, 0.5516, 0.5507],
[0.6187, 0.4103, 0.7126, 0.2069, 0.3950, 0.2517, 0.5913, 0.5683],
[0.6124, 0.4075, 0.7696, 0.4153, 0.3475, 0.3767, 0.5157, 0.5427],
[0.6145, 0.4008, 0.8750, 0.5383, 0.3975, 0.4650, 0.5562, 0.5533],
[0.0000, 0.0000, 0.8888, 0.3100, 0.5263, 0.2817, 0.7145, 0.6003],
[0.6113, 0.4088, 0.6859, 0.2208, 0.4363, 0.1700, 0.5188, 0.5533],
[0.6222, 0.4169, 0.8637, 0.5650, 0.4313, 0.4783, 0.5638, 0.5633],
[0.6223, 0.4130, 0.8100, 0.2983, 0.3525, 0.3900, 0.5694, 0.5103]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0173894782201387
step: 28
running loss: 0.0006210527935763821
Train Steps: 28/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6346, 0.4165, 0.9138, 0.3983, 0.3875, 0.4317, 0.7469, 0.5471],
[0.6240, 0.4217, 0.8150, 0.3133, 0.4425, 0.2650, 0.5650, 0.5817],
[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586],
[0.6277, 0.4029, 0.8250, 0.2433, 0.4325, 0.2100, 0.6366, 0.5207],
[ nan, nan, 0.7512, 0.2117, 0.4288, 0.2000, 0.5600, 0.5617],
[0.6097, 0.3988, 0.8650, 0.5250, 0.4213, 0.5200, 0.5675, 0.5050],
[0.6149, 0.4054, 0.6713, 0.2333, 0.4025, 0.2017, 0.5213, 0.5695],
[0.6239, 0.4123, 0.8313, 0.2550, 0.4500, 0.2050, 0.6175, 0.5400]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5899, 0.4050, 0.9158, 0.4174, 0.3807, 0.4620, 0.7336, 0.5475],
[0.5687, 0.4059, 0.8109, 0.3149, 0.4253, 0.2654, 0.5626, 0.5792],
[0.5833, 0.3953, 0.8511, 0.2648, 0.4415, 0.2807, 0.6835, 0.5603],
[0.6309, 0.4139, 0.8280, 0.2610, 0.4369, 0.2403, 0.6261, 0.5160],
[0.1151, 0.0865, 0.7205, 0.2217, 0.4265, 0.1935, 0.5202, 0.5690],
[0.6392, 0.4385, 0.8658, 0.5408, 0.4172, 0.5399, 0.5582, 0.5038],
[0.6263, 0.4299, 0.6765, 0.2299, 0.3918, 0.2112, 0.4994, 0.5611],
[0.6386, 0.4270, 0.8344, 0.2350, 0.4449, 0.1997, 0.6108, 0.5236]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6346, 0.4165, 0.9137, 0.3983, 0.3875, 0.4317, 0.7469, 0.5471],
[0.6240, 0.4217, 0.8150, 0.3133, 0.4425, 0.2650, 0.5650, 0.5817],
[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586],
[0.6277, 0.4029, 0.8250, 0.2433, 0.4325, 0.2100, 0.6366, 0.5207],
[0.0000, 0.0000, 0.7513, 0.2117, 0.4288, 0.2000, 0.5600, 0.5617],
[0.6097, 0.3988, 0.8650, 0.5250, 0.4212, 0.5200, 0.5675, 0.5050],
[0.6149, 0.4054, 0.6712, 0.2333, 0.4025, 0.2017, 0.5213, 0.5695],
[0.6239, 0.4123, 0.8313, 0.2550, 0.4500, 0.2050, 0.6175, 0.5400]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.018027903337497264
step: 29
running loss: 0.0006216518392240436
Train Steps: 29/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6201, 0.4064, 0.8688, 0.5050, 0.4225, 0.5100, 0.6138, 0.5500],
[0.6118, 0.4052, 0.8463, 0.3917, 0.3538, 0.3450, 0.5053, 0.5593],
[ nan, nan, 0.7515, 0.2708, 0.3987, 0.2267, 0.5162, 0.5567],
[0.6339, 0.4112, 0.8838, 0.5067, 0.4000, 0.5433, 0.7549, 0.5378],
[0.6179, 0.4008, 0.8600, 0.4015, 0.3932, 0.2515, 0.5711, 0.5438],
[0.6200, 0.3993, 0.8639, 0.3687, 0.3658, 0.3139, 0.6002, 0.5374],
[0.6200, 0.4055, 0.8011, 0.2988, 0.3842, 0.2798, 0.5949, 0.5183],
[0.6135, 0.3994, 0.7913, 0.3050, 0.3625, 0.3050, 0.5837, 0.5050]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6289, 0.4156, 0.8779, 0.4982, 0.4202, 0.5133, 0.6175, 0.5748],
[0.6280, 0.4271, 0.8509, 0.3736, 0.3577, 0.3567, 0.4989, 0.5659],
[0.0764, 0.0679, 0.7582, 0.2679, 0.4156, 0.2245, 0.5097, 0.5756],
[0.6544, 0.4261, 0.9022, 0.5067, 0.4018, 0.5514, 0.7537, 0.5663],
[0.6425, 0.4273, 0.8398, 0.3622, 0.4102, 0.2657, 0.5652, 0.5576],
[0.6033, 0.3992, 0.8812, 0.3680, 0.3698, 0.3246, 0.5951, 0.5382],
[0.6100, 0.4027, 0.8141, 0.2939, 0.3899, 0.2922, 0.6108, 0.5352],
[0.6272, 0.4086, 0.7947, 0.2922, 0.3735, 0.3166, 0.5857, 0.5293]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6201, 0.4064, 0.8687, 0.5050, 0.4225, 0.5100, 0.6137, 0.5500],
[0.6118, 0.4052, 0.8462, 0.3917, 0.3537, 0.3450, 0.5053, 0.5593],
[0.0000, 0.0000, 0.7515, 0.2708, 0.3988, 0.2267, 0.5163, 0.5567],
[0.6339, 0.4112, 0.8838, 0.5067, 0.4000, 0.5433, 0.7549, 0.5378],
[0.6179, 0.4008, 0.8600, 0.4015, 0.3932, 0.2515, 0.5711, 0.5438],
[0.6200, 0.3993, 0.8639, 0.3687, 0.3658, 0.3139, 0.6002, 0.5374],
[0.6201, 0.4055, 0.8011, 0.2988, 0.3842, 0.2798, 0.5949, 0.5183],
[0.6135, 0.3994, 0.7912, 0.3050, 0.3625, 0.3050, 0.5838, 0.5050]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.018376984866335988
step: 30
running loss: 0.0006125661622111996
Train Steps: 30/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6162, 0.3949, 0.8838, 0.4517, 0.4250, 0.5183, 0.5837, 0.5500],
[0.6261, 0.4131, 0.8938, 0.3550, 0.4000, 0.2683, 0.6188, 0.5283],
[0.6186, 0.4154, 0.6825, 0.2633, 0.4150, 0.2300, 0.5713, 0.5517],
[0.6142, 0.3982, 0.8650, 0.4883, 0.3912, 0.4317, 0.5315, 0.5350],
[0.6112, 0.4029, 0.8638, 0.4800, 0.4875, 0.5083, 0.5763, 0.5567],
[0.6296, 0.4060, 0.9100, 0.3267, 0.4726, 0.3367, 0.7446, 0.5355],
[0.6200, 0.3961, 0.8461, 0.5497, 0.4142, 0.4577, 0.5892, 0.5402],
[0.6262, 0.4085, 0.8438, 0.3150, 0.4025, 0.2633, 0.6339, 0.4810]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5082, 0.3386, 0.9000, 0.4524, 0.4091, 0.5285, 0.5743, 0.5588],
[0.6539, 0.4280, 0.9310, 0.3621, 0.3786, 0.2677, 0.6350, 0.5476],
[0.5480, 0.3625, 0.6927, 0.2695, 0.4049, 0.2346, 0.5865, 0.5690],
[0.5836, 0.3790, 0.8909, 0.5103, 0.3678, 0.4543, 0.5583, 0.5349],
[0.5760, 0.3655, 0.8916, 0.4884, 0.4742, 0.5025, 0.5968, 0.5890],
[0.5642, 0.3593, 0.9249, 0.3504, 0.4558, 0.3376, 0.7363, 0.5549],
[0.5540, 0.3576, 0.8712, 0.5523, 0.3851, 0.4578, 0.6114, 0.5569],
[0.6044, 0.3882, 0.8784, 0.3101, 0.3934, 0.2648, 0.6318, 0.4963]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6162, 0.3949, 0.8838, 0.4517, 0.4250, 0.5183, 0.5838, 0.5500],
[0.6261, 0.4131, 0.8938, 0.3550, 0.4000, 0.2683, 0.6187, 0.5283],
[0.6186, 0.4154, 0.6825, 0.2633, 0.4150, 0.2300, 0.5713, 0.5517],
[0.6143, 0.3982, 0.8650, 0.4883, 0.3913, 0.4317, 0.5315, 0.5350],
[0.6112, 0.4029, 0.8637, 0.4800, 0.4875, 0.5083, 0.5763, 0.5567],
[0.6296, 0.4060, 0.9100, 0.3267, 0.4726, 0.3367, 0.7446, 0.5355],
[0.6200, 0.3961, 0.8461, 0.5497, 0.4142, 0.4577, 0.5892, 0.5402],
[0.6262, 0.4085, 0.8438, 0.3150, 0.4025, 0.2633, 0.6339, 0.4810]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.019246386946178973
step: 31
running loss: 0.0006208511918122249
Train Steps: 31/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.6859, 0.2194, 0.4150, 0.1867, 0.5153, 0.5729],
[0.6113, 0.4104, 0.8650, 0.4250, 0.3925, 0.5967, 0.5787, 0.5116],
[0.6343, 0.4097, 0.9287, 0.4367, 0.4313, 0.3600, 0.7248, 0.5841],
[0.6200, 0.3993, 0.8639, 0.3687, 0.3658, 0.3139, 0.6002, 0.5374],
[0.6163, 0.4006, 0.8788, 0.4683, 0.3663, 0.4883, 0.5887, 0.5017],
[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334],
[0.6364, 0.4144, 0.8625, 0.3083, 0.4913, 0.2000, 0.6448, 0.5274],
[0.6361, 0.4076, 0.8862, 0.5350, 0.3713, 0.4650, 0.6654, 0.5297]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[-0.0313, -0.0344, 0.6675, 0.2363, 0.4315, 0.1697, 0.5175, 0.5917],
[ 0.7018, 0.4575, 0.8709, 0.4227, 0.3885, 0.5999, 0.5903, 0.5508],
[ 0.6001, 0.3855, 0.9231, 0.4592, 0.4337, 0.3570, 0.7339, 0.6016],
[ 0.5920, 0.3758, 0.8785, 0.3899, 0.3640, 0.3185, 0.6041, 0.5439],
[ 0.6057, 0.3949, 0.8959, 0.4820, 0.3706, 0.4992, 0.6088, 0.5532],
[ 0.6054, 0.3812, 0.7647, 0.2485, 0.3684, 0.3098, 0.6237, 0.5450],
[ 0.6482, 0.4166, 0.8815, 0.3270, 0.4856, 0.1997, 0.6592, 0.5412],
[ 0.6420, 0.4174, 0.8970, 0.5579, 0.3575, 0.4708, 0.6795, 0.5610]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.6859, 0.2194, 0.4150, 0.1867, 0.5153, 0.5729],
[0.6113, 0.4104, 0.8650, 0.4250, 0.3925, 0.5967, 0.5787, 0.5116],
[0.6343, 0.4097, 0.9287, 0.4367, 0.4313, 0.3600, 0.7248, 0.5841],
[0.6200, 0.3993, 0.8639, 0.3687, 0.3658, 0.3139, 0.6002, 0.5374],
[0.6163, 0.4006, 0.8788, 0.4683, 0.3663, 0.4883, 0.5888, 0.5017],
[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334],
[0.6364, 0.4144, 0.8625, 0.3083, 0.4913, 0.2000, 0.6448, 0.5274],
[0.6361, 0.4076, 0.8863, 0.5350, 0.3713, 0.4650, 0.6654, 0.5297]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.019706396793480963
step: 32
running loss: 0.0006158248997962801
Train Steps: 32/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6277, 0.4036, 0.8688, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742],
[0.6187, 0.4104, 0.7126, 0.2069, 0.3950, 0.2517, 0.5913, 0.5683],
[0.6097, 0.4000, 0.7325, 0.2667, 0.3450, 0.3517, 0.5284, 0.5045],
[0.6279, 0.4008, 0.8600, 0.4883, 0.4325, 0.5283, 0.7010, 0.5378],
[0.6271, 0.4040, 0.9000, 0.3250, 0.4938, 0.2300, 0.7192, 0.5413],
[0.6245, 0.4100, 0.7762, 0.2583, 0.4963, 0.1517, 0.5875, 0.5417],
[0.6275, 0.4024, 0.8500, 0.5383, 0.3912, 0.4883, 0.6288, 0.5100],
[0.6289, 0.4024, 0.9088, 0.4567, 0.3937, 0.5633, 0.7058, 0.5609]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5915, 0.3648, 0.8859, 0.3691, 0.3865, 0.2511, 0.6040, 0.4740],
[0.5877, 0.3866, 0.7135, 0.2236, 0.3872, 0.2383, 0.5726, 0.5677],
[0.5589, 0.3525, 0.7566, 0.2944, 0.3430, 0.3362, 0.5234, 0.5213],
[0.5980, 0.3662, 0.8820, 0.4993, 0.4230, 0.5237, 0.6867, 0.5484],
[0.5208, 0.3225, 0.9172, 0.3313, 0.4996, 0.2441, 0.7192, 0.5617],
[0.5197, 0.3270, 0.7861, 0.2565, 0.4710, 0.1536, 0.5770, 0.5490],
[0.5806, 0.3592, 0.8683, 0.5452, 0.3901, 0.4801, 0.6250, 0.5073],
[0.5634, 0.3657, 0.9120, 0.4750, 0.3990, 0.5621, 0.7043, 0.5740]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6277, 0.4036, 0.8687, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742],
[0.6187, 0.4103, 0.7126, 0.2069, 0.3950, 0.2517, 0.5913, 0.5683],
[0.6097, 0.4000, 0.7325, 0.2667, 0.3450, 0.3517, 0.5284, 0.5045],
[0.6279, 0.4008, 0.8600, 0.4883, 0.4325, 0.5283, 0.7010, 0.5378],
[0.6271, 0.4040, 0.9000, 0.3250, 0.4938, 0.2300, 0.7192, 0.5413],
[0.6245, 0.4100, 0.7763, 0.2583, 0.4963, 0.1517, 0.5875, 0.5417],
[0.6275, 0.4024, 0.8500, 0.5383, 0.3913, 0.4883, 0.6288, 0.5100],
[0.6289, 0.4024, 0.9087, 0.4567, 0.3938, 0.5633, 0.7058, 0.5609]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.020707069255877286
step: 33
running loss: 0.0006274869471477965
Train Steps: 33/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6127, 0.4115, 0.7163, 0.2883, 0.3625, 0.2950, 0.5327, 0.5495],
[0.6171, 0.4127, 0.8900, 0.4800, 0.4325, 0.5783, 0.5769, 0.5090],
[0.6157, 0.3956, 0.8323, 0.4138, 0.3479, 0.4431, 0.5914, 0.5131],
[0.6202, 0.3983, 0.8555, 0.5429, 0.3842, 0.4370, 0.5866, 0.5398],
[0.6264, 0.4069, 0.7900, 0.1650, 0.4275, 0.2267, 0.6290, 0.4947],
[0.6226, 0.4103, 0.8575, 0.3450, 0.4388, 0.2067, 0.5787, 0.5383],
[0.6162, 0.4134, 0.6700, 0.2467, 0.3962, 0.2533, 0.5737, 0.5467],
[0.6064, 0.3953, 0.8738, 0.4417, 0.3663, 0.4683, 0.5511, 0.5416]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6007, 0.3772, 0.7200, 0.2945, 0.3763, 0.2790, 0.5664, 0.5535],
[0.5869, 0.3720, 0.9010, 0.4810, 0.4447, 0.5518, 0.5943, 0.4871],
[0.6122, 0.3806, 0.8564, 0.4092, 0.3590, 0.4167, 0.6089, 0.5095],
[0.5744, 0.3446, 0.8711, 0.5548, 0.4080, 0.4152, 0.6318, 0.5181],
[0.5921, 0.3604, 0.7916, 0.1798, 0.4442, 0.2247, 0.6660, 0.4946],
[0.5655, 0.3537, 0.8685, 0.3517, 0.4483, 0.2133, 0.5934, 0.5236],
[0.5666, 0.3661, 0.6690, 0.2627, 0.4073, 0.2356, 0.6014, 0.5319],
[0.5724, 0.3551, 0.8916, 0.4487, 0.3799, 0.4450, 0.5941, 0.5318]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6127, 0.4114, 0.7163, 0.2883, 0.3625, 0.2950, 0.5327, 0.5495],
[0.6171, 0.4127, 0.8900, 0.4800, 0.4325, 0.5783, 0.5769, 0.5090],
[0.6157, 0.3956, 0.8323, 0.4138, 0.3479, 0.4431, 0.5914, 0.5131],
[0.6202, 0.3983, 0.8555, 0.5429, 0.3842, 0.4370, 0.5866, 0.5398],
[0.6264, 0.4069, 0.7900, 0.1650, 0.4275, 0.2267, 0.6290, 0.4947],
[0.6226, 0.4103, 0.8575, 0.3450, 0.4387, 0.2067, 0.5788, 0.5383],
[0.6162, 0.4134, 0.6700, 0.2467, 0.3963, 0.2533, 0.5738, 0.5467],
[0.6064, 0.3952, 0.8737, 0.4417, 0.3663, 0.4683, 0.5511, 0.5416]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.021375142212491482
step: 34
running loss: 0.000628680653308573
Train Steps: 34/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6198, 0.4105, 0.7950, 0.3267, 0.3675, 0.3767, 0.6038, 0.6167],
[ nan, nan, 0.8625, 0.2550, 0.5487, 0.2200, 0.7335, 0.5737],
[0.6111, 0.4033, 0.8300, 0.3267, 0.3588, 0.3333, 0.5444, 0.5637],
[0.6296, 0.4045, 0.9138, 0.4100, 0.4232, 0.4242, 0.7422, 0.5297],
[0.6179, 0.4118, 0.7278, 0.4237, 0.3588, 0.3400, 0.5675, 0.5917],
[0.6264, 0.4035, 0.8888, 0.4883, 0.4050, 0.5217, 0.6361, 0.4791],
[0.6152, 0.4131, 0.6863, 0.2567, 0.3625, 0.3300, 0.5765, 0.5305],
[ nan, nan, 0.8675, 0.2833, 0.5350, 0.1983, 0.6678, 0.5621]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6458, 0.4290, 0.7912, 0.3173, 0.3675, 0.3524, 0.5973, 0.5699],
[0.0816, 0.0432, 0.8271, 0.2405, 0.5499, 0.2154, 0.6919, 0.5486],
[0.6858, 0.4386, 0.8185, 0.3300, 0.3570, 0.2973, 0.5412, 0.5117],
[0.7040, 0.4585, 0.8861, 0.4092, 0.4093, 0.4017, 0.7211, 0.5145],
[0.6847, 0.4358, 0.7422, 0.3976, 0.3619, 0.3103, 0.5389, 0.5399],
[0.7012, 0.4481, 0.8807, 0.4806, 0.4154, 0.4745, 0.6137, 0.4292],
[0.6557, 0.4236, 0.6619, 0.2601, 0.3675, 0.3147, 0.5812, 0.5161],
[0.0547, 0.0357, 0.8371, 0.2571, 0.5378, 0.1797, 0.6543, 0.5340]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6198, 0.4105, 0.7950, 0.3267, 0.3675, 0.3767, 0.6037, 0.6167],
[0.0000, 0.0000, 0.8625, 0.2550, 0.5487, 0.2200, 0.7335, 0.5737],
[0.6111, 0.4033, 0.8300, 0.3267, 0.3587, 0.3333, 0.5444, 0.5637],
[0.6296, 0.4045, 0.9137, 0.4100, 0.4232, 0.4242, 0.7422, 0.5297],
[0.6179, 0.4118, 0.7278, 0.4237, 0.3587, 0.3400, 0.5675, 0.5917],
[0.6264, 0.4035, 0.8888, 0.4883, 0.4050, 0.5217, 0.6361, 0.4791],
[0.6152, 0.4131, 0.6862, 0.2567, 0.3625, 0.3300, 0.5765, 0.5305],
[0.0000, 0.0000, 0.8675, 0.2833, 0.5350, 0.1983, 0.6678, 0.5621]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.022489308787044138
step: 35
running loss: 0.0006425516796298325
Train Steps: 35/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.7425, 0.2117, 0.3937, 0.2433, 0.5438, 0.5567],
[0.6357, 0.4139, 0.8450, 0.5883, 0.3775, 0.4950, 0.6488, 0.5297],
[0.6299, 0.4303, 0.7963, 0.3933, 0.4850, 0.2283, 0.5480, 0.6222],
[0.6264, 0.4071, 0.9038, 0.3867, 0.3663, 0.3917, 0.6338, 0.5283],
[ nan, nan, 0.7512, 0.2117, 0.4288, 0.2000, 0.5600, 0.5617],
[0.6133, 0.4066, 0.6787, 0.2617, 0.3800, 0.2433, 0.5147, 0.5358],
[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395],
[0.6210, 0.4164, 0.7202, 0.2930, 0.4025, 0.2483, 0.5687, 0.5567]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.0647, 0.0577, 0.7094, 0.2131, 0.4062, 0.2470, 0.5556, 0.5255],
[0.7170, 0.4711, 0.8321, 0.5520, 0.4031, 0.4867, 0.6873, 0.5007],
[0.6999, 0.4748, 0.7984, 0.3779, 0.5006, 0.2218, 0.5600, 0.6054],
[0.6240, 0.4170, 0.9029, 0.3641, 0.3922, 0.3674, 0.6687, 0.5235],
[0.0865, 0.0725, 0.7177, 0.2025, 0.4379, 0.2046, 0.5630, 0.5395],
[0.6507, 0.4434, 0.6844, 0.2552, 0.4029, 0.2298, 0.5541, 0.5148],
[0.6804, 0.4533, 0.8606, 0.5392, 0.3824, 0.3423, 0.5690, 0.5038],
[0.5626, 0.3770, 0.7266, 0.2565, 0.4269, 0.2528, 0.5726, 0.5420]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.7425, 0.2117, 0.3938, 0.2433, 0.5437, 0.5567],
[0.6357, 0.4139, 0.8450, 0.5883, 0.3775, 0.4950, 0.6488, 0.5297],
[0.6299, 0.4303, 0.7962, 0.3933, 0.4850, 0.2283, 0.5480, 0.6222],
[0.6264, 0.4071, 0.9038, 0.3867, 0.3663, 0.3917, 0.6338, 0.5283],
[0.0000, 0.0000, 0.7513, 0.2117, 0.4288, 0.2000, 0.5600, 0.5617],
[0.6133, 0.4065, 0.6787, 0.2617, 0.3800, 0.2433, 0.5147, 0.5358],
[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395],
[0.6210, 0.4164, 0.7202, 0.2930, 0.4025, 0.2483, 0.5688, 0.5567]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.023610311618540436
step: 36
running loss: 0.000655841989403901
Train Steps: 36/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6042, 0.3990, 0.6831, 0.2875, 0.3500, 0.3133, 0.5143, 0.5510],
[0.6196, 0.4068, 0.7645, 0.2234, 0.4575, 0.1737, 0.5926, 0.5284],
[0.6201, 0.4082, 0.8827, 0.3715, 0.3825, 0.2712, 0.5845, 0.5412],
[0.6206, 0.4123, 0.7175, 0.2400, 0.3887, 0.2933, 0.6225, 0.5750],
[0.6164, 0.3956, 0.8757, 0.5088, 0.4300, 0.5320, 0.6022, 0.5202],
[0.6275, 0.4024, 0.8600, 0.2283, 0.5350, 0.1800, 0.7074, 0.5413],
[0.6258, 0.4038, 0.8750, 0.4883, 0.3900, 0.5500, 0.6375, 0.5217],
[0.6135, 0.3994, 0.7913, 0.3050, 0.3625, 0.3050, 0.5837, 0.5050]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5305, 0.3545, 0.6789, 0.2938, 0.3590, 0.3198, 0.5248, 0.5454],
[0.6119, 0.3984, 0.7472, 0.2210, 0.4547, 0.1996, 0.5760, 0.5310],
[0.6218, 0.4105, 0.8767, 0.3654, 0.3838, 0.2859, 0.5847, 0.5196],
[0.5847, 0.3989, 0.6975, 0.2397, 0.3882, 0.3049, 0.5973, 0.5677],
[0.5755, 0.3947, 0.8557, 0.5025, 0.4140, 0.5360, 0.5966, 0.5015],
[0.5259, 0.3512, 0.8314, 0.2048, 0.5442, 0.2115, 0.6936, 0.5579],
[0.6149, 0.4094, 0.8563, 0.4835, 0.4030, 0.5499, 0.6354, 0.5013],
[0.6113, 0.4014, 0.7697, 0.3001, 0.3698, 0.3214, 0.5749, 0.5048]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6042, 0.3990, 0.6831, 0.2875, 0.3500, 0.3133, 0.5143, 0.5510],
[0.6196, 0.4068, 0.7645, 0.2234, 0.4575, 0.1737, 0.5926, 0.5284],
[0.6201, 0.4082, 0.8827, 0.3715, 0.3825, 0.2712, 0.5845, 0.5412],
[0.6206, 0.4123, 0.7175, 0.2400, 0.3887, 0.2933, 0.6225, 0.5750],
[0.6164, 0.3956, 0.8757, 0.5088, 0.4300, 0.5320, 0.6022, 0.5202],
[0.6275, 0.4024, 0.8600, 0.2283, 0.5350, 0.1800, 0.7074, 0.5413],
[0.6258, 0.4038, 0.8750, 0.4883, 0.3900, 0.5500, 0.6375, 0.5217],
[0.6135, 0.3994, 0.7912, 0.3050, 0.3625, 0.3050, 0.5838, 0.5050]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.024129573779646307
step: 37
running loss: 0.0006521506426931435
Train Steps: 37/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466],
[0.6286, 0.3977, 0.9038, 0.4733, 0.3900, 0.4150, 0.7074, 0.5320],
[0.6076, 0.3958, 0.8700, 0.4667, 0.4546, 0.5046, 0.5231, 0.4960],
[0.6275, 0.4003, 0.9100, 0.3783, 0.4388, 0.3133, 0.7058, 0.5343],
[0.6314, 0.4050, 0.8227, 0.5431, 0.4150, 0.5517, 0.7121, 0.5690],
[0.6277, 0.4036, 0.8688, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742],
[0.6109, 0.4036, 0.7188, 0.1750, 0.3850, 0.2550, 0.5863, 0.5567],
[ nan, nan, 0.9050, 0.3500, 0.5138, 0.2300, 0.7359, 0.5702]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5915, 0.4067, 0.7443, 0.3600, 0.3274, 0.4274, 0.5061, 0.5529],
[0.6377, 0.4158, 0.8687, 0.4530, 0.3734, 0.4218, 0.6892, 0.5308],
[0.5794, 0.3966, 0.8383, 0.4475, 0.4386, 0.5175, 0.5149, 0.4928],
[0.6338, 0.4248, 0.8548, 0.3710, 0.4222, 0.3116, 0.6730, 0.5358],
[0.7068, 0.4678, 0.7913, 0.5072, 0.4048, 0.5658, 0.7041, 0.5697],
[0.6408, 0.4241, 0.8375, 0.3433, 0.3799, 0.2638, 0.5986, 0.4770],
[0.6320, 0.4270, 0.6807, 0.1809, 0.3609, 0.2769, 0.5538, 0.5540],
[0.0137, 0.0190, 0.8765, 0.3296, 0.4928, 0.2607, 0.7076, 0.5754]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466],
[0.6286, 0.3977, 0.9038, 0.4733, 0.3900, 0.4150, 0.7074, 0.5320],
[0.6076, 0.3958, 0.8700, 0.4667, 0.4546, 0.5046, 0.5231, 0.4960],
[0.6275, 0.4003, 0.9100, 0.3783, 0.4387, 0.3133, 0.7058, 0.5343],
[0.6314, 0.4050, 0.8227, 0.5431, 0.4150, 0.5517, 0.7121, 0.5690],
[0.6277, 0.4036, 0.8687, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742],
[0.6108, 0.4036, 0.7188, 0.1750, 0.3850, 0.2550, 0.5863, 0.5567],
[0.0000, 0.0000, 0.9050, 0.3500, 0.5138, 0.2300, 0.7359, 0.5702]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.02468388859415427
step: 38
running loss: 0.0006495760156356386
Train Steps: 38/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6090, 0.4010, 0.7838, 0.3483, 0.3538, 0.3783, 0.5462, 0.5077],
[0.6133, 0.4094, 0.8495, 0.4028, 0.3588, 0.3200, 0.5003, 0.5407],
[0.6262, 0.4052, 0.8888, 0.4700, 0.3675, 0.5117, 0.6350, 0.5233],
[ nan, nan, 0.7981, 0.3194, 0.3625, 0.3167, 0.5040, 0.5563],
[0.6274, 0.4003, 0.8638, 0.5967, 0.3688, 0.4900, 0.6108, 0.4661],
[0.6296, 0.3989, 0.9000, 0.4150, 0.3613, 0.3867, 0.6400, 0.5100],
[0.6128, 0.4084, 0.8738, 0.4683, 0.3613, 0.3700, 0.4960, 0.5397],
[0.6250, 0.4008, 0.8950, 0.4183, 0.3550, 0.4383, 0.6361, 0.4927]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6129, 0.4063, 0.7917, 0.3597, 0.3569, 0.3850, 0.5596, 0.5365],
[0.6281, 0.4296, 0.8484, 0.4040, 0.3571, 0.3257, 0.5343, 0.5817],
[0.6373, 0.4325, 0.8869, 0.4529, 0.3767, 0.5279, 0.6611, 0.5714],
[0.1334, 0.0916, 0.7740, 0.3285, 0.3362, 0.3465, 0.5411, 0.5706],
[0.6513, 0.4156, 0.8368, 0.5899, 0.3804, 0.4836, 0.6301, 0.5235],
[0.6552, 0.4389, 0.8928, 0.4076, 0.3683, 0.3872, 0.6558, 0.5557],
[0.6481, 0.4358, 0.8740, 0.4644, 0.3661, 0.3698, 0.5430, 0.5807],
[0.6519, 0.4143, 0.8887, 0.4221, 0.3605, 0.4488, 0.6484, 0.5383]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6090, 0.4010, 0.7837, 0.3483, 0.3537, 0.3783, 0.5462, 0.5077],
[0.6133, 0.4094, 0.8495, 0.4028, 0.3587, 0.3200, 0.5003, 0.5407],
[0.6262, 0.4052, 0.8888, 0.4700, 0.3675, 0.5117, 0.6350, 0.5233],
[0.0000, 0.0000, 0.7981, 0.3194, 0.3625, 0.3167, 0.5040, 0.5563],
[0.6274, 0.4003, 0.8637, 0.5967, 0.3688, 0.4900, 0.6108, 0.4661],
[0.6296, 0.3989, 0.9000, 0.4150, 0.3613, 0.3867, 0.6400, 0.5100],
[0.6127, 0.4084, 0.8737, 0.4683, 0.3613, 0.3700, 0.4960, 0.5397],
[0.6250, 0.4008, 0.8950, 0.4183, 0.3550, 0.4383, 0.6361, 0.4927]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.025601829052902758
step: 39
running loss: 0.0006564571552026349
Train Steps: 39/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6037, 0.4020, 0.8300, 0.4033, 0.3575, 0.4883, 0.5647, 0.5631],
[0.6300, 0.4102, 0.9088, 0.4433, 0.4088, 0.3067, 0.6820, 0.5540],
[0.6195, 0.4101, 0.8650, 0.3917, 0.3575, 0.4033, 0.5800, 0.5650],
[0.6031, 0.3986, 0.7462, 0.2833, 0.3638, 0.2717, 0.5253, 0.4726],
[0.6124, 0.4069, 0.8314, 0.5001, 0.3738, 0.4650, 0.5167, 0.5402],
[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758],
[0.6216, 0.4167, 0.8588, 0.5583, 0.3975, 0.5167, 0.5775, 0.5667],
[0.6185, 0.4080, 0.8625, 0.3483, 0.3788, 0.2650, 0.5320, 0.5272]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5923, 0.3935, 0.8309, 0.4015, 0.3470, 0.4915, 0.5611, 0.5772],
[0.5971, 0.3880, 0.9268, 0.4489, 0.4108, 0.3010, 0.6907, 0.5608],
[0.5750, 0.3796, 0.8649, 0.3878, 0.3541, 0.3999, 0.5692, 0.5792],
[0.6181, 0.4089, 0.7601, 0.2960, 0.3571, 0.2836, 0.5407, 0.4981],
[0.5764, 0.3802, 0.8338, 0.5028, 0.3890, 0.4537, 0.5403, 0.5809],
[0.5548, 0.3543, 0.8884, 0.4880, 0.4015, 0.5276, 0.6515, 0.5027],
[0.5754, 0.3802, 0.8593, 0.5455, 0.3952, 0.5068, 0.6076, 0.5875],
[0.6041, 0.3931, 0.8534, 0.3662, 0.3729, 0.2801, 0.5366, 0.5386]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6037, 0.4020, 0.8300, 0.4033, 0.3575, 0.4883, 0.5647, 0.5631],
[0.6300, 0.4102, 0.9087, 0.4433, 0.4087, 0.3067, 0.6820, 0.5540],
[0.6195, 0.4101, 0.8650, 0.3917, 0.3575, 0.4033, 0.5800, 0.5650],
[0.6031, 0.3986, 0.7462, 0.2833, 0.3638, 0.2717, 0.5253, 0.4726],
[0.6123, 0.4069, 0.8314, 0.5001, 0.3738, 0.4650, 0.5167, 0.5402],
[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758],
[0.6216, 0.4167, 0.8587, 0.5583, 0.3975, 0.5167, 0.5775, 0.5667],
[0.6186, 0.4080, 0.8625, 0.3483, 0.3787, 0.2650, 0.5320, 0.5272]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.026024623948615044
step: 40
running loss: 0.0006506155987153761
Train Steps: 40/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6227, 0.4193, 0.8838, 0.4933, 0.3663, 0.3733, 0.5637, 0.5633],
[0.6339, 0.4123, 0.8638, 0.5367, 0.4075, 0.5467, 0.7517, 0.5436],
[0.6265, 0.4251, 0.7113, 0.3550, 0.4375, 0.2117, 0.5587, 0.6118],
[0.6275, 0.4048, 0.8488, 0.2883, 0.4463, 0.2033, 0.6321, 0.5155],
[0.6137, 0.4035, 0.8850, 0.4417, 0.3900, 0.4283, 0.5449, 0.5617],
[0.6286, 0.4274, 0.8500, 0.4500, 0.4525, 0.2583, 0.5440, 0.6209],
[0.6262, 0.4163, 0.8850, 0.5183, 0.3763, 0.4150, 0.6025, 0.5500],
[0.6200, 0.4071, 0.7338, 0.1917, 0.4200, 0.2450, 0.6150, 0.5517]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5710, 0.3669, 0.8803, 0.4861, 0.3399, 0.3925, 0.5360, 0.5629],
[0.6074, 0.3811, 0.8732, 0.5031, 0.3837, 0.5618, 0.7136, 0.5447],
[0.6312, 0.4340, 0.7334, 0.3560, 0.4082, 0.2233, 0.5435, 0.6089],
[0.5749, 0.3547, 0.8671, 0.2773, 0.4278, 0.2215, 0.6111, 0.4986],
[0.5160, 0.3339, 0.8919, 0.4469, 0.3652, 0.4611, 0.5324, 0.5568],
[0.5851, 0.3807, 0.8481, 0.4560, 0.4351, 0.2759, 0.5394, 0.6058],
[0.5667, 0.3640, 0.8894, 0.5041, 0.3626, 0.4124, 0.5844, 0.5541],
[0.5533, 0.3655, 0.7546, 0.2004, 0.3957, 0.2607, 0.6060, 0.5405]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6227, 0.4193, 0.8838, 0.4933, 0.3663, 0.3733, 0.5638, 0.5633],
[0.6339, 0.4123, 0.8637, 0.5367, 0.4075, 0.5467, 0.7517, 0.5436],
[0.6265, 0.4251, 0.7113, 0.3550, 0.4375, 0.2117, 0.5587, 0.6118],
[0.6275, 0.4048, 0.8487, 0.2883, 0.4462, 0.2033, 0.6321, 0.5155],
[0.6137, 0.4035, 0.8850, 0.4417, 0.3900, 0.4283, 0.5449, 0.5617],
[0.6286, 0.4274, 0.8500, 0.4500, 0.4525, 0.2583, 0.5440, 0.6209],
[0.6262, 0.4163, 0.8850, 0.5183, 0.3762, 0.4150, 0.6025, 0.5500],
[0.6200, 0.4071, 0.7337, 0.1917, 0.4200, 0.2450, 0.6150, 0.5517]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.02692328830016777
step: 41
running loss: 0.0006566655682967748
Train Steps: 41/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6214, 0.4040, 0.8838, 0.3500, 0.3600, 0.5183, 0.6362, 0.5200],
[0.6164, 0.4102, 0.8850, 0.4867, 0.4213, 0.5983, 0.5609, 0.5038],
[0.6175, 0.4093, 0.8800, 0.4433, 0.4075, 0.4367, 0.5128, 0.4901],
[ nan, nan, 0.7225, 0.2167, 0.3987, 0.2283, 0.5427, 0.5181],
[0.6300, 0.4102, 0.9088, 0.4433, 0.4088, 0.3067, 0.6820, 0.5540],
[0.6205, 0.4081, 0.8950, 0.4017, 0.3788, 0.4700, 0.5963, 0.5667],
[0.6339, 0.4149, 0.8800, 0.5000, 0.3900, 0.5283, 0.7541, 0.5424],
[0.6154, 0.4048, 0.7100, 0.2067, 0.4338, 0.1667, 0.5413, 0.5220]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6538, 0.4220, 0.8873, 0.3851, 0.3581, 0.5102, 0.6221, 0.5243],
[0.6167, 0.4197, 0.9097, 0.5269, 0.4462, 0.5868, 0.5661, 0.5541],
[0.6237, 0.4020, 0.9165, 0.4854, 0.4226, 0.4382, 0.4926, 0.5166],
[0.0564, 0.0392, 0.7513, 0.2278, 0.3858, 0.2244, 0.5631, 0.5290],
[0.6554, 0.4202, 0.9537, 0.4827, 0.4247, 0.2915, 0.6790, 0.5506],
[0.6010, 0.3892, 0.9020, 0.4234, 0.3771, 0.4627, 0.5740, 0.5795],
[0.6802, 0.4307, 0.9158, 0.5482, 0.3977, 0.5348, 0.6974, 0.5587],
[0.6571, 0.4200, 0.7340, 0.2392, 0.4364, 0.1543, 0.5420, 0.5228]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6214, 0.4040, 0.8838, 0.3500, 0.3600, 0.5183, 0.6363, 0.5200],
[0.6164, 0.4102, 0.8850, 0.4867, 0.4212, 0.5983, 0.5609, 0.5038],
[0.6175, 0.4093, 0.8800, 0.4433, 0.4075, 0.4367, 0.5128, 0.4901],
[0.0000, 0.0000, 0.7225, 0.2167, 0.3988, 0.2283, 0.5427, 0.5181],
[0.6300, 0.4102, 0.9087, 0.4433, 0.4087, 0.3067, 0.6820, 0.5540],
[0.6205, 0.4081, 0.8950, 0.4017, 0.3787, 0.4700, 0.5962, 0.5667],
[0.6339, 0.4149, 0.8800, 0.5000, 0.3900, 0.5283, 0.7541, 0.5424],
[0.6154, 0.4048, 0.7100, 0.2067, 0.4338, 0.1667, 0.5413, 0.5220]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.027541582996491343
step: 42
running loss: 0.0006557519761069367
Train Steps: 42/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6222, 0.3957, 0.8838, 0.5017, 0.3937, 0.4600, 0.5900, 0.5017],
[0.6143, 0.4055, 0.8150, 0.2767, 0.3825, 0.2567, 0.5173, 0.4901],
[0.6101, 0.3977, 0.8550, 0.5667, 0.3862, 0.4417, 0.5128, 0.4869],
[0.6140, 0.4070, 0.8700, 0.5000, 0.4612, 0.4900, 0.5260, 0.5852],
[0.6076, 0.3953, 0.8125, 0.3917, 0.3525, 0.4083, 0.5346, 0.4954],
[0.6265, 0.4071, 0.8875, 0.3367, 0.3975, 0.3350, 0.6312, 0.5250],
[0.6229, 0.4198, 0.7662, 0.2700, 0.4700, 0.2133, 0.5675, 0.5783],
[0.6186, 0.3967, 0.7337, 0.1992, 0.4120, 0.2508, 0.6105, 0.5395]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6118, 0.3809, 0.9111, 0.5268, 0.4022, 0.4456, 0.5834, 0.5014],
[0.5783, 0.3738, 0.8171, 0.3106, 0.3702, 0.2482, 0.5296, 0.4924],
[0.5396, 0.3483, 0.8902, 0.5831, 0.3964, 0.4131, 0.5367, 0.4819],
[0.5588, 0.3638, 0.9016, 0.5124, 0.4678, 0.4860, 0.5316, 0.5854],
[0.5850, 0.3821, 0.8373, 0.3984, 0.3518, 0.3892, 0.5544, 0.4998],
[0.5832, 0.3674, 0.9191, 0.3663, 0.4033, 0.3351, 0.6651, 0.5223],
[0.5833, 0.3871, 0.7874, 0.2756, 0.4619, 0.2136, 0.5767, 0.5614],
[0.5861, 0.3766, 0.7723, 0.2376, 0.4008, 0.2322, 0.6142, 0.5345]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6222, 0.3957, 0.8838, 0.5017, 0.3938, 0.4600, 0.5900, 0.5017],
[0.6143, 0.4055, 0.8150, 0.2767, 0.3825, 0.2567, 0.5173, 0.4901],
[0.6101, 0.3977, 0.8550, 0.5667, 0.3862, 0.4417, 0.5128, 0.4869],
[0.6140, 0.4070, 0.8700, 0.5000, 0.4613, 0.4900, 0.5260, 0.5852],
[0.6076, 0.3952, 0.8125, 0.3917, 0.3525, 0.4083, 0.5346, 0.4954],
[0.6265, 0.4071, 0.8875, 0.3367, 0.3975, 0.3350, 0.6313, 0.5250],
[0.6229, 0.4198, 0.7663, 0.2700, 0.4700, 0.2133, 0.5675, 0.5783],
[0.6186, 0.3967, 0.7337, 0.1992, 0.4120, 0.2508, 0.6105, 0.5395]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.028159943351056427
step: 43
running loss: 0.0006548824035129402
Train Steps: 43/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6260, 0.4214, 0.8538, 0.5500, 0.3663, 0.3767, 0.5587, 0.5983],
[0.6193, 0.4108, 0.7438, 0.2700, 0.3650, 0.3683, 0.6238, 0.5717],
[0.6092, 0.4001, 0.8638, 0.4867, 0.4288, 0.5367, 0.5484, 0.5064],
[ nan, nan, 0.8300, 0.3150, 0.3588, 0.3383, 0.5208, 0.5194],
[0.6250, 0.4110, 0.7238, 0.2067, 0.4263, 0.1883, 0.5625, 0.5633],
[0.6261, 0.3987, 0.9045, 0.4208, 0.3600, 0.4633, 0.6570, 0.5162],
[0.6275, 0.4003, 0.9100, 0.3783, 0.4388, 0.3133, 0.7058, 0.5343],
[0.6142, 0.3982, 0.8650, 0.4883, 0.3912, 0.4317, 0.5315, 0.5350]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6471, 0.4310, 0.8641, 0.5437, 0.3815, 0.3744, 0.5533, 0.5701],
[0.6438, 0.4260, 0.7552, 0.2701, 0.3719, 0.3479, 0.6202, 0.5499],
[0.6414, 0.4279, 0.8818, 0.4889, 0.4370, 0.5421, 0.5285, 0.4820],
[0.0014, 0.0012, 0.8453, 0.3188, 0.3674, 0.3091, 0.5420, 0.5049],
[0.6419, 0.4286, 0.7340, 0.2096, 0.4328, 0.1638, 0.5606, 0.5363],
[0.6953, 0.4560, 0.9059, 0.4319, 0.3676, 0.4678, 0.6474, 0.4943],
[0.6849, 0.4451, 0.9102, 0.3899, 0.4505, 0.2879, 0.6936, 0.5105],
[0.6586, 0.4198, 0.8778, 0.5090, 0.4006, 0.4320, 0.5175, 0.4929]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6260, 0.4214, 0.8537, 0.5500, 0.3663, 0.3767, 0.5587, 0.5983],
[0.6193, 0.4108, 0.7437, 0.2700, 0.3650, 0.3683, 0.6237, 0.5717],
[0.6092, 0.4001, 0.8637, 0.4867, 0.4288, 0.5367, 0.5484, 0.5064],
[0.0000, 0.0000, 0.8300, 0.3150, 0.3587, 0.3383, 0.5208, 0.5194],
[0.6250, 0.4110, 0.7237, 0.2067, 0.4263, 0.1883, 0.5625, 0.5633],
[0.6261, 0.3987, 0.9045, 0.4208, 0.3600, 0.4633, 0.6570, 0.5162],
[0.6275, 0.4003, 0.9100, 0.3783, 0.4387, 0.3133, 0.7058, 0.5343],
[0.6143, 0.3982, 0.8650, 0.4883, 0.3913, 0.4317, 0.5315, 0.5350]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.028655284026172012
step: 44
running loss: 0.000651256455140273
Train Steps: 44/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6183, 0.4076, 0.8838, 0.4517, 0.3813, 0.4483, 0.5775, 0.5633],
[0.6137, 0.4038, 0.8563, 0.4050, 0.3813, 0.2550, 0.5106, 0.4954],
[0.6228, 0.4004, 0.8750, 0.5250, 0.3825, 0.5233, 0.6362, 0.5000],
[0.6095, 0.4002, 0.8533, 0.5168, 0.5031, 0.5094, 0.5125, 0.5433],
[0.6090, 0.4045, 0.7250, 0.2100, 0.4075, 0.2300, 0.5476, 0.5663],
[0.6124, 0.4069, 0.8314, 0.5001, 0.3738, 0.4650, 0.5167, 0.5402],
[0.6202, 0.4054, 0.8892, 0.4428, 0.3642, 0.3249, 0.5840, 0.5426],
[0.6221, 0.4107, 0.7788, 0.3033, 0.3950, 0.2817, 0.6075, 0.5517]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5749, 0.3847, 0.8832, 0.4350, 0.3910, 0.4564, 0.5788, 0.5423],
[0.5752, 0.3708, 0.8686, 0.4065, 0.4086, 0.2554, 0.5023, 0.4715],
[0.5742, 0.3650, 0.8813, 0.5068, 0.3964, 0.5120, 0.6576, 0.4739],
[0.6020, 0.3978, 0.8577, 0.5034, 0.5040, 0.5041, 0.5080, 0.5240],
[0.6640, 0.4409, 0.7202, 0.2139, 0.4073, 0.2258, 0.5346, 0.5368],
[0.6279, 0.4088, 0.8483, 0.4965, 0.4003, 0.4486, 0.5340, 0.5275],
[0.6190, 0.3872, 0.8941, 0.4202, 0.3754, 0.3232, 0.5813, 0.4973],
[0.6085, 0.4068, 0.8025, 0.2739, 0.4027, 0.2712, 0.6047, 0.5237]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6183, 0.4076, 0.8838, 0.4517, 0.3812, 0.4483, 0.5775, 0.5633],
[0.6137, 0.4038, 0.8562, 0.4050, 0.3812, 0.2550, 0.5106, 0.4954],
[0.6228, 0.4004, 0.8750, 0.5250, 0.3825, 0.5233, 0.6363, 0.5000],
[0.6095, 0.4002, 0.8533, 0.5168, 0.5031, 0.5094, 0.5125, 0.5433],
[0.6090, 0.4045, 0.7250, 0.2100, 0.4075, 0.2300, 0.5476, 0.5663],
[0.6123, 0.4069, 0.8314, 0.5001, 0.3738, 0.4650, 0.5167, 0.5402],
[0.6202, 0.4054, 0.8892, 0.4428, 0.3642, 0.3249, 0.5840, 0.5426],
[0.6221, 0.4107, 0.7788, 0.3033, 0.3950, 0.2817, 0.6075, 0.5517]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.02907089513610117
step: 45
running loss: 0.0006460198919133593
Train Steps: 45/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6198, 0.4075, 0.8650, 0.5617, 0.4150, 0.4367, 0.5450, 0.5650],
[0.6286, 0.4034, 0.8191, 0.2414, 0.4262, 0.2393, 0.6365, 0.5356],
[0.6075, 0.4000, 0.8513, 0.5183, 0.4510, 0.5329, 0.5180, 0.5280],
[0.6082, 0.4024, 0.8738, 0.4017, 0.3688, 0.3950, 0.5306, 0.5136],
[0.6325, 0.4066, 0.8438, 0.5350, 0.3925, 0.5267, 0.7113, 0.5795],
[0.6214, 0.4116, 0.7750, 0.2317, 0.4487, 0.1883, 0.6200, 0.5400],
[0.6200, 0.4086, 0.8414, 0.2974, 0.4117, 0.2274, 0.5869, 0.5391],
[0.6150, 0.3935, 0.8696, 0.5158, 0.4647, 0.5329, 0.6041, 0.5153]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6424, 0.4252, 0.8419, 0.5430, 0.4097, 0.4271, 0.5317, 0.5429],
[0.6416, 0.4061, 0.8005, 0.2153, 0.4281, 0.2328, 0.6118, 0.5114],
[0.5964, 0.3905, 0.8354, 0.4923, 0.4562, 0.5312, 0.5099, 0.5059],
[0.6142, 0.4033, 0.8649, 0.3768, 0.3471, 0.3857, 0.5197, 0.4894],
[0.6468, 0.4079, 0.8238, 0.5167, 0.3851, 0.5406, 0.6945, 0.5502],
[0.5346, 0.3638, 0.7716, 0.1978, 0.4523, 0.1814, 0.6084, 0.5259],
[0.5847, 0.3879, 0.8422, 0.2714, 0.4162, 0.2223, 0.5703, 0.5198],
[0.5986, 0.3831, 0.8542, 0.4812, 0.4572, 0.5328, 0.5836, 0.4991]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6198, 0.4075, 0.8650, 0.5617, 0.4150, 0.4367, 0.5450, 0.5650],
[0.6286, 0.4034, 0.8191, 0.2414, 0.4262, 0.2393, 0.6365, 0.5356],
[0.6075, 0.4000, 0.8512, 0.5183, 0.4510, 0.5329, 0.5180, 0.5280],
[0.6082, 0.4024, 0.8737, 0.4017, 0.3688, 0.3950, 0.5306, 0.5136],
[0.6325, 0.4066, 0.8438, 0.5350, 0.3925, 0.5267, 0.7113, 0.5795],
[0.6214, 0.4116, 0.7750, 0.2317, 0.4487, 0.1883, 0.6200, 0.5400],
[0.6199, 0.4086, 0.8414, 0.2974, 0.4117, 0.2274, 0.5869, 0.5391],
[0.6150, 0.3935, 0.8696, 0.5158, 0.4647, 0.5329, 0.6041, 0.5153]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.02950749092269689
step: 46
running loss: 0.0006414671939716715
Train Steps: 46/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6075, 0.4000, 0.8513, 0.5183, 0.4510, 0.5329, 0.5180, 0.5280],
[0.6127, 0.4115, 0.7163, 0.2883, 0.3625, 0.2950, 0.5327, 0.5495],
[0.6282, 0.4092, 0.8000, 0.2183, 0.4500, 0.2383, 0.6787, 0.5364],
[ nan, nan, 0.8938, 0.2850, 0.4662, 0.3117, 0.7406, 0.5528],
[0.6364, 0.4165, 0.9088, 0.4367, 0.4075, 0.3150, 0.6448, 0.5297],
[0.6178, 0.4059, 0.7525, 0.2250, 0.4313, 0.1783, 0.5404, 0.5240],
[0.6072, 0.4029, 0.7037, 0.2150, 0.3912, 0.2267, 0.5516, 0.5507],
[0.6346, 0.4144, 0.9088, 0.4667, 0.3850, 0.4333, 0.7121, 0.5899]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6545, 0.4337, 0.8315, 0.5277, 0.4499, 0.5490, 0.5029, 0.5197],
[0.6328, 0.4295, 0.6849, 0.2833, 0.3487, 0.3037, 0.4949, 0.5662],
[0.6140, 0.4039, 0.7645, 0.2126, 0.4507, 0.2166, 0.6423, 0.5386],
[0.1316, 0.0792, 0.9086, 0.2893, 0.4728, 0.2985, 0.7566, 0.5720],
[0.6985, 0.4589, 0.8860, 0.4478, 0.4048, 0.3236, 0.6257, 0.5292],
[0.5595, 0.3648, 0.7252, 0.2200, 0.4176, 0.1788, 0.5110, 0.5336],
[0.6185, 0.4166, 0.6774, 0.2080, 0.3846, 0.2352, 0.5337, 0.5579],
[0.6581, 0.4324, 0.8878, 0.4624, 0.3838, 0.4349, 0.6888, 0.5846]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6075, 0.4000, 0.8512, 0.5183, 0.4510, 0.5329, 0.5180, 0.5280],
[0.6127, 0.4114, 0.7163, 0.2883, 0.3625, 0.2950, 0.5327, 0.5495],
[0.6282, 0.4092, 0.8000, 0.2183, 0.4500, 0.2383, 0.6787, 0.5364],
[0.0000, 0.0000, 0.8938, 0.2850, 0.4663, 0.3117, 0.7406, 0.5528],
