Hello, when I use ImageNet dataset to train the network, such an error occurred. How should I solve it?
Thanks!
Traceback (most recent call last):
File "/root/autodl-tmp/srgan/train_srresnet.py", line 331, in
main()
File "/root/autodl-tmp/srgan/train_srresnet.py", line 101, in main
psnr, ssim = validate(srresnet_model,
File "/root/autodl-tmp/srgan/train_srresnet.py", line 298, in validate
psnr = psnr_model(sr, gt)
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1190, in _call_impl
return forward_call(*input, **kwargs)
File "/root/autodl-tmp/srgan/image_quality_assessment.py", line 416, in forward
psnr_metrics = _psnr_torch(raw_tensor, dst_tensor, self.crop_border, self.only_test_y_channel)
File "/root/autodl-tmp/srgan/image_quality_assessment.py", line 376, in _psnr_torch
_check_tensor_shape(raw_tensor, dst_tensor)
File "/root/autodl-tmp/srgan/image_quality_assessment.py", line 357, in _check_tensor_shape
assert raw_tensor.shape == dst_tensor.shape, \
AssertionError: Supplied images have different sizes torch.Size([1, 3, 504, 504]) and torch.Size([1, 3, 288, 288])
Lornatang
commented
1 year ago
Hello, when I use ImageNet dataset to train the network, such an error occurred. How should I solve it? Thanks!
Traceback (most recent call last): File "/root/autodl-tmp/srgan/train_srresnet.py", line 331, in
main()
File "/root/autodl-tmp/srgan/train_srresnet.py", line 101, in main
psnr, ssim = validate(srresnet_model,
File "/root/autodl-tmp/srgan/train_srresnet.py", line 298, in validate
psnr = psnr_model(sr, gt)
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1190, in _call_impl
return forward_call(*input, **kwargs)
File "/root/autodl-tmp/srgan/image_quality_assessment.py", line 416, in forward
psnr_metrics = _psnr_torch(raw_tensor, dst_tensor, self.crop_border, self.only_test_y_channel)
File "/root/autodl-tmp/srgan/image_quality_assessment.py", line 376, in _psnr_torch
_check_tensor_shape(raw_tensor, dst_tensor)
File "/root/autodl-tmp/srgan/image_quality_assessment.py", line 357, in _check_tensor_shape
assert raw_tensor.shape == dst_tensor.shape, \
AssertionError: Supplied images have different sizes torch.Size([1, 3, 504, 504]) and torch.Size([1, 3, 288, 288])