danielroich / id-disentanglement-pytorch Goto Github PK

In Inception.py in line 21 there is an error which says "'Resize' object has no attribute 'max_size'", How to resolve this? @danielroich

There is some error.
File "/data0/cdx/ID-disentanglement-pytorch/Training/train_script.py", line 159, in
attr_vec = torch.squeeze(attr_encoder(attr_images))
File "/home/amax/anaconda3/envs/cdx/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/data0/cdx/ID-disentanglement-pytorch/Models/Encoders/Inception.py", line 29, in forward
return self.model(resized_data * 255)
File "/home/amax/anaconda3/envs/cdx/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/home/amax/anaconda3/envs/cdx/lib/python3.8/site-packages/torch/nn/modules/container.py", line 141, in forward
input = module(input)
File "/home/amax/anaconda3/envs/cdx/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/home/amax/anaconda3/envs/cdx/lib/python3.8/site-packages/torchvision/models/inception.py", line 316, in forward
outputs = self._forward(x)
File "/home/amax/anaconda3/envs/cdx/lib/python3.8/site-packages/torchvision/models/inception.py", line 303, in _forward
branch3x3 = self.branch3x3_1(x)
File "/home/amax/anaconda3/envs/cdx/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/home/amax/anaconda3/envs/cdx/lib/python3.8/site-packages/torchvision/models/inception.py", line 405, in forward
x = self.conv(x)
File "/home/amax/anaconda3/envs/cdx/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/home/amax/anaconda3/envs/cdx/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 447, in forward
return self._conv_forward(input, self.weight, self.bias)
File "/home/amax/anaconda3/envs/cdx/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 443, in _conv_forward
return F.conv2d(input, weight, bias, self.stride,
RuntimeError: Expected 3D (unbatched) or 4D (batched) input to conv2d, but got input of size: [8, 1000]

in this train_script.py,
when running,the console shows:
"
File "D:/PycharmProjects/ID-disentanglement-Pytorch-master/Training/train_script.py", line 116, in
data = next(iter(test_loader))
"

how to do it?please.

May I ask if the codes of evaluation are provided including FID, identity, pose and attribute as shown in figure 1?