[0.6364, 0.4165, 0.9087, 0.4367, 0.4075, 0.3150, 0.6448, 0.5297],
[0.6178, 0.4059, 0.7525, 0.2250, 0.4313, 0.1783, 0.5404, 0.5240],
[0.6072, 0.4029, 0.7038, 0.2150, 0.3913, 0.2267, 0.5516, 0.5507],
[0.6346, 0.4144, 0.9087, 0.4667, 0.3850, 0.4333, 0.7121, 0.5899]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.030339945456944406
step: 47
running loss: 0.0006455307544030725
Train Steps: 47/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6260, 0.4161, 0.9000, 0.3833, 0.4450, 0.2133, 0.6237, 0.4986],
[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466],
[0.6197, 0.4118, 0.8688, 0.5517, 0.4037, 0.5233, 0.5875, 0.5600],
[0.6289, 0.4032, 0.8419, 0.5446, 0.4075, 0.5017, 0.6312, 0.5117],
[0.6196, 0.4090, 0.8450, 0.3900, 0.3575, 0.3933, 0.5975, 0.5583],
[0.6286, 0.4274, 0.8500, 0.4500, 0.4525, 0.2583, 0.5440, 0.6209],
[0.6353, 0.4128, 0.8488, 0.2600, 0.5525, 0.1616, 0.6694, 0.5540],
[0.6204, 0.4091, 0.8950, 0.4783, 0.3613, 0.4617, 0.6063, 0.5617]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6954, 0.4573, 0.8934, 0.3729, 0.4420, 0.2353, 0.6405, 0.5110],
[0.6154, 0.4141, 0.7470, 0.3557, 0.3407, 0.4372, 0.5124, 0.5594],
[0.6399, 0.4215, 0.8431, 0.5455, 0.3859, 0.5617, 0.5871, 0.5451],
[0.6166, 0.3978, 0.8250, 0.5295, 0.3898, 0.5311, 0.6521, 0.5186],
[0.6482, 0.4284, 0.8307, 0.3686, 0.3432, 0.4072, 0.6018, 0.5702],
[0.6427, 0.4318, 0.8174, 0.4371, 0.4419, 0.2847, 0.5541, 0.6283],
[0.4102, 0.2716, 0.8553, 0.2385, 0.5360, 0.1767, 0.7007, 0.5699],
[0.5646, 0.3775, 0.8764, 0.4672, 0.3465, 0.4999, 0.6117, 0.5606]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6260, 0.4161, 0.9000, 0.3833, 0.4450, 0.2133, 0.6237, 0.4986],
[0.6048, 0.3987, 0.7620, 0.3861, 0.3475, 0.4167, 0.5137, 0.5466],
[0.6197, 0.4118, 0.8687, 0.5517, 0.4038, 0.5233, 0.5875, 0.5600],
[0.6289, 0.4031, 0.8419, 0.5446, 0.4075, 0.5017, 0.6313, 0.5117],
[0.6196, 0.4090, 0.8450, 0.3900, 0.3575, 0.3933, 0.5975, 0.5583],
[0.6286, 0.4274, 0.8500, 0.4500, 0.4525, 0.2583, 0.5440, 0.6209],
[0.6353, 0.4128, 0.8487, 0.2600, 0.5525, 0.1616, 0.6694, 0.5540],
[0.6204, 0.4091, 0.8950, 0.4783, 0.3613, 0.4617, 0.6062, 0.5617]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0016, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03189117752481252
step: 48
running loss: 0.0006643995317669275
Train Steps: 48/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6043, 0.4022, 0.6887, 0.1983, 0.3775, 0.2483, 0.5480, 0.5136],
[0.6126, 0.3954, 0.8538, 0.4983, 0.4250, 0.4700, 0.5355, 0.5350],
[0.6168, 0.4055, 0.7575, 0.2950, 0.4050, 0.2717, 0.5938, 0.6167],
[0.6156, 0.4125, 0.8850, 0.4833, 0.4550, 0.5817, 0.5765, 0.5084],
[0.6080, 0.4010, 0.8750, 0.4500, 0.4825, 0.5617, 0.5837, 0.5583],
[0.6239, 0.4123, 0.8313, 0.2550, 0.4500, 0.2050, 0.6175, 0.5400],
[0.6286, 0.4040, 0.8696, 0.3047, 0.3924, 0.2887, 0.6300, 0.5367],
[ nan, nan, 0.7425, 0.2117, 0.3937, 0.2433, 0.5438, 0.5567]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6015, 0.4091, 0.6792, 0.2112, 0.3803, 0.2605, 0.5657, 0.5407],
[ 0.6865, 0.4520, 0.8424, 0.5097, 0.4201, 0.4669, 0.5732, 0.5527],
[ 0.6460, 0.4397, 0.7416, 0.2950, 0.3965, 0.2750, 0.6165, 0.6558],
[ 0.6428, 0.4430, 0.8711, 0.5092, 0.4494, 0.5808, 0.6035, 0.5408],
[ 0.6505, 0.4395, 0.8684, 0.4644, 0.4637, 0.5359, 0.6041, 0.5740],
[ 0.6279, 0.4122, 0.8126, 0.2524, 0.4543, 0.1920, 0.6404, 0.5525],
[ 0.6940, 0.4552, 0.8476, 0.3173, 0.3913, 0.2747, 0.6630, 0.5650],
[-0.0232, -0.0028, 0.7549, 0.2287, 0.4013, 0.2235, 0.5537, 0.5746]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6043, 0.4022, 0.6888, 0.1983, 0.3775, 0.2483, 0.5480, 0.5136],
[0.6126, 0.3954, 0.8537, 0.4983, 0.4250, 0.4700, 0.5355, 0.5350],
[0.6168, 0.4055, 0.7575, 0.2950, 0.4050, 0.2717, 0.5938, 0.6167],
[0.6155, 0.4124, 0.8850, 0.4833, 0.4550, 0.5817, 0.5765, 0.5084],
[0.6080, 0.4010, 0.8750, 0.4500, 0.4825, 0.5617, 0.5838, 0.5583],
[0.6239, 0.4123, 0.8313, 0.2550, 0.4500, 0.2050, 0.6175, 0.5400],
[0.6286, 0.4040, 0.8696, 0.3047, 0.3924, 0.2887, 0.6300, 0.5367],
[0.0000, 0.0000, 0.7425, 0.2117, 0.3938, 0.2433, 0.5437, 0.5567]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.032499423483386636
step: 49
running loss: 0.0006632535404772783
Train Steps: 49/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6263, 0.4233, 0.7924, 0.4626, 0.3788, 0.2883, 0.5573, 0.6047],
[0.6097, 0.3988, 0.8650, 0.5250, 0.4213, 0.5200, 0.5675, 0.5050],
[0.6122, 0.3993, 0.8738, 0.4667, 0.4517, 0.4879, 0.5155, 0.4927],
[0.6163, 0.4006, 0.8788, 0.4683, 0.3663, 0.4883, 0.5887, 0.5017],
[0.6145, 0.4008, 0.8750, 0.5383, 0.3975, 0.4650, 0.5563, 0.5533],
[0.6185, 0.4067, 0.8838, 0.4450, 0.4037, 0.4733, 0.5213, 0.5142],
[0.6346, 0.4144, 0.9088, 0.4667, 0.3850, 0.4333, 0.7121, 0.5899],
[ nan, nan, 0.8850, 0.3000, 0.5363, 0.2250, 0.7343, 0.5771]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6716, 0.4577, 0.7748, 0.4710, 0.3777, 0.2858, 0.5700, 0.6375],
[0.6477, 0.4321, 0.8409, 0.5273, 0.4271, 0.5287, 0.5504, 0.5211],
[0.6724, 0.4409, 0.8604, 0.4746, 0.4422, 0.5025, 0.5418, 0.5029],
[0.6832, 0.4455, 0.8589, 0.4731, 0.3588, 0.5001, 0.5931, 0.5311],
[0.6424, 0.4260, 0.8493, 0.5241, 0.3827, 0.4609, 0.5877, 0.5796],
[0.6399, 0.4265, 0.8529, 0.4411, 0.3920, 0.4770, 0.5210, 0.5491],
[0.6415, 0.4153, 0.8961, 0.4563, 0.3989, 0.4180, 0.7343, 0.6127],
[0.0013, 0.0094, 0.9064, 0.2967, 0.5239, 0.2192, 0.7298, 0.5917]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6263, 0.4232, 0.7924, 0.4626, 0.3787, 0.2883, 0.5573, 0.6047],
[0.6097, 0.3988, 0.8650, 0.5250, 0.4212, 0.5200, 0.5675, 0.5050],
[0.6122, 0.3993, 0.8737, 0.4667, 0.4517, 0.4879, 0.5155, 0.4927],
[0.6163, 0.4006, 0.8788, 0.4683, 0.3663, 0.4883, 0.5888, 0.5017],
[0.6145, 0.4008, 0.8750, 0.5383, 0.3975, 0.4650, 0.5562, 0.5533],
[0.6185, 0.4067, 0.8838, 0.4450, 0.4038, 0.4733, 0.5213, 0.5142],
[0.6346, 0.4144, 0.9087, 0.4667, 0.3850, 0.4333, 0.7121, 0.5899],
[0.0000, 0.0000, 0.8850, 0.3000, 0.5362, 0.2250, 0.7343, 0.5771]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03302222432103008
step: 50
running loss: 0.0006604444864206017
Train Steps: 50/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6239, 0.4107, 0.8162, 0.2763, 0.3625, 0.3600, 0.5988, 0.5700],
[0.6137, 0.4035, 0.8850, 0.4417, 0.3900, 0.4283, 0.5449, 0.5617],
[ nan, nan, 0.9050, 0.3500, 0.5138, 0.2300, 0.7359, 0.5702],
[0.6236, 0.3966, 0.8850, 0.4967, 0.3638, 0.4017, 0.5850, 0.5183],
[0.6102, 0.3999, 0.8750, 0.5133, 0.3825, 0.4750, 0.5637, 0.5083],
[0.6310, 0.4017, 0.8563, 0.5800, 0.3688, 0.4750, 0.6326, 0.5006],
[0.6300, 0.4102, 0.9088, 0.4433, 0.4088, 0.3067, 0.6820, 0.5540],
[0.6196, 0.4068, 0.7645, 0.2234, 0.4575, 0.1737, 0.5926, 0.5284]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6350, 0.4143, 0.7841, 0.2905, 0.3769, 0.3715, 0.5888, 0.5981],
[0.6583, 0.4429, 0.8623, 0.4535, 0.3923, 0.4489, 0.5495, 0.5690],
[0.0326, 0.0221, 0.9258, 0.3567, 0.5297, 0.2380, 0.7122, 0.5763],
[0.6316, 0.4160, 0.8865, 0.4939, 0.3749, 0.4176, 0.6057, 0.5378],
[0.5989, 0.4009, 0.8659, 0.5195, 0.3898, 0.4810, 0.5427, 0.5191],
[0.6340, 0.4147, 0.8485, 0.5868, 0.3658, 0.4756, 0.6203, 0.5119],
[0.6492, 0.4303, 0.9090, 0.4505, 0.4247, 0.3199, 0.6731, 0.5689],
[0.7051, 0.4617, 0.7650, 0.2274, 0.4712, 0.1993, 0.5996, 0.5446]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6239, 0.4107, 0.8162, 0.2763, 0.3625, 0.3600, 0.5987, 0.5700],
[0.6137, 0.4035, 0.8850, 0.4417, 0.3900, 0.4283, 0.5449, 0.5617],
[0.0000, 0.0000, 0.9050, 0.3500, 0.5138, 0.2300, 0.7359, 0.5702],
[0.6236, 0.3965, 0.8850, 0.4967, 0.3638, 0.4017, 0.5850, 0.5183],
[0.6102, 0.3999, 0.8750, 0.5133, 0.3825, 0.4750, 0.5638, 0.5083],
[0.6310, 0.4017, 0.8562, 0.5800, 0.3688, 0.4750, 0.6326, 0.5006],
[0.6300, 0.4102, 0.9087, 0.4433, 0.4087, 0.3067, 0.6820, 0.5540],
[0.6196, 0.4068, 0.7645, 0.2234, 0.4575, 0.1737, 0.5926, 0.5284]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03343431546818465
step: 51
running loss: 0.0006555748131016598
Train Steps: 51/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6202, 0.4066, 0.8746, 0.3376, 0.3717, 0.3090, 0.5842, 0.5165],
[0.6264, 0.4067, 0.9050, 0.4183, 0.3775, 0.4600, 0.6308, 0.4862],
[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383],
[0.6135, 0.3994, 0.7913, 0.3050, 0.3625, 0.3050, 0.5837, 0.5050],
[0.6163, 0.4114, 0.7650, 0.2017, 0.3763, 0.2867, 0.5631, 0.5071],
[0.6311, 0.3998, 0.7975, 0.5767, 0.3838, 0.4850, 0.7327, 0.5343],
[0.6222, 0.4108, 0.8938, 0.4233, 0.3600, 0.3817, 0.5825, 0.5283],
[0.6109, 0.4036, 0.7188, 0.1750, 0.3850, 0.2550, 0.5863, 0.5567]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5903, 0.3858, 0.8913, 0.3479, 0.4020, 0.3025, 0.5814, 0.5338],
[0.6145, 0.3955, 0.9317, 0.4338, 0.3939, 0.4503, 0.6172, 0.5075],
[0.5838, 0.3638, 0.8573, 0.3198, 0.3734, 0.3658, 0.6123, 0.5476],
[0.6290, 0.4002, 0.8091, 0.3085, 0.3937, 0.3147, 0.5827, 0.5231],
[0.6167, 0.4136, 0.7696, 0.2070, 0.4055, 0.2694, 0.5670, 0.5264],
[0.5940, 0.3831, 0.8313, 0.5702, 0.4039, 0.4745, 0.7099, 0.5393],
[0.6499, 0.4372, 0.9018, 0.4441, 0.3836, 0.3688, 0.5787, 0.5647],
[0.6392, 0.4080, 0.7350, 0.1964, 0.4205, 0.2529, 0.5691, 0.5825]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6202, 0.4066, 0.8746, 0.3376, 0.3717, 0.3090, 0.5842, 0.5165],
[0.6264, 0.4067, 0.9050, 0.4183, 0.3775, 0.4600, 0.6308, 0.4862],
[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383],
[0.6135, 0.3994, 0.7912, 0.3050, 0.3625, 0.3050, 0.5838, 0.5050],
[0.6163, 0.4114, 0.7650, 0.2017, 0.3762, 0.2867, 0.5631, 0.5071],
[0.6311, 0.3998, 0.7975, 0.5767, 0.3837, 0.4850, 0.7327, 0.5343],
[0.6222, 0.4108, 0.8938, 0.4233, 0.3600, 0.3817, 0.5825, 0.5283],
[0.6108, 0.4036, 0.7188, 0.1750, 0.3850, 0.2550, 0.5863, 0.5567]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03381663607433438
step: 52
running loss: 0.0006503199245064304
Train Steps: 52/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6239, 0.4174, 0.8425, 0.5733, 0.4825, 0.4500, 0.5625, 0.5933],
[0.6175, 0.4091, 0.7863, 0.2800, 0.3638, 0.3583, 0.6188, 0.5433],
[0.6147, 0.4026, 0.6600, 0.2467, 0.4088, 0.2150, 0.5489, 0.5773],
[0.6146, 0.4124, 0.8800, 0.4867, 0.3800, 0.4500, 0.5106, 0.5524],
[0.6198, 0.4114, 0.8263, 0.3283, 0.3550, 0.3583, 0.5813, 0.5667],
[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334],
[0.6260, 0.4133, 0.8800, 0.5117, 0.3713, 0.3283, 0.6223, 0.4967],
[0.6329, 0.4175, 0.8550, 0.2333, 0.5425, 0.2250, 0.7398, 0.5609]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6216, 0.4100, 0.8862, 0.5867, 0.4946, 0.4252, 0.5894, 0.5776],
[0.5798, 0.3730, 0.8235, 0.2799, 0.3553, 0.3580, 0.5904, 0.5176],
[0.5872, 0.3870, 0.6935, 0.2447, 0.4144, 0.2064, 0.5287, 0.5627],
[0.5558, 0.3519, 0.9112, 0.5062, 0.3737, 0.4437, 0.5028, 0.5373],
[0.5895, 0.3918, 0.8638, 0.3317, 0.3426, 0.3596, 0.5723, 0.5447],
[0.5498, 0.3511, 0.7831, 0.2351, 0.3763, 0.3139, 0.6081, 0.5010],
[0.5845, 0.3780, 0.9155, 0.5267, 0.3823, 0.3203, 0.6370, 0.4975],
[0.5984, 0.3738, 0.8927, 0.2421, 0.5714, 0.2009, 0.7444, 0.5272]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6239, 0.4174, 0.8425, 0.5733, 0.4825, 0.4500, 0.5625, 0.5933],
[0.6175, 0.4091, 0.7862, 0.2800, 0.3638, 0.3583, 0.6187, 0.5433],
[0.6147, 0.4026, 0.6600, 0.2467, 0.4087, 0.2150, 0.5489, 0.5773],
[0.6146, 0.4124, 0.8800, 0.4867, 0.3800, 0.4500, 0.5106, 0.5524],
[0.6198, 0.4114, 0.8263, 0.3283, 0.3550, 0.3583, 0.5813, 0.5667],
[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334],
[0.6260, 0.4133, 0.8800, 0.5117, 0.3713, 0.3283, 0.6223, 0.4967],
[0.6329, 0.4175, 0.8550, 0.2333, 0.5425, 0.2250, 0.7398, 0.5609]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03452799213118851
step: 53
running loss: 0.0006514715496450663
Train Steps: 53/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6260, 0.4161, 0.9000, 0.3833, 0.4450, 0.2133, 0.6237, 0.4986],
[0.6092, 0.4001, 0.8638, 0.4867, 0.4288, 0.5367, 0.5484, 0.5064],
[0.6082, 0.4024, 0.8738, 0.4017, 0.3688, 0.3950, 0.5306, 0.5136],
[0.6154, 0.4112, 0.7037, 0.2317, 0.4238, 0.1833, 0.5350, 0.5600],
[0.6107, 0.4050, 0.8700, 0.4850, 0.4470, 0.4848, 0.5043, 0.5431],
[0.6218, 0.4098, 0.7238, 0.1850, 0.4238, 0.2517, 0.6288, 0.5350],
[0.6276, 0.4002, 0.8800, 0.5533, 0.3575, 0.4400, 0.6132, 0.4672],
[0.6137, 0.4035, 0.8850, 0.4417, 0.3900, 0.4283, 0.5449, 0.5617]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5949, 0.3693, 0.9166, 0.3965, 0.4438, 0.2190, 0.6329, 0.4888],
[0.5678, 0.3612, 0.8888, 0.4901, 0.4240, 0.5450, 0.5531, 0.5003],
[0.5673, 0.3601, 0.8953, 0.4152, 0.3538, 0.3924, 0.5423, 0.4920],
[0.6909, 0.4426, 0.7072, 0.2401, 0.4204, 0.1919, 0.5422, 0.5530],
[0.5453, 0.3431, 0.8851, 0.4871, 0.4364, 0.5039, 0.5110, 0.5051],
[0.6636, 0.4255, 0.7338, 0.2045, 0.4271, 0.2490, 0.6436, 0.5372],
[0.5560, 0.3329, 0.8886, 0.5402, 0.3658, 0.4380, 0.6252, 0.4615],
[0.6067, 0.3854, 0.8926, 0.4606, 0.3783, 0.4371, 0.5586, 0.5382]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6260, 0.4161, 0.9000, 0.3833, 0.4450, 0.2133, 0.6237, 0.4986],
[0.6092, 0.4001, 0.8637, 0.4867, 0.4288, 0.5367, 0.5484, 0.5064],
[0.6082, 0.4024, 0.8737, 0.4017, 0.3688, 0.3950, 0.5306, 0.5136],
[0.6154, 0.4112, 0.7038, 0.2317, 0.4238, 0.1833, 0.5350, 0.5600],
[0.6107, 0.4050, 0.8700, 0.4850, 0.4470, 0.4848, 0.5043, 0.5431],
[0.6218, 0.4098, 0.7237, 0.1850, 0.4238, 0.2517, 0.6288, 0.5350],
[0.6276, 0.4002, 0.8800, 0.5533, 0.3575, 0.4400, 0.6132, 0.4672],
[0.6137, 0.4035, 0.8850, 0.4417, 0.3900, 0.4283, 0.5449, 0.5617]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.035225964384153485
step: 54
running loss: 0.0006523326737806201
Train Steps: 54/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6150, 0.3935, 0.8696, 0.5158, 0.4647, 0.5329, 0.6041, 0.5153],
[0.6059, 0.4002, 0.7562, 0.2767, 0.3538, 0.3033, 0.5529, 0.5455],
[0.6173, 0.4114, 0.7325, 0.2500, 0.4213, 0.1917, 0.5338, 0.5700],
[0.6026, 0.3979, 0.8550, 0.4233, 0.3613, 0.5233, 0.5582, 0.4967],
[0.6196, 0.4090, 0.8450, 0.3900, 0.3575, 0.3933, 0.5975, 0.5583],
[0.6058, 0.3986, 0.8324, 0.4626, 0.3838, 0.4983, 0.5147, 0.5466],
[0.6266, 0.4067, 0.8588, 0.2867, 0.4300, 0.2850, 0.6325, 0.5267],
[0.6236, 0.3977, 0.8985, 0.4806, 0.3835, 0.5216, 0.6613, 0.5166]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5942, 0.3785, 0.8978, 0.5211, 0.4668, 0.5194, 0.6236, 0.4956],
[0.5834, 0.3925, 0.7657, 0.2807, 0.3593, 0.2938, 0.5746, 0.5117],
[0.6970, 0.4616, 0.7445, 0.2467, 0.4266, 0.1788, 0.5442, 0.5388],
[0.5240, 0.3442, 0.8705, 0.4321, 0.3640, 0.5122, 0.5731, 0.4977],
[0.5492, 0.3548, 0.8602, 0.3845, 0.3575, 0.3699, 0.6041, 0.5329],
[0.5581, 0.3591, 0.8418, 0.4721, 0.3978, 0.4798, 0.5361, 0.5162],
[0.6528, 0.4251, 0.8704, 0.2919, 0.4347, 0.2784, 0.6402, 0.5054],
[0.6352, 0.3991, 0.9248, 0.4779, 0.3932, 0.5056, 0.6813, 0.4867]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6150, 0.3935, 0.8696, 0.5158, 0.4647, 0.5329, 0.6041, 0.5153],
[0.6059, 0.4002, 0.7563, 0.2767, 0.3537, 0.3033, 0.5529, 0.5455],
[0.6173, 0.4114, 0.7325, 0.2500, 0.4212, 0.1917, 0.5337, 0.5700],
[0.6026, 0.3979, 0.8550, 0.4233, 0.3613, 0.5233, 0.5582, 0.4967],
[0.6196, 0.4090, 0.8450, 0.3900, 0.3575, 0.3933, 0.5975, 0.5583],
[0.6058, 0.3986, 0.8324, 0.4626, 0.3837, 0.4983, 0.5147, 0.5466],
[0.6266, 0.4067, 0.8587, 0.2867, 0.4300, 0.2850, 0.6325, 0.5267],
[0.6236, 0.3977, 0.8985, 0.4806, 0.3835, 0.5216, 0.6613, 0.5166]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03592075948836282
step: 55
running loss: 0.0006531047179702331
Train Steps: 55/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6250, 0.4106, 0.8700, 0.3717, 0.3588, 0.4967, 0.6038, 0.5167],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098],
[0.6125, 0.3983, 0.8750, 0.4867, 0.4275, 0.4783, 0.5413, 0.5717],
[0.6147, 0.4026, 0.6600, 0.2467, 0.4088, 0.2150, 0.5489, 0.5773],
[0.6277, 0.4036, 0.8688, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742],
[0.6189, 0.4049, 0.8888, 0.4417, 0.4213, 0.5200, 0.5988, 0.5633],
[0.6292, 0.4010, 0.8988, 0.4800, 0.3638, 0.3817, 0.6357, 0.5051],
[0.6286, 0.4097, 0.8107, 0.2414, 0.4425, 0.2483, 0.6745, 0.5385]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6009, 0.3886, 0.8640, 0.3660, 0.3473, 0.4980, 0.6004, 0.5025],
[0.6008, 0.3929, 0.8754, 0.4582, 0.3570, 0.5216, 0.5903, 0.4871],
[0.6102, 0.4029, 0.8723, 0.4841, 0.4216, 0.4752, 0.5486, 0.5360],
[0.6062, 0.4069, 0.6612, 0.2374, 0.3979, 0.2247, 0.5234, 0.5572],
[0.5861, 0.3793, 0.8570, 0.3509, 0.3809, 0.2627, 0.6151, 0.4455],
[0.6013, 0.3983, 0.8778, 0.4348, 0.4101, 0.5217, 0.5876, 0.5433],
[0.6018, 0.3773, 0.8865, 0.4585, 0.3473, 0.3775, 0.6076, 0.4694],
[0.6657, 0.4308, 0.8050, 0.2541, 0.4369, 0.2434, 0.6707, 0.5185]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6250, 0.4105, 0.8700, 0.3717, 0.3587, 0.4967, 0.6037, 0.5167],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098],
[0.6125, 0.3983, 0.8750, 0.4867, 0.4275, 0.4783, 0.5412, 0.5717],
[0.6147, 0.4026, 0.6600, 0.2467, 0.4087, 0.2150, 0.5489, 0.5773],
[0.6277, 0.4036, 0.8687, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742],
[0.6189, 0.4049, 0.8888, 0.4417, 0.4212, 0.5200, 0.5987, 0.5633],
[0.6292, 0.4010, 0.8988, 0.4800, 0.3638, 0.3817, 0.6357, 0.5051],
[0.6286, 0.4097, 0.8107, 0.2414, 0.4425, 0.2483, 0.6745, 0.5385]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03618784763966687
step: 56
running loss: 0.0006462115649940513
Train Steps: 56/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.6935, 0.1930, 0.4150, 0.2250, 0.5450, 0.5650],
[0.6175, 0.3957, 0.8700, 0.4817, 0.4662, 0.5133, 0.5800, 0.5517],
[0.6275, 0.4157, 0.8337, 0.5800, 0.3763, 0.4200, 0.5547, 0.6125],
[0.6277, 0.4029, 0.8250, 0.2433, 0.4325, 0.2100, 0.6366, 0.5207],
[0.6125, 0.3983, 0.8750, 0.4867, 0.4275, 0.4783, 0.5413, 0.5717],
[0.6200, 0.3999, 0.8653, 0.5207, 0.4100, 0.5125, 0.5975, 0.5103],
[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395],
[0.6214, 0.4112, 0.7838, 0.2117, 0.3650, 0.3133, 0.5675, 0.5083]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.1162, 0.0801, 0.6802, 0.1951, 0.4182, 0.2635, 0.5322, 0.5675],
[0.6565, 0.4317, 0.8646, 0.4593, 0.4474, 0.4991, 0.5942, 0.5406],
[0.6423, 0.4291, 0.8379, 0.5595, 0.3659, 0.4292, 0.5599, 0.6017],
[0.6656, 0.4248, 0.8112, 0.2486, 0.4119, 0.2329, 0.6516, 0.5067],
[0.6346, 0.4177, 0.8700, 0.4794, 0.4136, 0.4643, 0.5676, 0.5569],
[0.6783, 0.4386, 0.8775, 0.5302, 0.3981, 0.5214, 0.5827, 0.4985],
[0.6109, 0.3950, 0.8578, 0.5303, 0.3491, 0.3746, 0.5703, 0.5402],
[0.6370, 0.4200, 0.7620, 0.1908, 0.3480, 0.3000, 0.5853, 0.4956]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.6935, 0.1930, 0.4150, 0.2250, 0.5450, 0.5650],
[0.6175, 0.3957, 0.8700, 0.4817, 0.4663, 0.5133, 0.5800, 0.5517],
[0.6275, 0.4157, 0.8338, 0.5800, 0.3762, 0.4200, 0.5547, 0.6125],
[0.6277, 0.4029, 0.8250, 0.2433, 0.4325, 0.2100, 0.6366, 0.5207],
[0.6125, 0.3983, 0.8750, 0.4867, 0.4275, 0.4783, 0.5412, 0.5717],
[0.6200, 0.3999, 0.8653, 0.5207, 0.4100, 0.5125, 0.5975, 0.5103],
[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395],
[0.6214, 0.4112, 0.7837, 0.2117, 0.3650, 0.3133, 0.5675, 0.5083]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.036844901071162894
step: 57
running loss: 0.0006464017731782964
Train Steps: 57/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6201, 0.4064, 0.8688, 0.5050, 0.4225, 0.5100, 0.6138, 0.5500],
[ nan, nan, 0.8850, 0.2817, 0.5112, 0.2183, 0.7184, 0.5436],
[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586],
[0.6271, 0.4020, 0.8375, 0.6083, 0.3925, 0.4867, 0.6037, 0.4626],
[0.6114, 0.4018, 0.7213, 0.1967, 0.3763, 0.2700, 0.5875, 0.5533],
[0.6271, 0.4040, 0.9000, 0.3250, 0.4938, 0.2300, 0.7192, 0.5413],
[0.6132, 0.4118, 0.8200, 0.3633, 0.3563, 0.5400, 0.5787, 0.5136],
[0.6275, 0.4013, 0.8850, 0.2833, 0.4975, 0.2233, 0.7058, 0.5343]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6270, 0.4258, 0.8462, 0.4879, 0.3983, 0.5099, 0.5488, 0.5659],
[0.1573, 0.1195, 0.8400, 0.2562, 0.4836, 0.2424, 0.6582, 0.5480],
[0.6321, 0.4317, 0.7994, 0.2551, 0.4191, 0.2894, 0.6537, 0.5727],
[0.6228, 0.4126, 0.8361, 0.6025, 0.3768, 0.4785, 0.5576, 0.4819],
[0.5831, 0.3975, 0.6814, 0.1729, 0.3564, 0.2846, 0.5472, 0.5592],
[0.6615, 0.4358, 0.8663, 0.3155, 0.4706, 0.2533, 0.6759, 0.5524],
[0.5915, 0.4250, 0.7890, 0.3555, 0.3250, 0.5123, 0.5517, 0.5376],
[0.6395, 0.4154, 0.8463, 0.2810, 0.4706, 0.2473, 0.6771, 0.5393]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6201, 0.4064, 0.8687, 0.5050, 0.4225, 0.5100, 0.6137, 0.5500],
[0.0000, 0.0000, 0.8850, 0.2817, 0.5113, 0.2183, 0.7184, 0.5436],
[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586],
[0.6271, 0.4020, 0.8375, 0.6083, 0.3925, 0.4867, 0.6037, 0.4626],
[0.6114, 0.4018, 0.7212, 0.1967, 0.3762, 0.2700, 0.5875, 0.5533],
[0.6271, 0.4040, 0.9000, 0.3250, 0.4938, 0.2300, 0.7192, 0.5413],
[0.6132, 0.4118, 0.8200, 0.3633, 0.3562, 0.5400, 0.5787, 0.5136],
[0.6275, 0.4013, 0.8850, 0.2833, 0.4975, 0.2233, 0.7058, 0.5343]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0013, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.038141772645758465
step: 58
running loss: 0.0006576167697544563
Train Steps: 58/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6111, 0.4033, 0.8300, 0.3267, 0.3588, 0.3333, 0.5444, 0.5637],
[0.6227, 0.4193, 0.8838, 0.4933, 0.3663, 0.3733, 0.5637, 0.5633],
[0.6200, 0.4049, 0.8638, 0.5617, 0.4125, 0.5100, 0.6013, 0.5317],
[0.6277, 0.4057, 0.8300, 0.2650, 0.4363, 0.1850, 0.6140, 0.4823],
[0.6201, 0.4102, 0.7288, 0.2417, 0.4150, 0.2383, 0.6100, 0.5500],
[0.6271, 0.4005, 0.8450, 0.6067, 0.3850, 0.4983, 0.6069, 0.4649],
[0.6186, 0.3967, 0.7337, 0.1992, 0.4120, 0.2508, 0.6105, 0.5395],
[0.6087, 0.3976, 0.8337, 0.3867, 0.3713, 0.3117, 0.5938, 0.5300]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5434, 0.3604, 0.8125, 0.3093, 0.3506, 0.3417, 0.5186, 0.5918],
[0.6032, 0.4228, 0.8550, 0.4658, 0.3610, 0.3783, 0.5531, 0.5995],
[0.6350, 0.4280, 0.8495, 0.5566, 0.4133, 0.5111, 0.6015, 0.5680],
[0.6236, 0.4199, 0.8116, 0.2509, 0.4350, 0.2018, 0.6264, 0.5068],
[0.5966, 0.3983, 0.7309, 0.2129, 0.3987, 0.2585, 0.5930, 0.5883],
[0.6126, 0.3992, 0.8214, 0.5925, 0.3858, 0.5042, 0.5894, 0.5219],
[0.5975, 0.3883, 0.7192, 0.2058, 0.3947, 0.2623, 0.5913, 0.5678],
[0.6132, 0.4144, 0.8182, 0.3650, 0.3688, 0.3395, 0.5849, 0.5806]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6111, 0.4033, 0.8300, 0.3267, 0.3587, 0.3333, 0.5444, 0.5637],
[0.6227, 0.4193, 0.8838, 0.4933, 0.3663, 0.3733, 0.5638, 0.5633],
[0.6199, 0.4049, 0.8637, 0.5617, 0.4125, 0.5100, 0.6012, 0.5317],
[0.6277, 0.4056, 0.8300, 0.2650, 0.4363, 0.1850, 0.6140, 0.4823],
[0.6201, 0.4102, 0.7287, 0.2417, 0.4150, 0.2383, 0.6100, 0.5500],
[0.6271, 0.4005, 0.8450, 0.6067, 0.3850, 0.4983, 0.6069, 0.4649],
[0.6186, 0.3967, 0.7337, 0.1992, 0.4120, 0.2508, 0.6105, 0.5395],
[0.6087, 0.3976, 0.8338, 0.3867, 0.3713, 0.3117, 0.5938, 0.5300]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0386340361146722
step: 59
running loss: 0.000654814171435122
Train Steps: 59/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6245, 0.4100, 0.7762, 0.2583, 0.4963, 0.1517, 0.5875, 0.5417],
[0.6236, 0.4084, 0.7738, 0.2133, 0.3663, 0.3233, 0.5813, 0.5567],
[0.6197, 0.4050, 0.7527, 0.2000, 0.4042, 0.2249, 0.5895, 0.4995],
[0.6200, 0.4055, 0.8011, 0.2988, 0.3842, 0.2798, 0.5949, 0.5183],
[0.6293, 0.4024, 0.8750, 0.5000, 0.4012, 0.5733, 0.7121, 0.5633],
[0.6142, 0.4127, 0.7575, 0.3067, 0.3438, 0.4383, 0.5778, 0.5207],
[0.6131, 0.4037, 0.6907, 0.2819, 0.3688, 0.2700, 0.5217, 0.5680],
[0.6286, 0.4034, 0.8191, 0.2414, 0.4262, 0.2393, 0.6365, 0.5356]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6260, 0.4173, 0.7693, 0.2477, 0.4896, 0.1354, 0.5837, 0.5601],
[0.5821, 0.3951, 0.7618, 0.2472, 0.3904, 0.3180, 0.5785, 0.5780],
[0.5168, 0.3570, 0.7499, 0.2007, 0.4158, 0.2174, 0.6111, 0.5105],
[0.6055, 0.4041, 0.8060, 0.3109, 0.3993, 0.2829, 0.6012, 0.5408],
[0.6270, 0.4130, 0.8786, 0.5441, 0.4146, 0.5860, 0.7014, 0.5775],
[0.5542, 0.3892, 0.7627, 0.2894, 0.3791, 0.4210, 0.5780, 0.5523],
[0.5910, 0.3917, 0.6935, 0.2902, 0.3789, 0.2751, 0.5223, 0.5864],
[0.6000, 0.3858, 0.8019, 0.2483, 0.4373, 0.2467, 0.6337, 0.5463]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6245, 0.4100, 0.7763, 0.2583, 0.4963, 0.1517, 0.5875, 0.5417],
[0.6236, 0.4084, 0.7738, 0.2133, 0.3663, 0.3233, 0.5813, 0.5567],
[0.6197, 0.4050, 0.7527, 0.2000, 0.4042, 0.2249, 0.5895, 0.4995],
[0.6201, 0.4055, 0.8011, 0.2988, 0.3842, 0.2798, 0.5949, 0.5183],
[0.6293, 0.4024, 0.8750, 0.5000, 0.4013, 0.5733, 0.7121, 0.5633],
[0.6142, 0.4127, 0.7575, 0.3067, 0.3438, 0.4383, 0.5778, 0.5207],
[0.6131, 0.4036, 0.6907, 0.2819, 0.3688, 0.2700, 0.5217, 0.5680],
[0.6286, 0.4034, 0.8191, 0.2414, 0.4262, 0.2393, 0.6365, 0.5356]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03914449064177461
step: 60
running loss: 0.0006524081773629102
Train Steps: 60/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6213, 0.4001, 0.7712, 0.2117, 0.4338, 0.1800, 0.5850, 0.5183],
[0.6109, 0.4041, 0.6975, 0.3167, 0.3513, 0.3383, 0.5153, 0.5319],
[0.6126, 0.4039, 0.8237, 0.3967, 0.3625, 0.3600, 0.5894, 0.6138],
[0.6332, 0.4165, 0.9100, 0.3350, 0.4188, 0.3683, 0.7438, 0.5528],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5413, 0.5683],
[0.6201, 0.4050, 0.7757, 0.2234, 0.4459, 0.1798, 0.5975, 0.5426],
[0.6260, 0.4161, 0.9000, 0.3833, 0.4450, 0.2133, 0.6237, 0.4986],
[0.6264, 0.4067, 0.9050, 0.4183, 0.3775, 0.4600, 0.6308, 0.4862]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6002, 0.3741, 0.7528, 0.2012, 0.4403, 0.1921, 0.5857, 0.5105],
[0.5763, 0.3811, 0.7150, 0.3156, 0.3673, 0.3497, 0.5242, 0.5349],
[0.6692, 0.4403, 0.8189, 0.4075, 0.3779, 0.3896, 0.6108, 0.6077],
[0.5852, 0.3847, 0.8953, 0.3522, 0.4302, 0.3928, 0.7393, 0.5533],
[0.5822, 0.3798, 0.8676, 0.5529, 0.3981, 0.3941, 0.5389, 0.5724],
[0.5916, 0.3839, 0.7662, 0.2230, 0.4605, 0.1916, 0.6009, 0.5561],
[0.5540, 0.3630, 0.8852, 0.3655, 0.4472, 0.2216, 0.6218, 0.5047],
[0.6438, 0.4159, 0.8962, 0.4108, 0.3776, 0.4650, 0.6316, 0.4925]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6213, 0.4001, 0.7713, 0.2117, 0.4338, 0.1800, 0.5850, 0.5183],
[0.6109, 0.4041, 0.6975, 0.3167, 0.3512, 0.3383, 0.5153, 0.5319],
[0.6126, 0.4038, 0.8238, 0.3967, 0.3625, 0.3600, 0.5894, 0.6138],
[0.6332, 0.4165, 0.9100, 0.3350, 0.4187, 0.3683, 0.7438, 0.5528],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5412, 0.5683],
[0.6201, 0.4050, 0.7757, 0.2234, 0.4459, 0.1798, 0.5975, 0.5426],
[0.6260, 0.4161, 0.9000, 0.3833, 0.4450, 0.2133, 0.6237, 0.4986],
[0.6264, 0.4067, 0.9050, 0.4183, 0.3775, 0.4600, 0.6308, 0.4862]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.039610637846635655
step: 61
running loss: 0.0006493547187973058
Train Steps: 61/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6364, 0.4144, 0.8625, 0.3083, 0.4913, 0.2000, 0.6448, 0.5274],
[0.6102, 0.4005, 0.8688, 0.5100, 0.4813, 0.5400, 0.5404, 0.5064],
[0.6257, 0.4060, 0.8300, 0.2333, 0.4688, 0.2583, 0.7050, 0.5633],
[0.6161, 0.4076, 0.8900, 0.4667, 0.4125, 0.5917, 0.6262, 0.5367],
[0.6332, 0.4118, 0.9238, 0.4267, 0.4012, 0.4733, 0.7525, 0.5436],
[0.6162, 0.3949, 0.8838, 0.4517, 0.4250, 0.5183, 0.5837, 0.5500],
[0.6196, 0.4090, 0.8450, 0.3900, 0.3575, 0.3933, 0.5975, 0.5583],
[0.6261, 0.4131, 0.8938, 0.3550, 0.4000, 0.2683, 0.6188, 0.5283]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6490, 0.4308, 0.8600, 0.3135, 0.4776, 0.1786, 0.6367, 0.5065],
[0.5685, 0.3786, 0.8593, 0.4983, 0.4870, 0.5088, 0.5418, 0.4965],
[0.5677, 0.3706, 0.8188, 0.2409, 0.4533, 0.2450, 0.7117, 0.5441],
[0.6425, 0.4133, 0.8852, 0.4869, 0.4178, 0.5740, 0.6153, 0.5150],
[0.6038, 0.3772, 0.9128, 0.4450, 0.4081, 0.4684, 0.7507, 0.5351],
[0.6241, 0.3928, 0.8778, 0.4593, 0.4418, 0.5083, 0.5830, 0.5158],
[0.6153, 0.3958, 0.8522, 0.3992, 0.3652, 0.3736, 0.5988, 0.5468],
[0.5823, 0.3788, 0.8807, 0.3593, 0.3960, 0.2584, 0.6143, 0.5197]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6364, 0.4144, 0.8625, 0.3083, 0.4913, 0.2000, 0.6448, 0.5274],
[0.6102, 0.4005, 0.8687, 0.5100, 0.4812, 0.5400, 0.5404, 0.5064],
[0.6257, 0.4060, 0.8300, 0.2333, 0.4688, 0.2583, 0.7050, 0.5633],
[0.6161, 0.4076, 0.8900, 0.4667, 0.4125, 0.5917, 0.6263, 0.5367],
[0.6332, 0.4118, 0.9237, 0.4267, 0.4013, 0.4733, 0.7525, 0.5436],
[0.6162, 0.3949, 0.8838, 0.4517, 0.4250, 0.5183, 0.5838, 0.5500],
[0.6196, 0.4090, 0.8450, 0.3900, 0.3575, 0.3933, 0.5975, 0.5583],
[0.6261, 0.4131, 0.8938, 0.3550, 0.4000, 0.2683, 0.6187, 0.5283]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.039949122903635725
step: 62
running loss: 0.0006443406919941246
Train Steps: 62/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6357, 0.4139, 0.8450, 0.5883, 0.3775, 0.4950, 0.6488, 0.5297],
[0.6250, 0.4110, 0.7238, 0.2067, 0.4263, 0.1883, 0.5625, 0.5633],
[0.6186, 0.4013, 0.8191, 0.3188, 0.4279, 0.2060, 0.5767, 0.5411],
[0.6125, 0.3983, 0.8750, 0.4867, 0.4275, 0.4783, 0.5413, 0.5717],
[0.6192, 0.3980, 0.7078, 0.2750, 0.4250, 0.2100, 0.5450, 0.5783],
[0.6273, 0.4110, 0.8900, 0.3817, 0.4188, 0.2167, 0.5858, 0.4835],
[0.6201, 0.4065, 0.7300, 0.1933, 0.4075, 0.2533, 0.6162, 0.5483],
[0.6325, 0.4066, 0.8438, 0.5350, 0.3925, 0.5267, 0.7113, 0.5795]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6489, 0.4172, 0.8604, 0.5817, 0.3890, 0.5051, 0.6722, 0.5223],
[0.5758, 0.3802, 0.7537, 0.2132, 0.4380, 0.1834, 0.5846, 0.5585],
[0.6042, 0.4036, 0.8379, 0.2920, 0.4279, 0.2024, 0.5808, 0.5277],
[0.6568, 0.4249, 0.9017, 0.5003, 0.4414, 0.4782, 0.5668, 0.5598],
[0.3651, 0.2423, 0.7194, 0.2475, 0.4385, 0.2289, 0.5711, 0.5761],
[0.6485, 0.4133, 0.9225, 0.3724, 0.4294, 0.2090, 0.6064, 0.4847],
[0.5770, 0.3819, 0.7592, 0.1862, 0.4164, 0.2548, 0.6278, 0.5392],
[0.6558, 0.4108, 0.8697, 0.5434, 0.4043, 0.5355, 0.7380, 0.5651]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6357, 0.4139, 0.8450, 0.5883, 0.3775, 0.4950, 0.6488, 0.5297],
[0.6250, 0.4110, 0.7237, 0.2067, 0.4263, 0.1883, 0.5625, 0.5633],
[0.6186, 0.4013, 0.8191, 0.3188, 0.4279, 0.2060, 0.5767, 0.5411],
[0.6125, 0.3983, 0.8750, 0.4867, 0.4275, 0.4783, 0.5412, 0.5717],
[0.6192, 0.3980, 0.7078, 0.2750, 0.4250, 0.2100, 0.5450, 0.5783],
[0.6273, 0.4110, 0.8900, 0.3817, 0.4187, 0.2167, 0.5858, 0.4835],
[0.6201, 0.4065, 0.7300, 0.1933, 0.4075, 0.2533, 0.6162, 0.5483],
[0.6325, 0.4066, 0.8438, 0.5350, 0.3925, 0.5267, 0.7113, 0.5795]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04169243582873605
step: 63
running loss: 0.000661784695694223
Train Steps: 63/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6317, 0.4038, 0.8287, 0.5900, 0.3800, 0.4717, 0.6295, 0.4986],
[0.6223, 0.4130, 0.8100, 0.2983, 0.3525, 0.3900, 0.5694, 0.5103],
[0.6226, 0.4098, 0.8912, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367],
[0.6250, 0.4116, 0.8700, 0.4850, 0.4650, 0.5567, 0.6088, 0.5183],
[0.6240, 0.4217, 0.8150, 0.3133, 0.4425, 0.2650, 0.5650, 0.5817],
[0.6132, 0.4118, 0.8200, 0.3633, 0.3563, 0.5400, 0.5787, 0.5136],
[0.6307, 0.4029, 0.8988, 0.4817, 0.3937, 0.3500, 0.7311, 0.5378],
[0.6113, 0.4104, 0.8650, 0.4250, 0.3925, 0.5967, 0.5787, 0.5116]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6751, 0.4236, 0.8554, 0.5983, 0.3808, 0.4436, 0.6582, 0.5019],
[0.6391, 0.4155, 0.8110, 0.3076, 0.3625, 0.3694, 0.5915, 0.5181],
[0.6277, 0.4008, 0.9097, 0.3904, 0.4020, 0.2135, 0.5999, 0.5297],
[0.6436, 0.3957, 0.8956, 0.4783, 0.4681, 0.5160, 0.6527, 0.5159],
[0.5659, 0.3881, 0.8140, 0.3132, 0.4450, 0.2331, 0.6016, 0.5673],
[0.6419, 0.4246, 0.8367, 0.3678, 0.3640, 0.4855, 0.6123, 0.5136],
[0.6364, 0.4119, 0.9123, 0.4822, 0.4031, 0.3257, 0.7460, 0.5331],
[0.6155, 0.3943, 0.8747, 0.4187, 0.4091, 0.5571, 0.5951, 0.5081]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6317, 0.4038, 0.8288, 0.5900, 0.3800, 0.4717, 0.6295, 0.4986],
[0.6223, 0.4130, 0.8100, 0.2983, 0.3525, 0.3900, 0.5694, 0.5103],
[0.6226, 0.4098, 0.8913, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367],
[0.6251, 0.4116, 0.8700, 0.4850, 0.4650, 0.5567, 0.6087, 0.5183],
[0.6240, 0.4217, 0.8150, 0.3133, 0.4425, 0.2650, 0.5650, 0.5817],
[0.6132, 0.4118, 0.8200, 0.3633, 0.3562, 0.5400, 0.5787, 0.5136],
[0.6307, 0.4029, 0.8988, 0.4817, 0.3938, 0.3500, 0.7311, 0.5378],
[0.6113, 0.4104, 0.8650, 0.4250, 0.3925, 0.5967, 0.5787, 0.5116]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04215108629432507
step: 64
running loss: 0.0006586107233488292
Train Steps: 64/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6201, 0.4029, 0.8776, 0.4602, 0.3683, 0.4203, 0.5938, 0.5450],
[0.6164, 0.3956, 0.8757, 0.5088, 0.4300, 0.5320, 0.6022, 0.5202],
[0.6189, 0.3911, 0.8800, 0.4917, 0.3713, 0.4800, 0.6038, 0.4833],
[0.6273, 0.4105, 0.8988, 0.4517, 0.3912, 0.2550, 0.5894, 0.4811],
[ nan, nan, 0.7525, 0.2291, 0.3838, 0.3017, 0.6050, 0.5667],
[0.6199, 0.4060, 0.8888, 0.4667, 0.3800, 0.5050, 0.6188, 0.5433],
[0.6300, 0.4102, 0.9088, 0.4433, 0.4088, 0.3067, 0.6820, 0.5540],
[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6841, 0.4391, 0.8785, 0.4640, 0.3834, 0.4200, 0.5930, 0.5421],
[0.6607, 0.4358, 0.8822, 0.5192, 0.4290, 0.5394, 0.6074, 0.5179],
[0.6769, 0.4259, 0.8845, 0.5061, 0.3831, 0.4829, 0.6011, 0.4728],
[0.6597, 0.4213, 0.9095, 0.4465, 0.4110, 0.2541, 0.5965, 0.4808],
[0.0435, 0.0366, 0.7480, 0.2466, 0.3787, 0.2960, 0.6180, 0.5568],
[0.7205, 0.4638, 0.9050, 0.4852, 0.3870, 0.5248, 0.6364, 0.5229],
[0.7102, 0.4620, 0.9185, 0.4474, 0.4126, 0.3109, 0.6806, 0.5438],
[0.7577, 0.4880, 0.9010, 0.5120, 0.4162, 0.5258, 0.6563, 0.4690]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6201, 0.4029, 0.8776, 0.4602, 0.3683, 0.4203, 0.5938, 0.5450],
[0.6164, 0.3956, 0.8757, 0.5088, 0.4300, 0.5320, 0.6022, 0.5202],
[0.6189, 0.3911, 0.8800, 0.4917, 0.3713, 0.4800, 0.6037, 0.4833],
[0.6273, 0.4105, 0.8988, 0.4517, 0.3913, 0.2550, 0.5894, 0.4811],
[0.0000, 0.0000, 0.7525, 0.2291, 0.3837, 0.3017, 0.6050, 0.5667],
[0.6199, 0.4060, 0.8888, 0.4667, 0.3800, 0.5050, 0.6187, 0.5433],
[0.6300, 0.4102, 0.9087, 0.4433, 0.4087, 0.3067, 0.6820, 0.5540],
[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0011, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04324785657809116
step: 65
running loss: 0.0006653516396629409
Train Steps: 65/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6286, 0.4060, 0.9188, 0.4333, 0.3675, 0.4167, 0.7034, 0.5528],
[0.6339, 0.4102, 0.9088, 0.4767, 0.3925, 0.5283, 0.7509, 0.5390],
[0.6175, 0.4013, 0.7734, 0.2783, 0.4475, 0.1786, 0.5790, 0.5351],
[0.6357, 0.4139, 0.8450, 0.5883, 0.3775, 0.4950, 0.6488, 0.5297],
[0.6197, 0.4118, 0.8688, 0.5517, 0.4037, 0.5233, 0.5875, 0.5600],
[0.6261, 0.3987, 0.8688, 0.4917, 0.4300, 0.5333, 0.7010, 0.5309],
[0.6250, 0.4131, 0.8688, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367],
[0.6229, 0.4066, 0.7612, 0.2967, 0.4250, 0.2167, 0.5925, 0.5350]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6728, 0.4450, 0.9098, 0.4187, 0.3732, 0.4188, 0.6945, 0.5405],
[0.6582, 0.4256, 0.9019, 0.4799, 0.3953, 0.5400, 0.7138, 0.5375],
[0.6464, 0.4291, 0.7980, 0.2633, 0.4291, 0.1830, 0.5571, 0.5232],
[0.6475, 0.4214, 0.8394, 0.5691, 0.3625, 0.5164, 0.6335, 0.5250],
[0.6215, 0.4021, 0.8771, 0.5360, 0.3976, 0.5311, 0.5583, 0.5489],
[0.6519, 0.4227, 0.8778, 0.4887, 0.4175, 0.5327, 0.6750, 0.5320],
[0.6482, 0.4330, 0.8629, 0.2958, 0.4095, 0.2383, 0.6013, 0.5273],
[0.6709, 0.4361, 0.7736, 0.2770, 0.4107, 0.2393, 0.5732, 0.5426]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6286, 0.4060, 0.9187, 0.4333, 0.3675, 0.4167, 0.7034, 0.5528],
[0.6339, 0.4102, 0.9087, 0.4767, 0.3925, 0.5283, 0.7509, 0.5390],
[0.6175, 0.4013, 0.7734, 0.2783, 0.4475, 0.1786, 0.5790, 0.5351],
[0.6357, 0.4139, 0.8450, 0.5883, 0.3775, 0.4950, 0.6488, 0.5297],
[0.6197, 0.4118, 0.8687, 0.5517, 0.4038, 0.5233, 0.5875, 0.5600],
