Why warped_cloth and it's mask missing after 294000.
And there is also an another problem that I must change the train code.↓
Traceback (most recent call last):
File "train_PBAFN_stage1.py", line 116, in
loss_vgg = criterionVGG(x_all[num], cur_person_clothes.cuda())
File "C:\Users\Leo\anaconda3\envs\PMC2D\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, kwargs)
File "C:\Users\Leo\Desktop\PF-AFN\PF-AFN_train\models\networks.py", line 164, in forward
x_vgg, y_vgg = self.vgg(x), self.vgg(y)
File "C:\Users\Leo\anaconda3\envs\PMC2D\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, *kwargs)
File "C:\Users\Leo\Desktop\PF-AFN\PF-AFN_train\models\networks.py", line 150, in forward
h_relu5 = self.slice5(h_relu4)
File "C:\Users\Leo\anaconda3\envs\PMC2D\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(input, kwargs)
File "C:\Users\Leo\anaconda3\envs\PMC2D\lib\site-packages\torch\nn\modules\container.py", line 204, in forward
input = module(input)
File "C:\Users\Leo\anaconda3\envs\PMC2D\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, *kwargs)
File "C:\Users\Leo\anaconda3\envs\PMC2D\lib\site-packages\torch\nn\modules\pooling.py", line 166, in forward
return F.max_pool2d(input, self.kernel_size, self.stride,
File "C:\Users\Leo\anaconda3\envs\PMC2D\lib\site-packages\torch_jit_internal.py", line 485, in fn
return if_false(args, **kwargs)
File "C:\Users\Leo\anaconda3\envs\PMC2D\lib\site-packages\torch\nn\functional.py", line 782, in _max_pool2d
return torch.max_pool2d(input, kernel_size, stride, padding, dilation, ceil_mode)
RuntimeError: Given input size: (512x2x1). Calculated output size: (512x1x0). Output size is too small
Why warped_cloth and it's mask missing after 294000.
And there is also an another problem that I must change the train code.↓ Traceback (most recent call last): File "train_PBAFN_stage1.py", line 116, in
loss_vgg = criterionVGG(x_all[num], cur_person_clothes.cuda())
File "C:\Users\Leo\anaconda3\envs\PMC2D\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, kwargs)
File "C:\Users\Leo\Desktop\PF-AFN\PF-AFN_train\models\networks.py", line 164, in forward
x_vgg, y_vgg = self.vgg(x), self.vgg(y)
File "C:\Users\Leo\anaconda3\envs\PMC2D\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, *kwargs)
File "C:\Users\Leo\Desktop\PF-AFN\PF-AFN_train\models\networks.py", line 150, in forward
h_relu5 = self.slice5(h_relu4)
File "C:\Users\Leo\anaconda3\envs\PMC2D\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(input, kwargs)
File "C:\Users\Leo\anaconda3\envs\PMC2D\lib\site-packages\torch\nn\modules\container.py", line 204, in forward
input = module(input)
File "C:\Users\Leo\anaconda3\envs\PMC2D\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, *kwargs)
File "C:\Users\Leo\anaconda3\envs\PMC2D\lib\site-packages\torch\nn\modules\pooling.py", line 166, in forward
return F.max_pool2d(input, self.kernel_size, self.stride,
File "C:\Users\Leo\anaconda3\envs\PMC2D\lib\site-packages\torch_jit_internal.py", line 485, in fn
return if_false(args, **kwargs)
File "C:\Users\Leo\anaconda3\envs\PMC2D\lib\site-packages\torch\nn\functional.py", line 782, in _max_pool2d
return torch.max_pool2d(input, kernel_size, stride, padding, dilation, ceil_mode)
RuntimeError: Given input size: (512x2x1). Calculated output size: (512x1x0). Output size is too small