[0.6261, 0.3987, 0.8687, 0.4917, 0.4300, 0.5333, 0.7010, 0.5309],
[0.6250, 0.4131, 0.8687, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367],
[0.6229, 0.4066, 0.7613, 0.2967, 0.4250, 0.2167, 0.5925, 0.5350]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.043584351253230125
step: 66
running loss: 0.0006603689583822746
Train Steps: 66/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334],
[0.6205, 0.4081, 0.8950, 0.4017, 0.3788, 0.4700, 0.5963, 0.5667],
[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383],
[0.6172, 0.4055, 0.8175, 0.2650, 0.3550, 0.3683, 0.5787, 0.5550],
[0.6129, 0.3930, 0.8769, 0.5105, 0.4146, 0.5642, 0.6000, 0.5082],
[0.6109, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117],
[0.6304, 0.4029, 0.8413, 0.5217, 0.4125, 0.5617, 0.7089, 0.5679],
[0.6228, 0.4119, 0.7938, 0.2233, 0.4674, 0.1773, 0.6188, 0.5433]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6590, 0.4183, 0.7758, 0.2653, 0.3696, 0.3135, 0.6233, 0.5215],
[0.6834, 0.4374, 0.8891, 0.4067, 0.3751, 0.4616, 0.6058, 0.5631],
[0.6540, 0.4188, 0.8939, 0.4728, 0.4269, 0.5779, 0.6053, 0.5424],
[0.6287, 0.4122, 0.8230, 0.2927, 0.3532, 0.3614, 0.5817, 0.5574],
[0.6505, 0.4088, 0.8768, 0.5240, 0.4169, 0.5441, 0.6076, 0.5048],
[0.6724, 0.4390, 0.8796, 0.4794, 0.3679, 0.4075, 0.5526, 0.5108],
[0.6069, 0.3898, 0.8456, 0.5323, 0.4040, 0.5576, 0.7046, 0.5654],
[0.7121, 0.4588, 0.8121, 0.2477, 0.4546, 0.1666, 0.6290, 0.5217]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334],
[0.6205, 0.4081, 0.8950, 0.4017, 0.3787, 0.4700, 0.5962, 0.5667],
[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383],
[0.6172, 0.4055, 0.8175, 0.2650, 0.3550, 0.3683, 0.5788, 0.5550],
[0.6129, 0.3930, 0.8769, 0.5105, 0.4146, 0.5642, 0.6000, 0.5082],
[0.6108, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117],
[0.6304, 0.4029, 0.8413, 0.5217, 0.4125, 0.5617, 0.7089, 0.5679],
[0.6228, 0.4119, 0.7937, 0.2233, 0.4674, 0.1773, 0.6187, 0.5433]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04411605268251151
step: 67
running loss: 0.0006584485475001718
Train Steps: 67/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6201, 0.4036, 0.8596, 0.3850, 0.3492, 0.3785, 0.5978, 0.5131],
[0.6271, 0.4040, 0.9000, 0.3250, 0.4938, 0.2300, 0.7192, 0.5413],
[0.6199, 0.4065, 0.7598, 0.2385, 0.4317, 0.1981, 0.5933, 0.5221],
[0.6197, 0.4050, 0.7527, 0.2000, 0.4042, 0.2249, 0.5895, 0.4995],
[0.6145, 0.4007, 0.8775, 0.4533, 0.4562, 0.5533, 0.6088, 0.5533],
[0.6146, 0.4124, 0.8800, 0.4867, 0.3800, 0.4500, 0.5106, 0.5524],
[0.6179, 0.3998, 0.8396, 0.3505, 0.3552, 0.3768, 0.6064, 0.5329],
[0.6075, 0.4007, 0.8275, 0.4917, 0.4050, 0.5100, 0.5167, 0.5280]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6283, 0.4003, 0.8561, 0.3963, 0.3301, 0.3903, 0.6070, 0.5052],
[0.6088, 0.3770, 0.9110, 0.3335, 0.4759, 0.2409, 0.7457, 0.5498],
[0.6425, 0.4072, 0.7553, 0.2335, 0.4060, 0.2231, 0.5940, 0.5234],
[0.6522, 0.4164, 0.7659, 0.1988, 0.3875, 0.2213, 0.6210, 0.5014],
[0.5815, 0.3730, 0.8650, 0.4474, 0.4370, 0.5787, 0.6060, 0.5581],
[0.6791, 0.4359, 0.8828, 0.4949, 0.3584, 0.4545, 0.5194, 0.5556],
[0.6427, 0.4100, 0.8443, 0.3498, 0.3293, 0.3790, 0.6097, 0.5322],
[0.6070, 0.3958, 0.8130, 0.4942, 0.4050, 0.5089, 0.5191, 0.5420]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6201, 0.4036, 0.8596, 0.3850, 0.3492, 0.3785, 0.5978, 0.5131],
[0.6271, 0.4040, 0.9000, 0.3250, 0.4938, 0.2300, 0.7192, 0.5413],
[0.6199, 0.4065, 0.7598, 0.2385, 0.4317, 0.1981, 0.5933, 0.5221],
[0.6197, 0.4050, 0.7527, 0.2000, 0.4042, 0.2249, 0.5895, 0.4995],
[0.6145, 0.4007, 0.8775, 0.4533, 0.4563, 0.5533, 0.6087, 0.5533],
[0.6146, 0.4124, 0.8800, 0.4867, 0.3800, 0.4500, 0.5106, 0.5524],
[0.6179, 0.3998, 0.8396, 0.3505, 0.3552, 0.3768, 0.6064, 0.5329],
[0.6075, 0.4006, 0.8275, 0.4917, 0.4050, 0.5100, 0.5167, 0.5280]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.044399865000741556
step: 68
running loss: 0.0006529391911873758
Train Steps: 68/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6250, 0.4008, 0.8950, 0.4183, 0.3550, 0.4383, 0.6361, 0.4927],
[0.6205, 0.4081, 0.8950, 0.4017, 0.3788, 0.4700, 0.5963, 0.5667],
[ nan, nan, 0.6992, 0.2791, 0.3950, 0.2383, 0.5483, 0.5819],
[0.6216, 0.4100, 0.7350, 0.2067, 0.4325, 0.2050, 0.5950, 0.5333],
[0.6193, 0.4108, 0.7425, 0.2350, 0.3887, 0.2750, 0.5900, 0.5717],
[0.6085, 0.4005, 0.8400, 0.4317, 0.3763, 0.4750, 0.5476, 0.5058],
[0.6146, 0.4124, 0.8800, 0.4867, 0.3800, 0.4500, 0.5106, 0.5524],
[0.6214, 0.4116, 0.7750, 0.2317, 0.4487, 0.1883, 0.6200, 0.5400]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6684, 0.4103, 0.8983, 0.4467, 0.3564, 0.4676, 0.6509, 0.4979],
[0.6697, 0.4285, 0.8877, 0.3976, 0.3835, 0.4953, 0.6155, 0.5776],
[0.1189, 0.0600, 0.6698, 0.2783, 0.3735, 0.2384, 0.5544, 0.5748],
[0.6611, 0.4208, 0.7464, 0.2118, 0.4308, 0.2101, 0.6222, 0.5398],
[0.6449, 0.4069, 0.7567, 0.2398, 0.3928, 0.2952, 0.5959, 0.5886],
[0.6412, 0.4086, 0.8399, 0.4462, 0.3675, 0.4937, 0.5392, 0.5161],
[0.6842, 0.4399, 0.8795, 0.5051, 0.3818, 0.4660, 0.5229, 0.5636],
[0.6966, 0.4450, 0.7876, 0.2467, 0.4578, 0.2063, 0.6285, 0.5483]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6250, 0.4008, 0.8950, 0.4183, 0.3550, 0.4383, 0.6361, 0.4927],
[0.6205, 0.4081, 0.8950, 0.4017, 0.3787, 0.4700, 0.5962, 0.5667],
[0.0000, 0.0000, 0.6992, 0.2791, 0.3950, 0.2383, 0.5483, 0.5819],
[0.6216, 0.4100, 0.7350, 0.2067, 0.4325, 0.2050, 0.5950, 0.5333],
[0.6193, 0.4108, 0.7425, 0.2350, 0.3887, 0.2750, 0.5900, 0.5717],
[0.6084, 0.4005, 0.8400, 0.4317, 0.3762, 0.4750, 0.5476, 0.5058],
[0.6146, 0.4124, 0.8800, 0.4867, 0.3800, 0.4500, 0.5106, 0.5524],
[0.6214, 0.4116, 0.7750, 0.2317, 0.4487, 0.1883, 0.6200, 0.5400]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04514229335472919
step: 69
running loss: 0.0006542361355757854
Train Steps: 69/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6176, 0.4017, 0.8788, 0.5100, 0.4075, 0.5250, 0.5913, 0.5033],
[0.6214, 0.4040, 0.8838, 0.3500, 0.3600, 0.5183, 0.6362, 0.5200],
[0.6289, 0.4019, 0.8113, 0.5467, 0.3875, 0.5017, 0.7367, 0.5332],
[0.6216, 0.4167, 0.8588, 0.5583, 0.3975, 0.5167, 0.5775, 0.5667],
[0.6168, 0.4081, 0.8438, 0.3367, 0.3500, 0.4667, 0.6212, 0.5400],
[0.6268, 0.4061, 0.8350, 0.2433, 0.4575, 0.2283, 0.6350, 0.5300],
[0.6161, 0.4024, 0.8662, 0.4683, 0.4935, 0.5364, 0.6063, 0.5567],
[0.6226, 0.4001, 0.8438, 0.5733, 0.3862, 0.4250, 0.5750, 0.5283]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5932, 0.3854, 0.8746, 0.4924, 0.4156, 0.5271, 0.5691, 0.5149],
[0.6065, 0.3985, 0.8727, 0.3528, 0.3805, 0.4974, 0.6261, 0.5165],
[0.5919, 0.3854, 0.8122, 0.5360, 0.3914, 0.4945, 0.6972, 0.5451],
[0.5852, 0.3936, 0.8503, 0.5523, 0.4109, 0.5134, 0.5696, 0.5734],
[0.5774, 0.3899, 0.8421, 0.3239, 0.3606, 0.4490, 0.6091, 0.5548],
[0.6649, 0.4226, 0.8385, 0.2488, 0.4642, 0.1997, 0.6237, 0.5406],
[0.5808, 0.3709, 0.8631, 0.4307, 0.4711, 0.4975, 0.5966, 0.5669],
[0.5930, 0.3836, 0.8309, 0.5664, 0.4003, 0.4188, 0.5687, 0.5385]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6176, 0.4017, 0.8788, 0.5100, 0.4075, 0.5250, 0.5913, 0.5033],
[0.6214, 0.4040, 0.8838, 0.3500, 0.3600, 0.5183, 0.6363, 0.5200],
[0.6289, 0.4019, 0.8112, 0.5467, 0.3875, 0.5017, 0.7367, 0.5332],
[0.6216, 0.4167, 0.8587, 0.5583, 0.3975, 0.5167, 0.5775, 0.5667],
[0.6168, 0.4081, 0.8438, 0.3367, 0.3500, 0.4667, 0.6212, 0.5400],
[0.6268, 0.4060, 0.8350, 0.2433, 0.4575, 0.2283, 0.6350, 0.5300],
[0.6161, 0.4024, 0.8662, 0.4683, 0.4935, 0.5364, 0.6062, 0.5567],
[0.6226, 0.4001, 0.8438, 0.5733, 0.3862, 0.4250, 0.5750, 0.5283]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.045491363474866375
step: 70
running loss: 0.0006498766210695197
Train Steps: 70/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6204, 0.4091, 0.8950, 0.4783, 0.3613, 0.4617, 0.6063, 0.5617],
[0.6200, 0.4055, 0.8011, 0.2988, 0.3842, 0.2798, 0.5949, 0.5183],
[0.6311, 0.4008, 0.7935, 0.5746, 0.3900, 0.5033, 0.6955, 0.5366],
[0.6098, 0.3991, 0.8638, 0.4717, 0.4263, 0.4967, 0.5212, 0.5650],
[0.6198, 0.4130, 0.8762, 0.4117, 0.3650, 0.4900, 0.5707, 0.5103],
[0.6371, 0.4092, 0.8337, 0.5850, 0.3950, 0.5117, 0.6559, 0.5262],
[0.6206, 0.4123, 0.7175, 0.2400, 0.3887, 0.2933, 0.6225, 0.5750],
[0.6224, 0.4097, 0.7438, 0.2267, 0.3850, 0.2850, 0.5988, 0.5250]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6027, 0.3895, 0.9023, 0.4631, 0.3711, 0.4540, 0.5978, 0.5551],
[0.5901, 0.3676, 0.8123, 0.2965, 0.3895, 0.2630, 0.5769, 0.5181],
[0.5757, 0.3723, 0.7930, 0.5494, 0.3922, 0.4865, 0.6760, 0.5425],
[0.5815, 0.3743, 0.8654, 0.4666, 0.4310, 0.4858, 0.5209, 0.5583],
[0.6159, 0.4109, 0.8653, 0.4103, 0.3742, 0.4880, 0.5513, 0.5205],
[0.6212, 0.4156, 0.8455, 0.5615, 0.4003, 0.5054, 0.6516, 0.5298],
[0.6269, 0.3967, 0.7233, 0.2441, 0.3980, 0.2832, 0.6001, 0.5731],
[0.5960, 0.3751, 0.7550, 0.2161, 0.4011, 0.2795, 0.5930, 0.5292]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6204, 0.4091, 0.8950, 0.4783, 0.3613, 0.4617, 0.6062, 0.5617],
[0.6201, 0.4055, 0.8011, 0.2988, 0.3842, 0.2798, 0.5949, 0.5183],
[0.6311, 0.4008, 0.7935, 0.5746, 0.3900, 0.5033, 0.6955, 0.5366],
[0.6098, 0.3991, 0.8637, 0.4717, 0.4263, 0.4967, 0.5213, 0.5650],
[0.6198, 0.4130, 0.8763, 0.4117, 0.3650, 0.4900, 0.5707, 0.5103],
[0.6371, 0.4092, 0.8338, 0.5850, 0.3950, 0.5117, 0.6559, 0.5262],
[0.6206, 0.4123, 0.7175, 0.2400, 0.3887, 0.2933, 0.6225, 0.5750],
[0.6224, 0.4097, 0.7437, 0.2267, 0.3850, 0.2850, 0.5987, 0.5250]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04574897524435073
step: 71
running loss: 0.0006443517640049399
Train Steps: 71/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6127, 0.4119, 0.8650, 0.5300, 0.4512, 0.5250, 0.5260, 0.5461],
[0.6038, 0.3946, 0.8413, 0.4883, 0.3563, 0.4550, 0.5266, 0.4693],
[0.6175, 0.3957, 0.8700, 0.4817, 0.4662, 0.5133, 0.5800, 0.5517],
[0.6243, 0.4128, 0.7762, 0.2717, 0.3825, 0.3133, 0.6212, 0.5417],
[0.6102, 0.3999, 0.8750, 0.5133, 0.3825, 0.4750, 0.5637, 0.5083],
[0.6196, 0.4094, 0.7562, 0.2817, 0.3937, 0.3183, 0.6013, 0.6183],
[0.6138, 0.4020, 0.8800, 0.4717, 0.4375, 0.4717, 0.5502, 0.5611],
[0.6261, 0.4066, 0.8325, 0.2150, 0.4763, 0.2667, 0.7002, 0.5633]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5633, 0.3836, 0.8420, 0.5337, 0.4440, 0.5154, 0.5364, 0.5381],
[0.5384, 0.3566, 0.8358, 0.4855, 0.3616, 0.4613, 0.5191, 0.4777],
[0.5452, 0.3580, 0.8498, 0.4636, 0.4535, 0.5147, 0.5744, 0.5431],
[0.5719, 0.3858, 0.7744, 0.2861, 0.3919, 0.3032, 0.6182, 0.5462],
[0.5891, 0.3935, 0.8548, 0.5052, 0.3834, 0.4553, 0.5580, 0.5031],
[0.5469, 0.3664, 0.7412, 0.2916, 0.4010, 0.3196, 0.6024, 0.6164],
[0.5542, 0.3592, 0.8591, 0.4615, 0.4228, 0.4564, 0.5400, 0.5590],
[0.5844, 0.3841, 0.8278, 0.2302, 0.4739, 0.2515, 0.7062, 0.5385]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6127, 0.4119, 0.8650, 0.5300, 0.4512, 0.5250, 0.5260, 0.5461],
[0.6038, 0.3946, 0.8413, 0.4883, 0.3562, 0.4550, 0.5266, 0.4693],
[0.6175, 0.3957, 0.8700, 0.4817, 0.4663, 0.5133, 0.5800, 0.5517],
[0.6243, 0.4128, 0.7763, 0.2717, 0.3825, 0.3133, 0.6212, 0.5417],
[0.6102, 0.3999, 0.8750, 0.5133, 0.3825, 0.4750, 0.5638, 0.5083],
[0.6196, 0.4094, 0.7563, 0.2817, 0.3938, 0.3183, 0.6012, 0.6183],
[0.6138, 0.4020, 0.8800, 0.4717, 0.4375, 0.4717, 0.5502, 0.5611],
[0.6261, 0.4066, 0.8325, 0.2150, 0.4762, 0.2667, 0.7002, 0.5633]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04638030182104558
step: 72
running loss: 0.0006441708586256331
Train Steps: 72/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6136, 0.4117, 0.8700, 0.5167, 0.4188, 0.5083, 0.5147, 0.5495],
[0.6249, 0.4138, 0.9038, 0.4517, 0.3862, 0.4917, 0.6138, 0.5333],
[0.6219, 0.4097, 0.8738, 0.3400, 0.3563, 0.4117, 0.5975, 0.5683],
[0.6154, 0.4048, 0.7100, 0.2067, 0.4338, 0.1667, 0.5413, 0.5220],
[0.6353, 0.4128, 0.8488, 0.2600, 0.5525, 0.1616, 0.6694, 0.5540],
[0.6222, 0.3937, 0.8350, 0.5617, 0.4138, 0.4600, 0.5800, 0.5233],
[0.6106, 0.4022, 0.7125, 0.2650, 0.3713, 0.2700, 0.5431, 0.5123],
[0.6196, 0.4094, 0.7562, 0.2817, 0.3937, 0.3183, 0.6013, 0.6183]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5476, 0.3818, 0.8540, 0.5142, 0.4185, 0.5273, 0.5357, 0.5329],
[0.5659, 0.3972, 0.8821, 0.4454, 0.3786, 0.5081, 0.6200, 0.5237],
[0.5426, 0.3779, 0.8634, 0.3470, 0.3503, 0.4327, 0.5906, 0.5590],
[0.5297, 0.3636, 0.7151, 0.2196, 0.4366, 0.1792, 0.5518, 0.5310],
[0.6560, 0.4389, 0.8403, 0.2511, 0.5428, 0.1872, 0.6646, 0.5584],
[0.5384, 0.3503, 0.8167, 0.5637, 0.4109, 0.4789, 0.5900, 0.5254],
[0.5101, 0.3595, 0.7190, 0.2721, 0.3746, 0.2856, 0.5514, 0.5176],
[0.5184, 0.3575, 0.7436, 0.2908, 0.4046, 0.3418, 0.6030, 0.6151]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6136, 0.4117, 0.8700, 0.5167, 0.4187, 0.5083, 0.5147, 0.5495],
[0.6249, 0.4138, 0.9038, 0.4517, 0.3862, 0.4917, 0.6137, 0.5333],
[0.6219, 0.4097, 0.8737, 0.3400, 0.3562, 0.4117, 0.5975, 0.5683],
[0.6154, 0.4048, 0.7100, 0.2067, 0.4338, 0.1667, 0.5413, 0.5220],
[0.6353, 0.4128, 0.8487, 0.2600, 0.5525, 0.1616, 0.6694, 0.5540],
[0.6222, 0.3937, 0.8350, 0.5617, 0.4137, 0.4600, 0.5800, 0.5233],
[0.6106, 0.4022, 0.7125, 0.2650, 0.3713, 0.2700, 0.5431, 0.5123],
[0.6196, 0.4094, 0.7563, 0.2817, 0.3938, 0.3183, 0.6012, 0.6183]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04742685717064887
step: 73
running loss: 0.0006496829749403955
Train Steps: 73/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6070, 0.3979, 0.8575, 0.5083, 0.4350, 0.5400, 0.5180, 0.5466],
[0.6114, 0.4018, 0.7213, 0.1967, 0.3763, 0.2700, 0.5875, 0.5533],
[0.6182, 0.3982, 0.7541, 0.2379, 0.3959, 0.2792, 0.6079, 0.5389],
[0.6175, 0.4013, 0.7734, 0.2783, 0.4475, 0.1786, 0.5790, 0.5351],
[0.6267, 0.4094, 0.8712, 0.3083, 0.4400, 0.2267, 0.6250, 0.5200],
[0.6293, 0.4024, 0.8750, 0.5000, 0.4012, 0.5733, 0.7121, 0.5633],
[0.6339, 0.4118, 0.7988, 0.5800, 0.3912, 0.4583, 0.7343, 0.5760],
[0.6249, 0.4138, 0.9038, 0.4517, 0.3862, 0.4917, 0.6138, 0.5333]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5360, 0.3843, 0.8365, 0.4999, 0.4472, 0.5498, 0.5199, 0.5358],
[0.5817, 0.4067, 0.7153, 0.1968, 0.3909, 0.2734, 0.5824, 0.5477],
[0.6057, 0.4180, 0.7590, 0.2297, 0.4045, 0.2917, 0.6042, 0.5432],
[0.5751, 0.4026, 0.7735, 0.2757, 0.4548, 0.1920, 0.5601, 0.5316],
[0.5739, 0.4009, 0.8505, 0.3059, 0.4595, 0.2439, 0.5841, 0.5173],
[0.5428, 0.3725, 0.8629, 0.4832, 0.4021, 0.5831, 0.6896, 0.5574],
[0.5653, 0.3907, 0.7998, 0.5568, 0.3800, 0.4650, 0.6964, 0.5689],
[0.5964, 0.4303, 0.8868, 0.4445, 0.3831, 0.4982, 0.6010, 0.5317]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6070, 0.3979, 0.8575, 0.5083, 0.4350, 0.5400, 0.5180, 0.5466],
[0.6114, 0.4018, 0.7212, 0.1967, 0.3762, 0.2700, 0.5875, 0.5533],
[0.6182, 0.3982, 0.7541, 0.2379, 0.3959, 0.2792, 0.6079, 0.5389],
[0.6175, 0.4013, 0.7734, 0.2783, 0.4475, 0.1786, 0.5790, 0.5351],
[0.6267, 0.4094, 0.8712, 0.3083, 0.4400, 0.2267, 0.6250, 0.5200],
[0.6293, 0.4024, 0.8750, 0.5000, 0.4013, 0.5733, 0.7121, 0.5633],
[0.6339, 0.4118, 0.7987, 0.5800, 0.3913, 0.4583, 0.7343, 0.5760],
[0.6249, 0.4138, 0.9038, 0.4517, 0.3862, 0.4917, 0.6137, 0.5333]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.047969518578611314
step: 74
running loss: 0.0006482367375488015
Train Steps: 74/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6126, 0.4067, 0.8638, 0.5383, 0.4188, 0.4850, 0.5016, 0.5392],
[0.6229, 0.4107, 0.8137, 0.2883, 0.4750, 0.1717, 0.5813, 0.5400],
[0.6150, 0.3949, 0.8800, 0.4033, 0.3825, 0.4900, 0.5875, 0.5483],
[0.6219, 0.4114, 0.8175, 0.2817, 0.3925, 0.2783, 0.5900, 0.5350],
[0.6271, 0.4024, 0.9000, 0.3517, 0.3700, 0.4517, 0.6931, 0.5285],
[0.6173, 0.4013, 0.8713, 0.4640, 0.4800, 0.5700, 0.6025, 0.5600],
[0.6268, 0.4061, 0.8350, 0.2433, 0.4575, 0.2283, 0.6350, 0.5300],
[0.6086, 0.3981, 0.8700, 0.4750, 0.4512, 0.5283, 0.5324, 0.5038]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5686, 0.4101, 0.8524, 0.5625, 0.4094, 0.4891, 0.5374, 0.5442],
[0.5875, 0.4116, 0.7930, 0.2905, 0.4642, 0.1922, 0.5773, 0.5451],
[0.5920, 0.3973, 0.8621, 0.3971, 0.3795, 0.4870, 0.6047, 0.5376],
[0.5645, 0.3967, 0.7930, 0.2855, 0.4020, 0.2773, 0.5988, 0.5453],
[0.5812, 0.3969, 0.8747, 0.3446, 0.3547, 0.4323, 0.6985, 0.5203],
[0.5914, 0.3975, 0.8695, 0.4539, 0.4608, 0.5580, 0.6136, 0.5605],
[0.5825, 0.3929, 0.8245, 0.2393, 0.4464, 0.2194, 0.6340, 0.5284],
[0.5679, 0.3847, 0.8464, 0.4783, 0.4435, 0.5161, 0.5504, 0.5069]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6126, 0.4067, 0.8637, 0.5383, 0.4187, 0.4850, 0.5016, 0.5392],
[0.6229, 0.4107, 0.8138, 0.2883, 0.4750, 0.1717, 0.5813, 0.5400],
[0.6150, 0.3949, 0.8800, 0.4033, 0.3825, 0.4900, 0.5875, 0.5483],
[0.6219, 0.4114, 0.8175, 0.2817, 0.3925, 0.2783, 0.5900, 0.5350],
[0.6271, 0.4024, 0.9000, 0.3517, 0.3700, 0.4517, 0.6931, 0.5285],
[0.6173, 0.4013, 0.8713, 0.4640, 0.4800, 0.5700, 0.6025, 0.5600],
[0.6268, 0.4060, 0.8350, 0.2433, 0.4575, 0.2283, 0.6350, 0.5300],
[0.6086, 0.3981, 0.8700, 0.4750, 0.4512, 0.5283, 0.5324, 0.5038]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04832018641172908
step: 75
running loss: 0.0006442691521563878
Train Steps: 75/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6286, 0.4060, 0.9188, 0.4333, 0.3675, 0.4167, 0.7034, 0.5528],
[0.6129, 0.3930, 0.8769, 0.5105, 0.4146, 0.5642, 0.6000, 0.5082],
[0.6250, 0.3961, 0.8672, 0.4929, 0.4199, 0.4972, 0.6312, 0.5301],
[ nan, nan, 0.8300, 0.3150, 0.3588, 0.3383, 0.5208, 0.5194],
[0.6206, 0.4001, 0.8900, 0.3933, 0.3588, 0.3567, 0.5837, 0.5083],
[0.6137, 0.4084, 0.8076, 0.3889, 0.3650, 0.3150, 0.5356, 0.5896],
[ nan, nan, 0.8525, 0.2217, 0.5413, 0.2367, 0.7367, 0.5482],
[0.6218, 0.4137, 0.7263, 0.2233, 0.4075, 0.2650, 0.6212, 0.5783]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6626, 0.4414, 0.9109, 0.4295, 0.3842, 0.4193, 0.7023, 0.5545],
[0.6793, 0.4529, 0.8732, 0.5148, 0.4264, 0.5669, 0.6052, 0.5096],
[0.6709, 0.4413, 0.8750, 0.5038, 0.4249, 0.5001, 0.6196, 0.5342],
[0.2023, 0.1378, 0.8027, 0.3239, 0.3842, 0.3492, 0.5233, 0.5351],
[0.6833, 0.4441, 0.8951, 0.4070, 0.3554, 0.3622, 0.5769, 0.4957],
[0.6971, 0.4723, 0.8174, 0.3886, 0.3557, 0.3141, 0.5261, 0.5929],
[0.1040, 0.0812, 0.8375, 0.2226, 0.5503, 0.2352, 0.7235, 0.5569],
[0.6915, 0.4451, 0.7427, 0.2376, 0.4066, 0.2849, 0.5986, 0.5743]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6286, 0.4060, 0.9187, 0.4333, 0.3675, 0.4167, 0.7034, 0.5528],
[0.6129, 0.3930, 0.8769, 0.5105, 0.4146, 0.5642, 0.6000, 0.5082],
[0.6250, 0.3961, 0.8672, 0.4929, 0.4199, 0.4972, 0.6312, 0.5301],
[0.0000, 0.0000, 0.8300, 0.3150, 0.3587, 0.3383, 0.5208, 0.5194],
[0.6206, 0.4001, 0.8900, 0.3933, 0.3587, 0.3567, 0.5838, 0.5083],
[0.6137, 0.4084, 0.8076, 0.3889, 0.3650, 0.3150, 0.5356, 0.5896],
[0.0000, 0.0000, 0.8525, 0.2217, 0.5412, 0.2367, 0.7367, 0.5482],
[0.6218, 0.4137, 0.7262, 0.2233, 0.4075, 0.2650, 0.6212, 0.5783]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0019, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05019753027590923
step: 76
running loss: 0.0006604938194198583
Train Steps: 76/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6277, 0.4036, 0.8688, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742],
[ nan, nan, 0.7525, 0.2291, 0.3838, 0.3017, 0.6050, 0.5667],
[0.6100, 0.4016, 0.8600, 0.5067, 0.4612, 0.5233, 0.5086, 0.5519],
[0.6239, 0.4107, 0.8162, 0.2763, 0.3625, 0.3600, 0.5988, 0.5700],
[0.6200, 0.4071, 0.7338, 0.1917, 0.4200, 0.2450, 0.6150, 0.5517],
[0.6272, 0.4071, 0.8738, 0.5600, 0.3675, 0.3783, 0.5926, 0.4742],
[0.6146, 0.4124, 0.8800, 0.4867, 0.3800, 0.4500, 0.5106, 0.5524],
[0.6200, 0.3993, 0.8639, 0.3687, 0.3658, 0.3139, 0.6002, 0.5374]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6749, 0.4230, 0.8694, 0.3523, 0.3925, 0.2650, 0.6397, 0.4864],
[0.0600, 0.0301, 0.7583, 0.2349, 0.3915, 0.3052, 0.6079, 0.5664],
[0.6410, 0.4068, 0.8578, 0.5020, 0.4575, 0.5220, 0.5322, 0.5538],
[0.6767, 0.4299, 0.8070, 0.2836, 0.3702, 0.3566, 0.6059, 0.5776],
[0.6658, 0.4451, 0.7451, 0.1958, 0.4262, 0.2458, 0.6349, 0.5657],
[0.6659, 0.4249, 0.8828, 0.5640, 0.3632, 0.3914, 0.6147, 0.4700],
[0.6506, 0.4232, 0.8870, 0.4793, 0.3805, 0.4489, 0.5319, 0.5572],
[0.6846, 0.4381, 0.8686, 0.3619, 0.3694, 0.3212, 0.6116, 0.5322]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6277, 0.4036, 0.8687, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742],
[0.0000, 0.0000, 0.7525, 0.2291, 0.3837, 0.3017, 0.6050, 0.5667],
[0.6100, 0.4016, 0.8600, 0.5067, 0.4613, 0.5233, 0.5086, 0.5519],
[0.6239, 0.4107, 0.8162, 0.2763, 0.3625, 0.3600, 0.5987, 0.5700],
[0.6200, 0.4071, 0.7337, 0.1917, 0.4200, 0.2450, 0.6150, 0.5517],
[0.6272, 0.4071, 0.8737, 0.5600, 0.3675, 0.3783, 0.5926, 0.4742],
[0.6146, 0.4124, 0.8800, 0.4867, 0.3800, 0.4500, 0.5106, 0.5524],
[0.6200, 0.3993, 0.8639, 0.3687, 0.3658, 0.3139, 0.6002, 0.5374]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05063753016293049
step: 77
running loss: 0.0006576302618562401
Train Steps: 77/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837],
[0.6109, 0.4003, 0.8650, 0.4883, 0.4775, 0.4867, 0.5175, 0.5683],
[0.6230, 0.4152, 0.7588, 0.2283, 0.4012, 0.2883, 0.6200, 0.5767],
[0.6192, 0.3980, 0.7078, 0.2750, 0.4250, 0.2100, 0.5450, 0.5783],
[0.6236, 0.3966, 0.8850, 0.4967, 0.3638, 0.4017, 0.5850, 0.5183],
[0.6254, 0.3993, 0.8988, 0.4767, 0.3987, 0.5517, 0.6955, 0.5285],
[0.6184, 0.4079, 0.8350, 0.3700, 0.3675, 0.2883, 0.5312, 0.5783],
[0.6274, 0.4117, 0.8100, 0.5801, 0.4000, 0.4583, 0.5582, 0.6118]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6171, 0.3931, 0.7081, 0.2966, 0.3679, 0.2957, 0.5455, 0.5772],
[0.6125, 0.3821, 0.8967, 0.4685, 0.4851, 0.4934, 0.5463, 0.5613],
[0.6223, 0.3868, 0.8138, 0.2293, 0.4097, 0.2930, 0.6357, 0.5563],
[0.6632, 0.4119, 0.7575, 0.2619, 0.4331, 0.2198, 0.5652, 0.5772],
[0.6501, 0.3907, 0.9321, 0.4798, 0.3699, 0.3962, 0.6038, 0.5200],
[0.5769, 0.3612, 0.9468, 0.4648, 0.3979, 0.5583, 0.7056, 0.5172],
[0.6279, 0.3926, 0.8856, 0.3573, 0.3740, 0.2902, 0.5336, 0.5701],
[0.5986, 0.3918, 0.8499, 0.5497, 0.4113, 0.4810, 0.5777, 0.6208]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837],
[0.6109, 0.4003, 0.8650, 0.4883, 0.4775, 0.4867, 0.5175, 0.5683],
[0.6230, 0.4152, 0.7588, 0.2283, 0.4013, 0.2883, 0.6200, 0.5767],
[0.6192, 0.3980, 0.7078, 0.2750, 0.4250, 0.2100, 0.5450, 0.5783],
[0.6236, 0.3965, 0.8850, 0.4967, 0.3638, 0.4017, 0.5850, 0.5183],
[0.6254, 0.3993, 0.8988, 0.4767, 0.3988, 0.5517, 0.6955, 0.5285],
[0.6184, 0.4079, 0.8350, 0.3700, 0.3675, 0.2883, 0.5312, 0.5783],
[0.6274, 0.4117, 0.8100, 0.5801, 0.4000, 0.4583, 0.5582, 0.6118]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.051187454839237034
step: 78
running loss: 0.0006562494210158595
Train Steps: 78/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6111, 0.4019, 0.8350, 0.3867, 0.3500, 0.4283, 0.5480, 0.5719],
[0.6145, 0.3983, 0.8700, 0.5017, 0.4400, 0.4800, 0.5375, 0.5750],
[0.6286, 0.4034, 0.8191, 0.2414, 0.4262, 0.2393, 0.6365, 0.5356],
[0.6164, 0.3972, 0.7818, 0.3381, 0.3599, 0.3387, 0.5880, 0.5153],
[0.6142, 0.3982, 0.8650, 0.4883, 0.3912, 0.4317, 0.5315, 0.5350],
[0.6304, 0.4029, 0.8413, 0.5217, 0.4125, 0.5617, 0.7089, 0.5679],
[0.6307, 0.4060, 0.8950, 0.5183, 0.3750, 0.3850, 0.6338, 0.4938],
[0.6226, 0.4125, 0.8800, 0.4900, 0.4512, 0.5600, 0.6275, 0.5517]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6750, 0.4192, 0.8474, 0.3967, 0.3528, 0.4086, 0.5324, 0.5612],
[0.6266, 0.3706, 0.8872, 0.4848, 0.4445, 0.4700, 0.5373, 0.5792],
[0.6138, 0.3691, 0.8315, 0.2530, 0.4299, 0.2373, 0.6471, 0.5371],
[0.6447, 0.3941, 0.7982, 0.3344, 0.3555, 0.3328, 0.5823, 0.5228],
[0.6479, 0.4008, 0.8742, 0.4860, 0.3814, 0.4307, 0.5192, 0.5254],
[0.6559, 0.4105, 0.8597, 0.4973, 0.4129, 0.5586, 0.7078, 0.5791],
[0.6423, 0.3960, 0.9124, 0.5206, 0.3707, 0.3737, 0.6229, 0.4838],
[0.6428, 0.3967, 0.9083, 0.4797, 0.4606, 0.5630, 0.6257, 0.5711]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6111, 0.4019, 0.8350, 0.3867, 0.3500, 0.4283, 0.5480, 0.5719],
[0.6145, 0.3983, 0.8700, 0.5017, 0.4400, 0.4800, 0.5375, 0.5750],
[0.6286, 0.4034, 0.8191, 0.2414, 0.4262, 0.2393, 0.6365, 0.5356],
[0.6164, 0.3972, 0.7818, 0.3381, 0.3599, 0.3387, 0.5880, 0.5153],
[0.6143, 0.3982, 0.8650, 0.4883, 0.3913, 0.4317, 0.5315, 0.5350],
[0.6304, 0.4029, 0.8413, 0.5217, 0.4125, 0.5617, 0.7089, 0.5679],
[0.6307, 0.4060, 0.8950, 0.5183, 0.3750, 0.3850, 0.6338, 0.4938],
[0.6226, 0.4125, 0.8800, 0.4900, 0.4512, 0.5600, 0.6275, 0.5517]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.051443345699226484
step: 79
running loss: 0.0006511815911294491
Train Steps: 79/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6175, 0.4093, 0.8800, 0.4433, 0.4075, 0.4367, 0.5128, 0.4901],
[0.6229, 0.4066, 0.8513, 0.5717, 0.4500, 0.5050, 0.6025, 0.5350],
[0.6222, 0.4072, 0.7164, 0.2166, 0.3738, 0.3167, 0.6100, 0.5533],
[0.6260, 0.4106, 0.8025, 0.2583, 0.4550, 0.1867, 0.6281, 0.4869],
[0.6197, 0.4091, 0.8800, 0.4783, 0.3538, 0.4767, 0.5950, 0.5550],
[0.6307, 0.4045, 0.8025, 0.5833, 0.3775, 0.4867, 0.6892, 0.5459],
[0.6311, 0.3998, 0.7975, 0.5767, 0.3838, 0.4850, 0.7327, 0.5343],
[0.6268, 0.4061, 0.8350, 0.2433, 0.4575, 0.2283, 0.6350, 0.5300]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6421, 0.4114, 0.9054, 0.4475, 0.4030, 0.4379, 0.4815, 0.5277],
[0.6290, 0.3797, 0.8638, 0.5687, 0.4455, 0.4976, 0.5647, 0.5426],
[0.6579, 0.4121, 0.7245, 0.2258, 0.3609, 0.3025, 0.5843, 0.5721],
[0.6677, 0.4169, 0.8331, 0.2470, 0.4378, 0.1644, 0.6066, 0.5146],
[0.6490, 0.4068, 0.9010, 0.4690, 0.3478, 0.4634, 0.5632, 0.5723],
[0.6050, 0.3680, 0.8381, 0.5526, 0.3784, 0.4725, 0.6788, 0.5530],
[0.6591, 0.4004, 0.8229, 0.5532, 0.3631, 0.4770, 0.6958, 0.5461],
[0.5582, 0.3386, 0.8518, 0.2422, 0.4435, 0.2046, 0.6203, 0.5380]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6175, 0.4093, 0.8800, 0.4433, 0.4075, 0.4367, 0.5128, 0.4901],
[0.6229, 0.4066, 0.8512, 0.5717, 0.4500, 0.5050, 0.6025, 0.5350],
[0.6222, 0.4072, 0.7164, 0.2166, 0.3738, 0.3167, 0.6100, 0.5533],
[0.6260, 0.4106, 0.8025, 0.2583, 0.4550, 0.1867, 0.6281, 0.4869],
[0.6197, 0.4091, 0.8800, 0.4783, 0.3537, 0.4767, 0.5950, 0.5550],
[0.6307, 0.4045, 0.8025, 0.5833, 0.3775, 0.4867, 0.6892, 0.5459],
[0.6311, 0.3998, 0.7975, 0.5767, 0.3837, 0.4850, 0.7327, 0.5343],
[0.6268, 0.4060, 0.8350, 0.2433, 0.4575, 0.2283, 0.6350, 0.5300]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.052004264638526365
step: 80
running loss: 0.0006500533079815795
Train Steps: 80/90 Loss: 0.0007 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6198, 0.4076, 0.7945, 0.2453, 0.4475, 0.1871, 0.5897, 0.5350],
[0.6260, 0.4106, 0.8025, 0.2583, 0.4550, 0.1867, 0.6281, 0.4869],
[0.6073, 0.3932, 0.8363, 0.5817, 0.4425, 0.5117, 0.5204, 0.4817],
[0.6185, 0.4098, 0.8838, 0.4900, 0.4537, 0.5800, 0.6288, 0.5400],
[0.6239, 0.4206, 0.8750, 0.5400, 0.3688, 0.4850, 0.5737, 0.5700],
[0.6275, 0.4013, 0.8850, 0.2833, 0.4975, 0.2233, 0.7058, 0.5343],
[0.6200, 0.4055, 0.8011, 0.2988, 0.3842, 0.2798, 0.5949, 0.5183],
[0.6199, 0.4093, 0.7913, 0.2533, 0.4288, 0.2467, 0.5975, 0.5700]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5703, 0.3669, 0.7581, 0.2540, 0.4432, 0.1998, 0.5945, 0.5471],
[0.6378, 0.4003, 0.7889, 0.2524, 0.4271, 0.1770, 0.6109, 0.5023],
[0.5915, 0.3625, 0.7947, 0.5689, 0.4100, 0.5077, 0.5169, 0.5048],
[0.6458, 0.4033, 0.8496, 0.4939, 0.4427, 0.5757, 0.5995, 0.5437],
[0.6419, 0.4080, 0.8402, 0.5368, 0.3544, 0.4809, 0.5785, 0.5598],
[0.6207, 0.3765, 0.8509, 0.2847, 0.4755, 0.2091, 0.7005, 0.5387],
[0.6051, 0.3781, 0.7718, 0.2943, 0.3607, 0.2736, 0.5701, 0.5217],
[0.5617, 0.3639, 0.7565, 0.2403, 0.4141, 0.2534, 0.6069, 0.5797]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6198, 0.4076, 0.7945, 0.2453, 0.4475, 0.1871, 0.5897, 0.5350],
[0.6260, 0.4106, 0.8025, 0.2583, 0.4550, 0.1867, 0.6281, 0.4869],
[0.6073, 0.3932, 0.8363, 0.5817, 0.4425, 0.5117, 0.5204, 0.4817],
[0.6185, 0.4098, 0.8838, 0.4900, 0.4538, 0.5800, 0.6288, 0.5400],
[0.6239, 0.4206, 0.8750, 0.5400, 0.3688, 0.4850, 0.5738, 0.5700],
[0.6275, 0.4013, 0.8850, 0.2833, 0.4975, 0.2233, 0.7058, 0.5343],
[0.6201, 0.4055, 0.8011, 0.2988, 0.3842, 0.2798, 0.5949, 0.5183],
[0.6198, 0.4093, 0.7912, 0.2533, 0.4288, 0.2467, 0.5975, 0.5700]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.052478661498753354
step: 81
running loss: 0.0006478847098611525
Train Steps: 81/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6357, 0.4139, 0.8450, 0.5883, 0.3775, 0.4950, 0.6488, 0.5297],
[0.6164, 0.4119, 0.7913, 0.2650, 0.3538, 0.3500, 0.5614, 0.5038],
[0.6101, 0.4042, 0.7775, 0.2617, 0.3713, 0.2817, 0.5440, 0.5650],
[0.6164, 0.3956, 0.8757, 0.5088, 0.4300, 0.5320, 0.6022, 0.5202],
[0.6201, 0.4098, 0.8575, 0.3617, 0.3700, 0.3550, 0.5988, 0.5667],
[0.6211, 0.3935, 0.8636, 0.4841, 0.4417, 0.5126, 0.6331, 0.5268],
[0.6175, 0.4091, 0.7863, 0.2800, 0.3638, 0.3583, 0.6188, 0.5433],
[0.6175, 0.4093, 0.8800, 0.4433, 0.4075, 0.4367, 0.5128, 0.4901]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5892, 0.3835, 0.8204, 0.6024, 0.3746, 0.4807, 0.6545, 0.5273],
[0.6529, 0.4333, 0.7754, 0.2854, 0.3490, 0.3485, 0.5996, 0.5021],
[0.5644, 0.3742, 0.7539, 0.2913, 0.3867, 0.2633, 0.5590, 0.5586],
[0.6384, 0.4279, 0.8462, 0.5287, 0.4235, 0.5200, 0.5983, 0.5212],
[0.6365, 0.4300, 0.8416, 0.3824, 0.3755, 0.3318, 0.6057, 0.5722],
[0.6088, 0.3886, 0.8468, 0.4973, 0.4447, 0.4895, 0.6455, 0.5237],
[0.6316, 0.4297, 0.7667, 0.2996, 0.3584, 0.3493, 0.6122, 0.5377],
[0.6340, 0.4251, 0.8641, 0.4704, 0.4122, 0.4273, 0.5046, 0.5069]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6357, 0.4139, 0.8450, 0.5883, 0.3775, 0.4950, 0.6488, 0.5297],
[0.6164, 0.4119, 0.7912, 0.2650, 0.3537, 0.3500, 0.5614, 0.5038],
[0.6101, 0.4042, 0.7775, 0.2617, 0.3713, 0.2817, 0.5440, 0.5650],
[0.6164, 0.3956, 0.8757, 0.5088, 0.4300, 0.5320, 0.6022, 0.5202],
[0.6201, 0.4098, 0.8575, 0.3617, 0.3700, 0.3550, 0.5987, 0.5667],
[0.6211, 0.3935, 0.8636, 0.4841, 0.4417, 0.5126, 0.6331, 0.5268],
[0.6175, 0.4091, 0.7862, 0.2800, 0.3638, 0.3583, 0.6187, 0.5433],
[0.6175, 0.4093, 0.8800, 0.4433, 0.4075, 0.4367, 0.5128, 0.4901]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05284168719663285
step: 82
running loss: 0.0006444108194711323
Train Steps: 82/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6175, 0.3957, 0.8700, 0.4817, 0.4662, 0.5133, 0.5800, 0.5517],
[0.6162, 0.4014, 0.8800, 0.5333, 0.3750, 0.4817, 0.5988, 0.5283],
[0.6149, 0.4054, 0.6713, 0.2333, 0.4025, 0.2017, 0.5213, 0.5695],
[0.6325, 0.4066, 0.8438, 0.5350, 0.3925, 0.5267, 0.7113, 0.5795],
[0.6250, 0.4116, 0.8700, 0.4850, 0.4650, 0.5567, 0.6088, 0.5183],
[0.6203, 0.4073, 0.8189, 0.2398, 0.4400, 0.2054, 0.5929, 0.5501],
[0.6185, 0.4098, 0.8838, 0.4900, 0.4537, 0.5800, 0.6288, 0.5400],
[0.6282, 0.4092, 0.8000, 0.2183, 0.4500, 0.2383, 0.6787, 0.5364]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6312, 0.4297, 0.8587, 0.4907, 0.4612, 0.5042, 0.5684, 0.5371],
[0.5988, 0.4089, 0.8584, 0.5445, 0.3812, 0.4816, 0.5975, 0.5158],
[0.5220, 0.3592, 0.6690, 0.2524, 0.3919, 0.1902, 0.5083, 0.5494],
[0.5786, 0.3829, 0.8285, 0.5459, 0.3944, 0.5311, 0.7094, 0.5628],
[0.5903, 0.3994, 0.8665, 0.5041, 0.4634, 0.5658, 0.6238, 0.5060],
[0.6346, 0.4473, 0.7965, 0.2709, 0.4465, 0.2053, 0.5946, 0.5359],
[0.6350, 0.4314, 0.8643, 0.5173, 0.4638, 0.5775, 0.6126, 0.5268],
[0.6126, 0.4190, 0.7661, 0.2302, 0.4490, 0.2217, 0.6696, 0.5299]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6175, 0.3957, 0.8700, 0.4817, 0.4663, 0.5133, 0.5800, 0.5517],
[0.6162, 0.4014, 0.8800, 0.5333, 0.3750, 0.4817, 0.5987, 0.5283],
[0.6149, 0.4054, 0.6712, 0.2333, 0.4025, 0.2017, 0.5213, 0.5695],
[0.6325, 0.4066, 0.8438, 0.5350, 0.3925, 0.5267, 0.7113, 0.5795],
[0.6251, 0.4116, 0.8700, 0.4850, 0.4650, 0.5567, 0.6087, 0.5183],
[0.6203, 0.4073, 0.8189, 0.2398, 0.4400, 0.2054, 0.5929, 0.5501],
[0.6185, 0.4098, 0.8838, 0.4900, 0.4538, 0.5800, 0.6288, 0.5400],
[0.6282, 0.4092, 0.8000, 0.2183, 0.4500, 0.2383, 0.6787, 0.5364]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05330092628719285
step: 83
running loss: 0.000642179834785456
Train Steps: 83/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6218, 0.4137, 0.7263, 0.2233, 0.4075, 0.2650, 0.6212, 0.5783],
[0.6135, 0.3994, 0.7913, 0.3050, 0.3625, 0.3050, 0.5837, 0.5050],
[0.6339, 0.4123, 0.8638, 0.5367, 0.4075, 0.5467, 0.7517, 0.5436],
[0.6201, 0.4098, 0.8575, 0.3617, 0.3700, 0.3550, 0.5988, 0.5667],
[0.6057, 0.4011, 0.8750, 0.4267, 0.4400, 0.5800, 0.5845, 0.5585],
[0.6199, 0.4093, 0.7913, 0.2533, 0.4288, 0.2467, 0.5975, 0.5700],
[0.6200, 0.3998, 0.8850, 0.3950, 0.3500, 0.4650, 0.6138, 0.5400],
[0.6310, 0.4017, 0.8563, 0.5800, 0.3688, 0.4750, 0.6326, 0.5006]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5973, 0.3945, 0.7225, 0.2356, 0.4205, 0.2714, 0.6090, 0.5509],
[0.6181, 0.4025, 0.7789, 0.3133, 0.3741, 0.3125, 0.5720, 0.4842],
[0.6007, 0.4061, 0.8564, 0.5378, 0.4134, 0.5479, 0.7513, 0.5355],
[0.6377, 0.4411, 0.8541, 0.3740, 0.3877, 0.3519, 0.6080, 0.5572],
[0.6030, 0.4121, 0.8575, 0.4374, 0.4640, 0.5614, 0.5938, 0.5109],
[0.5986, 0.4167, 0.7761, 0.2509, 0.4511, 0.2576, 0.6155, 0.5611],
[0.6257, 0.4321, 0.8652, 0.4166, 0.3818, 0.4734, 0.6011, 0.5235],
[0.6366, 0.4268, 0.8353, 0.5934, 0.3804, 0.4744, 0.6389, 0.4864]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6218, 0.4137, 0.7262, 0.2233, 0.4075, 0.2650, 0.6212, 0.5783],
[0.6135, 0.3994, 0.7912, 0.3050, 0.3625, 0.3050, 0.5838, 0.5050],
[0.6339, 0.4123, 0.8637, 0.5367, 0.4075, 0.5467, 0.7517, 0.5436],
[0.6201, 0.4098, 0.8575, 0.3617, 0.3700, 0.3550, 0.5987, 0.5667],
[0.6057, 0.4011, 0.8750, 0.4267, 0.4400, 0.5800, 0.5845, 0.5585],
[0.6198, 0.4093, 0.7912, 0.2533, 0.4288, 0.2467, 0.5975, 0.5700],
[0.6200, 0.3998, 0.8850, 0.3950, 0.3500, 0.4650, 0.6137, 0.5400],
[0.6310, 0.4017, 0.8562, 0.5800, 0.3688, 0.4750, 0.6326, 0.5006]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05356978881172836
step: 84
running loss: 0.0006377355810920042
Train Steps: 84/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6185, 0.4080, 0.8625, 0.3483, 0.3788, 0.2650, 0.5320, 0.5272],
[0.6178, 0.4059, 0.7525, 0.2250, 0.4313, 0.1783, 0.5404, 0.5240],
[0.6178, 0.4012, 0.8900, 0.4495, 0.3891, 0.5617, 0.5972, 0.4879],
[0.6263, 0.4039, 0.9000, 0.4400, 0.3625, 0.4667, 0.6424, 0.4804],
[0.6311, 0.3998, 0.7975, 0.5767, 0.3838, 0.4850, 0.7327, 0.5343],
[0.6169, 0.4052, 0.8742, 0.4779, 0.4288, 0.4917, 0.5763, 0.5617],
[0.6271, 0.4040, 0.9138, 0.3750, 0.4625, 0.2617, 0.7232, 0.5413],
[0.6277, 0.4036, 0.8688, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5875, 0.4149, 0.8459, 0.3509, 0.3870, 0.2874, 0.5411, 0.5442],
[0.5924, 0.4037, 0.7505, 0.2112, 0.4286, 0.1813, 0.5500, 0.5437],
[0.5634, 0.4030, 0.8751, 0.4425, 0.4029, 0.5792, 0.6001, 0.5064],
[0.5981, 0.4082, 0.8929, 0.4612, 0.3577, 0.4834, 0.6200, 0.4828],
[0.6246, 0.4228, 0.7950, 0.5650, 0.3801, 0.5068, 0.7198, 0.5421],
[0.5945, 0.4179, 0.8718, 0.4739, 0.4445, 0.5150, 0.5740, 0.5743],
[0.6081, 0.4048, 0.9095, 0.3811, 0.4746, 0.2754, 0.7238, 0.5498],
[0.5983, 0.4079, 0.8501, 0.3613, 0.3965, 0.2732, 0.6135, 0.4916]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6186, 0.4080, 0.8625, 0.3483, 0.3787, 0.2650, 0.5320, 0.5272],
[0.6178, 0.4059, 0.7525, 0.2250, 0.4313, 0.1783, 0.5404, 0.5240],
[0.6178, 0.4012, 0.8900, 0.4495, 0.3891, 0.5617, 0.5972, 0.4879],
[0.6263, 0.4038, 0.9000, 0.4400, 0.3625, 0.4667, 0.6424, 0.4804],
[0.6311, 0.3998, 0.7975, 0.5767, 0.3837, 0.4850, 0.7327, 0.5343],
[0.6169, 0.4052, 0.8742, 0.4779, 0.4288, 0.4917, 0.5763, 0.5617],
[0.6271, 0.4040, 0.9137, 0.3750, 0.4625, 0.2617, 0.7232, 0.5413],
[0.6277, 0.4036, 0.8687, 0.3617, 0.3925, 0.2600, 0.6132, 0.4742]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05381043939269148
step: 85
running loss: 0.0006330639928551939
Train Steps: 85/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6195, 0.4101, 0.8650, 0.3917, 0.3575, 0.4033, 0.5800, 0.5650],
[ nan, nan, 0.7335, 0.2569, 0.3788, 0.2667, 0.5066, 0.5578],
[0.6134, 0.4090, 0.6926, 0.2819, 0.3538, 0.3233, 0.5563, 0.5667],
[0.6135, 0.4115, 0.8838, 0.4667, 0.4288, 0.6050, 0.5778, 0.5097],
[0.6241, 0.4143, 0.8938, 0.4650, 0.4075, 0.5350, 0.6250, 0.5550],
[ nan, nan, 0.6935, 0.1930, 0.4150, 0.2250, 0.5450, 0.5650],
[0.6138, 0.4020, 0.8800, 0.4717, 0.4375, 0.4717, 0.5502, 0.5611],
[0.6296, 0.3989, 0.9000, 0.4150, 0.3613, 0.3867, 0.6400, 0.5100]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6852, 0.4618, 0.8708, 0.3944, 0.3783, 0.4155, 0.6161, 0.5445],
[0.0702, 0.0619, 0.7505, 0.2546, 0.3969, 0.2535, 0.5469, 0.5487],
[0.6904, 0.4733, 0.6993, 0.2870, 0.3562, 0.3299, 0.5718, 0.5590],
[0.7018, 0.4831, 0.8874, 0.4605, 0.4533, 0.6048, 0.5969, 0.4998],
[0.6675, 0.4485, 0.9028, 0.4753, 0.4376, 0.5313, 0.6724, 0.5408],
[0.0645, 0.0471, 0.7440, 0.2061, 0.4404, 0.2277, 0.5841, 0.5455],
[0.6645, 0.4337, 0.8776, 0.4873, 0.4567, 0.4745, 0.5866, 0.5565],
[0.6834, 0.4593, 0.8890, 0.4265, 0.3717, 0.3716, 0.6853, 0.5162]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6195, 0.4101, 0.8650, 0.3917, 0.3575, 0.4033, 0.5800, 0.5650],
[0.0000, 0.0000, 0.7335, 0.2569, 0.3787, 0.2667, 0.5066, 0.5578],
[0.6134, 0.4090, 0.6926, 0.2819, 0.3537, 0.3233, 0.5562, 0.5667],
[0.6135, 0.4115, 0.8838, 0.4667, 0.4288, 0.6050, 0.5778, 0.5097],
[0.6241, 0.4142, 0.8938, 0.4650, 0.4075, 0.5350, 0.6250, 0.5550],
[0.0000, 0.0000, 0.6935, 0.1930, 0.4150, 0.2250, 0.5450, 0.5650],
[0.6138, 0.4020, 0.8800, 0.4717, 0.4375, 0.4717, 0.5502, 0.5611],
[0.6296, 0.3989, 0.9000, 0.4150, 0.3613, 0.3867, 0.6400, 0.5100]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0012, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.055031666153809056
step: 86
running loss: 0.0006399030948117332
Train Steps: 86/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6128, 0.4084, 0.8738, 0.4683, 0.3613, 0.3700, 0.4960, 0.5397],
[0.6346, 0.4092, 0.7712, 0.5917, 0.4037, 0.4767, 0.7343, 0.5725],
[0.6218, 0.4098, 0.7238, 0.1850, 0.4238, 0.2517, 0.6288, 0.5350],
[0.6157, 0.4102, 0.8513, 0.3817, 0.3613, 0.3667, 0.5096, 0.5890],
[0.6204, 0.4007, 0.7838, 0.2100, 0.4475, 0.1733, 0.5825, 0.5167],
[0.6248, 0.4185, 0.8500, 0.5767, 0.4463, 0.4550, 0.5613, 0.5917],
[0.6264, 0.4049, 0.8988, 0.4633, 0.3813, 0.4983, 0.6326, 0.4843],
[0.6202, 0.4054, 0.8892, 0.4428, 0.3642, 0.3249, 0.5840, 0.5426]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6089, 0.4066, 0.8930, 0.4500, 0.3558, 0.3774, 0.5126, 0.5316],
[0.6178, 0.4133, 0.8086, 0.5496, 0.3828, 0.4906, 0.7146, 0.5772],
[0.5650, 0.3830, 0.7388, 0.1678, 0.4170, 0.2644, 0.6357, 0.5449],
[0.5711, 0.3814, 0.8569, 0.3553, 0.3582, 0.3664, 0.5219, 0.5682],
[0.6151, 0.3987, 0.7894, 0.2035, 0.4397, 0.1833, 0.6035, 0.5115],
[0.6286, 0.4139, 0.8668, 0.5642, 0.4487, 0.4700, 0.5509, 0.5796],
[0.5903, 0.3813, 0.9292, 0.4573, 0.3781, 0.5267, 0.6417, 0.4760],
[0.6194, 0.4071, 0.9080, 0.4125, 0.3576, 0.3366, 0.5864, 0.5319]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6127, 0.4084, 0.8737, 0.4683, 0.3613, 0.3700, 0.4960, 0.5397],
[0.6346, 0.4092, 0.7713, 0.5917, 0.4038, 0.4767, 0.7343, 0.5725],
[0.6218, 0.4098, 0.7237, 0.1850, 0.4238, 0.2517, 0.6288, 0.5350],
[0.6157, 0.4102, 0.8512, 0.3817, 0.3613, 0.3667, 0.5096, 0.5890],
[0.6204, 0.4007, 0.7837, 0.2100, 0.4475, 0.1733, 0.5825, 0.5167],
[0.6248, 0.4185, 0.8500, 0.5767, 0.4462, 0.4550, 0.5612, 0.5917],
[0.6264, 0.4049, 0.8988, 0.4633, 0.3812, 0.4983, 0.6326, 0.4843],
[0.6202, 0.4054, 0.8892, 0.4428, 0.3642, 0.3249, 0.5840, 0.5426]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05537027501850389
step: 87
running loss: 0.000636439942741424
Train Steps: 87/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6350, 0.4118, 0.8363, 0.2717, 0.4850, 0.1700, 0.6441, 0.5170],
[0.6154, 0.4112, 0.7037, 0.2317, 0.4238, 0.1833, 0.5350, 0.5600],
[0.6289, 0.4024, 0.9088, 0.4567, 0.3937, 0.5633, 0.7058, 0.5609],
[0.6261, 0.4066, 0.8325, 0.2150, 0.4763, 0.2667, 0.7002, 0.5633],
[ nan, nan, 0.6935, 0.1930, 0.4150, 0.2250, 0.5450, 0.5650],
[0.6274, 0.4270, 0.8938, 0.4967, 0.3550, 0.4283, 0.5700, 0.5733],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5413, 0.5683],
[0.6272, 0.4045, 0.8538, 0.5900, 0.3750, 0.4417, 0.5989, 0.4649]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6273, 0.3890, 0.8337, 0.2448, 0.4812, 0.1961, 0.6621, 0.5329],
[ 0.5398, 0.3412, 0.7003, 0.2040, 0.4109, 0.1969, 0.5295, 0.5867],
[ 0.6335, 0.3931, 0.9081, 0.4608, 0.3957, 0.5802, 0.7179, 0.5608],
[ 0.6215, 0.3847, 0.8332, 0.2021, 0.4697, 0.2656, 0.6955, 0.5724],
[ 0.0028, -0.0193, 0.7317, 0.1922, 0.4107, 0.2410, 0.5504, 0.5703],
[ 0.6439, 0.4225, 0.8855, 0.4874, 0.3613, 0.4436, 0.5802, 0.5788],
[ 0.6505, 0.4059, 0.8815, 0.5170, 0.3708, 0.3837, 0.5383, 0.5823],
[ 0.6387, 0.4065, 0.8629, 0.5829, 0.3632, 0.4534, 0.5999, 0.4838]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6350, 0.4118, 0.8363, 0.2717, 0.4850, 0.1700, 0.6441, 0.5170],
[0.6154, 0.4112, 0.7038, 0.2317, 0.4238, 0.1833, 0.5350, 0.5600],
[0.6289, 0.4024, 0.9087, 0.4567, 0.3938, 0.5633, 0.7058, 0.5609],
[0.6261, 0.4066, 0.8325, 0.2150, 0.4762, 0.2667, 0.7002, 0.5633],
[0.0000, 0.0000, 0.6935, 0.1930, 0.4150, 0.2250, 0.5450, 0.5650],
[0.6274, 0.4270, 0.8938, 0.4967, 0.3550, 0.4283, 0.5700, 0.5733],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5412, 0.5683],
[0.6271, 0.4045, 0.8537, 0.5900, 0.3750, 0.4417, 0.5989, 0.4649]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05571220855927095
step: 88
running loss: 0.0006330932790826245
Train Steps: 88/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6086, 0.4019, 0.7782, 0.4278, 0.3625, 0.4350, 0.5150, 0.5285],
[0.6219, 0.4097, 0.8738, 0.3400, 0.3563, 0.4117, 0.5975, 0.5683],
[0.6339, 0.4102, 0.9088, 0.4767, 0.3925, 0.5283, 0.7509, 0.5390],
[0.6229, 0.4086, 0.7538, 0.2600, 0.4775, 0.1617, 0.5900, 0.5383],
[0.6111, 0.4033, 0.8300, 0.3267, 0.3588, 0.3333, 0.5444, 0.5637],
[0.6133, 0.4094, 0.8495, 0.4028, 0.3588, 0.3200, 0.5003, 0.5407],
[0.6125, 0.4076, 0.8488, 0.3883, 0.3700, 0.3683, 0.5026, 0.5505],
[0.6246, 0.4126, 0.8850, 0.4833, 0.4200, 0.5350, 0.6112, 0.5250]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6336, 0.3862, 0.7997, 0.4040, 0.3665, 0.4314, 0.5084, 0.5298],
[0.6450, 0.4073, 0.8902, 0.3394, 0.3426, 0.4122, 0.5901, 0.5705],
[0.6138, 0.3758, 0.9187, 0.4917, 0.3973, 0.5376, 0.7533, 0.5515],
[0.6018, 0.3784, 0.7607, 0.2297, 0.4623, 0.1590, 0.5976, 0.5293],
[0.6231, 0.3946, 0.8374, 0.3192, 0.3491, 0.3294, 0.5278, 0.5643],
[0.5974, 0.3757, 0.8539, 0.3863, 0.3613, 0.3103, 0.4865, 0.5473],
[0.5614, 0.3451, 0.8446, 0.3562, 0.3489, 0.3618, 0.4804, 0.5477],
[0.6163, 0.3803, 0.9144, 0.4768, 0.4139, 0.5283, 0.6034, 0.5241]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6086, 0.4019, 0.7782, 0.4278, 0.3625, 0.4350, 0.5150, 0.5285],
[0.6219, 0.4097, 0.8737, 0.3400, 0.3562, 0.4117, 0.5975, 0.5683],
[0.6339, 0.4102, 0.9087, 0.4767, 0.3925, 0.5283, 0.7509, 0.5390],
[0.6229, 0.4086, 0.7538, 0.2600, 0.4775, 0.1617, 0.5900, 0.5383],
[0.6111, 0.4033, 0.8300, 0.3267, 0.3587, 0.3333, 0.5444, 0.5637],
[0.6133, 0.4094, 0.8495, 0.4028, 0.3587, 0.3200, 0.5003, 0.5407],
[0.6125, 0.4076, 0.8487, 0.3883, 0.3700, 0.3683, 0.5026, 0.5505],
[0.6246, 0.4126, 0.8850, 0.4833, 0.4200, 0.5350, 0.6112, 0.5250]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.056046031415462494
step: 89
running loss: 0.0006297306900613763
Train Steps: 89/90 Loss: 0.0006 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.8850, 0.3000, 0.5363, 0.2250, 0.7343, 0.5771],
[ nan, nan, 0.7192, 0.2346, 0.4037, 0.2050, 0.5138, 0.5650],
[0.6279, 0.4050, 0.8025, 0.2200, 0.4313, 0.2733, 0.6820, 0.5320],
[0.6226, 0.4098, 0.8912, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367],
[0.6239, 0.4061, 0.8850, 0.4600, 0.4225, 0.5200, 0.6138, 0.5450],
[0.6164, 0.4066, 0.6625, 0.3033, 0.3775, 0.2967, 0.5725, 0.5833],
[0.6263, 0.4030, 0.9000, 0.4767, 0.3800, 0.5167, 0.6415, 0.4771],
[0.6134, 0.4090, 0.6926, 0.2819, 0.3538, 0.3233, 0.5563, 0.5667]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.0543, 0.0123, 0.8911, 0.3049, 0.5193, 0.2527, 0.7156, 0.5693],
[0.0740, 0.0303, 0.7232, 0.2378, 0.4109, 0.2229, 0.4969, 0.5576],
[0.6706, 0.4200, 0.8034, 0.2314, 0.4377, 0.2683, 0.6421, 0.5472],
[0.6664, 0.4229, 0.8999, 0.4158, 0.4024, 0.2327, 0.5504, 0.5444],
[0.6982, 0.4263, 0.9126, 0.4696, 0.4135, 0.5241, 0.6159, 0.5539],
[0.6612, 0.4072, 0.6893, 0.3068, 0.3739, 0.2782, 0.5454, 0.5953],
[0.6631, 0.4017, 0.9254, 0.4943, 0.3901, 0.5292, 0.6213, 0.4722],
[0.6907, 0.4428, 0.7078, 0.2828, 0.3454, 0.3258, 0.5317, 0.5711]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.8850, 0.3000, 0.5362, 0.2250, 0.7343, 0.5771],
[0.0000, 0.0000, 0.7192, 0.2346, 0.4038, 0.2050, 0.5138, 0.5650],
[0.6279, 0.4050, 0.8025, 0.2200, 0.4313, 0.2733, 0.6820, 0.5320],
[0.6226, 0.4098, 0.8913, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367],
[0.6239, 0.4061, 0.8850, 0.4600, 0.4225, 0.5200, 0.6137, 0.5450],
[0.6164, 0.4066, 0.6625, 0.3033, 0.3775, 0.2967, 0.5725, 0.5833],
[0.6263, 0.4029, 0.9000, 0.4767, 0.3800, 0.5167, 0.6415, 0.4771],
[0.6134, 0.4090, 0.6926, 0.2819, 0.3537, 0.3233, 0.5562, 0.5667]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.05668294767383486
step: 90
running loss: 0.0006298105297092762
Valid Steps: 10/10 Loss: nan 06
--------------------------------------------------
Epoch: 9 Train Loss: 0.0006 Valid Loss: nan
--------------------------------------------------
size of train loader is: 90
torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6274, 0.4087, 0.8375, 0.5700, 0.4025, 0.4800, 0.5700, 0.6117],
[0.6339, 0.4159, 0.8400, 0.5617, 0.3825, 0.4150, 0.7343, 0.5748],
[0.6200, 0.3978, 0.8900, 0.4550, 0.3775, 0.5200, 0.6150, 0.5367],
[0.6268, 0.4052, 0.8175, 0.2250, 0.4688, 0.1917, 0.6375, 0.5267],
[0.6085, 0.4005, 0.8400, 0.4317, 0.3763, 0.4750, 0.5476, 0.5058],
[0.6263, 0.4039, 0.9000, 0.4400, 0.3625, 0.4667, 0.6424, 0.4804],
[0.6275, 0.4008, 0.8047, 0.2484, 0.4037, 0.2777, 0.6506, 0.5212],
[0.6203, 0.4021, 0.8780, 0.5031, 0.3667, 0.3882, 0.5842, 0.5405]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6319, 0.4033, 0.8382, 0.5868, 0.4032, 0.4758, 0.5705, 0.6225],
[0.6193, 0.4029, 0.8496, 0.5472, 0.3828, 0.3973, 0.6909, 0.5676],
[0.6050, 0.3735, 0.8999, 0.4544, 0.3672, 0.5176, 0.5923, 0.5468],
[0.5715, 0.3618, 0.8084, 0.2102, 0.4502, 0.1593, 0.6312, 0.5402],
[0.6272, 0.3849, 0.8458, 0.4138, 0.3584, 0.4622, 0.5293, 0.5167],
[0.6106, 0.3786, 0.9130, 0.4429, 0.3443, 0.4480, 0.6162, 0.4848],
[0.6164, 0.3759, 0.8053, 0.2452, 0.4003, 0.2702, 0.5980, 0.5262],
[0.6215, 0.3952, 0.8878, 0.5006, 0.3623, 0.3742, 0.5542, 0.5449]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6274, 0.4087, 0.8375, 0.5700, 0.4025, 0.4800, 0.5700, 0.6117],
[0.6339, 0.4159, 0.8400, 0.5617, 0.3825, 0.4150, 0.7343, 0.5748],
[0.6199, 0.3978, 0.8900, 0.4550, 0.3775, 0.5200, 0.6150, 0.5367],
[0.6268, 0.4052, 0.8175, 0.2250, 0.4688, 0.1917, 0.6375, 0.5267],
[0.6084, 0.4005, 0.8400, 0.4317, 0.3762, 0.4750, 0.5476, 0.5058],
[0.6263, 0.4038, 0.9000, 0.4400, 0.3625, 0.4667, 0.6424, 0.4804],
[0.6275, 0.4008, 0.8047, 0.2484, 0.4037, 0.2777, 0.6506, 0.5212],
[0.6203, 0.4020, 0.8780, 0.5031, 0.3667, 0.3882, 0.5842, 0.5405]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.00033010990591719747
step: 1
running loss: 0.00033010990591719747
Train Steps: 1/90 Loss: 0.0003 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.8750, 0.2467, 0.5138, 0.2617, 0.7382, 0.5552],
[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.6038, 0.3946, 0.8413, 0.4883, 0.3563, 0.4550, 0.5266, 0.4693],
[0.6182, 0.3967, 0.8263, 0.3065, 0.3526, 0.4161, 0.6192, 0.5290],
[0.6264, 0.4049, 0.8988, 0.4633, 0.3813, 0.4983, 0.6326, 0.4843],
[0.6112, 0.4029, 0.8638, 0.4800, 0.4875, 0.5083, 0.5763, 0.5567],
[0.6278, 0.4253, 0.8875, 0.5017, 0.4113, 0.2750, 0.5413, 0.6196],
[0.6136, 0.4060, 0.8025, 0.3217, 0.3650, 0.3000, 0.5060, 0.5646]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[-0.0342, -0.0272, 0.8486, 0.2634, 0.4950, 0.2271, 0.7346, 0.5626],
[ 0.6159, 0.4097, 0.8308, 0.5721, 0.3762, 0.4762, 0.6822, 0.5432],
[ 0.5889, 0.3787, 0.8285, 0.4872, 0.3594, 0.4427, 0.5375, 0.4913],
[ 0.6269, 0.4067, 0.8038, 0.3009, 0.3414, 0.3860, 0.6229, 0.5287],
[ 0.6134, 0.3922, 0.8882, 0.4636, 0.3768, 0.4819, 0.6375, 0.4844],
[ 0.6016, 0.3828, 0.8553, 0.4822, 0.4793, 0.4714, 0.5879, 0.5612],
[ 0.6456, 0.4502, 0.8314, 0.4961, 0.4227, 0.2749, 0.5583, 0.5983],
[ 0.5594, 0.3836, 0.7677, 0.3099, 0.3410, 0.2879, 0.4798, 0.5510]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.8750, 0.2467, 0.5138, 0.2617, 0.7382, 0.5552],
[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.6038, 0.3946, 0.8413, 0.4883, 0.3562, 0.4550, 0.5266, 0.4693],
[0.6182, 0.3967, 0.8263, 0.3065, 0.3526, 0.4161, 0.6192, 0.5290],
[0.6264, 0.4049, 0.8988, 0.4633, 0.3812, 0.4983, 0.6326, 0.4843],
[0.6112, 0.4029, 0.8637, 0.4800, 0.4875, 0.5083, 0.5763, 0.5567],
[0.6278, 0.4253, 0.8875, 0.5017, 0.4112, 0.2750, 0.5413, 0.6196],
[0.6136, 0.4060, 0.8025, 0.3217, 0.3650, 0.3000, 0.5060, 0.5646]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0007069317507557571
step: 2
running loss: 0.00035346587537787855
Train Steps: 2/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6108, 0.4011, 0.8037, 0.3400, 0.3700, 0.2933, 0.5658, 0.5617],
[0.6274, 0.4117, 0.8100, 0.5801, 0.4000, 0.4583, 0.5582, 0.6118],
[0.6128, 0.4022, 0.8738, 0.5067, 0.4983, 0.5231, 0.5364, 0.5064],
[0.6164, 0.4076, 0.8838, 0.4117, 0.3713, 0.5550, 0.6238, 0.5350],
[0.6260, 0.4106, 0.8025, 0.2583, 0.4550, 0.1867, 0.6281, 0.4869],
[0.6060, 0.3924, 0.8450, 0.5717, 0.4200, 0.5217, 0.5253, 0.4752],
[0.6107, 0.4013, 0.8700, 0.4650, 0.5049, 0.5176, 0.5850, 0.5550],
[0.6104, 0.4029, 0.8738, 0.4900, 0.4088, 0.4533, 0.5070, 0.5510]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5574, 0.3672, 0.7911, 0.3417, 0.3739, 0.2880, 0.5773, 0.5484],
[0.5857, 0.4212, 0.7881, 0.5672, 0.3776, 0.4325, 0.5911, 0.6166],
[0.5877, 0.4114, 0.8576, 0.5004, 0.4741, 0.4730, 0.5572, 0.5137],
[0.5858, 0.3907, 0.8654, 0.4103, 0.3588, 0.5215, 0.6651, 0.5400],
[0.6192, 0.4234, 0.7952, 0.2539, 0.4438, 0.1704, 0.6434, 0.4868],
[0.5735, 0.3856, 0.8259, 0.5744, 0.4119, 0.4878, 0.5524, 0.4930],
[0.6191, 0.4261, 0.8729, 0.4594, 0.4652, 0.4792, 0.6136, 0.5484],
[0.6088, 0.4250, 0.8484, 0.4860, 0.4031, 0.4150, 0.5401, 0.5447]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6108, 0.4011, 0.8037, 0.3400, 0.3700, 0.2933, 0.5658, 0.5617],
[0.6274, 0.4117, 0.8100, 0.5801, 0.4000, 0.4583, 0.5582, 0.6118],
[0.6128, 0.4022, 0.8737, 0.5067, 0.4983, 0.5231, 0.5364, 0.5064],
[0.6164, 0.4076, 0.8838, 0.4117, 0.3713, 0.5550, 0.6237, 0.5350],
[0.6260, 0.4106, 0.8025, 0.2583, 0.4550, 0.1867, 0.6281, 0.4869],
[0.6060, 0.3924, 0.8450, 0.5717, 0.4200, 0.5217, 0.5253, 0.4752],
[0.6107, 0.4013, 0.8700, 0.4650, 0.5049, 0.5176, 0.5850, 0.5550],
[0.6104, 0.4029, 0.8737, 0.4900, 0.4087, 0.4533, 0.5070, 0.5510]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0011995541281066835
step: 3
running loss: 0.00039985137603556115
Train Steps: 3/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6113, 0.4104, 0.8650, 0.4250, 0.3925, 0.5967, 0.5787, 0.5116],
[0.6193, 0.4079, 0.7288, 0.2500, 0.4250, 0.2550, 0.5989, 0.6266],
[0.6329, 0.4175, 0.8550, 0.2333, 0.5425, 0.2250, 0.7398, 0.5609],
[0.6264, 0.3972, 0.8853, 0.4771, 0.3853, 0.4511, 0.6293, 0.5334],
[0.6186, 0.3967, 0.7337, 0.1992, 0.4120, 0.2508, 0.6105, 0.5395],
[0.6082, 0.4042, 0.6975, 0.1917, 0.4100, 0.1983, 0.5502, 0.5578],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3788, 0.4900, 0.7121, 0.5864],
[0.6083, 0.3957, 0.8638, 0.4950, 0.4363, 0.5083, 0.5346, 0.4980]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5633, 0.3993, 0.8716, 0.4412, 0.3910, 0.5889, 0.5730, 0.5090],
[0.6544, 0.4508, 0.7246, 0.2789, 0.4351, 0.2671, 0.5843, 0.6092],
[0.5153, 0.3684, 0.8457, 0.2617, 0.5448, 0.2269, 0.7136, 0.5446],
[0.5525, 0.3710, 0.9015, 0.4977, 0.3737, 0.4679, 0.6343, 0.5163],
[0.6168, 0.4171, 0.7332, 0.2345, 0.4105, 0.2477, 0.5846, 0.5238],
[0.6235, 0.4353, 0.6781, 0.2241, 0.4157, 0.1958, 0.5455, 0.5421],
[0.5919, 0.4037, 0.8823, 0.5418, 0.3836, 0.4859, 0.7154, 0.5731],
[0.5329, 0.3702, 0.8681, 0.5204, 0.4421, 0.5144, 0.5354, 0.4807]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6113, 0.4104, 0.8650, 0.4250, 0.3925, 0.5967, 0.5787, 0.5116],
[0.6193, 0.4078, 0.7287, 0.2500, 0.4250, 0.2550, 0.5989, 0.6266],
[0.6329, 0.4175, 0.8550, 0.2333, 0.5425, 0.2250, 0.7398, 0.5609],
[0.6264, 0.3972, 0.8853, 0.4771, 0.3853, 0.4511, 0.6293, 0.5334],
[0.6186, 0.3967, 0.7337, 0.1992, 0.4120, 0.2508, 0.6105, 0.5395],
[0.6082, 0.4042, 0.6975, 0.1917, 0.4100, 0.1983, 0.5502, 0.5578],
[0.6314, 0.4107, 0.8750, 0.5100, 0.3787, 0.4900, 0.7121, 0.5864],
[0.6083, 0.3957, 0.8637, 0.4950, 0.4363, 0.5083, 0.5346, 0.4980]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.001964781025890261
step: 4
running loss: 0.0004911952564725652
Train Steps: 4/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6203, 0.4096, 0.8862, 0.4267, 0.3538, 0.4117, 0.6025, 0.5650],
[0.6129, 0.3930, 0.8769, 0.5105, 0.4146, 0.5642, 0.6000, 0.5082],
[0.6136, 0.4029, 0.8263, 0.3350, 0.3625, 0.3067, 0.5675, 0.5167],
[0.6213, 0.4001, 0.7712, 0.2117, 0.4338, 0.1800, 0.5850, 0.5183],
[0.6141, 0.4038, 0.8650, 0.4833, 0.4839, 0.5176, 0.5787, 0.5600],
[0.6262, 0.4163, 0.8850, 0.5183, 0.3763, 0.4150, 0.6025, 0.5500],
[0.6102, 0.4001, 0.7738, 0.3583, 0.3463, 0.3800, 0.5524, 0.5689],
[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6021, 0.4175, 0.8881, 0.4239, 0.3671, 0.4225, 0.6052, 0.5651],
[0.6143, 0.4123, 0.8668, 0.5317, 0.4316, 0.5661, 0.6044, 0.5064],
[0.5993, 0.4155, 0.8203, 0.3317, 0.3824, 0.3246, 0.5612, 0.5325],
[0.6159, 0.4190, 0.7533, 0.2214, 0.4518, 0.1878, 0.5800, 0.5094],
[0.6217, 0.4305, 0.8700, 0.4981, 0.4964, 0.5245, 0.5738, 0.5462],
[0.6181, 0.4288, 0.8747, 0.5019, 0.3862, 0.4134, 0.5927, 0.5407],
[0.5921, 0.3948, 0.7740, 0.3583, 0.3586, 0.3819, 0.5415, 0.5482],
[0.6055, 0.4110, 0.7385, 0.2399, 0.3841, 0.3300, 0.6114, 0.5342]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6203, 0.4096, 0.8863, 0.4267, 0.3537, 0.4117, 0.6025, 0.5650],
[0.6129, 0.3930, 0.8769, 0.5105, 0.4146, 0.5642, 0.6000, 0.5082],
[0.6136, 0.4029, 0.8263, 0.3350, 0.3625, 0.3067, 0.5675, 0.5167],
[0.6213, 0.4001, 0.7713, 0.2117, 0.4338, 0.1800, 0.5850, 0.5183],
[0.6141, 0.4038, 0.8650, 0.4833, 0.4839, 0.5176, 0.5788, 0.5600],
[0.6262, 0.4163, 0.8850, 0.5183, 0.3762, 0.4150, 0.6025, 0.5500],
[0.6102, 0.4001, 0.7738, 0.3583, 0.3462, 0.3800, 0.5524, 0.5689],
[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0001, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0001, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0021081157465232536
step: 5
running loss: 0.0004216231493046507
Train Steps: 5/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6206, 0.4001, 0.8900, 0.3933, 0.3588, 0.3567, 0.5837, 0.5083],
[ nan, nan, 0.7553, 0.2722, 0.3875, 0.2550, 0.5125, 0.5633],
[0.6154, 0.4048, 0.7100, 0.2067, 0.4338, 0.1667, 0.5413, 0.5220],
[0.6257, 0.4024, 0.8612, 0.5352, 0.4361, 0.5253, 0.6680, 0.5166],
[0.6152, 0.4131, 0.6863, 0.2567, 0.3625, 0.3300, 0.5765, 0.5305],
[0.6124, 0.4075, 0.7696, 0.4153, 0.3475, 0.3767, 0.5157, 0.5427],
[0.6161, 0.4099, 0.8738, 0.4383, 0.3788, 0.5483, 0.5605, 0.5019],
[0.6332, 0.4165, 0.9100, 0.3350, 0.4188, 0.3683, 0.7438, 0.5528]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6132, 0.4043, 0.9107, 0.4013, 0.3892, 0.3707, 0.5962, 0.5043],
[0.0139, 0.0169, 0.7506, 0.2564, 0.4062, 0.2713, 0.5084, 0.5668],
[0.6754, 0.4624, 0.7043, 0.2228, 0.4741, 0.1872, 0.5517, 0.5211],
[0.6439, 0.4191, 0.8781, 0.5365, 0.4522, 0.5445, 0.6816, 0.5261],
[0.6293, 0.4285, 0.6871, 0.2469, 0.3909, 0.3598, 0.5914, 0.5490],
[0.6005, 0.4066, 0.7894, 0.4102, 0.3767, 0.3983, 0.5329, 0.5549],
[0.6179, 0.4132, 0.9037, 0.4317, 0.3969, 0.5640, 0.5869, 0.5120],
[0.6048, 0.4038, 0.9222, 0.3448, 0.4445, 0.3862, 0.7535, 0.5470]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6206, 0.4001, 0.8900, 0.3933, 0.3587, 0.3567, 0.5838, 0.5083],
[0.0000, 0.0000, 0.7553, 0.2722, 0.3875, 0.2550, 0.5125, 0.5633],
[0.6154, 0.4048, 0.7100, 0.2067, 0.4338, 0.1667, 0.5413, 0.5220],
[0.6257, 0.4024, 0.8612, 0.5352, 0.4361, 0.5253, 0.6680, 0.5166],
[0.6152, 0.4131, 0.6862, 0.2567, 0.3625, 0.3300, 0.5765, 0.5305],
[0.6124, 0.4075, 0.7696, 0.4153, 0.3475, 0.3767, 0.5157, 0.5427],
[0.6161, 0.4099, 0.8737, 0.4383, 0.3787, 0.5483, 0.5605, 0.5019],
[0.6332, 0.4165, 0.9100, 0.3350, 0.4187, 0.3683, 0.7438, 0.5528]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.002486242665327154
step: 6
running loss: 0.0004143737775545257
Train Steps: 6/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6095, 0.3970, 0.8688, 0.4767, 0.4860, 0.4879, 0.5191, 0.4940],
[0.6128, 0.4084, 0.8738, 0.4683, 0.3613, 0.3700, 0.4960, 0.5397],
[0.6129, 0.4114, 0.6950, 0.2467, 0.4050, 0.2133, 0.5363, 0.5550],
[0.6199, 0.3952, 0.8573, 0.5374, 0.4075, 0.4687, 0.5942, 0.5377],
[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837],
[0.6271, 0.4005, 0.8450, 0.6067, 0.3850, 0.4983, 0.6069, 0.4649],
[0.6268, 0.4052, 0.8175, 0.2250, 0.4688, 0.1917, 0.6375, 0.5267],
[0.6201, 0.4036, 0.8596, 0.3850, 0.3492, 0.3785, 0.5978, 0.5131]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6171, 0.4000, 0.8989, 0.4624, 0.4872, 0.5078, 0.5293, 0.5201],
[0.6218, 0.4176, 0.8943, 0.4584, 0.3685, 0.3988, 0.5197, 0.5399],
[0.6205, 0.4179, 0.7013, 0.2469, 0.4153, 0.2526, 0.5713, 0.5631],
[0.6313, 0.3969, 0.8684, 0.5323, 0.4041, 0.4980, 0.6304, 0.5513],
[0.6323, 0.4256, 0.6733, 0.2832, 0.3674, 0.3227, 0.5471, 0.5779],
[0.6289, 0.3980, 0.8613, 0.5977, 0.3881, 0.5231, 0.6237, 0.4799],
[0.6523, 0.4320, 0.8302, 0.2181, 0.4760, 0.2077, 0.6532, 0.5335],
[0.6019, 0.3899, 0.8802, 0.3725, 0.3655, 0.4080, 0.6073, 0.5136]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6095, 0.3970, 0.8687, 0.4767, 0.4860, 0.4879, 0.5191, 0.4940],
[0.6127, 0.4084, 0.8737, 0.4683, 0.3613, 0.3700, 0.4960, 0.5397],
[0.6129, 0.4114, 0.6950, 0.2467, 0.4050, 0.2133, 0.5362, 0.5550],
[0.6199, 0.3952, 0.8573, 0.5374, 0.4075, 0.4687, 0.5942, 0.5377],
[0.6168, 0.4111, 0.6517, 0.2875, 0.3688, 0.2817, 0.5228, 0.5837],
[0.6271, 0.4005, 0.8450, 0.6067, 0.3850, 0.4983, 0.6069, 0.4649],
[0.6268, 0.4052, 0.8175, 0.2250, 0.4688, 0.1917, 0.6375, 0.5267],
[0.6201, 0.4036, 0.8596, 0.3850, 0.3492, 0.3785, 0.5978, 0.5131]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0027903580776182935
step: 7
running loss: 0.0003986225825168991
Train Steps: 7/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6192, 0.4128, 0.8513, 0.5617, 0.4200, 0.5267, 0.5850, 0.5633],
[0.6110, 0.4047, 0.8700, 0.4483, 0.3713, 0.3967, 0.5088, 0.5517],
[0.6098, 0.3991, 0.8638, 0.4717, 0.4263, 0.4967, 0.5212, 0.5650],
[0.6357, 0.4159, 0.8788, 0.5583, 0.3638, 0.4433, 0.6488, 0.5297],
[0.6226, 0.4103, 0.8575, 0.3450, 0.4388, 0.2067, 0.5787, 0.5383],
[0.6260, 0.4214, 0.8538, 0.5500, 0.3663, 0.3767, 0.5587, 0.5983],
[0.6259, 0.4133, 0.8200, 0.2317, 0.5025, 0.1533, 0.6250, 0.4947],
[0.6179, 0.3961, 0.8347, 0.6020, 0.3887, 0.4624, 0.5714, 0.5373]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6655, 0.4275, 0.8717, 0.5391, 0.4057, 0.5384, 0.5896, 0.5467],
[0.5990, 0.3900, 0.8523, 0.4329, 0.3639, 0.4221, 0.4961, 0.5334],
[0.6059, 0.3806, 0.8612, 0.4520, 0.4181, 0.5171, 0.5301, 0.5463],
[0.6200, 0.3915, 0.8680, 0.5255, 0.3656, 0.4592, 0.6387, 0.5337],
[0.6142, 0.4028, 0.8463, 0.3289, 0.4391, 0.2495, 0.5600, 0.5419],
[0.6230, 0.4021, 0.8543, 0.5149, 0.3631, 0.4069, 0.5589, 0.5789],
[0.6494, 0.4203, 0.8158, 0.2036, 0.4982, 0.1942, 0.6319, 0.4887],
[0.6183, 0.3849, 0.8135, 0.5679, 0.3800, 0.4807, 0.5747, 0.5301]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6192, 0.4128, 0.8512, 0.5617, 0.4200, 0.5267, 0.5850, 0.5633],
[0.6110, 0.4047, 0.8700, 0.4483, 0.3713, 0.3967, 0.5088, 0.5517],
[0.6098, 0.3991, 0.8637, 0.4717, 0.4263, 0.4967, 0.5213, 0.5650],
[0.6357, 0.4159, 0.8788, 0.5583, 0.3638, 0.4433, 0.6488, 0.5297],
[0.6226, 0.4103, 0.8575, 0.3450, 0.4387, 0.2067, 0.5788, 0.5383],
[0.6260, 0.4214, 0.8537, 0.5500, 0.3663, 0.3767, 0.5587, 0.5983],
[0.6259, 0.4132, 0.8200, 0.2317, 0.5025, 0.1533, 0.6250, 0.4947],
[0.6179, 0.3961, 0.8347, 0.6020, 0.3887, 0.4624, 0.5714, 0.5373]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.003120287772617303
step: 8
running loss: 0.00039003597157716285
Train Steps: 8/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6250, 0.4103, 0.8950, 0.4400, 0.3912, 0.5650, 0.6050, 0.5133],
[0.6219, 0.4089, 0.8938, 0.4800, 0.3825, 0.4450, 0.5850, 0.5200],
[0.6292, 0.4010, 0.8988, 0.4800, 0.3638, 0.3817, 0.6357, 0.5051],
[0.6083, 0.3957, 0.8638, 0.4950, 0.4363, 0.5083, 0.5346, 0.4980],
[0.6201, 0.4065, 0.7300, 0.1933, 0.4075, 0.2533, 0.6162, 0.5483],
[0.6339, 0.4081, 0.8425, 0.5417, 0.3850, 0.4833, 0.7335, 0.5760],
[0.6229, 0.4107, 0.8137, 0.2883, 0.4750, 0.1717, 0.5813, 0.5400],
[0.6201, 0.4029, 0.8776, 0.4602, 0.3683, 0.4203, 0.5938, 0.5450]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6907, 0.4464, 0.8934, 0.4423, 0.3799, 0.5879, 0.5853, 0.5208],
[0.6341, 0.4092, 0.8970, 0.4907, 0.3774, 0.4600, 0.5645, 0.5343],
[0.6480, 0.3964, 0.8914, 0.4762, 0.3615, 0.3755, 0.6009, 0.5030],
[0.6196, 0.3916, 0.8647, 0.4987, 0.4383, 0.5247, 0.5082, 0.4973],
[0.6607, 0.4309, 0.7277, 0.1843, 0.4020, 0.2626, 0.5911, 0.5482],
[0.6550, 0.4048, 0.8476, 0.5480, 0.3676, 0.4864, 0.7078, 0.5719],
[0.6345, 0.4082, 0.8107, 0.2881, 0.4759, 0.1987, 0.5459, 0.5407],
[0.6141, 0.3883, 0.8778, 0.4642, 0.3770, 0.4266, 0.5691, 0.5419]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6250, 0.4103, 0.8950, 0.4400, 0.3913, 0.5650, 0.6050, 0.5133],
[0.6219, 0.4089, 0.8938, 0.4800, 0.3825, 0.4450, 0.5850, 0.5200],
[0.6292, 0.4010, 0.8988, 0.4800, 0.3638, 0.3817, 0.6357, 0.5051],
[0.6083, 0.3957, 0.8637, 0.4950, 0.4363, 0.5083, 0.5346, 0.4980],
[0.6201, 0.4065, 0.7300, 0.1933, 0.4075, 0.2533, 0.6162, 0.5483],
[0.6339, 0.4081, 0.8425, 0.5417, 0.3850, 0.4833, 0.7335, 0.5760],
[0.6229, 0.4107, 0.8138, 0.2883, 0.4750, 0.1717, 0.5813, 0.5400],
[0.6201, 0.4029, 0.8776, 0.4602, 0.3683, 0.4203, 0.5938, 0.5450]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0034082017227774486
step: 9
running loss: 0.0003786890803086054
Train Steps: 9/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.8300, 0.3150, 0.3588, 0.3383, 0.5208, 0.5194],
[0.6111, 0.4019, 0.8350, 0.3867, 0.3500, 0.4283, 0.5480, 0.5719],
[0.6125, 0.4035, 0.7825, 0.3100, 0.3463, 0.4900, 0.5832, 0.5637],
[0.6263, 0.4039, 0.9000, 0.4400, 0.3625, 0.4667, 0.6424, 0.4804],
[0.6175, 0.4013, 0.7734, 0.2783, 0.4475, 0.1786, 0.5790, 0.5351],
[0.6173, 0.4114, 0.7325, 0.2500, 0.4213, 0.1917, 0.5338, 0.5700],
[0.6329, 0.4055, 0.9050, 0.4783, 0.3613, 0.3917, 0.6464, 0.5019],
[0.6081, 0.3950, 0.8538, 0.4667, 0.3850, 0.4917, 0.5342, 0.4954]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.0015, -0.0031, 0.7993, 0.3112, 0.3631, 0.3143, 0.5292, 0.5382],
[ 0.6202, 0.3914, 0.8323, 0.4142, 0.3660, 0.4016, 0.5376, 0.5640],
[ 0.6413, 0.4078, 0.7725, 0.3255, 0.3465, 0.4617, 0.6007, 0.5419],
[ 0.6826, 0.4191, 0.8940, 0.4635, 0.3621, 0.4411, 0.6330, 0.4861],
[ 0.6830, 0.4369, 0.7711, 0.2781, 0.4563, 0.1491, 0.5781, 0.5318],
[ 0.6227, 0.3945, 0.7264, 0.2345, 0.4269, 0.1709, 0.5418, 0.5762],
[ 0.6921, 0.4178, 0.8874, 0.4984, 0.3737, 0.3784, 0.6353, 0.5010],
[ 0.6811, 0.4307, 0.8601, 0.4722, 0.3757, 0.4662, 0.5190, 0.4957]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.8300, 0.3150, 0.3587, 0.3383, 0.5208, 0.5194],
[0.6111, 0.4019, 0.8350, 0.3867, 0.3500, 0.4283, 0.5480, 0.5719],
[0.6125, 0.4035, 0.7825, 0.3100, 0.3462, 0.4900, 0.5832, 0.5637],
[0.6263, 0.4038, 0.9000, 0.4400, 0.3625, 0.4667, 0.6424, 0.4804],
[0.6175, 0.4013, 0.7734, 0.2783, 0.4475, 0.1786, 0.5790, 0.5351],
[0.6173, 0.4114, 0.7325, 0.2500, 0.4212, 0.1917, 0.5337, 0.5700],
[0.6329, 0.4055, 0.9050, 0.4783, 0.3613, 0.3917, 0.6464, 0.5019],
[0.6081, 0.3950, 0.8537, 0.4667, 0.3850, 0.4917, 0.5342, 0.4954]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0039045417652232572
step: 10
running loss: 0.0003904541765223257
Train Steps: 10/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395],
[0.6115, 0.4005, 0.8838, 0.3867, 0.3763, 0.4700, 0.5800, 0.5550],
[0.6296, 0.4076, 0.8400, 0.5583, 0.3700, 0.4367, 0.6876, 0.5494],
[0.6266, 0.4101, 0.8350, 0.2333, 0.3950, 0.2950, 0.6264, 0.4921],
[0.6182, 0.3998, 0.8793, 0.4191, 0.3552, 0.4285, 0.6038, 0.5312],
[0.6261, 0.4066, 0.8325, 0.2150, 0.4763, 0.2667, 0.7002, 0.5633],
[0.6201, 0.4065, 0.7300, 0.1933, 0.4075, 0.2533, 0.6162, 0.5483],
[0.6274, 0.4099, 0.8625, 0.3233, 0.4400, 0.1983, 0.5876, 0.4869]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6111, 0.3954, 0.8494, 0.5584, 0.3472, 0.3372, 0.5197, 0.5469],
[0.5739, 0.3684, 0.8690, 0.3896, 0.3697, 0.4466, 0.5364, 0.5605],
[0.6279, 0.3980, 0.8315, 0.5804, 0.3685, 0.3994, 0.6520, 0.5557],
[0.6394, 0.4043, 0.8134, 0.2342, 0.3990, 0.2662, 0.6132, 0.5075],
[0.5666, 0.3551, 0.8625, 0.4179, 0.3445, 0.4102, 0.5713, 0.5328],
[0.6321, 0.3944, 0.8275, 0.2332, 0.4824, 0.2432, 0.6758, 0.5559],
[0.6157, 0.3995, 0.7224, 0.1973, 0.4033, 0.2224, 0.5934, 0.5523],
[0.6081, 0.3950, 0.8581, 0.3306, 0.4382, 0.1855, 0.5523, 0.5056]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395],
[0.6115, 0.4005, 0.8838, 0.3867, 0.3762, 0.4700, 0.5800, 0.5550],
[0.6296, 0.4076, 0.8400, 0.5583, 0.3700, 0.4367, 0.6876, 0.5494],
[0.6266, 0.4101, 0.8350, 0.2333, 0.3950, 0.2950, 0.6264, 0.4921],
[0.6182, 0.3998, 0.8793, 0.4191, 0.3552, 0.4285, 0.6038, 0.5312],
[0.6261, 0.4066, 0.8325, 0.2150, 0.4762, 0.2667, 0.7002, 0.5633],
[0.6201, 0.4065, 0.7300, 0.1933, 0.4075, 0.2533, 0.6162, 0.5483],
[0.6274, 0.4099, 0.8625, 0.3233, 0.4400, 0.1983, 0.5876, 0.4869]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0043209217401454225
step: 11
running loss: 0.0003928110672859475
Train Steps: 11/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6250, 0.4013, 0.8525, 0.5417, 0.4037, 0.5117, 0.6325, 0.5017],
[0.6202, 0.3983, 0.8555, 0.5429, 0.3842, 0.4370, 0.5866, 0.5398],
[0.6197, 0.4091, 0.8800, 0.4783, 0.3538, 0.4767, 0.5950, 0.5550],
[0.6254, 0.4076, 0.8700, 0.3267, 0.4150, 0.3083, 0.7050, 0.5609],
[0.6222, 0.4072, 0.7164, 0.2166, 0.3738, 0.3167, 0.6100, 0.5533],
[0.6264, 0.4067, 0.9050, 0.4183, 0.3775, 0.4600, 0.6308, 0.4862],
[0.6100, 0.4016, 0.8600, 0.5067, 0.4612, 0.5233, 0.5086, 0.5519],
[0.6286, 0.4097, 0.8107, 0.2414, 0.4425, 0.2483, 0.6745, 0.5385]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6466, 0.4067, 0.8561, 0.5692, 0.3907, 0.4857, 0.6159, 0.4922],
[0.5812, 0.3606, 0.8624, 0.5676, 0.3698, 0.4190, 0.5720, 0.5218],
[0.6026, 0.3910, 0.8887, 0.4900, 0.3473, 0.4561, 0.5905, 0.5322],
[0.6874, 0.4356, 0.8931, 0.3268, 0.3932, 0.2698, 0.6987, 0.5500],
[0.6209, 0.3994, 0.7293, 0.2280, 0.3702, 0.2973, 0.6075, 0.5366],
[0.6020, 0.3824, 0.9123, 0.4212, 0.3538, 0.4350, 0.6238, 0.4767],
[0.6339, 0.4077, 0.8634, 0.5291, 0.4464, 0.4912, 0.4958, 0.5456],
[0.6225, 0.3932, 0.8367, 0.2665, 0.4396, 0.2139, 0.6829, 0.5355]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6250, 0.4013, 0.8525, 0.5417, 0.4038, 0.5117, 0.6325, 0.5017],
[0.6202, 0.3983, 0.8555, 0.5429, 0.3842, 0.4370, 0.5866, 0.5398],
[0.6197, 0.4091, 0.8800, 0.4783, 0.3537, 0.4767, 0.5950, 0.5550],
[0.6254, 0.4076, 0.8700, 0.3267, 0.4150, 0.3083, 0.7050, 0.5609],
[0.6222, 0.4072, 0.7164, 0.2166, 0.3738, 0.3167, 0.6100, 0.5533],
[0.6264, 0.4067, 0.9050, 0.4183, 0.3775, 0.4600, 0.6308, 0.4862],
[0.6100, 0.4016, 0.8600, 0.5067, 0.4613, 0.5233, 0.5086, 0.5519],
[0.6286, 0.4097, 0.8107, 0.2414, 0.4425, 0.2483, 0.6745, 0.5385]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.004716772076790221
step: 12
running loss: 0.0003930643397325184
Train Steps: 12/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6175, 0.3957, 0.8700, 0.4817, 0.4662, 0.5133, 0.5800, 0.5517],
[0.6185, 0.4080, 0.8625, 0.3483, 0.3788, 0.2650, 0.5320, 0.5272],
[0.6273, 0.4110, 0.8900, 0.3817, 0.4188, 0.2167, 0.5858, 0.4835],
[0.6048, 0.3928, 0.8538, 0.5433, 0.3875, 0.5117, 0.5266, 0.4719],
[0.6199, 0.4015, 0.8716, 0.5228, 0.3833, 0.4772, 0.5883, 0.5148],
[0.6205, 0.4081, 0.8950, 0.4017, 0.3788, 0.4700, 0.5963, 0.5667],
[ nan, nan, 0.6992, 0.2791, 0.3950, 0.2383, 0.5483, 0.5819],
[0.6163, 0.4114, 0.7650, 0.2017, 0.3763, 0.2867, 0.5631, 0.5071]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6150, 0.3924, 0.8681, 0.4778, 0.4595, 0.5068, 0.6044, 0.5595],
[0.6532, 0.4270, 0.8590, 0.3559, 0.3754, 0.2603, 0.5552, 0.5468],
[0.6754, 0.4331, 0.9025, 0.3900, 0.4097, 0.2071, 0.6262, 0.5093],
[0.6148, 0.4029, 0.8485, 0.5439, 0.3948, 0.4812, 0.5710, 0.5134],
[0.6420, 0.4042, 0.8782, 0.5306, 0.3821, 0.4582, 0.6024, 0.5224],
[0.6530, 0.4177, 0.8900, 0.3976, 0.3744, 0.4545, 0.6184, 0.5700],
[0.0528, 0.0365, 0.6978, 0.2690, 0.3843, 0.2045, 0.5725, 0.5857],
[0.6206, 0.4146, 0.7602, 0.2088, 0.3685, 0.2788, 0.6094, 0.5118]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6175, 0.3957, 0.8700, 0.4817, 0.4663, 0.5133, 0.5800, 0.5517],
[0.6186, 0.4080, 0.8625, 0.3483, 0.3787, 0.2650, 0.5320, 0.5272],
[0.6273, 0.4110, 0.8900, 0.3817, 0.4187, 0.2167, 0.5858, 0.4835],
[0.6048, 0.3928, 0.8537, 0.5433, 0.3875, 0.5117, 0.5266, 0.4719],
[0.6199, 0.4015, 0.8716, 0.5228, 0.3833, 0.4772, 0.5883, 0.5148],
[0.6205, 0.4081, 0.8950, 0.4017, 0.3787, 0.4700, 0.5962, 0.5667],
[0.0000, 0.0000, 0.6992, 0.2791, 0.3950, 0.2383, 0.5483, 0.5819],
[0.6163, 0.4114, 0.7650, 0.2017, 0.3762, 0.2867, 0.5631, 0.5071]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.00511384145647753
step: 13
running loss: 0.0003933724197290408
Train Steps: 13/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6286, 0.4078, 0.8063, 0.2267, 0.4788, 0.1533, 0.5953, 0.4913],
[0.6255, 0.4017, 0.8688, 0.3217, 0.3638, 0.3550, 0.6344, 0.4901],
[0.6043, 0.4022, 0.6887, 0.1983, 0.3775, 0.2483, 0.5480, 0.5136],
[0.6199, 0.4102, 0.8950, 0.4417, 0.4012, 0.5367, 0.6112, 0.5967],
[0.6267, 0.4094, 0.8712, 0.3083, 0.4400, 0.2267, 0.6250, 0.5200],
[ nan, nan, 0.6935, 0.1930, 0.4150, 0.2250, 0.5450, 0.5650],
[0.6193, 0.3930, 0.8949, 0.4437, 0.3852, 0.5435, 0.6263, 0.5263],
[0.6109, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6139, 0.3975, 0.7991, 0.2557, 0.4762, 0.1688, 0.6188, 0.5154],
[ 0.6325, 0.4076, 0.8653, 0.3249, 0.3729, 0.3577, 0.6646, 0.5236],
[ 0.5999, 0.3938, 0.6965, 0.2217, 0.3897, 0.2614, 0.5847, 0.5240],
[ 0.6546, 0.4266, 0.9047, 0.4479, 0.4026, 0.5428, 0.6200, 0.5899],
[ 0.6073, 0.4046, 0.8692, 0.3171, 0.4470, 0.2431, 0.6499, 0.5239],
[-0.0289, -0.0041, 0.7068, 0.2008, 0.4259, 0.2260, 0.5732, 0.5807],
[ 0.5991, 0.3933, 0.8810, 0.4519, 0.3926, 0.5543, 0.6291, 0.5463],
[ 0.6007, 0.4034, 0.8795, 0.4790, 0.3675, 0.4355, 0.5861, 0.5176]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6286, 0.4078, 0.8062, 0.2267, 0.4787, 0.1533, 0.5953, 0.4913],
[0.6255, 0.4017, 0.8687, 0.3217, 0.3638, 0.3550, 0.6344, 0.4901],
[0.6043, 0.4022, 0.6888, 0.1983, 0.3775, 0.2483, 0.5480, 0.5136],
[0.6199, 0.4102, 0.8950, 0.4417, 0.4013, 0.5367, 0.6112, 0.5967],
[0.6267, 0.4094, 0.8712, 0.3083, 0.4400, 0.2267, 0.6250, 0.5200],
[0.0000, 0.0000, 0.6935, 0.1930, 0.4150, 0.2250, 0.5450, 0.5650],
[0.6193, 0.3930, 0.8949, 0.4437, 0.3852, 0.5435, 0.6263, 0.5263],
[0.6108, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.005352006017346866
step: 14
running loss: 0.00038228614409620477
Train Steps: 14/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6268, 0.4102, 0.8938, 0.3667, 0.4025, 0.2833, 0.6275, 0.5183],
[0.6202, 0.3983, 0.8555, 0.5429, 0.3842, 0.4370, 0.5866, 0.5398],
[0.6172, 0.4055, 0.8175, 0.2650, 0.3550, 0.3683, 0.5787, 0.5550],
[0.6026, 0.3979, 0.8550, 0.4233, 0.3613, 0.5233, 0.5582, 0.4967],
[0.6329, 0.4196, 0.9238, 0.4583, 0.4263, 0.2933, 0.7343, 0.5748],
[0.6364, 0.4154, 0.8938, 0.3717, 0.4500, 0.2583, 0.6448, 0.5285],
[0.6246, 0.4008, 0.8757, 0.5088, 0.4101, 0.5392, 0.6644, 0.5133],
[ nan, nan, 0.8938, 0.2850, 0.4662, 0.3117, 0.7406, 0.5528]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6304, 0.4434, 0.8698, 0.3517, 0.3991, 0.2967, 0.6378, 0.5092],
[0.6057, 0.4039, 0.8408, 0.5369, 0.3770, 0.4544, 0.5819, 0.5145],
[0.6102, 0.4243, 0.8122, 0.2548, 0.3479, 0.3743, 0.5690, 0.5382],
[0.6166, 0.4169, 0.8540, 0.4114, 0.3589, 0.5225, 0.5643, 0.5030],
[0.5879, 0.4055, 0.9096, 0.4521, 0.4069, 0.2987, 0.7183, 0.5450],
[0.5678, 0.3852, 0.8754, 0.3586, 0.4418, 0.2730, 0.6236, 0.5102],
[0.6362, 0.4257, 0.8712, 0.5049, 0.3944, 0.5445, 0.6412, 0.5012],
[0.0803, 0.0648, 0.8858, 0.2733, 0.4625, 0.3084, 0.7475, 0.5582]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6268, 0.4102, 0.8938, 0.3667, 0.4025, 0.2833, 0.6275, 0.5183],
[0.6202, 0.3983, 0.8555, 0.5429, 0.3842, 0.4370, 0.5866, 0.5398],
[0.6172, 0.4055, 0.8175, 0.2650, 0.3550, 0.3683, 0.5788, 0.5550],
[0.6026, 0.3979, 0.8550, 0.4233, 0.3613, 0.5233, 0.5582, 0.4967],
[0.6329, 0.4196, 0.9237, 0.4583, 0.4263, 0.2933, 0.7343, 0.5748],
[0.6364, 0.4154, 0.8938, 0.3717, 0.4500, 0.2583, 0.6448, 0.5285],
[0.6246, 0.4008, 0.8757, 0.5088, 0.4101, 0.5392, 0.6644, 0.5133],
[0.0000, 0.0000, 0.8938, 0.2850, 0.4663, 0.3117, 0.7406, 0.5528]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.005812907431391068
step: 15
running loss: 0.00038752716209273786
Train Steps: 15/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.6488, 0.1817, 0.4325, 0.1867, 0.5475, 0.5733],
[0.6201, 0.4065, 0.7300, 0.1933, 0.4075, 0.2533, 0.6162, 0.5483],
[0.6233, 0.4091, 0.8100, 0.2950, 0.3563, 0.3883, 0.6013, 0.5200],
[0.6250, 0.3993, 0.9138, 0.4333, 0.3763, 0.5217, 0.6995, 0.5320],
[0.6130, 0.4072, 0.8550, 0.4567, 0.3638, 0.3667, 0.5290, 0.5892],
[0.6173, 0.4013, 0.8713, 0.4640, 0.4800, 0.5700, 0.6025, 0.5600],
[0.6251, 0.4163, 0.8662, 0.4467, 0.3625, 0.3567, 0.6038, 0.5533],
[0.6364, 0.4144, 0.8625, 0.3083, 0.4913, 0.2000, 0.6448, 0.5274]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.0263, 0.0256, 0.6932, 0.1956, 0.4421, 0.2121, 0.5592, 0.5668],
[0.5857, 0.3967, 0.7539, 0.1916, 0.4034, 0.2748, 0.6176, 0.5288],
[0.6044, 0.4116, 0.8246, 0.3053, 0.3672, 0.4163, 0.6139, 0.5282],
[0.6559, 0.4351, 0.9174, 0.4294, 0.3850, 0.5451, 0.6995, 0.5243],
[0.6037, 0.4098, 0.8734, 0.4678, 0.3612, 0.3758, 0.5414, 0.5704],
[0.5970, 0.4016, 0.8845, 0.4692, 0.4716, 0.5759, 0.6031, 0.5291],
[0.6008, 0.4041, 0.8873, 0.4476, 0.3542, 0.3747, 0.5981, 0.5399],
[0.6103, 0.4158, 0.8827, 0.3146, 0.4869, 0.2184, 0.6485, 0.5120]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.6488, 0.1817, 0.4325, 0.1867, 0.5475, 0.5733],
[0.6201, 0.4065, 0.7300, 0.1933, 0.4075, 0.2533, 0.6162, 0.5483],
[0.6233, 0.4091, 0.8100, 0.2950, 0.3562, 0.3883, 0.6012, 0.5200],
[0.6250, 0.3993, 0.9137, 0.4333, 0.3762, 0.5217, 0.6995, 0.5320],
[0.6130, 0.4072, 0.8550, 0.4567, 0.3638, 0.3667, 0.5290, 0.5892],
[0.6173, 0.4013, 0.8713, 0.4640, 0.4800, 0.5700, 0.6025, 0.5600],
[0.6252, 0.4162, 0.8662, 0.4467, 0.3625, 0.3567, 0.6037, 0.5533],
[0.6364, 0.4144, 0.8625, 0.3083, 0.4913, 0.2000, 0.6448, 0.5274]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.006098556055803783
step: 16
running loss: 0.00038115975348773645
Train Steps: 16/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6176, 0.4030, 0.8850, 0.4850, 0.3688, 0.4050, 0.5312, 0.5783],
[0.6075, 0.4000, 0.8513, 0.5183, 0.4510, 0.5329, 0.5180, 0.5280],
[0.6276, 0.4095, 0.8237, 0.2250, 0.4662, 0.1783, 0.6171, 0.4869],
[0.6143, 0.4040, 0.8237, 0.3333, 0.4075, 0.2117, 0.5137, 0.4973],
[0.6172, 0.4055, 0.8175, 0.2650, 0.3550, 0.3683, 0.5787, 0.5550],
[0.6115, 0.3998, 0.7063, 0.2383, 0.4037, 0.1950, 0.5320, 0.4993],
[0.6264, 0.4049, 0.8988, 0.4633, 0.3813, 0.4983, 0.6326, 0.4843],
[0.6240, 0.4217, 0.8150, 0.3133, 0.4425, 0.2650, 0.5650, 0.5817]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5833, 0.3842, 0.8821, 0.4733, 0.3704, 0.4449, 0.5607, 0.5791],
[0.5857, 0.3952, 0.8461, 0.5062, 0.4464, 0.5468, 0.5452, 0.5381],
[0.5606, 0.3757, 0.8263, 0.1889, 0.4795, 0.2077, 0.6426, 0.4731],
[0.5283, 0.3615, 0.8104, 0.3245, 0.4075, 0.2385, 0.5421, 0.5131],
[0.5866, 0.3970, 0.8141, 0.2517, 0.3591, 0.3805, 0.5958, 0.5653],
[0.5578, 0.3751, 0.7063, 0.2147, 0.4096, 0.2207, 0.5562, 0.5014],
[0.6209, 0.3995, 0.8981, 0.4447, 0.3939, 0.5215, 0.6618, 0.4925],
[0.5742, 0.4028, 0.8075, 0.3001, 0.4348, 0.2643, 0.5919, 0.5839]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6176, 0.4030, 0.8850, 0.4850, 0.3688, 0.4050, 0.5312, 0.5783],
[0.6075, 0.4000, 0.8512, 0.5183, 0.4510, 0.5329, 0.5180, 0.5280],
[0.6276, 0.4095, 0.8238, 0.2250, 0.4663, 0.1783, 0.6171, 0.4869],
[0.6143, 0.4040, 0.8238, 0.3333, 0.4075, 0.2117, 0.5137, 0.4973],
[0.6172, 0.4055, 0.8175, 0.2650, 0.3550, 0.3683, 0.5788, 0.5550],
[0.6115, 0.3998, 0.7063, 0.2383, 0.4038, 0.1950, 0.5320, 0.4993],
[0.6264, 0.4049, 0.8988, 0.4633, 0.3812, 0.4983, 0.6326, 0.4843],
[0.6240, 0.4217, 0.8150, 0.3133, 0.4425, 0.2650, 0.5650, 0.5817]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.00670615334820468
step: 17
running loss: 0.00039447960871792236
Train Steps: 17/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6075, 0.4007, 0.8275, 0.4917, 0.4050, 0.5100, 0.5167, 0.5280],
[0.6186, 0.3967, 0.7337, 0.1992, 0.4120, 0.2508, 0.6105, 0.5395],
[0.6282, 0.4029, 0.8988, 0.3000, 0.4250, 0.4183, 0.7042, 0.5575],
[0.6111, 0.3995, 0.8788, 0.4567, 0.3813, 0.4833, 0.5450, 0.5700],
[0.6271, 0.4081, 0.9081, 0.4894, 0.3700, 0.4283, 0.6661, 0.5274],
[0.6311, 0.3998, 0.7975, 0.5767, 0.3838, 0.4850, 0.7327, 0.5343],
[0.6289, 0.4024, 0.9088, 0.4567, 0.3937, 0.5633, 0.7058, 0.5609],
[0.6250, 0.4146, 0.8838, 0.3933, 0.3588, 0.4283, 0.6162, 0.5367]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6088, 0.4146, 0.8243, 0.4837, 0.4125, 0.5085, 0.4962, 0.5246],
[0.5454, 0.3526, 0.7500, 0.1850, 0.4105, 0.2336, 0.5899, 0.5240],
[0.6472, 0.4219, 0.8957, 0.2913, 0.4292, 0.4209, 0.6909, 0.5476],
[0.6005, 0.4060, 0.8789, 0.4457, 0.3934, 0.4989, 0.5180, 0.5573],
[0.6391, 0.4281, 0.9070, 0.4751, 0.3749, 0.4296, 0.6496, 0.5202],
[0.6069, 0.3982, 0.7994, 0.5490, 0.3786, 0.4836, 0.7198, 0.5246],
[0.5879, 0.3833, 0.8961, 0.4360, 0.4143, 0.5762, 0.6696, 0.5471],
[0.6208, 0.4172, 0.8873, 0.3753, 0.3730, 0.4114, 0.5894, 0.5254]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6075, 0.4006, 0.8275, 0.4917, 0.4050, 0.5100, 0.5167, 0.5280],
[0.6186, 0.3967, 0.7337, 0.1992, 0.4120, 0.2508, 0.6105, 0.5395],
[0.6282, 0.4029, 0.8988, 0.3000, 0.4250, 0.4183, 0.7042, 0.5575],
[0.6111, 0.3995, 0.8788, 0.4567, 0.3812, 0.4833, 0.5450, 0.5700],
[0.6271, 0.4081, 0.9081, 0.4894, 0.3700, 0.4283, 0.6661, 0.5274],
[0.6311, 0.3998, 0.7975, 0.5767, 0.3837, 0.4850, 0.7327, 0.5343],
[0.6289, 0.4024, 0.9087, 0.4567, 0.3938, 0.5633, 0.7058, 0.5609],
[0.6250, 0.4146, 0.8838, 0.3933, 0.3587, 0.4283, 0.6162, 0.5367]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.007039182659354992
step: 18
running loss: 0.00039106570329749957
Train Steps: 18/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6286, 0.4274, 0.8500, 0.4500, 0.4525, 0.2583, 0.5440, 0.6209],
[0.6228, 0.4119, 0.7938, 0.2233, 0.4674, 0.1773, 0.6188, 0.5433],
[0.6198, 0.4101, 0.8838, 0.5283, 0.3763, 0.5267, 0.5913, 0.5567],
[0.6198, 0.3997, 0.8582, 0.5361, 0.4117, 0.5016, 0.5942, 0.5134],
[0.6154, 0.4048, 0.7100, 0.2067, 0.4338, 0.1667, 0.5413, 0.5220],
[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459],
[0.6357, 0.4118, 0.8400, 0.2500, 0.5413, 0.1633, 0.6725, 0.5586],
[ nan, nan, 0.7412, 0.2200, 0.4450, 0.1517, 0.5312, 0.4983]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.5953, 0.3860, 0.8574, 0.4379, 0.4426, 0.2795, 0.5448, 0.6258],
[ 0.6346, 0.3960, 0.8043, 0.1938, 0.4684, 0.1988, 0.6204, 0.5387],
[ 0.6455, 0.4134, 0.8872, 0.5100, 0.3674, 0.5438, 0.5928, 0.5578],
[ 0.6155, 0.3911, 0.8685, 0.5148, 0.4183, 0.5489, 0.5997, 0.5189],
[ 0.5396, 0.3379, 0.7125, 0.1986, 0.4258, 0.1941, 0.5334, 0.5251],
[ 0.6262, 0.3989, 0.8644, 0.2575, 0.4861, 0.2410, 0.6567, 0.5455],
[ 0.6301, 0.3905, 0.8583, 0.2206, 0.5306, 0.2024, 0.6591, 0.5488],
[ 0.0209, -0.0096, 0.7140, 0.2022, 0.4335, 0.1930, 0.5282, 0.5127]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6286, 0.4274, 0.8500, 0.4500, 0.4525, 0.2583, 0.5440, 0.6209],
[0.6228, 0.4119, 0.7937, 0.2233, 0.4674, 0.1773, 0.6187, 0.5433],
[0.6198, 0.4101, 0.8838, 0.5283, 0.3762, 0.5267, 0.5913, 0.5567],
[0.6198, 0.3997, 0.8582, 0.5361, 0.4117, 0.5016, 0.5942, 0.5134],
[0.6154, 0.4048, 0.7100, 0.2067, 0.4338, 0.1667, 0.5413, 0.5220],
[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459],
[0.6357, 0.4118, 0.8400, 0.2500, 0.5412, 0.1633, 0.6725, 0.5586],
[0.0000, 0.0000, 0.7412, 0.2200, 0.4450, 0.1517, 0.5312, 0.4983]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.00753981365414802
step: 19
running loss: 0.00039683229758673787
Train Steps: 19/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6108, 0.4011, 0.8037, 0.3400, 0.3700, 0.2933, 0.5658, 0.5617],
[0.6200, 0.4059, 0.8700, 0.4900, 0.4163, 0.5000, 0.6162, 0.5467],
[0.6097, 0.3988, 0.8650, 0.5250, 0.4213, 0.5200, 0.5675, 0.5050],
[0.6236, 0.4084, 0.7738, 0.2133, 0.3663, 0.3233, 0.5813, 0.5567],
[0.6142, 0.4127, 0.7575, 0.3067, 0.3438, 0.4383, 0.5778, 0.5207],
[0.6246, 0.4126, 0.8850, 0.4833, 0.4200, 0.5350, 0.6112, 0.5250],
[0.6214, 0.4116, 0.7750, 0.2317, 0.4487, 0.1883, 0.6200, 0.5400],
[0.6109, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6439, 0.4007, 0.8235, 0.3386, 0.3773, 0.2824, 0.5642, 0.5577],
[0.6291, 0.3961, 0.8844, 0.4833, 0.4212, 0.4785, 0.6076, 0.5477],
[0.6298, 0.3989, 0.8760, 0.5110, 0.4461, 0.4928, 0.5428, 0.5114],
[0.6189, 0.3918, 0.7877, 0.2282, 0.3809, 0.2835, 0.5803, 0.5645],
[0.6044, 0.4022, 0.7587, 0.2884, 0.3577, 0.4086, 0.5835, 0.5339],
[0.6266, 0.3994, 0.8935, 0.4803, 0.4208, 0.5055, 0.5916, 0.5261],
[0.6269, 0.3987, 0.7843, 0.2327, 0.4596, 0.1697, 0.6159, 0.5375],
[0.6304, 0.4008, 0.8788, 0.4662, 0.3646, 0.4020, 0.5589, 0.5101]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6108, 0.4011, 0.8037, 0.3400, 0.3700, 0.2933, 0.5658, 0.5617],
[0.6199, 0.4059, 0.8700, 0.4900, 0.4162, 0.5000, 0.6162, 0.5467],
[0.6097, 0.3988, 0.8650, 0.5250, 0.4212, 0.5200, 0.5675, 0.5050],
[0.6236, 0.4084, 0.7738, 0.2133, 0.3663, 0.3233, 0.5813, 0.5567],
[0.6142, 0.4127, 0.7575, 0.3067, 0.3438, 0.4383, 0.5778, 0.5207],
[0.6246, 0.4126, 0.8850, 0.4833, 0.4200, 0.5350, 0.6112, 0.5250],
[0.6214, 0.4116, 0.7750, 0.2317, 0.4487, 0.1883, 0.6200, 0.5400],
[0.6108, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.007740936329355463
step: 20
running loss: 0.00038704681646777316
Train Steps: 20/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6170, 0.4102, 0.7468, 0.3695, 0.3463, 0.3767, 0.5238, 0.5823],
[0.6299, 0.4008, 0.8450, 0.5350, 0.4213, 0.5000, 0.6350, 0.5100],
[0.6284, 0.4029, 0.8838, 0.3783, 0.3975, 0.2850, 0.6335, 0.5090],
[ nan, nan, 0.7625, 0.2433, 0.3713, 0.2867, 0.5235, 0.5220],
[0.6278, 0.4253, 0.8875, 0.5017, 0.4113, 0.2750, 0.5413, 0.6196],
[0.6198, 0.4130, 0.8762, 0.4117, 0.3650, 0.4900, 0.5707, 0.5103],
[0.6182, 0.3967, 0.8263, 0.3065, 0.3526, 0.4161, 0.6192, 0.5290],
[ nan, nan, 0.8900, 0.3217, 0.5038, 0.2233, 0.6694, 0.5609]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6662, 0.4223, 0.7406, 0.3587, 0.3473, 0.3636, 0.5362, 0.5764],
[ 0.6988, 0.4409, 0.8367, 0.5339, 0.4200, 0.4791, 0.6176, 0.5213],
[ 0.6454, 0.4078, 0.8821, 0.3713, 0.4065, 0.2698, 0.6423, 0.5060],
[ 0.0193, -0.0011, 0.7563, 0.2482, 0.3874, 0.2615, 0.5023, 0.5327],
[ 0.6599, 0.4391, 0.8735, 0.4986, 0.4344, 0.2519, 0.5618, 0.6114],
[ 0.6724, 0.4471, 0.8753, 0.4173, 0.3714, 0.4785, 0.5753, 0.5135],
[ 0.6454, 0.4219, 0.8223, 0.3016, 0.3528, 0.3894, 0.6167, 0.5270],
[ 0.1428, 0.0750, 0.8914, 0.3256, 0.5149, 0.1905, 0.6792, 0.5704]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6170, 0.4102, 0.7468, 0.3695, 0.3462, 0.3767, 0.5238, 0.5823],
[0.6299, 0.4008, 0.8450, 0.5350, 0.4212, 0.5000, 0.6350, 0.5100],
[0.6284, 0.4029, 0.8838, 0.3783, 0.3975, 0.2850, 0.6335, 0.5090],
[0.0000, 0.0000, 0.7625, 0.2433, 0.3713, 0.2867, 0.5235, 0.5220],
[0.6278, 0.4253, 0.8875, 0.5017, 0.4112, 0.2750, 0.5413, 0.6196],
[0.6198, 0.4130, 0.8763, 0.4117, 0.3650, 0.4900, 0.5707, 0.5103],
[0.6182, 0.3967, 0.8263, 0.3065, 0.3526, 0.4161, 0.6192, 0.5290],
[0.0000, 0.0000, 0.8900, 0.3217, 0.5038, 0.2233, 0.6694, 0.5609]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.008517837704857811
step: 21
running loss: 0.0004056113192789434
Train Steps: 21/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6038, 0.3946, 0.8413, 0.4883, 0.3563, 0.4550, 0.5266, 0.4693],
[0.6260, 0.4133, 0.8800, 0.5117, 0.3713, 0.3283, 0.6223, 0.4967],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3513, 0.4050, 0.6112, 0.5500],
[0.6272, 0.4045, 0.8538, 0.5900, 0.3750, 0.4417, 0.5989, 0.4649],
[0.6273, 0.4110, 0.8900, 0.3817, 0.4188, 0.2167, 0.5858, 0.4835],
[0.6196, 0.4090, 0.8450, 0.3900, 0.3575, 0.3933, 0.5975, 0.5583],
[0.6245, 0.4100, 0.7762, 0.2583, 0.4963, 0.1517, 0.5875, 0.5417],
[0.6286, 0.4274, 0.8500, 0.4500, 0.4525, 0.2583, 0.5440, 0.6209]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5720, 0.3776, 0.8345, 0.4755, 0.3489, 0.4654, 0.5330, 0.5079],
[0.5836, 0.3819, 0.8806, 0.5104, 0.3676, 0.3222, 0.6156, 0.5192],
[0.6031, 0.3888, 0.7692, 0.2578, 0.3459, 0.3895, 0.6086, 0.5580],
[0.6142, 0.4031, 0.8418, 0.5832, 0.3648, 0.4312, 0.6062, 0.4846],
[0.6351, 0.4040, 0.8955, 0.3888, 0.4027, 0.2019, 0.5870, 0.4993],
[0.5938, 0.3881, 0.8417, 0.3796, 0.3461, 0.3908, 0.5894, 0.5815],
[0.5953, 0.3816, 0.7752, 0.2554, 0.4761, 0.1240, 0.5810, 0.5446],
[0.5647, 0.3757, 0.8465, 0.4529, 0.4370, 0.2333, 0.5333, 0.6345]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6038, 0.3946, 0.8413, 0.4883, 0.3562, 0.4550, 0.5266, 0.4693],
[0.6260, 0.4133, 0.8800, 0.5117, 0.3713, 0.3283, 0.6223, 0.4967],
[0.6197, 0.4051, 0.7812, 0.2650, 0.3512, 0.4050, 0.6112, 0.5500],
[0.6271, 0.4045, 0.8537, 0.5900, 0.3750, 0.4417, 0.5989, 0.4649],
[0.6273, 0.4110, 0.8900, 0.3817, 0.4187, 0.2167, 0.5858, 0.4835],
[0.6196, 0.4090, 0.8450, 0.3900, 0.3575, 0.3933, 0.5975, 0.5583],
[0.6245, 0.4100, 0.7763, 0.2583, 0.4963, 0.1517, 0.5875, 0.5417],
[0.6286, 0.4274, 0.8500, 0.4500, 0.4525, 0.2583, 0.5440, 0.6209]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.008867989556165412
step: 22
running loss: 0.0004030904343711551
Train Steps: 22/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6257, 0.4060, 0.8300, 0.2333, 0.4688, 0.2583, 0.7050, 0.5633],
[0.6176, 0.4030, 0.8850, 0.4850, 0.3688, 0.4050, 0.5312, 0.5783],
[0.6200, 0.4112, 0.8862, 0.4100, 0.3638, 0.4917, 0.6088, 0.6050],
[0.6296, 0.4045, 0.9138, 0.4100, 0.4232, 0.4242, 0.7422, 0.5297],
[0.6273, 0.4110, 0.8900, 0.3817, 0.4188, 0.2167, 0.5858, 0.4835],
[0.6219, 0.4114, 0.8175, 0.2817, 0.3925, 0.2783, 0.5900, 0.5350],
[0.6277, 0.4118, 0.8988, 0.3833, 0.3950, 0.2650, 0.6290, 0.4938],
[0.6254, 0.4076, 0.8700, 0.3267, 0.4150, 0.3083, 0.7050, 0.5609]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6024, 0.3981, 0.8128, 0.2590, 0.4556, 0.2491, 0.6595, 0.5584],
[0.5549, 0.3711, 0.8749, 0.5209, 0.3631, 0.4099, 0.4960, 0.5748],
[0.5520, 0.3803, 0.8692, 0.4278, 0.3688, 0.4868, 0.5845, 0.5944],
[0.6277, 0.4208, 0.8766, 0.4481, 0.3989, 0.4240, 0.6891, 0.5475],
[0.6073, 0.4031, 0.8811, 0.4218, 0.4144, 0.2082, 0.5623, 0.4811],
[0.5931, 0.3978, 0.7811, 0.3136, 0.3934, 0.2683, 0.5637, 0.5376],
[0.6119, 0.4190, 0.8744, 0.4121, 0.3878, 0.2531, 0.6042, 0.5076],
[0.5991, 0.3918, 0.8556, 0.3521, 0.4053, 0.2951, 0.6678, 0.5565]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6257, 0.4060, 0.8300, 0.2333, 0.4688, 0.2583, 0.7050, 0.5633],
[0.6176, 0.4030, 0.8850, 0.4850, 0.3688, 0.4050, 0.5312, 0.5783],
[0.6200, 0.4112, 0.8863, 0.4100, 0.3638, 0.4917, 0.6087, 0.6050],
[0.6296, 0.4045, 0.9137, 0.4100, 0.4232, 0.4242, 0.7422, 0.5297],
[0.6273, 0.4110, 0.8900, 0.3817, 0.4187, 0.2167, 0.5858, 0.4835],
[0.6219, 0.4114, 0.8175, 0.2817, 0.3925, 0.2783, 0.5900, 0.5350],
[0.6277, 0.4117, 0.8988, 0.3833, 0.3950, 0.2650, 0.6290, 0.4938],
[0.6254, 0.4076, 0.8700, 0.3267, 0.4150, 0.3083, 0.7050, 0.5609]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.009468808741075918
step: 23
running loss: 0.00041168733656851816
Train Steps: 23/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6268, 0.4052, 0.8175, 0.2250, 0.4688, 0.1917, 0.6375, 0.5267],
[0.6127, 0.4066, 0.8550, 0.5567, 0.4662, 0.5141, 0.5070, 0.5412],
[0.6128, 0.4084, 0.8738, 0.4683, 0.3613, 0.3700, 0.4960, 0.5397],
[0.6101, 0.3977, 0.8550, 0.5667, 0.3862, 0.4417, 0.5128, 0.4869],
[0.6162, 0.3949, 0.8838, 0.4517, 0.4250, 0.5183, 0.5837, 0.5500],
[0.6087, 0.3951, 0.8387, 0.5833, 0.4188, 0.4933, 0.5146, 0.4830],
[0.6250, 0.3961, 0.8672, 0.4929, 0.4199, 0.4972, 0.6312, 0.5301],
[0.6267, 0.4094, 0.8712, 0.3083, 0.4400, 0.2267, 0.6250, 0.5200]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6148, 0.4041, 0.8155, 0.2686, 0.4448, 0.1657, 0.6586, 0.5228],
[0.6045, 0.4073, 0.8558, 0.5662, 0.4406, 0.4801, 0.5450, 0.5344],
[0.6265, 0.4334, 0.8728, 0.4929, 0.3422, 0.3535, 0.5344, 0.5387],
[0.6185, 0.4159, 0.8433, 0.5764, 0.3751, 0.4169, 0.5593, 0.4895],
[0.5972, 0.3902, 0.8796, 0.4573, 0.4146, 0.5011, 0.6148, 0.5498],
[0.6242, 0.4118, 0.8383, 0.6012, 0.3855, 0.4754, 0.5471, 0.5078],
[0.6271, 0.4017, 0.8617, 0.5176, 0.3983, 0.4823, 0.6515, 0.5281],
[0.6338, 0.4183, 0.8594, 0.3378, 0.4281, 0.2242, 0.6443, 0.5128]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6268, 0.4052, 0.8175, 0.2250, 0.4688, 0.1917, 0.6375, 0.5267],
[0.6127, 0.4066, 0.8550, 0.5567, 0.4662, 0.5141, 0.5070, 0.5412],
[0.6127, 0.4084, 0.8737, 0.4683, 0.3613, 0.3700, 0.4960, 0.5397],
[0.6101, 0.3977, 0.8550, 0.5667, 0.3862, 0.4417, 0.5128, 0.4869],
[0.6162, 0.3949, 0.8838, 0.4517, 0.4250, 0.5183, 0.5838, 0.5500],
[0.6087, 0.3951, 0.8388, 0.5833, 0.4187, 0.4933, 0.5146, 0.4830],
[0.6250, 0.3961, 0.8672, 0.4929, 0.4199, 0.4972, 0.6312, 0.5301],
[0.6267, 0.4094, 0.8712, 0.3083, 0.4400, 0.2267, 0.6250, 0.5200]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.00983630126575008
step: 24
running loss: 0.00040984588607292
Train Steps: 24/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6168, 0.4055, 0.7575, 0.2950, 0.4050, 0.2717, 0.5938, 0.6167],
[0.6357, 0.4097, 0.9038, 0.3883, 0.4213, 0.2950, 0.6686, 0.5390],
[0.6299, 0.4303, 0.7963, 0.3933, 0.4850, 0.2283, 0.5480, 0.6222],
[0.6329, 0.4175, 0.8550, 0.2333, 0.5425, 0.2250, 0.7398, 0.5609],
[0.6182, 0.3982, 0.7541, 0.2379, 0.3959, 0.2792, 0.6079, 0.5389],
[0.6277, 0.4013, 0.8888, 0.4767, 0.3600, 0.3567, 0.6148, 0.4672],
[0.6100, 0.4071, 0.7601, 0.3444, 0.3400, 0.4117, 0.5625, 0.5617],
[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5478, 0.3742, 0.7595, 0.3074, 0.3959, 0.2678, 0.5664, 0.5896],
[0.5971, 0.4027, 0.8927, 0.3894, 0.4067, 0.2946, 0.6613, 0.5152],
[0.6388, 0.4374, 0.8103, 0.4226, 0.4771, 0.2424, 0.5317, 0.6015],
[0.6420, 0.4268, 0.8663, 0.2420, 0.5460, 0.2147, 0.7460, 0.5467],
[0.5977, 0.3995, 0.7534, 0.2410, 0.3814, 0.2896, 0.6142, 0.5233],
[0.6387, 0.4289, 0.8900, 0.4843, 0.3351, 0.3626, 0.6269, 0.4801],
[0.5766, 0.3897, 0.7768, 0.3512, 0.3272, 0.4412, 0.5664, 0.5261],
[0.5779, 0.3848, 0.8936, 0.4680, 0.4346, 0.6008, 0.6111, 0.5183]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6168, 0.4055, 0.7575, 0.2950, 0.4050, 0.2717, 0.5938, 0.6167],
[0.6357, 0.4097, 0.9038, 0.3883, 0.4212, 0.2950, 0.6686, 0.5390],
[0.6299, 0.4303, 0.7962, 0.3933, 0.4850, 0.2283, 0.5480, 0.6222],
[0.6329, 0.4175, 0.8550, 0.2333, 0.5425, 0.2250, 0.7398, 0.5609],
[0.6182, 0.3982, 0.7541, 0.2379, 0.3959, 0.2792, 0.6079, 0.5389],
[0.6277, 0.4013, 0.8888, 0.4767, 0.3600, 0.3567, 0.6148, 0.4672],
[0.6100, 0.4071, 0.7601, 0.3444, 0.3400, 0.4117, 0.5625, 0.5617],
[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.010191787354415283
step: 25
running loss: 0.00040767149417661133
Train Steps: 25/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6350, 0.4144, 0.9250, 0.4100, 0.4125, 0.3750, 0.7129, 0.5945],
[0.6277, 0.4118, 0.8988, 0.3833, 0.3950, 0.2650, 0.6290, 0.4938],
[0.6339, 0.4159, 0.8400, 0.5617, 0.3825, 0.4150, 0.7343, 0.5748],
[0.6224, 0.3964, 0.8225, 0.5717, 0.4150, 0.4617, 0.5775, 0.5267],
[0.6138, 0.4101, 0.8800, 0.5083, 0.4637, 0.5950, 0.5587, 0.5077],
[0.6157, 0.4102, 0.8513, 0.3817, 0.3613, 0.3667, 0.5096, 0.5890],
[0.6332, 0.4128, 0.9200, 0.3517, 0.4400, 0.3833, 0.7461, 0.5494],
[0.6138, 0.4054, 0.8750, 0.4750, 0.4363, 0.5017, 0.5086, 0.5822]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6597, 0.4380, 0.9125, 0.4130, 0.4238, 0.3909, 0.7084, 0.5772],
[0.6539, 0.4436, 0.8975, 0.3660, 0.3861, 0.2707, 0.6218, 0.4967],
[0.6279, 0.4259, 0.8352, 0.5556, 0.3844, 0.4193, 0.7031, 0.5480],
[0.6050, 0.4060, 0.8342, 0.5771, 0.4128, 0.4695, 0.5517, 0.5103],
[0.5663, 0.3743, 0.8819, 0.5145, 0.4564, 0.5949, 0.5561, 0.5101],
[0.6380, 0.4306, 0.8561, 0.3709, 0.3507, 0.3565, 0.5027, 0.5586],
[0.6158, 0.4169, 0.9179, 0.3553, 0.4339, 0.3942, 0.7244, 0.5386],
[0.6019, 0.4118, 0.8663, 0.4772, 0.4382, 0.4870, 0.5078, 0.5601]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6350, 0.4144, 0.9250, 0.4100, 0.4125, 0.3750, 0.7129, 0.5945],
[0.6277, 0.4117, 0.8988, 0.3833, 0.3950, 0.2650, 0.6290, 0.4938],
[0.6339, 0.4159, 0.8400, 0.5617, 0.3825, 0.4150, 0.7343, 0.5748],
[0.6224, 0.3964, 0.8225, 0.5717, 0.4150, 0.4617, 0.5775, 0.5267],
[0.6138, 0.4101, 0.8800, 0.5083, 0.4638, 0.5950, 0.5587, 0.5077],
[0.6157, 0.4102, 0.8512, 0.3817, 0.3613, 0.3667, 0.5096, 0.5890],
[0.6332, 0.4128, 0.9200, 0.3517, 0.4400, 0.3833, 0.7461, 0.5494],
[0.6138, 0.4054, 0.8750, 0.4750, 0.4363, 0.5017, 0.5086, 0.5822]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.010435777367092669
step: 26
running loss: 0.0004013760525804873
Train Steps: 26/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6201, 0.4029, 0.8776, 0.4602, 0.3683, 0.4203, 0.5938, 0.5450],
[0.6148, 0.3996, 0.8488, 0.3867, 0.3488, 0.4067, 0.5863, 0.5000],
[0.6307, 0.4045, 0.8025, 0.5833, 0.3775, 0.4867, 0.6892, 0.5459],
[0.6109, 0.4041, 0.6975, 0.3167, 0.3513, 0.3383, 0.5153, 0.5319],
[0.6164, 0.4119, 0.7913, 0.2650, 0.3538, 0.3500, 0.5614, 0.5038],
[0.6059, 0.4002, 0.7562, 0.2767, 0.3538, 0.3033, 0.5529, 0.5455],
[0.6189, 0.4033, 0.8650, 0.5267, 0.4487, 0.5150, 0.5925, 0.5050],
[0.6226, 0.4098, 0.8912, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6733, 0.4420, 0.9006, 0.4592, 0.3952, 0.4471, 0.6059, 0.5509],
[0.6782, 0.4406, 0.8676, 0.3867, 0.3818, 0.4237, 0.6056, 0.5240],
[0.6645, 0.4411, 0.8261, 0.5779, 0.4138, 0.5102, 0.7137, 0.5565],
[0.6322, 0.4215, 0.7219, 0.3003, 0.3706, 0.3627, 0.5216, 0.5281],
[0.6336, 0.4272, 0.8046, 0.2458, 0.3731, 0.3714, 0.5971, 0.5173],
[0.6348, 0.4317, 0.7630, 0.2643, 0.3831, 0.3224, 0.5698, 0.5473],
[0.6039, 0.4015, 0.9008, 0.5119, 0.4727, 0.5480, 0.5999, 0.5222],
[0.6702, 0.4475, 0.9149, 0.4061, 0.4231, 0.2565, 0.5952, 0.5360]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6201, 0.4029, 0.8776, 0.4602, 0.3683, 0.4203, 0.5938, 0.5450],
[0.6148, 0.3996, 0.8487, 0.3867, 0.3487, 0.4067, 0.5863, 0.5000],
[0.6307, 0.4045, 0.8025, 0.5833, 0.3775, 0.4867, 0.6892, 0.5459],
[0.6109, 0.4041, 0.6975, 0.3167, 0.3512, 0.3383, 0.5153, 0.5319],
[0.6164, 0.4119, 0.7912, 0.2650, 0.3537, 0.3500, 0.5614, 0.5038],
[0.6059, 0.4002, 0.7563, 0.2767, 0.3537, 0.3033, 0.5529, 0.5455],
[0.6189, 0.4033, 0.8650, 0.5267, 0.4487, 0.5150, 0.5925, 0.5050],
[0.6226, 0.4098, 0.8913, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.011048498621676117
step: 27
running loss: 0.000409203652654671
Train Steps: 27/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6199, 0.4015, 0.8716, 0.5228, 0.3833, 0.4772, 0.5883, 0.5148],
[0.6162, 0.4134, 0.6700, 0.2467, 0.3962, 0.2533, 0.5737, 0.5467],
[0.6219, 0.3934, 0.8688, 0.5267, 0.4313, 0.4967, 0.5988, 0.4983],
[0.6175, 0.4013, 0.7734, 0.2783, 0.4475, 0.1786, 0.5790, 0.5351],
[0.6048, 0.3928, 0.8538, 0.5433, 0.3875, 0.5117, 0.5266, 0.4719],
[0.6187, 0.4104, 0.7126, 0.2069, 0.3950, 0.2517, 0.5913, 0.5683],
[0.6149, 0.4054, 0.6713, 0.2333, 0.4025, 0.2017, 0.5213, 0.5695],
[0.6268, 0.4052, 0.8175, 0.2250, 0.4688, 0.1917, 0.6375, 0.5267]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6253, 0.3900, 0.8995, 0.5372, 0.4009, 0.5019, 0.6102, 0.5218],
[0.6573, 0.4399, 0.6953, 0.2518, 0.4098, 0.2716, 0.5794, 0.5534],
[0.6543, 0.4098, 0.8893, 0.5400, 0.4585, 0.5274, 0.6245, 0.5081],
[0.6368, 0.4064, 0.7912, 0.2724, 0.4639, 0.2089, 0.5825, 0.5365],
[0.6131, 0.3953, 0.8726, 0.5570, 0.4134, 0.5330, 0.5629, 0.5069],
[0.6109, 0.4030, 0.7297, 0.1998, 0.4061, 0.2826, 0.6012, 0.5700],
[0.6804, 0.4367, 0.6936, 0.2261, 0.4120, 0.2187, 0.5295, 0.5860],
[0.6497, 0.4117, 0.8310, 0.2360, 0.4834, 0.2101, 0.6582, 0.5428]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6199, 0.4015, 0.8716, 0.5228, 0.3833, 0.4772, 0.5883, 0.5148],
[0.6162, 0.4134, 0.6700, 0.2467, 0.3963, 0.2533, 0.5738, 0.5467],
[0.6219, 0.3934, 0.8687, 0.5267, 0.4313, 0.4967, 0.5987, 0.4983],
[0.6175, 0.4013, 0.7734, 0.2783, 0.4475, 0.1786, 0.5790, 0.5351],
[0.6048, 0.3928, 0.8537, 0.5433, 0.3875, 0.5117, 0.5266, 0.4719],
[0.6187, 0.4103, 0.7126, 0.2069, 0.3950, 0.2517, 0.5913, 0.5683],
[0.6149, 0.4054, 0.6712, 0.2333, 0.4025, 0.2017, 0.5213, 0.5695],
[0.6268, 0.4052, 0.8175, 0.2250, 0.4688, 0.1917, 0.6375, 0.5267]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.01147236383985728
step: 28
running loss: 0.0004097272799949029
Train Steps: 28/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6257, 0.4060, 0.8300, 0.2333, 0.4688, 0.2583, 0.7050, 0.5633],
[0.6200, 0.4070, 0.8938, 0.4183, 0.3538, 0.4567, 0.6175, 0.5400],
[0.6284, 0.4029, 0.8838, 0.3783, 0.3975, 0.2850, 0.6335, 0.5090],
[0.6250, 0.4116, 0.8700, 0.4850, 0.4650, 0.5567, 0.6088, 0.5183],
[0.6175, 0.4093, 0.8800, 0.4433, 0.4075, 0.4367, 0.5128, 0.4901],
[0.6200, 0.3961, 0.8461, 0.5497, 0.4142, 0.4577, 0.5892, 0.5402],
[0.6136, 0.4029, 0.8263, 0.3350, 0.3625, 0.3067, 0.5675, 0.5167],
[ nan, nan, 0.8675, 0.2833, 0.5350, 0.1983, 0.6678, 0.5621]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6964, 0.4375, 0.8261, 0.2212, 0.4650, 0.2734, 0.7027, 0.5774],
[0.6946, 0.4328, 0.8898, 0.4038, 0.3624, 0.4662, 0.6211, 0.5375],
[0.6542, 0.4034, 0.8801, 0.3598, 0.4098, 0.3013, 0.6400, 0.5122],
[0.6437, 0.4128, 0.8703, 0.4686, 0.4730, 0.5749, 0.6123, 0.5324],
[0.6431, 0.4101, 0.8832, 0.4444, 0.4106, 0.4485, 0.5275, 0.5117],
[0.6653, 0.4102, 0.8407, 0.5278, 0.4112, 0.4669, 0.5808, 0.5438],
[0.6775, 0.4272, 0.8181, 0.3206, 0.3716, 0.3246, 0.5615, 0.5419],
[0.0300, 0.0195, 0.8411, 0.2661, 0.5341, 0.2151, 0.6922, 0.5651]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6257, 0.4060, 0.8300, 0.2333, 0.4688, 0.2583, 0.7050, 0.5633],
[0.6200, 0.4070, 0.8938, 0.4183, 0.3537, 0.4567, 0.6175, 0.5400],
[0.6284, 0.4029, 0.8838, 0.3783, 0.3975, 0.2850, 0.6335, 0.5090],
[0.6251, 0.4116, 0.8700, 0.4850, 0.4650, 0.5567, 0.6087, 0.5183],
[0.6175, 0.4093, 0.8800, 0.4433, 0.4075, 0.4367, 0.5128, 0.4901],
[0.6200, 0.3961, 0.8461, 0.5497, 0.4142, 0.4577, 0.5892, 0.5402],
[0.6136, 0.4029, 0.8263, 0.3350, 0.3625, 0.3067, 0.5675, 0.5167],
[0.0000, 0.0000, 0.8675, 0.2833, 0.5350, 0.1983, 0.6678, 0.5621]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.011934660928091034
step: 29
running loss: 0.00041154003200313913
Train Steps: 29/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6339, 0.4118, 0.7988, 0.5800, 0.3912, 0.4583, 0.7343, 0.5760],
[0.6205, 0.4081, 0.8950, 0.4017, 0.3788, 0.4700, 0.5963, 0.5667],
[0.6275, 0.4008, 0.8047, 0.2484, 0.4037, 0.2777, 0.6506, 0.5212],
[0.6109, 0.4003, 0.8650, 0.4883, 0.4775, 0.4867, 0.5175, 0.5683],
[ nan, nan, 0.8363, 0.3317, 0.3563, 0.3367, 0.5329, 0.5142],
[0.6031, 0.3986, 0.7462, 0.2833, 0.3638, 0.2717, 0.5253, 0.4726],
[ nan, nan, 0.7553, 0.2722, 0.3875, 0.2550, 0.5125, 0.5633],
[0.6156, 0.4125, 0.8850, 0.4833, 0.4550, 0.5817, 0.5765, 0.5084]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.7444, 0.4550, 0.7838, 0.5614, 0.3935, 0.4228, 0.7239, 0.5780],
[0.7114, 0.4385, 0.8891, 0.3816, 0.3997, 0.4399, 0.6062, 0.5688],
[0.6936, 0.4127, 0.8160, 0.2357, 0.4294, 0.2486, 0.6374, 0.5281],
[0.6937, 0.4294, 0.8518, 0.4698, 0.5013, 0.4684, 0.5379, 0.5678],
[0.1745, 0.0923, 0.8023, 0.3025, 0.3639, 0.3292, 0.5370, 0.5189],
[0.6800, 0.4200, 0.7463, 0.2655, 0.3864, 0.2591, 0.5379, 0.4902],
[0.0922, 0.0367, 0.7440, 0.2449, 0.3967, 0.2344, 0.4970, 0.5574],
[0.6934, 0.4381, 0.8870, 0.4631, 0.4642, 0.5533, 0.5820, 0.5214]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6339, 0.4118, 0.7987, 0.5800, 0.3913, 0.4583, 0.7343, 0.5760],
[0.6205, 0.4081, 0.8950, 0.4017, 0.3787, 0.4700, 0.5962, 0.5667],
[0.6275, 0.4008, 0.8047, 0.2484, 0.4037, 0.2777, 0.6506, 0.5212],
[0.6109, 0.4003, 0.8650, 0.4883, 0.4775, 0.4867, 0.5175, 0.5683],
[0.0000, 0.0000, 0.8363, 0.3317, 0.3562, 0.3367, 0.5329, 0.5142],
[0.6031, 0.3986, 0.7462, 0.2833, 0.3638, 0.2717, 0.5253, 0.4726],
[0.0000, 0.0000, 0.7553, 0.2722, 0.3875, 0.2550, 0.5125, 0.5633],
[0.6155, 0.4124, 0.8850, 0.4833, 0.4550, 0.5817, 0.5765, 0.5084]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0017, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.013682589953532442
step: 30
running loss: 0.00045608633178441474
Train Steps: 30/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6199, 0.4071, 0.7600, 0.2117, 0.4037, 0.2767, 0.6138, 0.5550],
[0.6128, 0.4116, 0.8450, 0.4583, 0.3675, 0.4867, 0.5337, 0.5446],
[0.6143, 0.4055, 0.8150, 0.2767, 0.3825, 0.2567, 0.5173, 0.4901],
[0.6140, 0.4070, 0.8700, 0.5000, 0.4612, 0.4900, 0.5260, 0.5852],
[0.6275, 0.4008, 0.8047, 0.2484, 0.4037, 0.2777, 0.6506, 0.5212],
[0.6087, 0.3951, 0.8387, 0.5833, 0.4188, 0.4933, 0.5146, 0.4830],
[0.6165, 0.4106, 0.7575, 0.1733, 0.3838, 0.2650, 0.5680, 0.5116],
[0.6222, 0.4172, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6379, 0.3909, 0.7579, 0.2245, 0.4173, 0.2712, 0.6210, 0.5547],
[0.6233, 0.3771, 0.8362, 0.4750, 0.3749, 0.4593, 0.5709, 0.5568],
[0.5827, 0.3658, 0.7819, 0.3057, 0.3846, 0.2551, 0.5367, 0.5088],
[0.6191, 0.3872, 0.8765, 0.5207, 0.4641, 0.4718, 0.5482, 0.5878],
[0.6211, 0.3721, 0.8128, 0.2735, 0.4169, 0.2571, 0.6458, 0.5189],
[0.6149, 0.3738, 0.8328, 0.6057, 0.4157, 0.4810, 0.5209, 0.4928],
[0.6080, 0.3842, 0.7540, 0.1936, 0.3971, 0.2233, 0.5777, 0.4945],
[0.5913, 0.3738, 0.8921, 0.5489, 0.3768, 0.4280, 0.5715, 0.5629]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6199, 0.4071, 0.7600, 0.2117, 0.4038, 0.2767, 0.6137, 0.5550],
[0.6128, 0.4116, 0.8450, 0.4583, 0.3675, 0.4867, 0.5337, 0.5446],
[0.6143, 0.4055, 0.8150, 0.2767, 0.3825, 0.2567, 0.5173, 0.4901],
[0.6140, 0.4070, 0.8700, 0.5000, 0.4613, 0.4900, 0.5260, 0.5852],
[0.6275, 0.4008, 0.8047, 0.2484, 0.4037, 0.2777, 0.6506, 0.5212],
[0.6087, 0.3951, 0.8388, 0.5833, 0.4187, 0.4933, 0.5146, 0.4830],
[0.6165, 0.4106, 0.7575, 0.1733, 0.3837, 0.2650, 0.5680, 0.5116],
[0.6222, 0.4171, 0.8850, 0.5217, 0.3738, 0.4600, 0.5700, 0.5633]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.014052209124201909
step: 31
running loss: 0.0004532970685226422
Train Steps: 31/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6302, 0.4007, 0.8850, 0.5500, 0.3613, 0.4517, 0.6335, 0.5012],
[0.6198, 0.4101, 0.8838, 0.5283, 0.3763, 0.5267, 0.5913, 0.5567],
[0.6180, 0.4064, 0.7200, 0.2467, 0.4275, 0.2367, 0.5963, 0.6217],
[0.6186, 0.4060, 0.8750, 0.5050, 0.3538, 0.4367, 0.5813, 0.6083],
[0.6246, 0.4126, 0.8850, 0.4833, 0.4200, 0.5350, 0.6112, 0.5250],
[ nan, nan, 0.8625, 0.2550, 0.5487, 0.2200, 0.7335, 0.5737],
[0.6199, 0.4015, 0.8716, 0.5228, 0.3833, 0.4772, 0.5883, 0.5148],
[0.6239, 0.4206, 0.8750, 0.5400, 0.3688, 0.4850, 0.5737, 0.5700]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6495, 0.4011, 0.8692, 0.5537, 0.3627, 0.4384, 0.6152, 0.4814],
[ 0.5820, 0.3635, 0.8739, 0.5224, 0.3707, 0.5128, 0.5727, 0.5245],
[ 0.6267, 0.4012, 0.7082, 0.2621, 0.4269, 0.2425, 0.5802, 0.5959],
[ 0.6077, 0.3814, 0.8682, 0.5002, 0.3490, 0.4299, 0.5728, 0.5763],
[ 0.6103, 0.3933, 0.8777, 0.4750, 0.4192, 0.5271, 0.5952, 0.5091],
[-0.0732, -0.0449, 0.8521, 0.2557, 0.5387, 0.2475, 0.7223, 0.5523],
[ 0.5827, 0.3624, 0.8614, 0.5299, 0.3894, 0.4689, 0.5755, 0.4910],
[ 0.6196, 0.3949, 0.8621, 0.5466, 0.3767, 0.4803, 0.5679, 0.5404]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6302, 0.4007, 0.8850, 0.5500, 0.3613, 0.4517, 0.6335, 0.5012],
[0.6198, 0.4101, 0.8838, 0.5283, 0.3762, 0.5267, 0.5913, 0.5567],
[0.6180, 0.4064, 0.7200, 0.2467, 0.4275, 0.2367, 0.5962, 0.6217],
[0.6186, 0.4060, 0.8750, 0.5050, 0.3537, 0.4367, 0.5813, 0.6083],
[0.6246, 0.4126, 0.8850, 0.4833, 0.4200, 0.5350, 0.6112, 0.5250],
[0.0000, 0.0000, 0.8625, 0.2550, 0.5487, 0.2200, 0.7335, 0.5737],
[0.6199, 0.4015, 0.8716, 0.5228, 0.3833, 0.4772, 0.5883, 0.5148],
[0.6239, 0.4206, 0.8750, 0.5400, 0.3688, 0.4850, 0.5738, 0.5700]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.014462272200034931
step: 32
running loss: 0.0004519460062510916
Train Steps: 32/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6163, 0.4001, 0.8788, 0.5033, 0.4012, 0.4633, 0.5338, 0.5767],
[0.6109, 0.4015, 0.7668, 0.3639, 0.3513, 0.3667, 0.5200, 0.5641],
[0.6339, 0.4112, 0.8838, 0.5067, 0.4000, 0.5433, 0.7549, 0.5378],
[0.6292, 0.4010, 0.8988, 0.4800, 0.3638, 0.3817, 0.6357, 0.5051],
[0.6276, 0.4002, 0.8800, 0.5533, 0.3575, 0.4400, 0.6132, 0.4672],
[0.6248, 0.4185, 0.8500, 0.5767, 0.4463, 0.4550, 0.5613, 0.5917],
[0.6086, 0.4019, 0.7782, 0.4278, 0.3625, 0.4350, 0.5150, 0.5285],
[0.6168, 0.4029, 0.8523, 0.3417, 0.3588, 0.5000, 0.6125, 0.5400]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5832, 0.3911, 0.8822, 0.4977, 0.3909, 0.4613, 0.5244, 0.5735],
[0.5820, 0.3953, 0.7600, 0.3603, 0.3348, 0.3778, 0.5203, 0.5651],
[0.5541, 0.3639, 0.8830, 0.5053, 0.3868, 0.5514, 0.7251, 0.5361],
[0.5904, 0.3968, 0.8927, 0.4745, 0.3561, 0.3798, 0.6333, 0.5047],
[0.6538, 0.4274, 0.8706, 0.5482, 0.3517, 0.4422, 0.6079, 0.4647],
[0.5155, 0.3559, 0.8503, 0.5779, 0.4409, 0.4510, 0.5537, 0.5804],
[0.5931, 0.3919, 0.7732, 0.4311, 0.3554, 0.4521, 0.5282, 0.5202],
[0.5779, 0.3841, 0.8554, 0.3345, 0.3512, 0.5036, 0.6164, 0.5412]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6163, 0.4001, 0.8788, 0.5033, 0.4013, 0.4633, 0.5337, 0.5767],
[0.6109, 0.4015, 0.7668, 0.3639, 0.3512, 0.3667, 0.5200, 0.5641],
[0.6339, 0.4112, 0.8838, 0.5067, 0.4000, 0.5433, 0.7549, 0.5378],
[0.6292, 0.4010, 0.8988, 0.4800, 0.3638, 0.3817, 0.6357, 0.5051],
[0.6276, 0.4002, 0.8800, 0.5533, 0.3575, 0.4400, 0.6132, 0.4672],
[0.6248, 0.4185, 0.8500, 0.5767, 0.4462, 0.4550, 0.5612, 0.5917],
[0.6086, 0.4019, 0.7782, 0.4278, 0.3625, 0.4350, 0.5150, 0.5285],
[0.6168, 0.4029, 0.8523, 0.3417, 0.3587, 0.5000, 0.6125, 0.5400]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.015006558765890077
step: 33
running loss: 0.000454744205026972
Train Steps: 33/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6236, 0.3967, 0.8675, 0.5400, 0.3862, 0.4517, 0.5825, 0.5200],
[0.6104, 0.4029, 0.8738, 0.4900, 0.4088, 0.4533, 0.5070, 0.5510],
[0.6264, 0.4069, 0.7900, 0.1650, 0.4275, 0.2267, 0.6290, 0.4947],
[0.6204, 0.4049, 0.7975, 0.2700, 0.3937, 0.2567, 0.5700, 0.5183],
[0.6200, 0.4039, 0.8880, 0.4799, 0.3625, 0.4285, 0.5866, 0.5148],
[0.6286, 0.4086, 0.8408, 0.2801, 0.4163, 0.2800, 0.6725, 0.5393],
[0.6198, 0.4105, 0.7950, 0.3267, 0.3675, 0.3767, 0.6038, 0.6167],
[ nan, nan, 0.6992, 0.2791, 0.3950, 0.2383, 0.5483, 0.5819]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6451, 0.4259, 0.8675, 0.5698, 0.3666, 0.4369, 0.5717, 0.5125],
[ 0.5645, 0.3908, 0.8689, 0.5002, 0.3998, 0.4359, 0.5041, 0.5314],
[ 0.6088, 0.4146, 0.7864, 0.1810, 0.4185, 0.2331, 0.6403, 0.5081],
[ 0.5629, 0.3920, 0.7945, 0.2791, 0.3713, 0.2506, 0.5538, 0.5200],
[ 0.6072, 0.3994, 0.8853, 0.4779, 0.3450, 0.4178, 0.5725, 0.5193],
[ 0.5482, 0.3731, 0.8415, 0.2738, 0.3922, 0.2913, 0.6542, 0.5502],
[ 0.5835, 0.4134, 0.8025, 0.3365, 0.3402, 0.3861, 0.5850, 0.6057],
[-0.0904, -0.0457, 0.7108, 0.2879, 0.3720, 0.2219, 0.5418, 0.5538]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6236, 0.3967, 0.8675, 0.5400, 0.3862, 0.4517, 0.5825, 0.5200],
[0.6104, 0.4029, 0.8737, 0.4900, 0.4087, 0.4533, 0.5070, 0.5510],
[0.6264, 0.4069, 0.7900, 0.1650, 0.4275, 0.2267, 0.6290, 0.4947],
[0.6204, 0.4049, 0.7975, 0.2700, 0.3938, 0.2567, 0.5700, 0.5183],
[0.6201, 0.4039, 0.8880, 0.4799, 0.3625, 0.4285, 0.5866, 0.5148],
[0.6286, 0.4086, 0.8408, 0.2801, 0.4162, 0.2800, 0.6725, 0.5393],
[0.6198, 0.4105, 0.7950, 0.3267, 0.3675, 0.3767, 0.6037, 0.6167],
[0.0000, 0.0000, 0.6992, 0.2791, 0.3950, 0.2383, 0.5483, 0.5819]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.015572562260786071
step: 34
running loss: 0.00045801653708194326
Train Steps: 34/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6120, 0.4014, 0.6863, 0.2817, 0.3700, 0.2783, 0.5513, 0.5667],
[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383],
[0.6135, 0.3994, 0.7913, 0.3050, 0.3625, 0.3050, 0.5837, 0.5050],
[0.6162, 0.4134, 0.6700, 0.2467, 0.3962, 0.2533, 0.5737, 0.5467],
[0.6150, 0.4097, 0.7468, 0.3194, 0.3825, 0.2633, 0.5463, 0.5800],
[0.6272, 0.4120, 0.9038, 0.4117, 0.3725, 0.3200, 0.6175, 0.5250],
[0.6241, 0.4143, 0.8938, 0.4650, 0.4075, 0.5350, 0.6250, 0.5550],
[ nan, nan, 0.7425, 0.2117, 0.3937, 0.2433, 0.5438, 0.5567]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.5648, 0.3873, 0.7104, 0.2988, 0.3594, 0.2853, 0.5460, 0.5725],
[ 0.5962, 0.4024, 0.8461, 0.3272, 0.3354, 0.3844, 0.6203, 0.5423],
[ 0.5860, 0.4008, 0.7996, 0.3109, 0.3559, 0.3106, 0.5874, 0.5184],
[ 0.5606, 0.4088, 0.6864, 0.2589, 0.3830, 0.2525, 0.5607, 0.5531],
[ 0.5616, 0.4096, 0.7585, 0.3136, 0.3572, 0.2629, 0.5283, 0.5779],
[ 0.5532, 0.3874, 0.9154, 0.4124, 0.3580, 0.3366, 0.6117, 0.5302],
[ 0.5849, 0.4117, 0.9025, 0.4614, 0.3938, 0.5506, 0.6109, 0.5616],
[-0.0348, -0.0089, 0.7443, 0.2201, 0.3803, 0.2465, 0.5251, 0.5509]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6120, 0.4013, 0.6862, 0.2817, 0.3700, 0.2783, 0.5512, 0.5667],
[0.6200, 0.4024, 0.8390, 0.3139, 0.3525, 0.3833, 0.6162, 0.5383],
[0.6135, 0.3994, 0.7912, 0.3050, 0.3625, 0.3050, 0.5838, 0.5050],
[0.6162, 0.4134, 0.6700, 0.2467, 0.3963, 0.2533, 0.5738, 0.5467],
[0.6150, 0.4097, 0.7468, 0.3194, 0.3825, 0.2633, 0.5462, 0.5800],
[0.6272, 0.4120, 0.9038, 0.4117, 0.3725, 0.3200, 0.6175, 0.5250],
[0.6241, 0.4142, 0.8938, 0.4650, 0.4075, 0.5350, 0.6250, 0.5550],
[0.0000, 0.0000, 0.7425, 0.2117, 0.3938, 0.2433, 0.5437, 0.5567]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.015958790871081874
step: 35
running loss: 0.0004559654534594821
Train Steps: 35/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6135, 0.3994, 0.7913, 0.3050, 0.3625, 0.3050, 0.5837, 0.5050],
[0.6140, 0.4070, 0.8700, 0.5000, 0.4612, 0.4900, 0.5260, 0.5852],
[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383],
[0.6239, 0.4174, 0.8425, 0.5733, 0.4825, 0.4500, 0.5625, 0.5933],
[0.6185, 0.4129, 0.8900, 0.4567, 0.3937, 0.5417, 0.5734, 0.5110],
[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586],
[0.6257, 0.4024, 0.8612, 0.5352, 0.4361, 0.5253, 0.6680, 0.5166],
[0.6260, 0.4153, 0.9000, 0.4533, 0.4025, 0.2633, 0.6223, 0.4967]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5715, 0.3983, 0.7859, 0.2862, 0.3385, 0.2973, 0.5770, 0.5222],
[0.5618, 0.4052, 0.8710, 0.4820, 0.4305, 0.4784, 0.5196, 0.5981],
[0.6019, 0.4226, 0.8774, 0.4308, 0.4082, 0.5659, 0.6071, 0.5512],
[0.5632, 0.4007, 0.8402, 0.5524, 0.4494, 0.4242, 0.5551, 0.6019],
[0.5532, 0.4036, 0.8765, 0.4356, 0.3600, 0.5315, 0.5501, 0.5206],
[0.5350, 0.3746, 0.8441, 0.2485, 0.4228, 0.2560, 0.6971, 0.5770],
[0.5611, 0.3938, 0.8491, 0.5134, 0.3984, 0.5053, 0.6425, 0.5280],
[0.5484, 0.3925, 0.8883, 0.4308, 0.3827, 0.2655, 0.6115, 0.5072]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6135, 0.3994, 0.7912, 0.3050, 0.3625, 0.3050, 0.5838, 0.5050],
[0.6140, 0.4070, 0.8700, 0.5000, 0.4613, 0.4900, 0.5260, 0.5852],
[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383],
[0.6239, 0.4174, 0.8425, 0.5733, 0.4825, 0.4500, 0.5625, 0.5933],
[0.6186, 0.4129, 0.8900, 0.4567, 0.3938, 0.5417, 0.5734, 0.5110],
[0.6264, 0.4055, 0.8425, 0.2767, 0.4425, 0.2767, 0.7050, 0.5586],
[0.6257, 0.4024, 0.8612, 0.5352, 0.4361, 0.5253, 0.6680, 0.5166],
[0.6260, 0.4153, 0.9000, 0.4533, 0.4025, 0.2633, 0.6223, 0.4967]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.016739433369366452
step: 36
running loss: 0.00046498426026017923
Train Steps: 36/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6185, 0.4080, 0.8625, 0.3483, 0.3788, 0.2650, 0.5320, 0.5272],
[0.6182, 0.3987, 0.7878, 0.2889, 0.3699, 0.3260, 0.6086, 0.5367],
[0.6192, 0.3980, 0.7078, 0.2750, 0.4250, 0.2100, 0.5450, 0.5783],
[0.6179, 0.4008, 0.7505, 0.2678, 0.4368, 0.1891, 0.5831, 0.5263],
[0.6058, 0.3986, 0.8324, 0.4626, 0.3838, 0.4983, 0.5147, 0.5466],
[0.6265, 0.4071, 0.8875, 0.3367, 0.3975, 0.3350, 0.6312, 0.5250],
[0.6307, 0.4060, 0.8950, 0.5183, 0.3750, 0.3850, 0.6338, 0.4938],
[0.6122, 0.3993, 0.8738, 0.4667, 0.4517, 0.4879, 0.5155, 0.4927]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5706, 0.3897, 0.8698, 0.3285, 0.3751, 0.2562, 0.5224, 0.5354],
[0.5487, 0.3692, 0.7964, 0.2755, 0.3574, 0.3253, 0.5934, 0.5550],
[0.5685, 0.3815, 0.7108, 0.2668, 0.4292, 0.2223, 0.5417, 0.6050],
[0.6088, 0.4080, 0.7604, 0.2438, 0.4274, 0.1796, 0.5675, 0.5478],
[0.5814, 0.3926, 0.8298, 0.4636, 0.3864, 0.4965, 0.5183, 0.5379],
[0.5431, 0.3703, 0.8917, 0.3262, 0.3925, 0.3486, 0.6546, 0.5392],
[0.5391, 0.3666, 0.8971, 0.5011, 0.3574, 0.3801, 0.6286, 0.4892],
[0.5493, 0.3695, 0.8689, 0.4610, 0.4409, 0.4958, 0.5160, 0.4922]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6186, 0.4080, 0.8625, 0.3483, 0.3787, 0.2650, 0.5320, 0.5272],
[0.6182, 0.3987, 0.7878, 0.2889, 0.3699, 0.3260, 0.6086, 0.5367],
[0.6192, 0.3980, 0.7078, 0.2750, 0.4250, 0.2100, 0.5450, 0.5783],
[0.6179, 0.4008, 0.7505, 0.2678, 0.4368, 0.1891, 0.5831, 0.5263],
[0.6058, 0.3986, 0.8324, 0.4626, 0.3837, 0.4983, 0.5147, 0.5466],
[0.6265, 0.4071, 0.8875, 0.3367, 0.3975, 0.3350, 0.6313, 0.5250],
[0.6307, 0.4060, 0.8950, 0.5183, 0.3750, 0.3850, 0.6338, 0.4938],
[0.6122, 0.3993, 0.8737, 0.4667, 0.4517, 0.4879, 0.5155, 0.4927]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.017385684681357816
step: 37
running loss: 0.0004698833697664275
Train Steps: 37/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6132, 0.4118, 0.8200, 0.3633, 0.3563, 0.5400, 0.5787, 0.5136],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5413, 0.5683],
[0.6169, 0.4108, 0.6821, 0.2722, 0.3825, 0.2550, 0.5550, 0.5717],
[0.6192, 0.3980, 0.7078, 0.2750, 0.4250, 0.2100, 0.5450, 0.5783],
[0.6115, 0.4005, 0.8838, 0.3867, 0.3763, 0.4700, 0.5800, 0.5550],
[0.6272, 0.4120, 0.9038, 0.4117, 0.3725, 0.3200, 0.6175, 0.5250],
[0.6201, 0.4065, 0.7300, 0.1933, 0.4075, 0.2533, 0.6162, 0.5483],
[0.6205, 0.4012, 0.8675, 0.3283, 0.3713, 0.3050, 0.5813, 0.5117]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6185, 0.4146, 0.8208, 0.3592, 0.3667, 0.5381, 0.5866, 0.5155],
[0.5871, 0.3943, 0.8878, 0.5392, 0.3985, 0.3881, 0.5449, 0.5594],
[0.6026, 0.4076, 0.6866, 0.2655, 0.3988, 0.2523, 0.5521, 0.5697],
[0.6158, 0.4022, 0.7173, 0.2858, 0.4572, 0.2319, 0.5530, 0.5862],
[0.6032, 0.4139, 0.8797, 0.3877, 0.3929, 0.4822, 0.5769, 0.5445],
[0.6120, 0.4118, 0.9116, 0.4091, 0.3926, 0.3357, 0.6214, 0.5160],
[0.6625, 0.4409, 0.7361, 0.2061, 0.4297, 0.2643, 0.6194, 0.5430],
[0.5817, 0.3856, 0.8910, 0.3248, 0.3996, 0.3122, 0.5976, 0.5089]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6132, 0.4118, 0.8200, 0.3633, 0.3562, 0.5400, 0.5787, 0.5136],
[0.6200, 0.4101, 0.8838, 0.5317, 0.3825, 0.3800, 0.5412, 0.5683],
[0.6169, 0.4108, 0.6821, 0.2722, 0.3825, 0.2550, 0.5550, 0.5717],
[0.6192, 0.3980, 0.7078, 0.2750, 0.4250, 0.2100, 0.5450, 0.5783],
[0.6115, 0.4005, 0.8838, 0.3867, 0.3762, 0.4700, 0.5800, 0.5550],
[0.6272, 0.4120, 0.9038, 0.4117, 0.3725, 0.3200, 0.6175, 0.5250],
[0.6201, 0.4065, 0.7300, 0.1933, 0.4075, 0.2533, 0.6162, 0.5483],
[0.6205, 0.4012, 0.8675, 0.3283, 0.3713, 0.3050, 0.5813, 0.5117]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.017598614853341132
step: 38
running loss: 0.00046312144350897714
Train Steps: 38/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6043, 0.4022, 0.6887, 0.1983, 0.3775, 0.2483, 0.5480, 0.5136],
[0.6137, 0.4035, 0.8850, 0.4417, 0.3900, 0.4283, 0.5449, 0.5617],
[0.6162, 0.4014, 0.8800, 0.5333, 0.3750, 0.4817, 0.5988, 0.5283],
[0.6131, 0.4064, 0.8638, 0.5200, 0.4788, 0.4783, 0.5258, 0.5867],
[ nan, nan, 0.6859, 0.2194, 0.4150, 0.1867, 0.5153, 0.5729],
[0.6273, 0.4100, 0.7137, 0.2133, 0.4000, 0.2650, 0.6075, 0.5633],
[0.6304, 0.4029, 0.8413, 0.5217, 0.4125, 0.5617, 0.7089, 0.5679],
[0.6304, 0.4024, 0.8925, 0.4800, 0.3937, 0.4817, 0.7485, 0.5297]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6718, 0.4344, 0.6978, 0.2278, 0.3973, 0.2618, 0.5353, 0.5026],
[0.6814, 0.4551, 0.8863, 0.4626, 0.3983, 0.4597, 0.5437, 0.5441],
[0.6454, 0.4267, 0.8699, 0.5458, 0.3998, 0.5120, 0.5762, 0.5138],
[0.6757, 0.4400, 0.8705, 0.5272, 0.4855, 0.4925, 0.5310, 0.5669],
[0.0959, 0.0477, 0.7053, 0.2470, 0.4459, 0.1847, 0.5273, 0.5702],
[0.6634, 0.4301, 0.7144, 0.2299, 0.4122, 0.2717, 0.6030, 0.5523],
[0.7147, 0.4760, 0.8374, 0.5446, 0.4280, 0.5935, 0.7018, 0.5490],
[0.6632, 0.4300, 0.8874, 0.5051, 0.4079, 0.4964, 0.7220, 0.5106]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6043, 0.4022, 0.6888, 0.1983, 0.3775, 0.2483, 0.5480, 0.5136],
[0.6137, 0.4035, 0.8850, 0.4417, 0.3900, 0.4283, 0.5449, 0.5617],
[0.6162, 0.4014, 0.8800, 0.5333, 0.3750, 0.4817, 0.5987, 0.5283],
[0.6132, 0.4063, 0.8637, 0.5200, 0.4787, 0.4783, 0.5258, 0.5867],
[0.0000, 0.0000, 0.6859, 0.2194, 0.4150, 0.1867, 0.5153, 0.5729],
[0.6273, 0.4099, 0.7138, 0.2133, 0.4000, 0.2650, 0.6075, 0.5633],
[0.6304, 0.4029, 0.8413, 0.5217, 0.4125, 0.5617, 0.7089, 0.5679],
[0.6304, 0.4024, 0.8925, 0.4800, 0.3938, 0.4817, 0.7485, 0.5297]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0010, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.018550915468949825
step: 39
running loss: 0.00047566449920384167
Train Steps: 39/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6053, 0.4035, 0.6897, 0.1916, 0.4000, 0.2117, 0.5440, 0.5168],
[0.6339, 0.4118, 0.7988, 0.5800, 0.3912, 0.4583, 0.7343, 0.5760],
[0.6185, 0.4129, 0.8900, 0.4567, 0.3937, 0.5417, 0.5734, 0.5110],
[0.6260, 0.4253, 0.8938, 0.4400, 0.3675, 0.3650, 0.5675, 0.5767],
[0.6072, 0.4029, 0.7037, 0.2150, 0.3912, 0.2267, 0.5516, 0.5507],
[ nan, nan, 0.6412, 0.1900, 0.4238, 0.1883, 0.5487, 0.5700],
[0.6150, 0.3935, 0.8696, 0.5158, 0.4647, 0.5329, 0.6041, 0.5153],
[0.6185, 0.4067, 0.8838, 0.4450, 0.4037, 0.4733, 0.5213, 0.5142]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6169, 0.3839, 0.6956, 0.2080, 0.4152, 0.2001, 0.5619, 0.5252],
[0.7022, 0.4459, 0.7833, 0.5770, 0.3878, 0.4553, 0.7285, 0.5615],
[0.7060, 0.4618, 0.8837, 0.4516, 0.4031, 0.5463, 0.5737, 0.5116],
[0.6692, 0.4372, 0.8901, 0.4432, 0.3769, 0.3541, 0.5819, 0.5860],
[0.6585, 0.4263, 0.7016, 0.2302, 0.4021, 0.2140, 0.5644, 0.5644],
[0.1082, 0.0597, 0.6819, 0.2193, 0.4518, 0.2031, 0.5519, 0.5844],
[0.6855, 0.4326, 0.8580, 0.5093, 0.4684, 0.5414, 0.5962, 0.5084],
[0.6360, 0.4014, 0.8779, 0.4440, 0.4092, 0.4681, 0.5291, 0.5039]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6054, 0.4035, 0.6897, 0.1916, 0.4000, 0.2117, 0.5440, 0.5168],
[0.6339, 0.4118, 0.7987, 0.5800, 0.3913, 0.4583, 0.7343, 0.5760],
[0.6186, 0.4129, 0.8900, 0.4567, 0.3938, 0.5417, 0.5734, 0.5110],
[0.6260, 0.4253, 0.8938, 0.4400, 0.3675, 0.3650, 0.5675, 0.5767],
[0.6072, 0.4029, 0.7038, 0.2150, 0.3913, 0.2267, 0.5516, 0.5507],
[0.0000, 0.0000, 0.6413, 0.1900, 0.4238, 0.1883, 0.5487, 0.5700],
[0.6150, 0.3935, 0.8696, 0.5158, 0.4647, 0.5329, 0.6041, 0.5153],
[0.6185, 0.4067, 0.8838, 0.4450, 0.4038, 0.4733, 0.5213, 0.5142]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.01935047988081351
step: 40
running loss: 0.00048376199702033774
Train Steps: 40/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334],
[0.6042, 0.3990, 0.6831, 0.2875, 0.3500, 0.3133, 0.5143, 0.5510],
[0.6250, 0.4054, 0.8770, 0.4723, 0.4662, 0.5367, 0.6162, 0.5433],
[0.6200, 0.4086, 0.8414, 0.2974, 0.4117, 0.2274, 0.5869, 0.5391],
[0.6304, 0.4029, 0.8413, 0.5217, 0.4125, 0.5617, 0.7089, 0.5679],
[0.6198, 0.4115, 0.7762, 0.2717, 0.3713, 0.3200, 0.5837, 0.5683],
[0.6173, 0.4013, 0.8713, 0.4640, 0.4800, 0.5700, 0.6025, 0.5600],
[0.6200, 0.3993, 0.8519, 0.4923, 0.3962, 0.4717, 0.6013, 0.5433]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6516, 0.4067, 0.7639, 0.2336, 0.3768, 0.3196, 0.6163, 0.5172],
[0.5634, 0.3469, 0.7085, 0.2859, 0.3648, 0.3074, 0.5218, 0.5476],
[0.6775, 0.4278, 0.8840, 0.4648, 0.4622, 0.5190, 0.6203, 0.5268],
[0.6685, 0.4191, 0.8493, 0.2953, 0.4208, 0.2197, 0.5933, 0.5217],
[0.6808, 0.4332, 0.8404, 0.5141, 0.4195, 0.5606, 0.7106, 0.5578],
[0.6479, 0.4090, 0.7783, 0.2634, 0.3727, 0.3091, 0.5903, 0.5485],
[0.6854, 0.4254, 0.8617, 0.4614, 0.4806, 0.5480, 0.6056, 0.5317],
[0.6326, 0.3945, 0.8462, 0.4798, 0.3954, 0.4619, 0.6060, 0.5428]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334],
[0.6042, 0.3990, 0.6831, 0.2875, 0.3500, 0.3133, 0.5143, 0.5510],
[0.6250, 0.4054, 0.8770, 0.4723, 0.4663, 0.5367, 0.6162, 0.5433],
[0.6199, 0.4086, 0.8414, 0.2974, 0.4117, 0.2274, 0.5869, 0.5391],
[0.6304, 0.4029, 0.8413, 0.5217, 0.4125, 0.5617, 0.7089, 0.5679],
[0.6198, 0.4115, 0.7763, 0.2717, 0.3713, 0.3200, 0.5838, 0.5683],
[0.6173, 0.4013, 0.8713, 0.4640, 0.4800, 0.5700, 0.6025, 0.5600],
[0.6200, 0.3993, 0.8519, 0.4923, 0.3963, 0.4717, 0.6012, 0.5433]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.019759502029046416
step: 41
running loss: 0.0004819390738791809
Train Steps: 41/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6187, 0.4104, 0.7126, 0.2069, 0.3950, 0.2517, 0.5913, 0.5683],
[0.6264, 0.4069, 0.7900, 0.1650, 0.4275, 0.2267, 0.6290, 0.4947],
[0.6136, 0.3955, 0.8400, 0.3267, 0.3500, 0.4200, 0.5863, 0.5467],
[0.6213, 0.4001, 0.7712, 0.2117, 0.4338, 0.1800, 0.5850, 0.5183],
[0.6248, 0.4185, 0.8500, 0.5767, 0.4463, 0.4550, 0.5613, 0.5917],
[0.6246, 0.4090, 0.6964, 0.2027, 0.3925, 0.2683, 0.6088, 0.5583],
[0.6204, 0.4013, 0.8075, 0.2400, 0.4313, 0.2050, 0.5800, 0.5150],
[0.6332, 0.4165, 0.9100, 0.3350, 0.4188, 0.3683, 0.7438, 0.5528]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6332, 0.3977, 0.6971, 0.2190, 0.3922, 0.2525, 0.5969, 0.5592],
[0.6500, 0.3900, 0.7688, 0.1750, 0.4375, 0.2283, 0.6539, 0.5060],
[0.5769, 0.3600, 0.8426, 0.3437, 0.3481, 0.4058, 0.5943, 0.5408],
[0.6526, 0.3892, 0.7577, 0.2210, 0.4365, 0.1818, 0.5951, 0.5200],
[0.7137, 0.4460, 0.8387, 0.6048, 0.4453, 0.4621, 0.5559, 0.5927],
[0.6569, 0.4075, 0.6810, 0.2255, 0.3898, 0.2605, 0.5880, 0.5565],
[0.6181, 0.3658, 0.7769, 0.2475, 0.4378, 0.2099, 0.5868, 0.5283],
[0.6375, 0.4019, 0.9070, 0.3575, 0.4146, 0.3607, 0.7427, 0.5510]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6187, 0.4103, 0.7126, 0.2069, 0.3950, 0.2517, 0.5913, 0.5683],
[0.6264, 0.4069, 0.7900, 0.1650, 0.4275, 0.2267, 0.6290, 0.4947],
[0.6136, 0.3955, 0.8400, 0.3267, 0.3500, 0.4200, 0.5863, 0.5467],
[0.6213, 0.4001, 0.7713, 0.2117, 0.4338, 0.1800, 0.5850, 0.5183],
[0.6248, 0.4185, 0.8500, 0.5767, 0.4462, 0.4550, 0.5612, 0.5917],
[0.6246, 0.4090, 0.6964, 0.2027, 0.3925, 0.2683, 0.6087, 0.5583],
[0.6204, 0.4013, 0.8075, 0.2400, 0.4313, 0.2050, 0.5800, 0.5150],
[0.6332, 0.4165, 0.9100, 0.3350, 0.4187, 0.3683, 0.7438, 0.5528]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.02012144192121923
step: 42
running loss: 0.00047908195050521974
Train Steps: 42/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.8850, 0.2817, 0.5112, 0.2183, 0.7184, 0.5436],
[0.6275, 0.4024, 0.7722, 0.2080, 0.4392, 0.2234, 0.6435, 0.5290],
[0.6109, 0.4003, 0.8650, 0.4883, 0.4775, 0.4867, 0.5175, 0.5683],
[0.6075, 0.4000, 0.8513, 0.5183, 0.4510, 0.5329, 0.5180, 0.5280],
[0.6213, 0.4131, 0.8438, 0.3550, 0.3513, 0.4400, 0.5716, 0.5123],
[0.6143, 0.4055, 0.8150, 0.2767, 0.3825, 0.2567, 0.5173, 0.4901],
[0.6176, 0.4017, 0.8788, 0.5100, 0.4075, 0.5250, 0.5913, 0.5033],
[0.6245, 0.4115, 0.8700, 0.4883, 0.4625, 0.5517, 0.6100, 0.5217]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.0542, -0.0027, 0.8669, 0.2556, 0.5190, 0.1917, 0.7471, 0.5670],
[ 0.6373, 0.3760, 0.7465, 0.2069, 0.4317, 0.2301, 0.6611, 0.5499],
[ 0.6509, 0.4078, 0.8469, 0.4730, 0.4775, 0.4878, 0.5511, 0.5893],
[ 0.6428, 0.3937, 0.8409, 0.5153, 0.4562, 0.5230, 0.5367, 0.5416],
[ 0.6606, 0.4011, 0.8424, 0.3529, 0.3611, 0.4268, 0.5778, 0.5345],
[ 0.6471, 0.4007, 0.7889, 0.2801, 0.3805, 0.2498, 0.5351, 0.5312],
[ 0.6499, 0.3934, 0.8639, 0.4930, 0.4056, 0.5281, 0.6079, 0.5312],
[ 0.6847, 0.4187, 0.8458, 0.4770, 0.4485, 0.5440, 0.6391, 0.5610]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.8850, 0.2817, 0.5113, 0.2183, 0.7184, 0.5436],
[0.6275, 0.4024, 0.7722, 0.2080, 0.4392, 0.2234, 0.6435, 0.5290],
[0.6109, 0.4003, 0.8650, 0.4883, 0.4775, 0.4867, 0.5175, 0.5683],
[0.6075, 0.4000, 0.8512, 0.5183, 0.4510, 0.5329, 0.5180, 0.5280],
[0.6213, 0.4131, 0.8438, 0.3550, 0.3512, 0.4400, 0.5716, 0.5123],
[0.6143, 0.4055, 0.8150, 0.2767, 0.3825, 0.2567, 0.5173, 0.4901],
[0.6176, 0.4017, 0.8788, 0.5100, 0.4075, 0.5250, 0.5913, 0.5033],
[0.6245, 0.4115, 0.8700, 0.4883, 0.4625, 0.5517, 0.6100, 0.5217]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.020595025533111766
step: 43
running loss: 0.0004789540821653899
Train Steps: 43/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6157, 0.3956, 0.8323, 0.4138, 0.3479, 0.4431, 0.5914, 0.5131],
[0.6127, 0.4118, 0.8650, 0.5083, 0.4088, 0.5367, 0.5300, 0.5456],
[0.6086, 0.4019, 0.7782, 0.4278, 0.3625, 0.4350, 0.5150, 0.5285],
[0.6113, 0.4006, 0.8700, 0.5350, 0.3638, 0.3767, 0.5097, 0.4882],
[0.6259, 0.4133, 0.8200, 0.2317, 0.5025, 0.1533, 0.6250, 0.4947],
[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150],
[0.6339, 0.4102, 0.9088, 0.4767, 0.3925, 0.5283, 0.7509, 0.5390],
[0.6216, 0.4100, 0.7350, 0.2067, 0.4325, 0.2050, 0.5950, 0.5333]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5879, 0.3822, 0.8430, 0.3862, 0.3465, 0.4548, 0.5848, 0.5375],
[0.6455, 0.4225, 0.8797, 0.4847, 0.4201, 0.5532, 0.5451, 0.5790],
[0.5972, 0.3725, 0.7776, 0.4046, 0.3612, 0.4352, 0.5180, 0.5511],
[0.5742, 0.3705, 0.8650, 0.5016, 0.3802, 0.4013, 0.5332, 0.5245],
[0.6719, 0.4335, 0.8126, 0.2123, 0.5088, 0.1532, 0.6522, 0.5176],
[0.6547, 0.4174, 0.8908, 0.4526, 0.4380, 0.5870, 0.6292, 0.5493],
[0.6425, 0.4106, 0.8989, 0.4601, 0.4023, 0.5418, 0.7542, 0.5687],
[0.6464, 0.4193, 0.7281, 0.1871, 0.4320, 0.2155, 0.6112, 0.5420]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6157, 0.3956, 0.8323, 0.4138, 0.3479, 0.4431, 0.5914, 0.5131],
[0.6127, 0.4118, 0.8650, 0.5083, 0.4087, 0.5367, 0.5300, 0.5456],
[0.6086, 0.4019, 0.7782, 0.4278, 0.3625, 0.4350, 0.5150, 0.5285],
[0.6113, 0.4006, 0.8700, 0.5350, 0.3638, 0.3767, 0.5097, 0.4882],
[0.6259, 0.4132, 0.8200, 0.2317, 0.5025, 0.1533, 0.6250, 0.4947],
[0.6251, 0.4108, 0.8888, 0.4700, 0.4325, 0.5817, 0.6075, 0.5150],
[0.6339, 0.4102, 0.9087, 0.4767, 0.3925, 0.5283, 0.7509, 0.5390],
[0.6216, 0.4100, 0.7350, 0.2067, 0.4325, 0.2050, 0.5950, 0.5333]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.02098468688200228
step: 44
running loss: 0.00047692470186368814
Train Steps: 44/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6250, 0.4106, 0.8700, 0.3717, 0.3588, 0.4967, 0.6038, 0.5167],
[0.6090, 0.4045, 0.7250, 0.2100, 0.4075, 0.2300, 0.5476, 0.5663],
[0.6284, 0.4127, 0.8538, 0.5867, 0.4363, 0.5083, 0.6038, 0.5433],
[0.6162, 0.3949, 0.8838, 0.4517, 0.4250, 0.5183, 0.5837, 0.5500],
[0.6252, 0.4158, 0.8988, 0.4083, 0.3788, 0.4783, 0.6225, 0.5633],
[0.6199, 0.4065, 0.7598, 0.2385, 0.4317, 0.1981, 0.5933, 0.5221],
[0.6300, 0.4102, 0.9088, 0.4433, 0.4088, 0.3067, 0.6820, 0.5540],
[0.6276, 0.4095, 0.8237, 0.2250, 0.4662, 0.1783, 0.6171, 0.4869]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5912, 0.3878, 0.8807, 0.3672, 0.3595, 0.4962, 0.6225, 0.5206],
[0.5541, 0.3758, 0.7213, 0.2091, 0.3880, 0.2429, 0.5415, 0.5559],
[0.5959, 0.3878, 0.8543, 0.5744, 0.4372, 0.5065, 0.5773, 0.5287],
[0.5881, 0.3708, 0.8818, 0.4274, 0.4238, 0.5098, 0.5767, 0.5491],
[0.6098, 0.4083, 0.8911, 0.3873, 0.3684, 0.4666, 0.6218, 0.5463],
[0.6152, 0.3969, 0.7550, 0.2310, 0.4111, 0.2159, 0.5823, 0.5025],
[0.5669, 0.3730, 0.9082, 0.4236, 0.4116, 0.3081, 0.6940, 0.5416],
[0.6773, 0.4370, 0.8223, 0.2095, 0.4636, 0.1752, 0.6199, 0.4743]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6250, 0.4105, 0.8700, 0.3717, 0.3587, 0.4967, 0.6037, 0.5167],
[0.6090, 0.4045, 0.7250, 0.2100, 0.4075, 0.2300, 0.5476, 0.5663],
[0.6284, 0.4127, 0.8537, 0.5867, 0.4363, 0.5083, 0.6037, 0.5433],
[0.6162, 0.3949, 0.8838, 0.4517, 0.4250, 0.5183, 0.5838, 0.5500],
[0.6252, 0.4158, 0.8988, 0.4083, 0.3787, 0.4783, 0.6225, 0.5633],
[0.6199, 0.4065, 0.7598, 0.2385, 0.4317, 0.1981, 0.5933, 0.5221],
[0.6300, 0.4102, 0.9087, 0.4433, 0.4087, 0.3067, 0.6820, 0.5540],
[0.6276, 0.4095, 0.8238, 0.2250, 0.4663, 0.1783, 0.6171, 0.4869]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.021359838166972622
step: 45
running loss: 0.0004746630703771694
Train Steps: 45/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6329, 0.4055, 0.9050, 0.4783, 0.3613, 0.3917, 0.6464, 0.5019],
[0.6218, 0.4137, 0.7263, 0.2233, 0.4075, 0.2650, 0.6212, 0.5783],
[0.6145, 0.4007, 0.8775, 0.4533, 0.4562, 0.5533, 0.6088, 0.5533],
[0.6227, 0.4193, 0.8838, 0.4933, 0.3663, 0.3733, 0.5637, 0.5633],
[ nan, nan, 0.8750, 0.2467, 0.5138, 0.2617, 0.7382, 0.5552],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4012, 0.4633, 0.5338, 0.5767],
[0.6200, 0.3998, 0.8850, 0.3950, 0.3500, 0.4650, 0.6138, 0.5400],
[0.6137, 0.4084, 0.8076, 0.3889, 0.3650, 0.3150, 0.5356, 0.5896]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5748, 0.3760, 0.9063, 0.4830, 0.3700, 0.4068, 0.6425, 0.4730],
[0.6236, 0.4329, 0.7296, 0.2235, 0.3907, 0.2747, 0.6246, 0.5548],
[0.5967, 0.4017, 0.8822, 0.4524, 0.4647, 0.5588, 0.6056, 0.5269],
[0.6249, 0.4424, 0.8794, 0.4925, 0.3538, 0.3837, 0.5687, 0.5527],
[0.0318, 0.0366, 0.8491, 0.2514, 0.5056, 0.2510, 0.7441, 0.5336],
[0.6129, 0.4187, 0.8801, 0.5066, 0.4024, 0.4690, 0.5349, 0.5547],
[0.5513, 0.3737, 0.8868, 0.4114, 0.3565, 0.4728, 0.6038, 0.5205],
[0.6103, 0.4197, 0.8110, 0.4017, 0.3478, 0.3106, 0.5409, 0.5645]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6329, 0.4055, 0.9050, 0.4783, 0.3613, 0.3917, 0.6464, 0.5019],
[0.6218, 0.4137, 0.7262, 0.2233, 0.4075, 0.2650, 0.6212, 0.5783],
[0.6145, 0.4007, 0.8775, 0.4533, 0.4563, 0.5533, 0.6087, 0.5533],
[0.6227, 0.4193, 0.8838, 0.4933, 0.3663, 0.3733, 0.5638, 0.5633],
[0.0000, 0.0000, 0.8750, 0.2467, 0.5138, 0.2617, 0.7382, 0.5552],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4013, 0.4633, 0.5337, 0.5767],
[0.6200, 0.3998, 0.8850, 0.3950, 0.3500, 0.4650, 0.6137, 0.5400],
[0.6137, 0.4084, 0.8076, 0.3889, 0.3650, 0.3150, 0.5356, 0.5896]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.021688233740860596
step: 46
running loss: 0.00047148334219262165
Train Steps: 46/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.7268, 0.2333, 0.4125, 0.1933, 0.5112, 0.5383],
[ nan, nan, 0.8488, 0.2300, 0.5563, 0.2100, 0.7390, 0.5679],
[0.6332, 0.4165, 0.9100, 0.3350, 0.4188, 0.3683, 0.7438, 0.5528],
[0.6274, 0.4117, 0.8100, 0.5801, 0.4000, 0.4583, 0.5582, 0.6118],
[0.6314, 0.4050, 0.8227, 0.5431, 0.4150, 0.5517, 0.7121, 0.5690],
[0.6064, 0.4019, 0.8650, 0.4517, 0.4037, 0.5367, 0.5703, 0.5609],
[0.6307, 0.4060, 0.8950, 0.5183, 0.3750, 0.3850, 0.6338, 0.4938],
[0.6227, 0.4049, 0.8750, 0.5367, 0.3775, 0.3667, 0.5725, 0.5317]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.0505, 0.0629, 0.7221, 0.2172, 0.3990, 0.1907, 0.4836, 0.5072],
[0.0711, 0.0606, 0.8532, 0.2203, 0.5276, 0.2427, 0.7032, 0.5434],
[0.6273, 0.4385, 0.9236, 0.3451, 0.4138, 0.3583, 0.7116, 0.5344],
[0.6543, 0.4615, 0.8308, 0.5804, 0.3941, 0.4709, 0.5442, 0.5924],
[0.6330, 0.4136, 0.8432, 0.5356, 0.4166, 0.5505, 0.7111, 0.5536],
[0.6060, 0.4188, 0.8725, 0.4506, 0.4011, 0.5457, 0.5526, 0.5252],
[0.6341, 0.4384, 0.9139, 0.5257, 0.3681, 0.3829, 0.6115, 0.4767],
[0.6443, 0.4431, 0.8885, 0.5408, 0.3817, 0.3726, 0.5642, 0.5151]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.7268, 0.2333, 0.4125, 0.1933, 0.5113, 0.5383],
[0.0000, 0.0000, 0.8487, 0.2300, 0.5562, 0.2100, 0.7390, 0.5679],
[0.6332, 0.4165, 0.9100, 0.3350, 0.4187, 0.3683, 0.7438, 0.5528],
[0.6274, 0.4117, 0.8100, 0.5801, 0.4000, 0.4583, 0.5582, 0.6118],
[0.6314, 0.4050, 0.8227, 0.5431, 0.4150, 0.5517, 0.7121, 0.5690],
[0.6064, 0.4019, 0.8650, 0.4517, 0.4038, 0.5367, 0.5703, 0.5609],
[0.6307, 0.4060, 0.8950, 0.5183, 0.3750, 0.3850, 0.6338, 0.4938],
[0.6227, 0.4049, 0.8750, 0.5367, 0.3775, 0.3667, 0.5725, 0.5317]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.022245831292821094
step: 47
running loss: 0.0004733155594217254
Train Steps: 47/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6307, 0.3998, 0.8500, 0.5233, 0.3850, 0.5050, 0.7446, 0.5320],
[0.6164, 0.3972, 0.7818, 0.3381, 0.3599, 0.3387, 0.5880, 0.5153],
[0.6209, 0.3920, 0.8650, 0.5367, 0.4400, 0.5067, 0.6025, 0.4950],
[0.6226, 0.4185, 0.8850, 0.5500, 0.3800, 0.4250, 0.5625, 0.5617],
[0.6357, 0.4159, 0.8788, 0.5583, 0.3638, 0.4433, 0.6488, 0.5297],
[0.6137, 0.4035, 0.8850, 0.4417, 0.3900, 0.4283, 0.5449, 0.5617],
[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334],
[0.6198, 0.4115, 0.7762, 0.2717, 0.3713, 0.3200, 0.5837, 0.5683]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5713, 0.3957, 0.8536, 0.5315, 0.3781, 0.5025, 0.6913, 0.5320],
[0.5430, 0.3901, 0.7948, 0.3414, 0.3455, 0.3305, 0.5656, 0.5079],
[0.5416, 0.3661, 0.8745, 0.5353, 0.4398, 0.4958, 0.5801, 0.4915],
[0.6007, 0.4279, 0.9035, 0.5517, 0.3764, 0.4135, 0.5504, 0.5678],
[0.6196, 0.4281, 0.8863, 0.5627, 0.3712, 0.4381, 0.6375, 0.5271],
[0.6077, 0.4280, 0.9010, 0.4555, 0.3897, 0.4254, 0.5202, 0.5663],
[0.5874, 0.4125, 0.7613, 0.2292, 0.3627, 0.3174, 0.5922, 0.5303],
[0.5564, 0.3966, 0.7779, 0.2761, 0.3650, 0.3021, 0.5742, 0.5564]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6307, 0.3998, 0.8500, 0.5233, 0.3850, 0.5050, 0.7446, 0.5320],
[0.6164, 0.3972, 0.7818, 0.3381, 0.3599, 0.3387, 0.5880, 0.5153],
[0.6209, 0.3920, 0.8650, 0.5367, 0.4400, 0.5067, 0.6025, 0.4950],
[0.6226, 0.4185, 0.8850, 0.5500, 0.3800, 0.4250, 0.5625, 0.5617],
[0.6357, 0.4159, 0.8788, 0.5583, 0.3638, 0.4433, 0.6488, 0.5297],
[0.6137, 0.4035, 0.8850, 0.4417, 0.3900, 0.4283, 0.5449, 0.5617],
[0.6189, 0.3961, 0.7589, 0.2256, 0.3759, 0.3280, 0.6184, 0.5334],
[0.6198, 0.4115, 0.7763, 0.2717, 0.3713, 0.3200, 0.5838, 0.5683]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.02273709830478765
step: 48
running loss: 0.0004736895480164094
Train Steps: 48/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6286, 0.4086, 0.8408, 0.2801, 0.4163, 0.2800, 0.6725, 0.5393],
[0.6239, 0.4061, 0.8850, 0.4600, 0.4225, 0.5200, 0.6138, 0.5450],
[0.6246, 0.4008, 0.8757, 0.5088, 0.4101, 0.5392, 0.6644, 0.5133],
[0.6271, 0.4020, 0.8375, 0.6083, 0.3925, 0.4867, 0.6037, 0.4626],
[0.6262, 0.4052, 0.8888, 0.4700, 0.3675, 0.5117, 0.6350, 0.5233],
[0.6127, 0.4115, 0.7163, 0.2883, 0.3625, 0.2950, 0.5327, 0.5495],
[0.6206, 0.4001, 0.8900, 0.3933, 0.3588, 0.3567, 0.5837, 0.5083],
[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5733, 0.3989, 0.8587, 0.2864, 0.4182, 0.2777, 0.6666, 0.5564],
[0.5894, 0.4048, 0.8967, 0.4735, 0.4157, 0.5211, 0.6128, 0.5577],
[0.5565, 0.3758, 0.9014, 0.5329, 0.4087, 0.5500, 0.6531, 0.5286],
[0.5870, 0.3902, 0.8603, 0.6248, 0.4068, 0.4734, 0.6039, 0.4739],
[0.5898, 0.4098, 0.9070, 0.4832, 0.3771, 0.5000, 0.6268, 0.5352],
[0.5793, 0.4194, 0.7333, 0.2957, 0.3599, 0.2952, 0.5088, 0.5769],
[0.5803, 0.4017, 0.9111, 0.4044, 0.3606, 0.3576, 0.5664, 0.5195],
[0.5550, 0.3854, 0.8797, 0.2995, 0.4887, 0.2015, 0.6591, 0.5446]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6286, 0.4086, 0.8408, 0.2801, 0.4162, 0.2800, 0.6725, 0.5393],
[0.6239, 0.4061, 0.8850, 0.4600, 0.4225, 0.5200, 0.6137, 0.5450],
[0.6246, 0.4008, 0.8757, 0.5088, 0.4101, 0.5392, 0.6644, 0.5133],
[0.6271, 0.4020, 0.8375, 0.6083, 0.3925, 0.4867, 0.6037, 0.4626],
[0.6262, 0.4052, 0.8888, 0.4700, 0.3675, 0.5117, 0.6350, 0.5233],
[0.6127, 0.4114, 0.7163, 0.2883, 0.3625, 0.2950, 0.5327, 0.5495],
[0.6206, 0.4001, 0.8900, 0.3933, 0.3587, 0.3567, 0.5838, 0.5083],
[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.023219668451929465
step: 49
running loss: 0.0004738707847332544
Train Steps: 49/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6211, 0.3993, 0.7650, 0.1933, 0.4575, 0.1550, 0.5965, 0.4895],
[0.6200, 0.4039, 0.8880, 0.4799, 0.3625, 0.4285, 0.5866, 0.5148],
[0.6260, 0.4133, 0.8800, 0.5117, 0.3713, 0.3283, 0.6223, 0.4967],
[0.6196, 0.4090, 0.8450, 0.3900, 0.3575, 0.3933, 0.5975, 0.5583],
[0.6200, 0.4049, 0.8638, 0.5617, 0.4125, 0.5100, 0.6013, 0.5317],
[0.6286, 0.4097, 0.8107, 0.2414, 0.4425, 0.2483, 0.6745, 0.5385],
[0.6226, 0.4103, 0.8575, 0.3450, 0.4388, 0.2067, 0.5787, 0.5383],
[0.6274, 0.4087, 0.8375, 0.5700, 0.4025, 0.4800, 0.5700, 0.6117]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5143, 0.3352, 0.7564, 0.1950, 0.4566, 0.1685, 0.6002, 0.4866],
[0.6141, 0.3955, 0.8951, 0.4780, 0.3630, 0.4330, 0.5919, 0.5264],
[0.6263, 0.4158, 0.8824, 0.5108, 0.3786, 0.3296, 0.6314, 0.5002],
[0.6027, 0.3875, 0.8526, 0.3889, 0.3475, 0.4036, 0.6088, 0.5667],
[0.5613, 0.3617, 0.8650, 0.5623, 0.4191, 0.5066, 0.6014, 0.5359],
[0.5758, 0.3717, 0.8225, 0.2557, 0.4555, 0.2425, 0.6712, 0.5450],
[0.5658, 0.3698, 0.8539, 0.3462, 0.4375, 0.2139, 0.5617, 0.5394],
[0.5803, 0.3703, 0.8256, 0.5701, 0.4086, 0.4908, 0.5831, 0.6090]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6211, 0.3993, 0.7650, 0.1933, 0.4575, 0.1550, 0.5965, 0.4895],
[0.6201, 0.4039, 0.8880, 0.4799, 0.3625, 0.4285, 0.5866, 0.5148],
[0.6260, 0.4133, 0.8800, 0.5117, 0.3713, 0.3283, 0.6223, 0.4967],
[0.6196, 0.4090, 0.8450, 0.3900, 0.3575, 0.3933, 0.5975, 0.5583],
[0.6199, 0.4049, 0.8637, 0.5617, 0.4125, 0.5100, 0.6012, 0.5317],
[0.6286, 0.4097, 0.8107, 0.2414, 0.4425, 0.2483, 0.6745, 0.5385],
[0.6226, 0.4103, 0.8575, 0.3450, 0.4387, 0.2067, 0.5788, 0.5383],
[0.6274, 0.4087, 0.8375, 0.5700, 0.4025, 0.4800, 0.5700, 0.6117]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.023799304181011394
step: 50
running loss: 0.0004759860836202279
Train Steps: 50/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6200, 0.3998, 0.8850, 0.3950, 0.3500, 0.4650, 0.6138, 0.5400],
[0.6261, 0.4131, 0.8938, 0.3550, 0.4000, 0.2683, 0.6188, 0.5283],
[0.6248, 0.4185, 0.8500, 0.5767, 0.4463, 0.4550, 0.5613, 0.5917],
[0.6336, 0.4086, 0.8900, 0.3950, 0.3900, 0.2950, 0.6504, 0.5066],
[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395],
[0.6164, 0.4066, 0.6625, 0.3033, 0.3775, 0.2967, 0.5725, 0.5833],
[0.6204, 0.4110, 0.7913, 0.2667, 0.4062, 0.2500, 0.6225, 0.5367],
[0.6201, 0.4064, 0.8688, 0.5050, 0.4225, 0.5100, 0.6138, 0.5500]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6089, 0.3839, 0.8779, 0.4035, 0.3542, 0.4681, 0.6114, 0.5448],
[0.6044, 0.3894, 0.8943, 0.3586, 0.4072, 0.2674, 0.6360, 0.5405],
[0.5996, 0.3847, 0.8351, 0.5734, 0.4571, 0.4574, 0.5717, 0.5991],
[0.6905, 0.4306, 0.9103, 0.3863, 0.3879, 0.2945, 0.6742, 0.5114],
[0.6187, 0.3879, 0.8670, 0.5505, 0.3616, 0.3690, 0.5881, 0.5461],
[0.4900, 0.3153, 0.6603, 0.3017, 0.3806, 0.3047, 0.5667, 0.5835],
[0.6272, 0.4046, 0.7958, 0.2784, 0.4054, 0.2550, 0.6150, 0.5347],
[0.5972, 0.3814, 0.8602, 0.5074, 0.4322, 0.5232, 0.6212, 0.5594]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6200, 0.3998, 0.8850, 0.3950, 0.3500, 0.4650, 0.6137, 0.5400],
[0.6261, 0.4131, 0.8938, 0.3550, 0.4000, 0.2683, 0.6187, 0.5283],
[0.6248, 0.4185, 0.8500, 0.5767, 0.4462, 0.4550, 0.5612, 0.5917],
[0.6336, 0.4086, 0.8900, 0.3950, 0.3900, 0.2950, 0.6504, 0.5066],
[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395],
[0.6164, 0.4066, 0.6625, 0.3033, 0.3775, 0.2967, 0.5725, 0.5833],
[0.6204, 0.4110, 0.7912, 0.2667, 0.4062, 0.2500, 0.6225, 0.5367],
[0.6201, 0.4064, 0.8687, 0.5050, 0.4225, 0.5100, 0.6137, 0.5500]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.024365292192669585
step: 51
running loss: 0.0004777508273072468
Train Steps: 51/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6261, 0.4045, 0.8865, 0.5369, 0.3895, 0.4859, 0.6683, 0.5249],
[0.6364, 0.4165, 0.9088, 0.4367, 0.4075, 0.3150, 0.6448, 0.5297],
[0.6102, 0.4020, 0.8638, 0.3717, 0.3625, 0.5017, 0.6038, 0.5500],
[0.6263, 0.4030, 0.9000, 0.4767, 0.3800, 0.5167, 0.6415, 0.4771],
[0.6202, 0.4053, 0.8638, 0.5283, 0.4546, 0.5108, 0.5900, 0.5133],
[0.6265, 0.4251, 0.7113, 0.3550, 0.4375, 0.2117, 0.5587, 0.6118],
[0.6266, 0.4101, 0.8350, 0.2333, 0.3950, 0.2950, 0.6264, 0.4921],
[0.6277, 0.4083, 0.8350, 0.2717, 0.4562, 0.1800, 0.5918, 0.4878]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6439, 0.4036, 0.8803, 0.5353, 0.3712, 0.4872, 0.6681, 0.5360],
[0.6116, 0.3821, 0.8909, 0.4335, 0.4142, 0.3066, 0.6441, 0.5334],
[0.5969, 0.3855, 0.8576, 0.3654, 0.3585, 0.4943, 0.6255, 0.5415],
[0.6176, 0.3881, 0.8856, 0.4795, 0.3741, 0.5054, 0.6522, 0.4894],
[0.6183, 0.3785, 0.8550, 0.5274, 0.4576, 0.5067, 0.5971, 0.5188],
[0.5650, 0.3853, 0.7067, 0.3604, 0.4218, 0.2029, 0.5690, 0.6241],
[0.6409, 0.4029, 0.8242, 0.2356, 0.3934, 0.2916, 0.6437, 0.5114],
[0.5672, 0.3577, 0.8080, 0.2659, 0.4671, 0.1860, 0.5837, 0.4921]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6261, 0.4045, 0.8865, 0.5369, 0.3895, 0.4859, 0.6683, 0.5249],
[0.6364, 0.4165, 0.9087, 0.4367, 0.4075, 0.3150, 0.6448, 0.5297],
[0.6102, 0.4020, 0.8637, 0.3717, 0.3625, 0.5017, 0.6037, 0.5500],
[0.6263, 0.4029, 0.9000, 0.4767, 0.3800, 0.5167, 0.6415, 0.4771],
[0.6202, 0.4053, 0.8637, 0.5283, 0.4546, 0.5108, 0.5900, 0.5133],
[0.6265, 0.4251, 0.7113, 0.3550, 0.4375, 0.2117, 0.5587, 0.6118],
[0.6266, 0.4101, 0.8350, 0.2333, 0.3950, 0.2950, 0.6264, 0.4921],
[0.6277, 0.4083, 0.8350, 0.2717, 0.4563, 0.1800, 0.5918, 0.4878]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.02468289455282502
step: 52
running loss: 0.00047467104909278883
Train Steps: 52/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6260, 0.4253, 0.8938, 0.4400, 0.3675, 0.3650, 0.5675, 0.5767],
[ nan, nan, 0.7225, 0.2167, 0.3987, 0.2283, 0.5427, 0.5181],
[0.6336, 0.4191, 0.8938, 0.5167, 0.3937, 0.3517, 0.7343, 0.5748],
[0.6250, 0.4131, 0.8688, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367],
[0.6200, 0.3913, 0.8788, 0.5217, 0.4075, 0.5100, 0.6060, 0.4913],
[0.6214, 0.4175, 0.7300, 0.2883, 0.4338, 0.2167, 0.5698, 0.5773],
[0.6156, 0.4125, 0.8850, 0.4833, 0.4550, 0.5817, 0.5765, 0.5084],
[0.6267, 0.4094, 0.8712, 0.3083, 0.4400, 0.2267, 0.6250, 0.5200]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6829, 0.4331, 0.8681, 0.4453, 0.3672, 0.3511, 0.5824, 0.5813],
[0.0488, 0.0061, 0.7005, 0.2047, 0.4013, 0.2191, 0.5391, 0.5093],
[0.6749, 0.4260, 0.8833, 0.5126, 0.4011, 0.3471, 0.7377, 0.5690],
[0.6430, 0.4035, 0.8453, 0.2920, 0.4334, 0.2236, 0.6163, 0.5345],
[0.6359, 0.3727, 0.8428, 0.5143, 0.4045, 0.5073, 0.6094, 0.4836],
[0.6329, 0.4247, 0.7100, 0.2810, 0.4323, 0.2096, 0.5824, 0.5666],
[0.6682, 0.4187, 0.8638, 0.4755, 0.4442, 0.5742, 0.5900, 0.5133],
[0.6326, 0.3849, 0.8501, 0.2994, 0.4474, 0.2098, 0.6189, 0.5257]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6260, 0.4253, 0.8938, 0.4400, 0.3675, 0.3650, 0.5675, 0.5767],
[0.0000, 0.0000, 0.7225, 0.2167, 0.3988, 0.2283, 0.5427, 0.5181],
[0.6336, 0.4191, 0.8938, 0.5167, 0.3938, 0.3517, 0.7343, 0.5748],
[0.6250, 0.4131, 0.8687, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367],
[0.6199, 0.3913, 0.8788, 0.5217, 0.4075, 0.5100, 0.6060, 0.4913],
[0.6214, 0.4175, 0.7300, 0.2883, 0.4338, 0.2167, 0.5698, 0.5773],
[0.6155, 0.4124, 0.8850, 0.4833, 0.4550, 0.5817, 0.5765, 0.5084],
[0.6267, 0.4094, 0.8712, 0.3083, 0.4400, 0.2267, 0.6250, 0.5200]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.024981963797472417
step: 53
running loss: 0.00047135780749947955
Train Steps: 53/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6175, 0.4091, 0.7863, 0.2800, 0.3638, 0.3583, 0.6188, 0.5433],
[0.6135, 0.4115, 0.8838, 0.4667, 0.4288, 0.6050, 0.5778, 0.5097],
[0.6203, 0.4056, 0.8942, 0.4086, 0.3643, 0.3617, 0.5917, 0.5482],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098],
[0.6127, 0.4115, 0.7163, 0.2883, 0.3625, 0.2950, 0.5327, 0.5495],
[ nan, nan, 0.8900, 0.3217, 0.5038, 0.2233, 0.6694, 0.5609],
[0.6164, 0.4119, 0.7913, 0.2650, 0.3538, 0.3500, 0.5614, 0.5038],
[0.6264, 0.4049, 0.8988, 0.4633, 0.3813, 0.4983, 0.6326, 0.4843]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6558, 0.4323, 0.7786, 0.2756, 0.3678, 0.3484, 0.6330, 0.5481],
[ 0.6911, 0.4423, 0.8657, 0.4683, 0.4272, 0.5781, 0.5810, 0.5236],
[ 0.6710, 0.4255, 0.8808, 0.4174, 0.3541, 0.3507, 0.6189, 0.5552],
[ 0.6651, 0.4252, 0.8548, 0.4724, 0.3746, 0.5103, 0.6280, 0.5095],
[ 0.6851, 0.4552, 0.7107, 0.2866, 0.3654, 0.2804, 0.5467, 0.5620],
[-0.0314, -0.0217, 0.8840, 0.3413, 0.5100, 0.1859, 0.7191, 0.5681],
[ 0.6652, 0.4315, 0.7833, 0.2691, 0.3491, 0.3422, 0.5961, 0.5102],
[ 0.6593, 0.4110, 0.8902, 0.4746, 0.3892, 0.4822, 0.6407, 0.4775]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6175, 0.4091, 0.7862, 0.2800, 0.3638, 0.3583, 0.6187, 0.5433],
[0.6135, 0.4115, 0.8838, 0.4667, 0.4288, 0.6050, 0.5778, 0.5097],
[0.6203, 0.4056, 0.8942, 0.4086, 0.3643, 0.3617, 0.5917, 0.5482],
[0.6132, 0.3930, 0.8672, 0.4754, 0.3712, 0.5222, 0.5974, 0.5098],
[0.6127, 0.4114, 0.7163, 0.2883, 0.3625, 0.2950, 0.5327, 0.5495],
[0.0000, 0.0000, 0.8900, 0.3217, 0.5038, 0.2233, 0.6694, 0.5609],
[0.6164, 0.4119, 0.7912, 0.2650, 0.3537, 0.3500, 0.5614, 0.5038],
[0.6264, 0.4049, 0.8988, 0.4633, 0.3812, 0.4983, 0.6326, 0.4843]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.025597798521630466
step: 54
running loss: 0.00047403330595611977
Train Steps: 54/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6127, 0.4084, 0.8700, 0.4467, 0.3987, 0.4317, 0.5013, 0.5471],
[0.6296, 0.4008, 0.9150, 0.4317, 0.4263, 0.3050, 0.7256, 0.5413],
[0.6192, 0.4128, 0.8513, 0.5617, 0.4200, 0.5267, 0.5850, 0.5633],
[ nan, nan, 0.7335, 0.2569, 0.3788, 0.2667, 0.5066, 0.5578],
[0.6109, 0.4015, 0.7668, 0.3639, 0.3513, 0.3667, 0.5200, 0.5641],
[0.6277, 0.4013, 0.8888, 0.4767, 0.3600, 0.3567, 0.6148, 0.4672],
[0.6226, 0.4098, 0.8912, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367],
[0.6072, 0.4029, 0.7037, 0.2150, 0.3912, 0.2267, 0.5516, 0.5507]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6535, 0.4354, 0.8624, 0.4512, 0.3896, 0.4346, 0.5115, 0.5233],
[ 0.6379, 0.4002, 0.9202, 0.4149, 0.4190, 0.3058, 0.7154, 0.5308],
[ 0.6623, 0.4254, 0.8586, 0.5727, 0.4205, 0.5445, 0.6047, 0.5441],
[-0.0117, 0.0061, 0.7192, 0.2681, 0.3944, 0.2608, 0.5313, 0.5637],
[ 0.6767, 0.4417, 0.7500, 0.3647, 0.3468, 0.3627, 0.5505, 0.5424],
[ 0.6308, 0.4081, 0.8827, 0.4676, 0.3585, 0.3575, 0.6272, 0.4758],
[ 0.6622, 0.4342, 0.8869, 0.4127, 0.4088, 0.2478, 0.5990, 0.5257],
[ 0.6462, 0.4288, 0.6884, 0.2136, 0.3919, 0.2280, 0.5715, 0.5308]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6127, 0.4084, 0.8700, 0.4467, 0.3988, 0.4317, 0.5013, 0.5471],
[0.6296, 0.4008, 0.9150, 0.4317, 0.4263, 0.3050, 0.7256, 0.5413],
[0.6192, 0.4128, 0.8512, 0.5617, 0.4200, 0.5267, 0.5850, 0.5633],
[0.0000, 0.0000, 0.7335, 0.2569, 0.3787, 0.2667, 0.5066, 0.5578],
[0.6109, 0.4015, 0.7668, 0.3639, 0.3512, 0.3667, 0.5200, 0.5641],
[0.6277, 0.4013, 0.8888, 0.4767, 0.3600, 0.3567, 0.6148, 0.4672],
[0.6226, 0.4098, 0.8913, 0.4100, 0.4025, 0.2383, 0.5763, 0.5367],
[0.6072, 0.4029, 0.7038, 0.2150, 0.3913, 0.2267, 0.5516, 0.5507]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.02595448528882116
step: 55
running loss: 0.0004718997325240211
Train Steps: 55/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6173, 0.4013, 0.8713, 0.4640, 0.4800, 0.5700, 0.6025, 0.5600],
[0.6200, 0.3993, 0.8639, 0.3687, 0.3658, 0.3139, 0.6002, 0.5374],
[0.6277, 0.4057, 0.8300, 0.2650, 0.4363, 0.1850, 0.6140, 0.4823],
[0.6277, 0.4118, 0.8988, 0.3833, 0.3950, 0.2650, 0.6290, 0.4938],
[0.6147, 0.4026, 0.6600, 0.2467, 0.4088, 0.2150, 0.5489, 0.5773],
[0.6271, 0.4020, 0.8375, 0.6083, 0.3925, 0.4867, 0.6037, 0.4626],
[0.6102, 0.4005, 0.8688, 0.5100, 0.4813, 0.5400, 0.5404, 0.5064],
[0.6289, 0.4024, 0.9088, 0.4567, 0.3937, 0.5633, 0.7058, 0.5609]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6168, 0.4003, 0.8846, 0.4705, 0.4641, 0.5626, 0.5990, 0.5645],
[0.6576, 0.4380, 0.8644, 0.3584, 0.3492, 0.3211, 0.5855, 0.5366],
[0.6508, 0.4180, 0.8447, 0.2560, 0.4321, 0.1896, 0.6037, 0.4935],
[0.6707, 0.4402, 0.9167, 0.3831, 0.3854, 0.2592, 0.6097, 0.5180],
[0.6497, 0.4374, 0.6726, 0.2335, 0.3940, 0.2255, 0.5302, 0.5871],
[0.6735, 0.4251, 0.8556, 0.6107, 0.3848, 0.4843, 0.5976, 0.4758],
[0.6407, 0.4308, 0.8873, 0.5028, 0.4670, 0.5341, 0.5162, 0.5112],
[0.6604, 0.4275, 0.9052, 0.4598, 0.3730, 0.5711, 0.7126, 0.5736]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6173, 0.4013, 0.8713, 0.4640, 0.4800, 0.5700, 0.6025, 0.5600],
[0.6200, 0.3993, 0.8639, 0.3687, 0.3658, 0.3139, 0.6002, 0.5374],
[0.6277, 0.4056, 0.8300, 0.2650, 0.4363, 0.1850, 0.6140, 0.4823],
[0.6277, 0.4117, 0.8988, 0.3833, 0.3950, 0.2650, 0.6290, 0.4938],
[0.6147, 0.4026, 0.6600, 0.2467, 0.4087, 0.2150, 0.5489, 0.5773],
[0.6271, 0.4020, 0.8375, 0.6083, 0.3925, 0.4867, 0.6037, 0.4626],
[0.6102, 0.4005, 0.8687, 0.5100, 0.4812, 0.5400, 0.5404, 0.5064],
[0.6289, 0.4024, 0.9087, 0.4567, 0.3938, 0.5633, 0.7058, 0.5609]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.026293839560821652
step: 56
running loss: 0.0004695328493003866
Train Steps: 56/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6227, 0.4193, 0.8838, 0.4933, 0.3663, 0.3733, 0.5637, 0.5633],
[0.6261, 0.4066, 0.8325, 0.2150, 0.4763, 0.2667, 0.7002, 0.5633],
[0.6093, 0.3990, 0.8400, 0.4333, 0.3688, 0.4633, 0.5560, 0.5656],
[0.6249, 0.4138, 0.9038, 0.4517, 0.3862, 0.4917, 0.6138, 0.5333],
[ nan, nan, 0.8213, 0.2700, 0.3775, 0.2817, 0.5425, 0.5533],
[0.6266, 0.4070, 0.8712, 0.5600, 0.3713, 0.4783, 0.5775, 0.6100],
[0.6165, 0.4106, 0.7575, 0.1733, 0.3838, 0.2650, 0.5680, 0.5116],
[0.6186, 0.4154, 0.6825, 0.2633, 0.4150, 0.2300, 0.5713, 0.5517]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6809, 0.4527, 0.8958, 0.5070, 0.3730, 0.3764, 0.5636, 0.5649],
[0.6687, 0.4385, 0.8463, 0.2286, 0.4897, 0.2646, 0.7110, 0.5588],
[0.6743, 0.4415, 0.8559, 0.4503, 0.3849, 0.4493, 0.5528, 0.5542],
[0.6415, 0.4214, 0.9230, 0.4754, 0.3986, 0.4939, 0.6279, 0.5129],
[0.0709, 0.0313, 0.8239, 0.2984, 0.3913, 0.2874, 0.5317, 0.5538],
[0.6992, 0.4456, 0.8838, 0.5829, 0.3848, 0.4956, 0.5796, 0.5727],
[0.6580, 0.4399, 0.7690, 0.1786, 0.3969, 0.2561, 0.5709, 0.4883],
[0.7060, 0.4708, 0.7031, 0.2578, 0.4217, 0.2420, 0.5853, 0.5384]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6227, 0.4193, 0.8838, 0.4933, 0.3663, 0.3733, 0.5638, 0.5633],
[0.6261, 0.4066, 0.8325, 0.2150, 0.4762, 0.2667, 0.7002, 0.5633],
[0.6093, 0.3990, 0.8400, 0.4333, 0.3688, 0.4633, 0.5560, 0.5656],
[0.6249, 0.4138, 0.9038, 0.4517, 0.3862, 0.4917, 0.6137, 0.5333],
[0.0000, 0.0000, 0.8213, 0.2700, 0.3775, 0.2817, 0.5425, 0.5533],
[0.6266, 0.4070, 0.8712, 0.5600, 0.3713, 0.4783, 0.5775, 0.6100],
[0.6165, 0.4106, 0.7575, 0.1733, 0.3837, 0.2650, 0.5680, 0.5116],
[0.6186, 0.4154, 0.6825, 0.2633, 0.4150, 0.2300, 0.5713, 0.5517]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0008, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.02706561255035922
step: 57
running loss: 0.0004748353079010389
Train Steps: 57/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.8625, 0.2550, 0.5487, 0.2200, 0.7335, 0.5737],
[0.6070, 0.3979, 0.8575, 0.5083, 0.4350, 0.5400, 0.5180, 0.5466],
[0.6125, 0.4035, 0.7825, 0.3100, 0.3463, 0.4900, 0.5832, 0.5637],
[0.6283, 0.4283, 0.7477, 0.3542, 0.5125, 0.1917, 0.5500, 0.6167],
[0.6197, 0.4091, 0.8800, 0.4783, 0.3538, 0.4767, 0.5950, 0.5550],
[0.6127, 0.4066, 0.8550, 0.5567, 0.4662, 0.5141, 0.5070, 0.5412],
[0.6164, 0.3972, 0.7818, 0.3381, 0.3599, 0.3387, 0.5880, 0.5153],
[0.6314, 0.4050, 0.8227, 0.5431, 0.4150, 0.5517, 0.7121, 0.5690]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.0304, 0.0195, 0.8875, 0.2379, 0.5391, 0.2203, 0.7275, 0.5593],
[0.6255, 0.4086, 0.8686, 0.5094, 0.4391, 0.5338, 0.5083, 0.5156],
[0.6054, 0.4096, 0.7995, 0.3114, 0.3484, 0.4842, 0.5791, 0.5237],
[0.6546, 0.4381, 0.7531, 0.3264, 0.4934, 0.1947, 0.5435, 0.6094],
[0.6182, 0.4169, 0.8919, 0.4782, 0.3639, 0.4761, 0.5869, 0.5366],
[0.6371, 0.4349, 0.8747, 0.5479, 0.4648, 0.4981, 0.5032, 0.5233],
[0.6280, 0.4171, 0.7957, 0.3231, 0.3506, 0.3399, 0.5864, 0.4858],
[0.6626, 0.4187, 0.8417, 0.5371, 0.4203, 0.5553, 0.7206, 0.5507]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.8625, 0.2550, 0.5487, 0.2200, 0.7335, 0.5737],
[0.6070, 0.3979, 0.8575, 0.5083, 0.4350, 0.5400, 0.5180, 0.5466],
[0.6125, 0.4035, 0.7825, 0.3100, 0.3462, 0.4900, 0.5832, 0.5637],
[0.6283, 0.4283, 0.7477, 0.3542, 0.5125, 0.1917, 0.5500, 0.6167],
[0.6197, 0.4091, 0.8800, 0.4783, 0.3537, 0.4767, 0.5950, 0.5550],
[0.6127, 0.4066, 0.8550, 0.5567, 0.4662, 0.5141, 0.5070, 0.5412],
[0.6164, 0.3972, 0.7818, 0.3381, 0.3599, 0.3387, 0.5880, 0.5153],
[0.6314, 0.4050, 0.8227, 0.5431, 0.4150, 0.5517, 0.7121, 0.5690]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.0273065606597811
step: 58
running loss: 0.00047080276999622583
Train Steps: 58/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6146, 0.4124, 0.8800, 0.4867, 0.3800, 0.4500, 0.5106, 0.5524],
[0.6203, 0.4073, 0.8189, 0.2398, 0.4400, 0.2054, 0.5929, 0.5501],
[0.6085, 0.4005, 0.8400, 0.4317, 0.3763, 0.4750, 0.5476, 0.5058],
[0.6201, 0.4017, 0.8871, 0.4621, 0.3517, 0.4675, 0.5999, 0.5106],
[0.6325, 0.4066, 0.8438, 0.5350, 0.3925, 0.5267, 0.7113, 0.5795],
[0.6224, 0.3964, 0.8225, 0.5717, 0.4150, 0.4617, 0.5775, 0.5267],
[0.6257, 0.4060, 0.8300, 0.2333, 0.4688, 0.2583, 0.7050, 0.5633],
[0.6222, 0.4169, 0.8638, 0.5650, 0.4313, 0.4783, 0.5637, 0.5633]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5931, 0.4097, 0.8874, 0.4887, 0.3945, 0.4566, 0.4961, 0.5504],
[0.6113, 0.4209, 0.8224, 0.2378, 0.4481, 0.2116, 0.5767, 0.5303],
[0.6100, 0.4114, 0.8547, 0.4254, 0.3745, 0.4647, 0.5253, 0.5002],
[0.5575, 0.3701, 0.8966, 0.4368, 0.3579, 0.4684, 0.5695, 0.5236],
[0.6361, 0.4070, 0.8598, 0.5326, 0.4002, 0.5371, 0.7005, 0.5858],
[0.5959, 0.3916, 0.8418, 0.5647, 0.4152, 0.4711, 0.5487, 0.5289],
[0.6106, 0.4112, 0.8561, 0.2199, 0.4688, 0.2690, 0.6868, 0.5519],
[0.6009, 0.4062, 0.8732, 0.5490, 0.4295, 0.4702, 0.5407, 0.5784]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6146, 0.4124, 0.8800, 0.4867, 0.3800, 0.4500, 0.5106, 0.5524],
[0.6203, 0.4073, 0.8189, 0.2398, 0.4400, 0.2054, 0.5929, 0.5501],
[0.6084, 0.4005, 0.8400, 0.4317, 0.3762, 0.4750, 0.5476, 0.5058],
[0.6201, 0.4017, 0.8871, 0.4621, 0.3517, 0.4675, 0.5999, 0.5106],
[0.6325, 0.4066, 0.8438, 0.5350, 0.3925, 0.5267, 0.7113, 0.5795],
[0.6224, 0.3964, 0.8225, 0.5717, 0.4150, 0.4617, 0.5775, 0.5267],
[0.6257, 0.4060, 0.8300, 0.2333, 0.4688, 0.2583, 0.7050, 0.5633],
[0.6222, 0.4169, 0.8637, 0.5650, 0.4313, 0.4783, 0.5638, 0.5633]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.027555422129807994
step: 59
running loss: 0.00046704105304759314
Train Steps: 59/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6271, 0.4020, 0.8375, 0.6083, 0.3925, 0.4867, 0.6037, 0.4626],
[0.6364, 0.4144, 0.8625, 0.3083, 0.4913, 0.2000, 0.6448, 0.5274],
[0.6270, 0.4267, 0.7150, 0.3317, 0.4900, 0.1817, 0.5560, 0.6183],
[0.6211, 0.4069, 0.8750, 0.5117, 0.4150, 0.4900, 0.5875, 0.5167],
[0.6138, 0.4054, 0.8750, 0.4750, 0.4363, 0.5017, 0.5086, 0.5822],
[0.6286, 0.4097, 0.8107, 0.2414, 0.4425, 0.2483, 0.6745, 0.5385],
[0.6142, 0.4127, 0.7575, 0.3067, 0.3438, 0.4383, 0.5778, 0.5207],
[0.6186, 0.4013, 0.8191, 0.3188, 0.4279, 0.2060, 0.5767, 0.5411]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5805, 0.3695, 0.8528, 0.5969, 0.3916, 0.4936, 0.5851, 0.4726],
[0.6133, 0.4126, 0.8841, 0.3074, 0.4825, 0.2126, 0.6232, 0.5347],
[0.5386, 0.3626, 0.7153, 0.2838, 0.4685, 0.2080, 0.5480, 0.6325],
[0.5736, 0.3836, 0.8924, 0.5182, 0.4034, 0.5241, 0.5703, 0.5236],
[0.5928, 0.4034, 0.8754, 0.4717, 0.4411, 0.5010, 0.4946, 0.5865],
[0.6145, 0.3952, 0.8317, 0.2403, 0.4494, 0.2615, 0.6516, 0.5482],
[0.5552, 0.3814, 0.7775, 0.2858, 0.3488, 0.4323, 0.5621, 0.5333],
[0.5896, 0.3951, 0.8348, 0.2885, 0.4179, 0.2225, 0.5542, 0.5421]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6271, 0.4020, 0.8375, 0.6083, 0.3925, 0.4867, 0.6037, 0.4626],
[0.6364, 0.4144, 0.8625, 0.3083, 0.4913, 0.2000, 0.6448, 0.5274],
[0.6270, 0.4266, 0.7150, 0.3317, 0.4900, 0.1817, 0.5560, 0.6183],
[0.6211, 0.4069, 0.8750, 0.5117, 0.4150, 0.4900, 0.5875, 0.5167],
[0.6138, 0.4054, 0.8750, 0.4750, 0.4363, 0.5017, 0.5086, 0.5822],
[0.6286, 0.4097, 0.8107, 0.2414, 0.4425, 0.2483, 0.6745, 0.5385],
[0.6142, 0.4127, 0.7575, 0.3067, 0.3438, 0.4383, 0.5778, 0.5207],
[0.6186, 0.4013, 0.8191, 0.3188, 0.4279, 0.2060, 0.5767, 0.5411]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.028138416208093986
step: 60
running loss: 0.0004689736034682331
Train Steps: 60/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6268, 0.4061, 0.8350, 0.2433, 0.4575, 0.2283, 0.6350, 0.5300],
[ nan, nan, 0.7412, 0.2200, 0.4450, 0.1517, 0.5312, 0.4983],
[0.6122, 0.4006, 0.8850, 0.4217, 0.4088, 0.5517, 0.6063, 0.5517],
[0.6282, 0.4034, 0.7830, 0.2080, 0.4532, 0.2080, 0.6404, 0.5323],
[0.6198, 0.4101, 0.8838, 0.5283, 0.3763, 0.5267, 0.5913, 0.5567],
[0.6122, 0.3993, 0.8738, 0.4667, 0.4517, 0.4879, 0.5155, 0.4927],
[0.6229, 0.4066, 0.7612, 0.2967, 0.4250, 0.2167, 0.5925, 0.5350],
[0.6274, 0.4270, 0.8938, 0.4967, 0.3550, 0.4283, 0.5700, 0.5733]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6601, 0.4249, 0.8365, 0.2621, 0.4635, 0.2275, 0.6326, 0.5491],
[-0.0086, -0.0145, 0.7348, 0.2205, 0.4374, 0.1838, 0.5444, 0.5287],
[ 0.5796, 0.3725, 0.8702, 0.4454, 0.4151, 0.5646, 0.6027, 0.5698],
[ 0.6180, 0.3984, 0.7739, 0.2203, 0.4497, 0.2328, 0.6333, 0.5667],
[ 0.5950, 0.3945, 0.8707, 0.5517, 0.3807, 0.5406, 0.5929, 0.5902],
[ 0.5702, 0.3789, 0.8715, 0.4924, 0.4610, 0.5067, 0.5206, 0.5155],
[ 0.5951, 0.3871, 0.7522, 0.2959, 0.4304, 0.2437, 0.5927, 0.5768],
[ 0.5827, 0.3908, 0.8806, 0.5121, 0.3746, 0.4485, 0.5799, 0.5850]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6268, 0.4060, 0.8350, 0.2433, 0.4575, 0.2283, 0.6350, 0.5300],
[0.0000, 0.0000, 0.7412, 0.2200, 0.4450, 0.1517, 0.5312, 0.4983],
[0.6122, 0.4006, 0.8850, 0.4217, 0.4087, 0.5517, 0.6062, 0.5517],
[0.6282, 0.4034, 0.7830, 0.2080, 0.4532, 0.2080, 0.6404, 0.5323],
[0.6198, 0.4101, 0.8838, 0.5283, 0.3762, 0.5267, 0.5913, 0.5567],
[0.6122, 0.3993, 0.8737, 0.4667, 0.4517, 0.4879, 0.5155, 0.4927],
[0.6229, 0.4066, 0.7613, 0.2967, 0.4250, 0.2167, 0.5925, 0.5350],
[0.6274, 0.4270, 0.8938, 0.4967, 0.3550, 0.4283, 0.5700, 0.5733]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.028534956247312948
step: 61
running loss: 0.00046778616798873684
Train Steps: 61/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6129, 0.3930, 0.8769, 0.5105, 0.4146, 0.5642, 0.6000, 0.5082],
[0.6182, 0.3998, 0.8793, 0.4191, 0.3552, 0.4285, 0.6038, 0.5312],
[0.6234, 0.4179, 0.7825, 0.3450, 0.3813, 0.2867, 0.5675, 0.5617],
[ nan, nan, 0.7425, 0.2117, 0.3937, 0.2433, 0.5438, 0.5567],
[0.6296, 0.3989, 0.9000, 0.4150, 0.3613, 0.3867, 0.6400, 0.5100],
[0.6250, 0.4131, 0.8688, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367],
[0.6150, 0.3949, 0.8800, 0.4033, 0.3825, 0.4900, 0.5875, 0.5483],
[0.6203, 0.4056, 0.8942, 0.4086, 0.3643, 0.3617, 0.5917, 0.5482]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5669, 0.3619, 0.8556, 0.5292, 0.4412, 0.5751, 0.6005, 0.5261],
[0.6083, 0.3899, 0.8528, 0.4225, 0.3767, 0.4475, 0.6131, 0.5482],
[0.5707, 0.3839, 0.7689, 0.3624, 0.4002, 0.2881, 0.5756, 0.5738],
[0.0472, 0.0215, 0.7341, 0.2395, 0.3982, 0.2607, 0.5287, 0.5618],
[0.6124, 0.3909, 0.8916, 0.4302, 0.3773, 0.3933, 0.6496, 0.5194],
[0.6038, 0.3976, 0.8544, 0.3207, 0.4519, 0.2539, 0.6068, 0.5451],
[0.6097, 0.3940, 0.8519, 0.4202, 0.4003, 0.4898, 0.5916, 0.5555],
[0.5586, 0.3608, 0.8751, 0.4247, 0.3675, 0.3782, 0.5871, 0.5745]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6129, 0.3930, 0.8769, 0.5105, 0.4146, 0.5642, 0.6000, 0.5082],
[0.6182, 0.3998, 0.8793, 0.4191, 0.3552, 0.4285, 0.6038, 0.5312],
[0.6234, 0.4179, 0.7825, 0.3450, 0.3812, 0.2867, 0.5675, 0.5617],
[0.0000, 0.0000, 0.7425, 0.2117, 0.3938, 0.2433, 0.5437, 0.5567],
[0.6296, 0.3989, 0.9000, 0.4150, 0.3613, 0.3867, 0.6400, 0.5100],
[0.6250, 0.4131, 0.8687, 0.2983, 0.4275, 0.2367, 0.6162, 0.5367],
[0.6150, 0.3949, 0.8800, 0.4033, 0.3825, 0.4900, 0.5875, 0.5483],
[0.6203, 0.4056, 0.8942, 0.4086, 0.3643, 0.3617, 0.5917, 0.5482]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.028984240110730752
step: 62
running loss: 0.00046748774372146375
Train Steps: 62/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6126, 0.3954, 0.8538, 0.4983, 0.4250, 0.4700, 0.5355, 0.5350],
[0.6250, 0.4008, 0.8950, 0.4183, 0.3550, 0.4383, 0.6361, 0.4927],
[0.6302, 0.4007, 0.8850, 0.5500, 0.3613, 0.4517, 0.6335, 0.5012],
[0.6339, 0.4159, 0.8400, 0.5617, 0.3825, 0.4150, 0.7343, 0.5748],
[0.6068, 0.3963, 0.8650, 0.4317, 0.4037, 0.5083, 0.5253, 0.4999],
[0.6214, 0.4040, 0.8838, 0.3500, 0.3600, 0.5183, 0.6362, 0.5200],
[0.6286, 0.4086, 0.8408, 0.2801, 0.4163, 0.2800, 0.6725, 0.5393],
[0.6182, 0.4099, 0.7812, 0.3000, 0.3937, 0.2367, 0.5325, 0.5750]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5621, 0.3566, 0.8446, 0.5022, 0.4237, 0.4701, 0.5275, 0.5495],
[0.6145, 0.3894, 0.8666, 0.4223, 0.3447, 0.4410, 0.6383, 0.5094],
[0.5641, 0.3690, 0.8509, 0.5467, 0.3611, 0.4495, 0.6190, 0.5186],
[0.5908, 0.3902, 0.8255, 0.5633, 0.3920, 0.4061, 0.7199, 0.5706],
[0.6059, 0.3850, 0.8353, 0.4464, 0.4018, 0.5076, 0.5215, 0.4927],
[0.5895, 0.3806, 0.8615, 0.3665, 0.3606, 0.5174, 0.6403, 0.5171],
[0.6403, 0.4124, 0.8280, 0.2962, 0.4103, 0.2930, 0.6851, 0.5467],
[0.6094, 0.4098, 0.7718, 0.3154, 0.4044, 0.2346, 0.5285, 0.5751]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6126, 0.3954, 0.8537, 0.4983, 0.4250, 0.4700, 0.5355, 0.5350],
[0.6250, 0.4008, 0.8950, 0.4183, 0.3550, 0.4383, 0.6361, 0.4927],
[0.6302, 0.4007, 0.8850, 0.5500, 0.3613, 0.4517, 0.6335, 0.5012],
[0.6339, 0.4159, 0.8400, 0.5617, 0.3825, 0.4150, 0.7343, 0.5748],
[0.6068, 0.3963, 0.8650, 0.4317, 0.4038, 0.5083, 0.5253, 0.4999],
[0.6214, 0.4040, 0.8838, 0.3500, 0.3600, 0.5183, 0.6363, 0.5200],
[0.6286, 0.4086, 0.8408, 0.2801, 0.4162, 0.2800, 0.6725, 0.5393],
[0.6182, 0.4099, 0.7812, 0.3000, 0.3938, 0.2367, 0.5325, 0.5750]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.029316391359316185
step: 63
running loss: 0.0004653395453859712
Train Steps: 63/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6147, 0.4081, 0.8538, 0.3400, 0.3663, 0.3150, 0.5142, 0.4875],
[0.6229, 0.4066, 0.7612, 0.2967, 0.4250, 0.2167, 0.5925, 0.5350],
[0.6163, 0.4006, 0.8788, 0.4683, 0.3663, 0.4883, 0.5887, 0.5017],
[0.6226, 0.4001, 0.8438, 0.5733, 0.3862, 0.4250, 0.5750, 0.5283],
[0.6111, 0.4019, 0.8350, 0.3867, 0.3500, 0.4283, 0.5480, 0.5719],
[0.6261, 0.4029, 0.8720, 0.3364, 0.3665, 0.3753, 0.6531, 0.5183],
[0.6097, 0.4024, 0.8488, 0.3717, 0.3875, 0.5517, 0.5836, 0.5591],
[0.6082, 0.4024, 0.8738, 0.4017, 0.3688, 0.3950, 0.5306, 0.5136]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6310, 0.4094, 0.8501, 0.3549, 0.3542, 0.2914, 0.5601, 0.4993],
[0.6054, 0.3872, 0.7358, 0.2707, 0.4196, 0.2048, 0.6096, 0.5439],
[0.6054, 0.3931, 0.8595, 0.4581, 0.3593, 0.4813, 0.5988, 0.5172],
[0.5903, 0.3818, 0.8267, 0.5510, 0.3844, 0.4066, 0.5926, 0.5354],
[0.6094, 0.3951, 0.8160, 0.3809, 0.3438, 0.4054, 0.5520, 0.5542],
[0.6233, 0.3981, 0.8425, 0.3481, 0.3685, 0.3532, 0.6469, 0.5067],
[0.5660, 0.3539, 0.8270, 0.3669, 0.3908, 0.5373, 0.6171, 0.5336],
[0.5670, 0.3656, 0.8518, 0.3878, 0.3705, 0.3865, 0.5457, 0.4974]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6147, 0.4081, 0.8537, 0.3400, 0.3663, 0.3150, 0.5142, 0.4875],
[0.6229, 0.4066, 0.7613, 0.2967, 0.4250, 0.2167, 0.5925, 0.5350],
[0.6163, 0.4006, 0.8788, 0.4683, 0.3663, 0.4883, 0.5888, 0.5017],
[0.6226, 0.4001, 0.8438, 0.5733, 0.3862, 0.4250, 0.5750, 0.5283],
[0.6111, 0.4019, 0.8350, 0.3867, 0.3500, 0.4283, 0.5480, 0.5719],
[0.6261, 0.4029, 0.8720, 0.3364, 0.3665, 0.3753, 0.6531, 0.5183],
[0.6097, 0.4024, 0.8487, 0.3717, 0.3875, 0.5517, 0.5836, 0.5591],
[0.6082, 0.4024, 0.8737, 0.4017, 0.3688, 0.3950, 0.5306, 0.5136]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.029691978357732296
step: 64
running loss: 0.0004639371618395671
Train Steps: 64/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6329, 0.4196, 0.9238, 0.4583, 0.4263, 0.2933, 0.7343, 0.5748],
[0.6075, 0.4007, 0.8275, 0.4917, 0.4050, 0.5100, 0.5167, 0.5280],
[0.6189, 0.4049, 0.8888, 0.4417, 0.4213, 0.5200, 0.5988, 0.5633],
[0.6267, 0.4065, 0.8313, 0.2467, 0.4788, 0.1733, 0.6312, 0.5133],
[0.6339, 0.4102, 0.8588, 0.3133, 0.4425, 0.2117, 0.6417, 0.5089],
[0.6198, 0.3997, 0.8582, 0.5361, 0.4117, 0.5016, 0.5942, 0.5134],
[0.6202, 0.4054, 0.8892, 0.4428, 0.3642, 0.3249, 0.5840, 0.5426],
[0.6135, 0.4115, 0.8838, 0.4667, 0.4288, 0.6050, 0.5778, 0.5097]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6060, 0.4027, 0.9025, 0.4582, 0.3996, 0.2778, 0.7325, 0.5489],
[0.6204, 0.4067, 0.8110, 0.4773, 0.3780, 0.4878, 0.5226, 0.5209],
[0.5794, 0.3736, 0.8835, 0.4338, 0.3948, 0.5220, 0.6071, 0.5618],
[0.6142, 0.4049, 0.8165, 0.2311, 0.4544, 0.1651, 0.6256, 0.5015],
[0.6073, 0.3961, 0.8408, 0.3007, 0.4270, 0.2088, 0.6565, 0.4918],
[0.5828, 0.3903, 0.8484, 0.5090, 0.3845, 0.5092, 0.5891, 0.4947],
[0.6020, 0.3937, 0.8769, 0.4152, 0.3334, 0.3141, 0.5947, 0.5279],
[0.5650, 0.3774, 0.8745, 0.4475, 0.3991, 0.5974, 0.5709, 0.5031]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6329, 0.4196, 0.9237, 0.4583, 0.4263, 0.2933, 0.7343, 0.5748],
[0.6075, 0.4006, 0.8275, 0.4917, 0.4050, 0.5100, 0.5167, 0.5280],
[0.6189, 0.4049, 0.8888, 0.4417, 0.4212, 0.5200, 0.5987, 0.5633],
[0.6266, 0.4065, 0.8313, 0.2467, 0.4787, 0.1733, 0.6313, 0.5133],
[0.6339, 0.4102, 0.8587, 0.3133, 0.4425, 0.2117, 0.6417, 0.5089],
[0.6198, 0.3997, 0.8582, 0.5361, 0.4117, 0.5016, 0.5942, 0.5134],
[0.6202, 0.4054, 0.8892, 0.4428, 0.3642, 0.3249, 0.5840, 0.5426],
[0.6135, 0.4115, 0.8838, 0.4667, 0.4288, 0.6050, 0.5778, 0.5097]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.030056098359636962
step: 65
running loss: 0.000462401513225184
Train Steps: 65/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6201, 0.4017, 0.8871, 0.4621, 0.3517, 0.4675, 0.5999, 0.5106],
[0.6200, 0.3998, 0.8850, 0.3950, 0.3500, 0.4650, 0.6138, 0.5400],
[0.6219, 0.4097, 0.8738, 0.3400, 0.3563, 0.4117, 0.5975, 0.5683],
[0.6112, 0.4029, 0.8638, 0.4800, 0.4875, 0.5083, 0.5763, 0.5567],
[0.6279, 0.4050, 0.8025, 0.2200, 0.4313, 0.2733, 0.6820, 0.5320],
[0.6198, 0.4115, 0.7762, 0.2717, 0.3713, 0.3200, 0.5837, 0.5683],
[0.6137, 0.4038, 0.8563, 0.4050, 0.3813, 0.2550, 0.5106, 0.4954],
[0.6228, 0.4119, 0.7938, 0.2233, 0.4674, 0.1773, 0.6188, 0.5433]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6325, 0.4188, 0.8790, 0.4454, 0.3357, 0.4470, 0.5937, 0.5070],
[0.6276, 0.4159, 0.8831, 0.3919, 0.3389, 0.4420, 0.6121, 0.5288],
[0.5823, 0.4039, 0.8797, 0.3453, 0.3316, 0.3823, 0.6009, 0.5428],
[0.6027, 0.3982, 0.8725, 0.4607, 0.4668, 0.4718, 0.5631, 0.5381],
[0.5903, 0.3948, 0.8057, 0.2344, 0.4171, 0.2533, 0.6727, 0.5183],
[0.6415, 0.4335, 0.7790, 0.2666, 0.3548, 0.2899, 0.5766, 0.5454],
[0.6410, 0.4316, 0.8549, 0.4109, 0.3794, 0.2458, 0.5019, 0.4821],
[0.6050, 0.4117, 0.7940, 0.2302, 0.4581, 0.1521, 0.6242, 0.5132]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6201, 0.4017, 0.8871, 0.4621, 0.3517, 0.4675, 0.5999, 0.5106],
[0.6200, 0.3998, 0.8850, 0.3950, 0.3500, 0.4650, 0.6137, 0.5400],
[0.6219, 0.4097, 0.8737, 0.3400, 0.3562, 0.4117, 0.5975, 0.5683],
[0.6112, 0.4029, 0.8637, 0.4800, 0.4875, 0.5083, 0.5763, 0.5567],
[0.6279, 0.4050, 0.8025, 0.2200, 0.4313, 0.2733, 0.6820, 0.5320],
[0.6198, 0.4115, 0.7763, 0.2717, 0.3713, 0.3200, 0.5838, 0.5683],
[0.6137, 0.4038, 0.8562, 0.4050, 0.3812, 0.2550, 0.5106, 0.4954],
[0.6228, 0.4119, 0.7937, 0.2233, 0.4674, 0.1773, 0.6187, 0.5433]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.030345589388161898
step: 66
running loss: 0.0004597816573963924
Train Steps: 66/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6300, 0.4013, 0.8938, 0.5350, 0.3675, 0.4600, 0.6456, 0.4973],
[0.6173, 0.4114, 0.7325, 0.2500, 0.4213, 0.1917, 0.5338, 0.5700],
[0.6058, 0.3978, 0.8287, 0.3600, 0.3400, 0.4050, 0.5529, 0.5461],
[0.6182, 0.3930, 0.8841, 0.3892, 0.3556, 0.4967, 0.6222, 0.5279],
[ nan, nan, 0.8625, 0.2550, 0.5487, 0.2200, 0.7335, 0.5737],
[0.6300, 0.4133, 0.8538, 0.2167, 0.5587, 0.2250, 0.7390, 0.5413],
[0.6141, 0.4038, 0.8650, 0.4833, 0.4839, 0.5176, 0.5787, 0.5600],
[ nan, nan, 0.7625, 0.2433, 0.3713, 0.2867, 0.5235, 0.5220]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6730, 0.4373, 0.9066, 0.5274, 0.3590, 0.4573, 0.6407, 0.4906],
[0.6628, 0.4471, 0.7531, 0.2596, 0.4204, 0.1885, 0.5333, 0.5555],
[0.6626, 0.4496, 0.8338, 0.3639, 0.3408, 0.4037, 0.5647, 0.5396],
[0.6586, 0.4142, 0.8963, 0.4003, 0.3388, 0.4788, 0.6314, 0.5172],
[0.0469, 0.0414, 0.8846, 0.2554, 0.5381, 0.2105, 0.7217, 0.5614],
[0.6127, 0.3974, 0.8840, 0.2309, 0.5523, 0.2475, 0.7283, 0.5359],
[0.6800, 0.4512, 0.8846, 0.4860, 0.4886, 0.5012, 0.5734, 0.5537],
[0.0506, 0.0346, 0.7934, 0.2526, 0.3742, 0.2824, 0.5256, 0.5156]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6300, 0.4013, 0.8938, 0.5350, 0.3675, 0.4600, 0.6456, 0.4973],
[0.6173, 0.4114, 0.7325, 0.2500, 0.4212, 0.1917, 0.5337, 0.5700],
[0.6058, 0.3978, 0.8288, 0.3600, 0.3400, 0.4050, 0.5529, 0.5461],
[0.6182, 0.3930, 0.8841, 0.3892, 0.3556, 0.4967, 0.6222, 0.5279],
[0.0000, 0.0000, 0.8625, 0.2550, 0.5487, 0.2200, 0.7335, 0.5737],
[0.6300, 0.4133, 0.8537, 0.2167, 0.5587, 0.2250, 0.7390, 0.5413],
[0.6141, 0.4038, 0.8650, 0.4833, 0.4839, 0.5176, 0.5788, 0.5600],
[0.0000, 0.0000, 0.7625, 0.2433, 0.3713, 0.2867, 0.5235, 0.5220]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03091353503987193
step: 67
running loss: 0.0004613960453712229
Train Steps: 67/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6162, 0.4134, 0.6700, 0.2467, 0.3962, 0.2533, 0.5737, 0.5467],
[0.6263, 0.4057, 0.8800, 0.3833, 0.3650, 0.3717, 0.6375, 0.4804],
[0.6204, 0.4091, 0.8950, 0.4783, 0.3613, 0.4617, 0.6063, 0.5617],
[0.6296, 0.4060, 0.9100, 0.3267, 0.4726, 0.3367, 0.7446, 0.5355],
[0.6182, 0.3967, 0.8263, 0.3065, 0.3526, 0.4161, 0.6192, 0.5290],
[0.6101, 0.3977, 0.8550, 0.5667, 0.3862, 0.4417, 0.5128, 0.4869],
[0.6339, 0.4102, 0.9088, 0.4767, 0.3925, 0.5283, 0.7509, 0.5390],
[0.6204, 0.4055, 0.8438, 0.5733, 0.4574, 0.4801, 0.5487, 0.5617]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6072, 0.4156, 0.6845, 0.2488, 0.3885, 0.2646, 0.5822, 0.5506],
[0.6824, 0.4430, 0.9033, 0.3734, 0.3597, 0.3630, 0.6155, 0.4861],
[0.6485, 0.4382, 0.9266, 0.4681, 0.3643, 0.4627, 0.5905, 0.5646],
[0.6429, 0.4136, 0.9213, 0.3295, 0.4761, 0.3300, 0.7252, 0.5254],
[0.6812, 0.4458, 0.8530, 0.3079, 0.3447, 0.4176, 0.6092, 0.5309],
[0.6150, 0.4112, 0.8791, 0.5605, 0.3931, 0.4561, 0.5007, 0.4900],
[0.6644, 0.4421, 0.9267, 0.4800, 0.3993, 0.5388, 0.7369, 0.5406],
[0.6674, 0.4306, 0.8511, 0.5840, 0.4571, 0.4663, 0.5463, 0.5880]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6162, 0.4134, 0.6700, 0.2467, 0.3963, 0.2533, 0.5738, 0.5467],
[0.6263, 0.4057, 0.8800, 0.3833, 0.3650, 0.3717, 0.6375, 0.4804],
[0.6204, 0.4091, 0.8950, 0.4783, 0.3613, 0.4617, 0.6062, 0.5617],
[0.6296, 0.4060, 0.9100, 0.3267, 0.4726, 0.3367, 0.7446, 0.5355],
[0.6182, 0.3967, 0.8263, 0.3065, 0.3526, 0.4161, 0.6192, 0.5290],
[0.6101, 0.3977, 0.8550, 0.5667, 0.3862, 0.4417, 0.5128, 0.4869],
[0.6339, 0.4102, 0.9087, 0.4767, 0.3925, 0.5283, 0.7509, 0.5390],
[0.6204, 0.4055, 0.8438, 0.5733, 0.4574, 0.4801, 0.5487, 0.5617]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03130897891242057
step: 68
running loss: 0.0004604261604767731
Train Steps: 68/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6246, 0.4090, 0.6964, 0.2027, 0.3925, 0.2683, 0.6088, 0.5583],
[0.6241, 0.4143, 0.8938, 0.4650, 0.4075, 0.5350, 0.6250, 0.5550],
[0.6239, 0.4174, 0.8425, 0.5733, 0.4825, 0.4500, 0.5625, 0.5933],
[0.6239, 0.4206, 0.8750, 0.5400, 0.3688, 0.4850, 0.5737, 0.5700],
[0.6223, 0.4171, 0.8750, 0.5500, 0.4050, 0.4817, 0.5675, 0.5600],
[0.6199, 0.3952, 0.8573, 0.5374, 0.4075, 0.4687, 0.5942, 0.5377],
[0.6216, 0.4100, 0.7350, 0.2067, 0.4325, 0.2050, 0.5950, 0.5333],
[0.6183, 0.4076, 0.8838, 0.4517, 0.3813, 0.4483, 0.5775, 0.5633]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6401, 0.4268, 0.7226, 0.2012, 0.4088, 0.2647, 0.6165, 0.5383],
[0.6213, 0.4168, 0.9257, 0.4448, 0.4271, 0.5342, 0.6339, 0.5451],
[0.6416, 0.4361, 0.8674, 0.5556, 0.4946, 0.4437, 0.5999, 0.5797],
[0.6356, 0.4275, 0.9069, 0.5226, 0.3884, 0.4892, 0.5855, 0.5514],
[0.6988, 0.4739, 0.9074, 0.5321, 0.4143, 0.4907, 0.5857, 0.5554],
[0.6401, 0.4200, 0.8829, 0.5230, 0.4142, 0.4624, 0.6204, 0.5285],
[0.5978, 0.3988, 0.7610, 0.2069, 0.4505, 0.2119, 0.6215, 0.5091],
[0.6463, 0.4257, 0.9085, 0.4362, 0.4016, 0.4561, 0.5870, 0.5596]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6246, 0.4090, 0.6964, 0.2027, 0.3925, 0.2683, 0.6087, 0.5583],
[0.6241, 0.4142, 0.8938, 0.4650, 0.4075, 0.5350, 0.6250, 0.5550],
[0.6239, 0.4174, 0.8425, 0.5733, 0.4825, 0.4500, 0.5625, 0.5933],
[0.6239, 0.4206, 0.8750, 0.5400, 0.3688, 0.4850, 0.5738, 0.5700],
[0.6223, 0.4171, 0.8750, 0.5500, 0.4050, 0.4817, 0.5675, 0.5600],
[0.6199, 0.3952, 0.8573, 0.5374, 0.4075, 0.4687, 0.5942, 0.5377],
[0.6216, 0.4100, 0.7350, 0.2067, 0.4325, 0.2050, 0.5950, 0.5333],
[0.6183, 0.4076, 0.8838, 0.4517, 0.3812, 0.4483, 0.5775, 0.5633]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.031762625847477466
step: 69
running loss: 0.00046032791083300674
Train Steps: 69/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395],
[0.6200, 0.4086, 0.8414, 0.2974, 0.4117, 0.2274, 0.5869, 0.5391],
[0.6201, 0.4065, 0.7300, 0.1933, 0.4075, 0.2533, 0.6162, 0.5483],
[0.6215, 0.4119, 0.7688, 0.2300, 0.4200, 0.2283, 0.5925, 0.5317],
[0.6151, 0.4058, 0.7068, 0.2680, 0.3400, 0.4083, 0.5775, 0.5733],
[0.6257, 0.4024, 0.8612, 0.5352, 0.4361, 0.5253, 0.6680, 0.5166],
[0.6211, 0.3935, 0.8636, 0.4841, 0.4417, 0.5126, 0.6331, 0.5268],
[0.6109, 0.4041, 0.6975, 0.3167, 0.3513, 0.3383, 0.5153, 0.5319]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6460, 0.4203, 0.9000, 0.5420, 0.3821, 0.3687, 0.5508, 0.5364],
[0.6151, 0.4056, 0.8694, 0.2938, 0.4477, 0.2250, 0.5831, 0.5344],
[0.5969, 0.3859, 0.7443, 0.1821, 0.4409, 0.2535, 0.6052, 0.5541],
[0.5619, 0.3696, 0.7780, 0.2227, 0.4654, 0.2409, 0.6000, 0.5386],
[0.6365, 0.4150, 0.7459, 0.2567, 0.3699, 0.4079, 0.5746, 0.5771],
[0.6522, 0.4290, 0.8946, 0.5280, 0.4635, 0.5333, 0.6704, 0.5245],
[0.6457, 0.4102, 0.9029, 0.4656, 0.4647, 0.5256, 0.6216, 0.5263],
[0.6640, 0.4348, 0.7400, 0.3104, 0.3679, 0.3367, 0.5077, 0.5379]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6182, 0.3972, 0.8720, 0.5527, 0.3638, 0.3582, 0.5696, 0.5395],
[0.6199, 0.4086, 0.8414, 0.2974, 0.4117, 0.2274, 0.5869, 0.5391],
[0.6201, 0.4065, 0.7300, 0.1933, 0.4075, 0.2533, 0.6162, 0.5483],
[0.6215, 0.4119, 0.7688, 0.2300, 0.4200, 0.2283, 0.5925, 0.5317],
[0.6151, 0.4058, 0.7068, 0.2680, 0.3400, 0.4083, 0.5775, 0.5733],
[0.6257, 0.4024, 0.8612, 0.5352, 0.4361, 0.5253, 0.6680, 0.5166],
[0.6211, 0.3935, 0.8636, 0.4841, 0.4417, 0.5126, 0.6331, 0.5268],
[0.6109, 0.4041, 0.6975, 0.3167, 0.3512, 0.3383, 0.5153, 0.5319]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03225781302899122
step: 70
running loss: 0.0004608259004141603
Train Steps: 70/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6310, 0.4017, 0.8563, 0.5800, 0.3688, 0.4750, 0.6326, 0.5006],
[0.6197, 0.3930, 0.8793, 0.4736, 0.4152, 0.5464, 0.6308, 0.5235],
[0.6142, 0.4127, 0.7575, 0.3067, 0.3438, 0.4383, 0.5778, 0.5207],
[0.6227, 0.4083, 0.8938, 0.4800, 0.3800, 0.2950, 0.5737, 0.5350],
[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383],
[0.6198, 0.4105, 0.7950, 0.3267, 0.3675, 0.3767, 0.6038, 0.6167],
[0.6200, 0.4049, 0.8638, 0.5617, 0.4125, 0.5100, 0.6013, 0.5317],
[0.6201, 0.4102, 0.7288, 0.2417, 0.4150, 0.2383, 0.6100, 0.5500]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6148, 0.3716, 0.8605, 0.5585, 0.3871, 0.4737, 0.6259, 0.5169],
[0.6468, 0.4023, 0.8991, 0.4805, 0.4321, 0.5419, 0.6411, 0.5354],
[0.6433, 0.4191, 0.7664, 0.3155, 0.3697, 0.4264, 0.5722, 0.5404],
[0.6585, 0.4212, 0.8732, 0.4792, 0.3988, 0.3011, 0.5767, 0.5431],
[0.6219, 0.3866, 0.9016, 0.4525, 0.4625, 0.5749, 0.6231, 0.5492],
[0.6424, 0.4062, 0.7986, 0.3269, 0.3891, 0.3860, 0.6075, 0.6323],
[0.6266, 0.4012, 0.8681, 0.5553, 0.4246, 0.4999, 0.5951, 0.5453],
[0.6402, 0.4050, 0.7469, 0.2468, 0.4276, 0.2472, 0.5946, 0.5733]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6310, 0.4017, 0.8562, 0.5800, 0.3688, 0.4750, 0.6326, 0.5006],
[0.6197, 0.3930, 0.8793, 0.4736, 0.4152, 0.5464, 0.6308, 0.5235],
[0.6142, 0.4127, 0.7575, 0.3067, 0.3438, 0.4383, 0.5778, 0.5207],
[0.6227, 0.4083, 0.8938, 0.4800, 0.3800, 0.2950, 0.5738, 0.5350],
[0.6175, 0.4013, 0.8900, 0.4500, 0.4375, 0.5850, 0.6175, 0.5383],
[0.6198, 0.4105, 0.7950, 0.3267, 0.3675, 0.3767, 0.6037, 0.6167],
[0.6199, 0.4049, 0.8637, 0.5617, 0.4125, 0.5100, 0.6012, 0.5317],
[0.6201, 0.4102, 0.7287, 0.2417, 0.4150, 0.2383, 0.6100, 0.5500]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.032472519553266466
step: 71
running loss: 0.0004573594303276967
Train Steps: 71/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6277, 0.4013, 0.8888, 0.4767, 0.3600, 0.3567, 0.6148, 0.4672],
[0.6277, 0.4083, 0.8350, 0.2717, 0.4562, 0.1800, 0.5918, 0.4878],
[0.6339, 0.4102, 0.9088, 0.4767, 0.3925, 0.5283, 0.7509, 0.5390],
[0.6218, 0.4185, 0.7338, 0.2650, 0.4625, 0.1950, 0.5687, 0.5800],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533],
[0.6286, 0.4274, 0.8500, 0.4500, 0.4525, 0.2583, 0.5440, 0.6209],
[0.6193, 0.4050, 0.7313, 0.2433, 0.4075, 0.2117, 0.5649, 0.5656],
[0.6090, 0.4010, 0.7838, 0.3483, 0.3538, 0.3783, 0.5462, 0.5077]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5940, 0.3746, 0.8675, 0.4779, 0.3429, 0.3852, 0.6126, 0.4978],
[0.6416, 0.4011, 0.7967, 0.2772, 0.4555, 0.2147, 0.5898, 0.5085],
[0.6110, 0.3931, 0.8839, 0.4816, 0.3927, 0.5575, 0.7458, 0.5450],
[0.5519, 0.3622, 0.6993, 0.2598, 0.4502, 0.2145, 0.5542, 0.5974],
[0.6182, 0.4113, 0.8660, 0.4374, 0.4177, 0.5403, 0.5742, 0.5472],
[0.6018, 0.4055, 0.8068, 0.4443, 0.4412, 0.2809, 0.5477, 0.6292],
[0.5763, 0.3665, 0.7078, 0.2500, 0.4051, 0.2317, 0.5698, 0.5809],
[0.5822, 0.3735, 0.7703, 0.3540, 0.3481, 0.3917, 0.5402, 0.5193]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6277, 0.4013, 0.8888, 0.4767, 0.3600, 0.3567, 0.6148, 0.4672],
[0.6277, 0.4083, 0.8350, 0.2717, 0.4563, 0.1800, 0.5918, 0.4878],
[0.6339, 0.4102, 0.9087, 0.4767, 0.3925, 0.5283, 0.7509, 0.5390],
[0.6218, 0.4185, 0.7337, 0.2650, 0.4625, 0.1950, 0.5688, 0.5800],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533],
[0.6286, 0.4274, 0.8500, 0.4500, 0.4525, 0.2583, 0.5440, 0.6209],
[0.6193, 0.4050, 0.7312, 0.2433, 0.4075, 0.2117, 0.5649, 0.5656],
[0.6090, 0.4010, 0.7837, 0.3483, 0.3537, 0.3783, 0.5462, 0.5077]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03298366616945714
step: 72
running loss: 0.0004581064745757936
Train Steps: 72/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6222, 0.4072, 0.7164, 0.2166, 0.3738, 0.3167, 0.6100, 0.5533],
[0.6198, 0.4114, 0.8263, 0.3283, 0.3550, 0.3583, 0.5813, 0.5667],
[0.6307, 0.4060, 0.8950, 0.5183, 0.3750, 0.3850, 0.6338, 0.4938],
[0.6225, 0.4196, 0.8788, 0.3467, 0.3750, 0.3400, 0.5413, 0.5433],
[0.6109, 0.4041, 0.6975, 0.3167, 0.3513, 0.3383, 0.5153, 0.5319],
[0.6109, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117],
[0.6097, 0.4024, 0.8488, 0.3717, 0.3875, 0.5517, 0.5836, 0.5591],
[0.6219, 0.4097, 0.8738, 0.3400, 0.3563, 0.4117, 0.5975, 0.5683]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6499, 0.4078, 0.7000, 0.2581, 0.3769, 0.3111, 0.6247, 0.5697],
[0.6281, 0.4074, 0.8035, 0.3519, 0.3447, 0.3648, 0.5826, 0.5726],
[0.6364, 0.4119, 0.8539, 0.5459, 0.3686, 0.3947, 0.6423, 0.4841],
[0.6095, 0.3974, 0.8234, 0.3717, 0.3595, 0.3201, 0.5477, 0.5440],
[0.6284, 0.3995, 0.6904, 0.3434, 0.3354, 0.3422, 0.5280, 0.5376],
[0.5998, 0.3851, 0.8500, 0.4988, 0.3631, 0.4099, 0.5674, 0.5175],
[0.6158, 0.3904, 0.8237, 0.4010, 0.3881, 0.5619, 0.6200, 0.5523],
[0.6299, 0.4122, 0.8502, 0.3714, 0.3427, 0.4069, 0.6090, 0.5711]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6222, 0.4072, 0.7164, 0.2166, 0.3738, 0.3167, 0.6100, 0.5533],
[0.6198, 0.4114, 0.8263, 0.3283, 0.3550, 0.3583, 0.5813, 0.5667],
[0.6307, 0.4060, 0.8950, 0.5183, 0.3750, 0.3850, 0.6338, 0.4938],
[0.6225, 0.4196, 0.8788, 0.3467, 0.3750, 0.3400, 0.5412, 0.5433],
[0.6109, 0.4041, 0.6975, 0.3167, 0.3512, 0.3383, 0.5153, 0.5319],
[0.6108, 0.4009, 0.8725, 0.4700, 0.3550, 0.4167, 0.5650, 0.5117],
[0.6097, 0.4024, 0.8487, 0.3717, 0.3875, 0.5517, 0.5836, 0.5591],
[0.6219, 0.4097, 0.8737, 0.3400, 0.3562, 0.4117, 0.5975, 0.5683]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.033311496314127
step: 73
running loss: 0.0004563218673168082
Train Steps: 73/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6076, 0.3958, 0.8700, 0.4667, 0.4546, 0.5046, 0.5231, 0.4960],
[0.6042, 0.3990, 0.6831, 0.2875, 0.3500, 0.3133, 0.5143, 0.5510],
[ nan, nan, 0.7648, 0.2722, 0.3962, 0.2183, 0.5060, 0.5422],
[0.6271, 0.4005, 0.8450, 0.6067, 0.3850, 0.4983, 0.6069, 0.4649],
[0.6129, 0.4069, 0.8750, 0.5067, 0.3875, 0.4233, 0.5235, 0.5881],
[0.6278, 0.4253, 0.8875, 0.5017, 0.4113, 0.2750, 0.5413, 0.6196],
[0.6296, 0.4076, 0.8400, 0.5583, 0.3700, 0.4367, 0.6876, 0.5494],
[0.6166, 0.4008, 0.8563, 0.5667, 0.4388, 0.4933, 0.5575, 0.5567]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6001, 0.3739, 0.8487, 0.4550, 0.4385, 0.5025, 0.5561, 0.5098],
[0.6396, 0.3958, 0.6744, 0.2837, 0.3477, 0.3114, 0.5517, 0.5619],
[0.0268, 0.0122, 0.7260, 0.2481, 0.3726, 0.2221, 0.5261, 0.5384],
[0.6357, 0.3967, 0.8064, 0.5874, 0.3649, 0.5221, 0.6275, 0.4840],
[0.5734, 0.3575, 0.8358, 0.5049, 0.3809, 0.4387, 0.5359, 0.5817],
[0.6598, 0.4303, 0.8430, 0.4853, 0.4221, 0.2899, 0.5880, 0.6172],
[0.6129, 0.3875, 0.8133, 0.5460, 0.3682, 0.4424, 0.7284, 0.5532],
[0.6262, 0.3910, 0.8388, 0.5480, 0.4184, 0.5080, 0.5845, 0.5708]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6076, 0.3958, 0.8700, 0.4667, 0.4546, 0.5046, 0.5231, 0.4960],
[0.6042, 0.3990, 0.6831, 0.2875, 0.3500, 0.3133, 0.5143, 0.5510],
[0.0000, 0.0000, 0.7648, 0.2722, 0.3963, 0.2183, 0.5060, 0.5422],
[0.6271, 0.4005, 0.8450, 0.6067, 0.3850, 0.4983, 0.6069, 0.4649],
[0.6129, 0.4069, 0.8750, 0.5067, 0.3875, 0.4233, 0.5235, 0.5881],
[0.6278, 0.4253, 0.8875, 0.5017, 0.4112, 0.2750, 0.5413, 0.6196],
[0.6296, 0.4076, 0.8400, 0.5583, 0.3700, 0.4367, 0.6876, 0.5494],
[0.6166, 0.4008, 0.8562, 0.5667, 0.4387, 0.4933, 0.5575, 0.5567]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03379115313873626
step: 74
running loss: 0.00045663720457751706
Train Steps: 74/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6122, 0.4048, 0.7506, 0.3014, 0.3475, 0.3333, 0.5487, 0.5749],
[0.6201, 0.4151, 0.8588, 0.5467, 0.3700, 0.3950, 0.5637, 0.5933],
[0.6106, 0.4022, 0.7125, 0.2650, 0.3713, 0.2700, 0.5431, 0.5123],
[0.6136, 0.4029, 0.8263, 0.3350, 0.3625, 0.3067, 0.5675, 0.5167],
[0.6264, 0.4035, 0.8888, 0.4883, 0.4050, 0.5217, 0.6361, 0.4791],
[0.6093, 0.3990, 0.8400, 0.4333, 0.3688, 0.4633, 0.5560, 0.5656],
[0.6307, 0.4029, 0.8650, 0.5200, 0.3763, 0.4017, 0.7311, 0.5366],
[0.6260, 0.4161, 0.9000, 0.3833, 0.4450, 0.2133, 0.6237, 0.4986]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6089, 0.3922, 0.7377, 0.3172, 0.3326, 0.3313, 0.5328, 0.5695],
[0.6255, 0.4055, 0.8288, 0.5502, 0.3399, 0.3870, 0.5390, 0.5697],
[0.6152, 0.4073, 0.6935, 0.2694, 0.3570, 0.2763, 0.5415, 0.5174],
[0.5788, 0.3750, 0.7982, 0.3405, 0.3481, 0.3064, 0.5433, 0.5249],
[0.6074, 0.3984, 0.8524, 0.4886, 0.3761, 0.5244, 0.6152, 0.4800],
[0.6091, 0.3986, 0.8160, 0.4387, 0.3483, 0.4726, 0.5366, 0.5699],
[0.6254, 0.4090, 0.8349, 0.5263, 0.3610, 0.4049, 0.7104, 0.5167],
[0.6412, 0.4223, 0.8794, 0.3954, 0.4289, 0.2125, 0.5985, 0.4951]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6122, 0.4048, 0.7506, 0.3014, 0.3475, 0.3333, 0.5487, 0.5749],
[0.6202, 0.4151, 0.8587, 0.5467, 0.3700, 0.3950, 0.5638, 0.5933],
[0.6106, 0.4022, 0.7125, 0.2650, 0.3713, 0.2700, 0.5431, 0.5123],
[0.6136, 0.4029, 0.8263, 0.3350, 0.3625, 0.3067, 0.5675, 0.5167],
[0.6264, 0.4035, 0.8888, 0.4883, 0.4050, 0.5217, 0.6361, 0.4791],
[0.6093, 0.3990, 0.8400, 0.4333, 0.3688, 0.4633, 0.5560, 0.5656],
[0.6307, 0.4029, 0.8650, 0.5200, 0.3762, 0.4017, 0.7311, 0.5366],
[0.6260, 0.4161, 0.9000, 0.3833, 0.4450, 0.2133, 0.6237, 0.4986]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03405617133830674
step: 75
running loss: 0.00045408228451075655
Train Steps: 75/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6102, 0.4001, 0.7738, 0.3583, 0.3463, 0.3800, 0.5524, 0.5689],
[0.6037, 0.4020, 0.8300, 0.4033, 0.3575, 0.4883, 0.5647, 0.5631],
[0.6293, 0.3982, 0.8700, 0.5300, 0.3763, 0.4717, 0.7050, 0.5297],
[0.6269, 0.4073, 0.8900, 0.4933, 0.3625, 0.4183, 0.6288, 0.5150],
[0.6339, 0.4159, 0.8400, 0.5617, 0.3825, 0.4150, 0.7343, 0.5748],
[0.6163, 0.4114, 0.7650, 0.2017, 0.3763, 0.2867, 0.5631, 0.5071],
[0.6097, 0.3988, 0.8650, 0.5250, 0.4213, 0.5200, 0.5675, 0.5050],
[0.6199, 0.4060, 0.8888, 0.4667, 0.3800, 0.5050, 0.6188, 0.5433]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6041, 0.3908, 0.7807, 0.3757, 0.3441, 0.3718, 0.5173, 0.5518],
[0.5819, 0.3833, 0.8373, 0.4099, 0.3521, 0.4983, 0.5535, 0.5542],
[0.6308, 0.3993, 0.8683, 0.5513, 0.3575, 0.4532, 0.6896, 0.5235],
[0.6291, 0.4198, 0.8922, 0.5122, 0.3483, 0.4118, 0.6168, 0.5032],
[0.6506, 0.4303, 0.8431, 0.5729, 0.3834, 0.3998, 0.7119, 0.5599],
[0.6258, 0.4162, 0.7446, 0.2005, 0.3655, 0.2652, 0.5402, 0.5004],
[0.6046, 0.4005, 0.8637, 0.5245, 0.4355, 0.5057, 0.5201, 0.4984],
[0.6070, 0.4025, 0.8941, 0.4713, 0.3727, 0.5104, 0.5979, 0.5312]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6102, 0.4001, 0.7738, 0.3583, 0.3462, 0.3800, 0.5524, 0.5689],
[0.6037, 0.4020, 0.8300, 0.4033, 0.3575, 0.4883, 0.5647, 0.5631],
[0.6293, 0.3982, 0.8700, 0.5300, 0.3762, 0.4717, 0.7050, 0.5297],
[0.6269, 0.4073, 0.8900, 0.4933, 0.3625, 0.4183, 0.6288, 0.5150],
[0.6339, 0.4159, 0.8400, 0.5617, 0.3825, 0.4150, 0.7343, 0.5748],
[0.6163, 0.4114, 0.7650, 0.2017, 0.3762, 0.2867, 0.5631, 0.5071],
[0.6097, 0.3988, 0.8650, 0.5250, 0.4212, 0.5200, 0.5675, 0.5050],
[0.6199, 0.4060, 0.8888, 0.4667, 0.3800, 0.5050, 0.6187, 0.5433]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03425430311472155
step: 76
running loss: 0.00045071451466738885
Train Steps: 76/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6133, 0.4094, 0.8495, 0.4028, 0.3588, 0.3200, 0.5003, 0.5407],
[0.6307, 0.4060, 0.8950, 0.5183, 0.3750, 0.3850, 0.6338, 0.4938],
[0.6122, 0.3993, 0.8738, 0.4667, 0.4517, 0.4879, 0.5155, 0.4927],
[0.6275, 0.4111, 0.8463, 0.2617, 0.4487, 0.1983, 0.6211, 0.4904],
[0.6272, 0.4071, 0.8738, 0.5600, 0.3675, 0.3783, 0.5926, 0.4742],
[ nan, nan, 0.7625, 0.2433, 0.3713, 0.2867, 0.5235, 0.5220],
[0.6102, 0.4020, 0.8638, 0.3717, 0.3625, 0.5017, 0.6038, 0.5500],
[0.6339, 0.4102, 0.8588, 0.3133, 0.4425, 0.2117, 0.6417, 0.5089]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.5782, 0.3960, 0.8596, 0.4026, 0.3638, 0.2947, 0.5104, 0.5605],
[ 0.5868, 0.3921, 0.8928, 0.5126, 0.3761, 0.3818, 0.6223, 0.5027],
[ 0.5819, 0.3889, 0.8771, 0.4751, 0.4446, 0.4962, 0.5090, 0.5008],
[ 0.6055, 0.4110, 0.8534, 0.2530, 0.4695, 0.1872, 0.6282, 0.5183],
[ 0.5992, 0.3971, 0.8742, 0.5657, 0.3681, 0.3804, 0.6038, 0.4837],
[-0.0291, -0.0051, 0.7582, 0.2469, 0.3822, 0.2729, 0.5228, 0.5483],
[ 0.5652, 0.3814, 0.8680, 0.3559, 0.3709, 0.4956, 0.6065, 0.5715],
[ 0.6148, 0.4079, 0.8644, 0.3119, 0.4575, 0.2078, 0.6471, 0.5255]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6133, 0.4094, 0.8495, 0.4028, 0.3587, 0.3200, 0.5003, 0.5407],
[0.6307, 0.4060, 0.8950, 0.5183, 0.3750, 0.3850, 0.6338, 0.4938],
[0.6122, 0.3993, 0.8737, 0.4667, 0.4517, 0.4879, 0.5155, 0.4927],
[0.6275, 0.4111, 0.8462, 0.2617, 0.4487, 0.1983, 0.6211, 0.4904],
[0.6272, 0.4071, 0.8737, 0.5600, 0.3675, 0.3783, 0.5926, 0.4742],
[0.0000, 0.0000, 0.7625, 0.2433, 0.3713, 0.2867, 0.5235, 0.5220],
[0.6102, 0.4020, 0.8637, 0.3717, 0.3625, 0.5017, 0.6037, 0.5500],
[0.6339, 0.4102, 0.8587, 0.3133, 0.4425, 0.2117, 0.6417, 0.5089]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03449908675975166
step: 77
running loss: 0.00044804008778898265
Train Steps: 77/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6346, 0.4144, 0.9088, 0.4667, 0.3850, 0.4333, 0.7121, 0.5899],
[0.6182, 0.3998, 0.8793, 0.4191, 0.3552, 0.4285, 0.6038, 0.5312],
[0.6262, 0.4052, 0.8888, 0.4700, 0.3675, 0.5117, 0.6350, 0.5233],
[0.6192, 0.3980, 0.7078, 0.2750, 0.4250, 0.2100, 0.5450, 0.5783],
[0.6161, 0.4024, 0.8662, 0.4683, 0.4935, 0.5364, 0.6063, 0.5567],
[0.6260, 0.4133, 0.8800, 0.5117, 0.3713, 0.3283, 0.6223, 0.4967],
[0.6346, 0.4092, 0.7712, 0.5917, 0.4037, 0.4767, 0.7343, 0.5725],
[0.6076, 0.3958, 0.8700, 0.4667, 0.4546, 0.5046, 0.5231, 0.4960]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5928, 0.4148, 0.9317, 0.4549, 0.3857, 0.4069, 0.6875, 0.5749],
[0.6258, 0.4227, 0.8987, 0.4046, 0.3453, 0.4238, 0.5952, 0.5166],
[0.5839, 0.4023, 0.9205, 0.4549, 0.3527, 0.4937, 0.6135, 0.5055],
[0.6059, 0.4120, 0.7293, 0.2632, 0.4128, 0.1986, 0.5330, 0.5595],
[0.6360, 0.4297, 0.9069, 0.4480, 0.4612, 0.5162, 0.5732, 0.5343],
[0.5389, 0.3747, 0.9047, 0.5002, 0.3684, 0.3171, 0.6194, 0.4796],
[0.5922, 0.4071, 0.8178, 0.5521, 0.3789, 0.4638, 0.7159, 0.5648],
[0.5700, 0.3894, 0.9051, 0.4533, 0.4485, 0.4864, 0.5142, 0.4808]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6346, 0.4144, 0.9087, 0.4667, 0.3850, 0.4333, 0.7121, 0.5899],
[0.6182, 0.3998, 0.8793, 0.4191, 0.3552, 0.4285, 0.6038, 0.5312],
[0.6262, 0.4052, 0.8888, 0.4700, 0.3675, 0.5117, 0.6350, 0.5233],
[0.6192, 0.3980, 0.7078, 0.2750, 0.4250, 0.2100, 0.5450, 0.5783],
[0.6161, 0.4024, 0.8662, 0.4683, 0.4935, 0.5364, 0.6062, 0.5567],
[0.6260, 0.4133, 0.8800, 0.5117, 0.3713, 0.3283, 0.6223, 0.4967],
[0.6346, 0.4092, 0.7713, 0.5917, 0.4038, 0.4767, 0.7343, 0.5725],
[0.6076, 0.3958, 0.8700, 0.4667, 0.4546, 0.5046, 0.5231, 0.4960]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0006, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03509918806958012
step: 78
running loss: 0.0004499895906356426
Train Steps: 78/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6202, 0.4064, 0.7879, 0.2179, 0.4567, 0.1725, 0.5955, 0.5478],
[0.6282, 0.4029, 0.8988, 0.3000, 0.4250, 0.4183, 0.7042, 0.5575],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533],
[0.6186, 0.4154, 0.6825, 0.2633, 0.4150, 0.2300, 0.5713, 0.5517],
[0.6203, 0.4056, 0.8942, 0.4086, 0.3643, 0.3617, 0.5917, 0.5482],
[0.6164, 0.4066, 0.6625, 0.3033, 0.3775, 0.2967, 0.5725, 0.5833],
[0.6193, 0.4108, 0.7425, 0.2350, 0.3887, 0.2750, 0.5900, 0.5717],
[0.6042, 0.3990, 0.6831, 0.2875, 0.3500, 0.3133, 0.5143, 0.5510]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5432, 0.3973, 0.8100, 0.2312, 0.4705, 0.1608, 0.5825, 0.5160],
[0.5358, 0.3683, 0.9406, 0.3140, 0.4232, 0.4218, 0.7012, 0.5485],
[0.5776, 0.4162, 0.9353, 0.4523, 0.4308, 0.5172, 0.5749, 0.5158],
[0.6260, 0.4445, 0.7304, 0.2638, 0.4196, 0.2368, 0.5704, 0.5261],
[0.5931, 0.4030, 0.9394, 0.4244, 0.3533, 0.3649, 0.5951, 0.5182],
[0.6915, 0.4722, 0.7127, 0.3191, 0.3733, 0.2816, 0.5586, 0.5610],
[0.5933, 0.4062, 0.7941, 0.2518, 0.3930, 0.2678, 0.5787, 0.5510],
[0.5903, 0.4067, 0.7309, 0.2871, 0.3600, 0.3128, 0.5212, 0.5276]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6202, 0.4064, 0.7879, 0.2179, 0.4567, 0.1725, 0.5955, 0.5478],
[0.6282, 0.4029, 0.8988, 0.3000, 0.4250, 0.4183, 0.7042, 0.5575],
[0.6140, 0.4034, 0.8850, 0.4317, 0.4288, 0.5067, 0.5825, 0.5533],
[0.6186, 0.4154, 0.6825, 0.2633, 0.4150, 0.2300, 0.5713, 0.5517],
[0.6203, 0.4056, 0.8942, 0.4086, 0.3643, 0.3617, 0.5917, 0.5482],
[0.6164, 0.4066, 0.6625, 0.3033, 0.3775, 0.2967, 0.5725, 0.5833],
[0.6193, 0.4108, 0.7425, 0.2350, 0.3887, 0.2750, 0.5900, 0.5717],
[0.6042, 0.3990, 0.6831, 0.2875, 0.3500, 0.3133, 0.5143, 0.5510]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0009, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03596113619278185
step: 79
running loss: 0.00045520425560483354
Train Steps: 79/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.7553, 0.2722, 0.3875, 0.2550, 0.5125, 0.5633],
[0.6307, 0.3998, 0.8500, 0.5233, 0.3850, 0.5050, 0.7446, 0.5320],
[0.6064, 0.4019, 0.8650, 0.4517, 0.4037, 0.5367, 0.5703, 0.5609],
[0.6190, 0.4135, 0.8000, 0.4883, 0.3566, 0.3647, 0.5613, 0.5900],
[0.6203, 0.4076, 0.8611, 0.2878, 0.4050, 0.2554, 0.5907, 0.5496],
[0.6276, 0.4002, 0.8800, 0.5533, 0.3575, 0.4400, 0.6132, 0.4672],
[0.6097, 0.3988, 0.8650, 0.5250, 0.4213, 0.5200, 0.5675, 0.5050],
[0.6227, 0.4049, 0.8750, 0.5367, 0.3775, 0.3667, 0.5725, 0.5317]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[-0.0010, 0.0065, 0.7765, 0.2641, 0.4116, 0.2566, 0.5234, 0.5575],
[ 0.6268, 0.4027, 0.8630, 0.4974, 0.4012, 0.5111, 0.7375, 0.5369],
[ 0.6158, 0.4085, 0.8687, 0.4403, 0.4261, 0.5473, 0.5952, 0.5478],
[ 0.6377, 0.4170, 0.8245, 0.4601, 0.3776, 0.3475, 0.5361, 0.5637],
[ 0.6432, 0.4277, 0.8856, 0.2673, 0.4200, 0.2645, 0.6101, 0.5431],
[ 0.6187, 0.3922, 0.8841, 0.5153, 0.3864, 0.4361, 0.6395, 0.4873],
[ 0.6301, 0.4144, 0.8737, 0.4948, 0.4597, 0.5032, 0.5711, 0.5104],
[ 0.6202, 0.4080, 0.8791, 0.5169, 0.3921, 0.3731, 0.5952, 0.5370]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.7553, 0.2722, 0.3875, 0.2550, 0.5125, 0.5633],
[0.6307, 0.3998, 0.8500, 0.5233, 0.3850, 0.5050, 0.7446, 0.5320],
[0.6064, 0.4019, 0.8650, 0.4517, 0.4038, 0.5367, 0.5703, 0.5609],
[0.6190, 0.4135, 0.8000, 0.4883, 0.3566, 0.3647, 0.5612, 0.5900],
[0.6203, 0.4076, 0.8611, 0.2878, 0.4050, 0.2554, 0.5907, 0.5496],
[0.6276, 0.4002, 0.8800, 0.5533, 0.3575, 0.4400, 0.6132, 0.4672],
[0.6097, 0.3988, 0.8650, 0.5250, 0.4212, 0.5200, 0.5675, 0.5050],
[0.6227, 0.4049, 0.8750, 0.5367, 0.3775, 0.3667, 0.5725, 0.5317]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.036256922205211595
step: 80
running loss: 0.0004532115275651449
Train Steps: 80/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6179, 0.3993, 0.8925, 0.4789, 0.3879, 0.4900, 0.6041, 0.5279],
[0.6140, 0.4070, 0.8700, 0.5000, 0.4612, 0.4900, 0.5260, 0.5852],
[0.6257, 0.4167, 0.8775, 0.3433, 0.3563, 0.4133, 0.6200, 0.5667],
[0.6357, 0.4159, 0.8788, 0.5583, 0.3638, 0.4433, 0.6488, 0.5297],
[0.6186, 0.4013, 0.8191, 0.3188, 0.4279, 0.2060, 0.5767, 0.5411],
[0.6093, 0.3990, 0.8400, 0.4333, 0.3688, 0.4633, 0.5560, 0.5656],
[0.6201, 0.4065, 0.7300, 0.1933, 0.4075, 0.2533, 0.6162, 0.5483],
[0.6284, 0.4093, 0.8900, 0.4700, 0.3650, 0.3850, 0.6212, 0.5167]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6646, 0.4309, 0.8815, 0.4630, 0.3912, 0.5001, 0.6282, 0.5300],
[0.6050, 0.4034, 0.8733, 0.5086, 0.4680, 0.4959, 0.5481, 0.5852],
[0.6617, 0.4315, 0.8732, 0.3614, 0.3578, 0.4102, 0.6455, 0.5599],
[0.6401, 0.4181, 0.8733, 0.5595, 0.3670, 0.4489, 0.6568, 0.5374],
[0.6406, 0.4236, 0.8144, 0.3135, 0.4189, 0.2087, 0.5796, 0.5340],
[0.6158, 0.4083, 0.8343, 0.4385, 0.3714, 0.4626, 0.5720, 0.5615],
[0.6516, 0.4322, 0.7191, 0.2065, 0.4086, 0.2620, 0.6223, 0.5469],
[0.6441, 0.4177, 0.8827, 0.4689, 0.3794, 0.3867, 0.6357, 0.5137]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6179, 0.3993, 0.8925, 0.4789, 0.3879, 0.4900, 0.6041, 0.5279],
[0.6140, 0.4070, 0.8700, 0.5000, 0.4613, 0.4900, 0.5260, 0.5852],
[0.6257, 0.4167, 0.8775, 0.3433, 0.3562, 0.4133, 0.6200, 0.5667],
[0.6357, 0.4159, 0.8788, 0.5583, 0.3638, 0.4433, 0.6488, 0.5297],
[0.6186, 0.4013, 0.8191, 0.3188, 0.4279, 0.2060, 0.5767, 0.5411],
[0.6093, 0.3990, 0.8400, 0.4333, 0.3688, 0.4633, 0.5560, 0.5656],
[0.6201, 0.4065, 0.7300, 0.1933, 0.4075, 0.2533, 0.6162, 0.5483],
[0.6284, 0.4092, 0.8900, 0.4700, 0.3650, 0.3850, 0.6212, 0.5167]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03644900632207282
step: 81
running loss: 0.00044998773237126937
Train Steps: 81/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6305, 0.3983, 0.8950, 0.4833, 0.3688, 0.4683, 0.6375, 0.5117],
[0.6239, 0.4107, 0.8162, 0.2763, 0.3625, 0.3600, 0.5988, 0.5700],
[0.6082, 0.4042, 0.6975, 0.1917, 0.4100, 0.1983, 0.5502, 0.5578],
[0.6179, 0.4118, 0.7278, 0.4237, 0.3588, 0.3400, 0.5675, 0.5917],
[0.6282, 0.4034, 0.7830, 0.2080, 0.4532, 0.2080, 0.6404, 0.5323],
[0.6193, 0.4050, 0.7313, 0.2433, 0.4075, 0.2117, 0.5649, 0.5656],
[0.6300, 0.4013, 0.8938, 0.5350, 0.3675, 0.4600, 0.6456, 0.4973],
[0.6186, 0.4060, 0.8750, 0.5050, 0.3538, 0.4367, 0.5813, 0.6083]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6277, 0.3878, 0.9010, 0.5158, 0.3749, 0.4779, 0.6465, 0.5020],
[0.6288, 0.4082, 0.7888, 0.2897, 0.3721, 0.3737, 0.5910, 0.5788],
[0.5866, 0.3920, 0.6858, 0.2162, 0.4286, 0.2067, 0.5621, 0.5650],
[0.6369, 0.4128, 0.7630, 0.4370, 0.3602, 0.3508, 0.5537, 0.5989],
[0.6528, 0.4111, 0.7752, 0.2209, 0.4564, 0.2176, 0.6471, 0.5461],
[0.6481, 0.4258, 0.7230, 0.2635, 0.4205, 0.2282, 0.5779, 0.5720],
[0.6336, 0.3955, 0.8779, 0.5571, 0.3745, 0.4803, 0.6392, 0.4987],
[0.6238, 0.4054, 0.8646, 0.5141, 0.3662, 0.4475, 0.5779, 0.6036]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6305, 0.3983, 0.8950, 0.4833, 0.3688, 0.4683, 0.6375, 0.5117],
[0.6239, 0.4107, 0.8162, 0.2763, 0.3625, 0.3600, 0.5987, 0.5700],
[0.6082, 0.4042, 0.6975, 0.1917, 0.4100, 0.1983, 0.5502, 0.5578],
[0.6179, 0.4118, 0.7278, 0.4237, 0.3587, 0.3400, 0.5675, 0.5917],
[0.6282, 0.4034, 0.7830, 0.2080, 0.4532, 0.2080, 0.6404, 0.5323],
[0.6193, 0.4050, 0.7312, 0.2433, 0.4075, 0.2117, 0.5649, 0.5656],
[0.6300, 0.4013, 0.8938, 0.5350, 0.3675, 0.4600, 0.6456, 0.4973],
[0.6186, 0.4060, 0.8750, 0.5050, 0.3537, 0.4367, 0.5813, 0.6083]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0002, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.036643293395172805
step: 82
running loss: 0.00044686943164844883
Train Steps: 82/90 Loss: 0.0004 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6264, 0.4067, 0.9050, 0.4183, 0.3775, 0.4600, 0.6308, 0.4862],
[ nan, nan, 0.7097, 0.2346, 0.4250, 0.1850, 0.5175, 0.5583],
[ nan, nan, 0.7425, 0.2117, 0.3937, 0.2433, 0.5438, 0.5567],
[0.6129, 0.4114, 0.6950, 0.2467, 0.4050, 0.2133, 0.5363, 0.5550],
[0.6124, 0.4030, 0.8650, 0.4867, 0.4999, 0.5106, 0.5137, 0.5773],
[0.6189, 0.4029, 0.8375, 0.5767, 0.4745, 0.4829, 0.5551, 0.5598],
[0.6193, 0.4108, 0.7425, 0.2350, 0.3887, 0.2750, 0.5900, 0.5717],
[0.6224, 0.3964, 0.8225, 0.5717, 0.4150, 0.4617, 0.5775, 0.5267]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6645, 0.4274, 0.8826, 0.4182, 0.3632, 0.4493, 0.6396, 0.5114],
[0.1255, 0.0742, 0.7000, 0.2189, 0.4249, 0.2004, 0.5262, 0.5696],
[0.1267, 0.0676, 0.7274, 0.2114, 0.3882, 0.2491, 0.5524, 0.5611],
[0.6629, 0.4283, 0.6798, 0.2681, 0.3986, 0.2032, 0.5701, 0.5781],
[0.6747, 0.4213, 0.8377, 0.5059, 0.4841, 0.4928, 0.5337, 0.5692],
[0.6728, 0.4323, 0.8164, 0.5713, 0.4575, 0.4565, 0.5950, 0.5876],
[0.6986, 0.4415, 0.7335, 0.2450, 0.3789, 0.2552, 0.6003, 0.5945],
[0.7199, 0.4423, 0.8084, 0.5859, 0.3913, 0.4404, 0.6138, 0.5356]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6264, 0.4067, 0.9050, 0.4183, 0.3775, 0.4600, 0.6308, 0.4862],
[0.0000, 0.0000, 0.7097, 0.2346, 0.4250, 0.1850, 0.5175, 0.5583],
[0.0000, 0.0000, 0.7425, 0.2117, 0.3938, 0.2433, 0.5437, 0.5567],
[0.6129, 0.4114, 0.6950, 0.2467, 0.4050, 0.2133, 0.5362, 0.5550],
[0.6124, 0.4030, 0.8650, 0.4867, 0.4999, 0.5106, 0.5137, 0.5773],
[0.6189, 0.4029, 0.8375, 0.5767, 0.4745, 0.4829, 0.5551, 0.5598],
[0.6193, 0.4108, 0.7425, 0.2350, 0.3887, 0.2750, 0.5900, 0.5717],
[0.6224, 0.3964, 0.8225, 0.5717, 0.4150, 0.4617, 0.5775, 0.5267]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0014, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03802865924080834
step: 83
running loss: 0.0004581766173591366
Train Steps: 83/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[ nan, nan, 0.8363, 0.3317, 0.3563, 0.3367, 0.5329, 0.5142],
[0.6222, 0.4072, 0.7164, 0.2166, 0.3738, 0.3167, 0.6100, 0.5533],
[0.6332, 0.4165, 0.9100, 0.3350, 0.4188, 0.3683, 0.7438, 0.5528],
[0.6229, 0.4066, 0.7612, 0.2967, 0.4250, 0.2167, 0.5925, 0.5350],
[0.6138, 0.4020, 0.8800, 0.4717, 0.4375, 0.4717, 0.5502, 0.5611],
[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459],
[0.6214, 0.3982, 0.8938, 0.4517, 0.3663, 0.4083, 0.5863, 0.5050],
[0.6260, 0.4214, 0.8538, 0.5500, 0.3663, 0.3767, 0.5587, 0.5983]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.0603, 0.0229, 0.7907, 0.3199, 0.3460, 0.3630, 0.5440, 0.5371],
[0.6344, 0.3954, 0.6876, 0.2187, 0.3711, 0.3368, 0.6029, 0.5666],
[0.6674, 0.4167, 0.8742, 0.3484, 0.4033, 0.3879, 0.7346, 0.5647],
[0.6683, 0.3995, 0.7279, 0.2874, 0.4217, 0.2310, 0.5822, 0.5594],
[0.6703, 0.4092, 0.8422, 0.4734, 0.4231, 0.4850, 0.5436, 0.5723],
[0.6740, 0.4162, 0.8302, 0.2882, 0.4772, 0.2208, 0.6648, 0.5577],
[0.6306, 0.3858, 0.8653, 0.4550, 0.3553, 0.4258, 0.5858, 0.5191],
[0.6742, 0.4291, 0.8340, 0.5555, 0.3548, 0.3969, 0.5518, 0.6012]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.0000, 0.0000, 0.8363, 0.3317, 0.3562, 0.3367, 0.5329, 0.5142],
[0.6222, 0.4072, 0.7164, 0.2166, 0.3738, 0.3167, 0.6100, 0.5533],
[0.6332, 0.4165, 0.9100, 0.3350, 0.4187, 0.3683, 0.7438, 0.5528],
[0.6229, 0.4066, 0.7613, 0.2967, 0.4250, 0.2167, 0.5925, 0.5350],
[0.6138, 0.4020, 0.8800, 0.4717, 0.4375, 0.4717, 0.5502, 0.5611],
[0.6361, 0.4102, 0.8650, 0.2983, 0.4888, 0.2000, 0.6702, 0.5459],
[0.6214, 0.3982, 0.8938, 0.4517, 0.3663, 0.4083, 0.5863, 0.5050],
[0.6260, 0.4214, 0.8537, 0.5500, 0.3663, 0.3767, 0.5587, 0.5983]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03851493066758849
step: 84
running loss: 0.0004585110793760534
Train Steps: 84/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6203, 0.4096, 0.8862, 0.4267, 0.3538, 0.4117, 0.6025, 0.5650],
[0.6240, 0.4217, 0.8150, 0.3133, 0.4425, 0.2650, 0.5650, 0.5817],
[0.6332, 0.4128, 0.9200, 0.3517, 0.4400, 0.3833, 0.7461, 0.5494],
[0.6182, 0.3982, 0.7541, 0.2379, 0.3959, 0.2792, 0.6079, 0.5389],
[0.6137, 0.4084, 0.8076, 0.3889, 0.3650, 0.3150, 0.5356, 0.5896],
[0.6185, 0.4129, 0.8900, 0.4567, 0.3937, 0.5417, 0.5734, 0.5110],
[0.6186, 0.4060, 0.8750, 0.5050, 0.3538, 0.4367, 0.5813, 0.6083],
[0.6361, 0.4071, 0.9100, 0.4783, 0.3738, 0.3967, 0.6670, 0.5332]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6436, 0.4039, 0.8519, 0.4282, 0.3554, 0.4118, 0.5926, 0.5785],
[0.6478, 0.4293, 0.7909, 0.3250, 0.4391, 0.2788, 0.5641, 0.5899],
[0.6030, 0.3804, 0.8897, 0.3661, 0.4324, 0.3936, 0.7197, 0.5556],
[0.5850, 0.3690, 0.7338, 0.2239, 0.3816, 0.2882, 0.5983, 0.5582],
[0.5742, 0.3576, 0.7863, 0.3901, 0.3561, 0.3192, 0.5261, 0.6010],
[0.5740, 0.3685, 0.8627, 0.4725, 0.3765, 0.5421, 0.5540, 0.5164],
[0.6090, 0.3848, 0.8427, 0.4962, 0.3518, 0.4459, 0.5653, 0.6092],
[0.6362, 0.3829, 0.8636, 0.4940, 0.3785, 0.4176, 0.6509, 0.5184]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6203, 0.4096, 0.8863, 0.4267, 0.3537, 0.4117, 0.6025, 0.5650],
[0.6240, 0.4217, 0.8150, 0.3133, 0.4425, 0.2650, 0.5650, 0.5817],
[0.6332, 0.4128, 0.9200, 0.3517, 0.4400, 0.3833, 0.7461, 0.5494],
[0.6182, 0.3982, 0.7541, 0.2379, 0.3959, 0.2792, 0.6079, 0.5389],
[0.6137, 0.4084, 0.8076, 0.3889, 0.3650, 0.3150, 0.5356, 0.5896],
[0.6186, 0.4129, 0.8900, 0.4567, 0.3938, 0.5417, 0.5734, 0.5110],
[0.6186, 0.4060, 0.8750, 0.5050, 0.3537, 0.4367, 0.5813, 0.6083],
[0.6361, 0.4071, 0.9100, 0.4783, 0.3738, 0.3967, 0.6670, 0.5332]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0004, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03894413818488829
step: 85
running loss: 0.00045816633158692104
Train Steps: 85/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6204, 0.4049, 0.7975, 0.2700, 0.3937, 0.2567, 0.5700, 0.5183],
[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758],
[0.6329, 0.4175, 0.8550, 0.2333, 0.5425, 0.2250, 0.7398, 0.5609],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4012, 0.4633, 0.5338, 0.5767],
[0.6200, 0.3961, 0.8461, 0.5497, 0.4142, 0.4577, 0.5892, 0.5402],
[0.6272, 0.4071, 0.8738, 0.5600, 0.3675, 0.3783, 0.5926, 0.4742],
[0.6189, 0.4033, 0.8650, 0.5267, 0.4487, 0.5150, 0.5925, 0.5050],
[0.6274, 0.4003, 0.8638, 0.5967, 0.3688, 0.4900, 0.6108, 0.4661]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6141, 0.3935, 0.7946, 0.2674, 0.3842, 0.2769, 0.5639, 0.5398],
[0.6237, 0.3929, 0.8780, 0.4692, 0.4058, 0.5315, 0.6351, 0.5098],
[0.6030, 0.3903, 0.8513, 0.2258, 0.5386, 0.2168, 0.7136, 0.5800],
[0.6055, 0.3781, 0.8742, 0.4740, 0.3947, 0.4553, 0.5317, 0.6069],
[0.5899, 0.3682, 0.8513, 0.5185, 0.4040, 0.4640, 0.5885, 0.5614],
[0.6357, 0.3988, 0.8772, 0.5516, 0.3704, 0.3951, 0.5980, 0.4916],
[0.5939, 0.3816, 0.8711, 0.5063, 0.4372, 0.5173, 0.5934, 0.5332],
[0.6167, 0.3730, 0.8572, 0.5795, 0.3756, 0.4856, 0.6109, 0.4972]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6204, 0.4049, 0.7975, 0.2700, 0.3938, 0.2567, 0.5700, 0.5183],
[0.6263, 0.4029, 0.8900, 0.4933, 0.4075, 0.5183, 0.6406, 0.4758],
[0.6329, 0.4175, 0.8550, 0.2333, 0.5425, 0.2250, 0.7398, 0.5609],
[0.6163, 0.4001, 0.8788, 0.5033, 0.4013, 0.4633, 0.5337, 0.5767],
[0.6200, 0.3961, 0.8461, 0.5497, 0.4142, 0.4577, 0.5892, 0.5402],
[0.6272, 0.4071, 0.8737, 0.5600, 0.3675, 0.3783, 0.5926, 0.4742],
[0.6189, 0.4033, 0.8650, 0.5267, 0.4487, 0.5150, 0.5925, 0.5050],
[0.6274, 0.4003, 0.8637, 0.5967, 0.3688, 0.4900, 0.6108, 0.4661]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03921863157302141
step: 86
running loss: 0.0004560305996862955
Train Steps: 86/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6270, 0.4267, 0.7150, 0.3317, 0.4900, 0.1817, 0.5560, 0.6183],
[0.6307, 0.4045, 0.8025, 0.5833, 0.3775, 0.4867, 0.6892, 0.5459],
[ nan, nan, 0.8625, 0.2550, 0.5487, 0.2200, 0.7335, 0.5737],
[0.6109, 0.3943, 0.8525, 0.4950, 0.4338, 0.4800, 0.5449, 0.5383],
[ nan, nan, 0.7725, 0.2611, 0.3675, 0.2733, 0.5413, 0.5167],
[0.6115, 0.4081, 0.6725, 0.2433, 0.4088, 0.1933, 0.5167, 0.5544],
[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.6201, 0.4004, 0.8786, 0.5043, 0.3833, 0.5138, 0.5997, 0.5092]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[ 0.6535, 0.4477, 0.7380, 0.3077, 0.4887, 0.1751, 0.5390, 0.6052],
[ 0.6257, 0.4103, 0.8346, 0.5530, 0.4003, 0.4779, 0.6911, 0.5352],
[-0.0232, -0.0088, 0.8852, 0.2373, 0.5437, 0.2008, 0.7311, 0.5667],
[ 0.6336, 0.4117, 0.8687, 0.4738, 0.4279, 0.4695, 0.5236, 0.5331],
[ 0.0291, 0.0120, 0.7872, 0.2631, 0.3804, 0.2830, 0.5299, 0.5368],
[ 0.5745, 0.3887, 0.7025, 0.2337, 0.4180, 0.1965, 0.5124, 0.5520],
[ 0.6495, 0.4207, 0.8767, 0.5533, 0.3920, 0.4965, 0.6463, 0.5284],
[ 0.6101, 0.3976, 0.8975, 0.4903, 0.3915, 0.5094, 0.5763, 0.4975]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6270, 0.4266, 0.7150, 0.3317, 0.4900, 0.1817, 0.5560, 0.6183],
[0.6307, 0.4045, 0.8025, 0.5833, 0.3775, 0.4867, 0.6892, 0.5459],
[0.0000, 0.0000, 0.8625, 0.2550, 0.5487, 0.2200, 0.7335, 0.5737],
[0.6109, 0.3943, 0.8525, 0.4950, 0.4338, 0.4800, 0.5449, 0.5383],
[0.0000, 0.0000, 0.7725, 0.2611, 0.3675, 0.2733, 0.5412, 0.5167],
[0.6115, 0.4081, 0.6725, 0.2433, 0.4087, 0.1933, 0.5167, 0.5544],
[0.6364, 0.4092, 0.8525, 0.5633, 0.3875, 0.4950, 0.6599, 0.5285],
[0.6201, 0.4004, 0.8786, 0.5043, 0.3833, 0.5138, 0.5997, 0.5092]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.039484524459112436
step: 87
running loss: 0.00045384510872543027
Train Steps: 87/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6267, 0.4080, 0.8438, 0.2633, 0.4763, 0.1800, 0.6259, 0.5240],
[0.6239, 0.4123, 0.8313, 0.2550, 0.4500, 0.2050, 0.6175, 0.5400],
[0.6254, 0.3993, 0.8988, 0.4767, 0.3987, 0.5517, 0.6955, 0.5285],
[0.6182, 0.3972, 0.8552, 0.5914, 0.3683, 0.4181, 0.5688, 0.5378],
[0.6223, 0.4028, 0.8988, 0.4200, 0.3763, 0.5733, 0.6375, 0.5167],
[0.6185, 0.4079, 0.8838, 0.4617, 0.4838, 0.5650, 0.6175, 0.5850],
[0.6224, 0.4097, 0.7438, 0.2267, 0.3850, 0.2850, 0.5988, 0.5250],
[0.6357, 0.4139, 0.8450, 0.5883, 0.3775, 0.4950, 0.6488, 0.5297]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5603, 0.3784, 0.8676, 0.2693, 0.4874, 0.1654, 0.6212, 0.5118],
[0.5558, 0.3819, 0.8536, 0.2485, 0.4586, 0.1737, 0.6244, 0.5170],
[0.5744, 0.3882, 0.9210, 0.4832, 0.4121, 0.5297, 0.6812, 0.5251],
[0.6119, 0.4007, 0.8821, 0.6022, 0.3731, 0.4060, 0.5844, 0.5124],
[0.6405, 0.4299, 0.9178, 0.4135, 0.3962, 0.5504, 0.6143, 0.5061],
[0.5793, 0.4005, 0.9085, 0.4624, 0.4908, 0.5308, 0.6161, 0.5828],
[0.5847, 0.4053, 0.7593, 0.2255, 0.4041, 0.2817, 0.5970, 0.5267],
[0.5840, 0.4049, 0.8577, 0.5849, 0.3925, 0.4816, 0.6681, 0.5257]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6267, 0.4080, 0.8438, 0.2633, 0.4762, 0.1800, 0.6259, 0.5240],
[0.6239, 0.4123, 0.8313, 0.2550, 0.4500, 0.2050, 0.6175, 0.5400],
[0.6254, 0.3993, 0.8988, 0.4767, 0.3988, 0.5517, 0.6955, 0.5285],
[0.6182, 0.3972, 0.8552, 0.5914, 0.3683, 0.4181, 0.5688, 0.5378],
[0.6223, 0.4028, 0.8988, 0.4200, 0.3762, 0.5733, 0.6375, 0.5167],
[0.6184, 0.4079, 0.8838, 0.4617, 0.4837, 0.5650, 0.6175, 0.5850],
[0.6224, 0.4097, 0.7437, 0.2267, 0.3850, 0.2850, 0.5987, 0.5250],
[0.6357, 0.4139, 0.8450, 0.5883, 0.3775, 0.4950, 0.6488, 0.5297]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0005, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.03999189910246059
step: 88
running loss: 0.00045445339889159766
Train Steps: 88/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6163, 0.4001, 0.8788, 0.5033, 0.4012, 0.4633, 0.5338, 0.5767],
[0.6117, 0.4019, 0.8538, 0.4067, 0.3513, 0.3583, 0.5663, 0.5133],
[0.6245, 0.4100, 0.7762, 0.2583, 0.4963, 0.1517, 0.5875, 0.5417],
[0.6289, 0.4032, 0.8419, 0.5446, 0.4075, 0.5017, 0.6312, 0.5117],
[0.6131, 0.4037, 0.6907, 0.2819, 0.3688, 0.2700, 0.5217, 0.5680],
[0.6172, 0.4055, 0.8175, 0.2650, 0.3550, 0.3683, 0.5787, 0.5550],
[0.6216, 0.4099, 0.7225, 0.2033, 0.4188, 0.2217, 0.5975, 0.5283],
[0.6055, 0.4015, 0.7425, 0.2033, 0.4113, 0.1883, 0.5217, 0.4823]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.6066, 0.3985, 0.9077, 0.5174, 0.4141, 0.4509, 0.5534, 0.5614],
[0.5354, 0.3544, 0.8979, 0.4296, 0.3646, 0.3531, 0.5639, 0.4929],
[0.5940, 0.4112, 0.8060, 0.2632, 0.5045, 0.1279, 0.6124, 0.5162],
[0.6000, 0.3899, 0.8762, 0.5717, 0.4203, 0.5012, 0.6693, 0.4945],
[0.5872, 0.3957, 0.7123, 0.2898, 0.3786, 0.2703, 0.5455, 0.5416],
[0.5807, 0.3968, 0.8483, 0.2766, 0.3685, 0.3557, 0.5858, 0.5332],
[0.5939, 0.4277, 0.7381, 0.2260, 0.4264, 0.2097, 0.5972, 0.5062],
[0.5100, 0.3544, 0.7657, 0.2191, 0.4093, 0.1690, 0.5424, 0.4659]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6163, 0.4001, 0.8788, 0.5033, 0.4013, 0.4633, 0.5337, 0.5767],
[0.6116, 0.4019, 0.8537, 0.4067, 0.3512, 0.3583, 0.5663, 0.5133],
[0.6245, 0.4100, 0.7763, 0.2583, 0.4963, 0.1517, 0.5875, 0.5417],
[0.6289, 0.4031, 0.8419, 0.5446, 0.4075, 0.5017, 0.6313, 0.5117],
[0.6131, 0.4036, 0.6907, 0.2819, 0.3688, 0.2700, 0.5217, 0.5680],
[0.6172, 0.4055, 0.8175, 0.2650, 0.3550, 0.3683, 0.5788, 0.5550],
[0.6216, 0.4099, 0.7225, 0.2033, 0.4187, 0.2217, 0.5975, 0.5283],
[0.6055, 0.4015, 0.7425, 0.2033, 0.4112, 0.1883, 0.5217, 0.4823]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0007, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.040671683149412274
step: 89
running loss: 0.0004569852039259806
Train Steps: 89/90 Loss: 0.0005 torch.Size([8, 600, 800])
torch.Size([8, 8])
tensor([[0.6110, 0.4047, 0.8700, 0.4483, 0.3713, 0.3967, 0.5088, 0.5517],
[0.6138, 0.4101, 0.8800, 0.5083, 0.4637, 0.5950, 0.5587, 0.5077],
[0.6272, 0.4045, 0.8538, 0.5900, 0.3750, 0.4417, 0.5989, 0.4649],
[0.6224, 0.4179, 0.8700, 0.5683, 0.4037, 0.4683, 0.5650, 0.5600],
[0.6222, 0.4108, 0.8938, 0.4233, 0.3600, 0.3817, 0.5825, 0.5283],
[0.6272, 0.4120, 0.9038, 0.4117, 0.3725, 0.3200, 0.6175, 0.5250],
[0.6069, 0.3975, 0.8625, 0.5083, 0.4388, 0.5483, 0.5650, 0.4967],
[0.6189, 0.3911, 0.8800, 0.4917, 0.3713, 0.4800, 0.6038, 0.4833]],
device='cuda:0', dtype=torch.float64)
predictions are: tensor([[0.5591, 0.3871, 0.8722, 0.4501, 0.3691, 0.3893, 0.5137, 0.5304],
[0.6191, 0.4178, 0.8732, 0.5310, 0.4599, 0.5640, 0.5903, 0.5062],
[0.6055, 0.4156, 0.8485, 0.5866, 0.3716, 0.4301, 0.6193, 0.4586],
[0.5629, 0.3912, 0.8800, 0.5770, 0.4015, 0.4430, 0.5927, 0.5503],
[0.5660, 0.3942, 0.8862, 0.4269, 0.3550, 0.3593, 0.5990, 0.5308],
[0.5981, 0.4102, 0.9046, 0.4074, 0.3817, 0.3150, 0.6375, 0.5045],
[0.6029, 0.4083, 0.8549, 0.5220, 0.4479, 0.5373, 0.5806, 0.5060],
[0.6232, 0.4102, 0.8882, 0.4807, 0.3777, 0.4603, 0.6204, 0.4733]],
device='cuda:0', grad_fn=<AddmmBackward>)
landmarks are: tensor([[[0.6110, 0.4047, 0.8700, 0.4483, 0.3713, 0.3967, 0.5088, 0.5517],
[0.6138, 0.4101, 0.8800, 0.5083, 0.4638, 0.5950, 0.5587, 0.5077],
[0.6271, 0.4045, 0.8537, 0.5900, 0.3750, 0.4417, 0.5989, 0.4649],
[0.6224, 0.4179, 0.8700, 0.5683, 0.4038, 0.4683, 0.5650, 0.5600],
[0.6222, 0.4108, 0.8938, 0.4233, 0.3600, 0.3817, 0.5825, 0.5283],
[0.6272, 0.4120, 0.9038, 0.4117, 0.3725, 0.3200, 0.6175, 0.5250],
[0.6069, 0.3975, 0.8625, 0.5083, 0.4387, 0.5483, 0.5650, 0.4967],
[0.6189, 0.3911, 0.8800, 0.4917, 0.3713, 0.4800, 0.6037, 0.4833]]],
device='cuda:0')
loss_train_step before backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train_step after backward: tensor(0.0003, device='cuda:0', grad_fn=<MseLossBackward>)
loss_train: 0.04101139504928142
step: 90
running loss: 0.00045568216721423796
Valid Steps: 10/10 Loss: nan 05
--------------------------------------------------
Epoch: 10 Train Loss: 0.0005 Valid Loss: nan
--------------------------------------------------
Training Complete
Total Elapsed Time : 452.1295247077942 s
Comments