TypeError: linear(): argument 'input' (position 1) must be Tensor, not tuple

[anandhiray]

When I run infer.py in fgvc, I get this error.

File "infer.py", line 100, in visualize attention_maps = net.visualize(X) File "/kaggle/working/CAL/fgvc/models/cal.py", line 180, in visualize p = self.fc(feature_matrix 100) File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl return forward_call(input, **kwargs) File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/linear.py", line 96, in forward return F.linear(input, self.weight, self.bias) File "/opt/conda/lib/python3.7/site-packages/torch/nn/functional.py", line 1847, in linear return torch._C._nn.linear(input, weight, bias) TypeError: linear(): argument 'input' (position 1) must be Tensor, not tuple

Can you help me fix this? Thank you!

[raoyongming]

Hi @anandhiray, thanks for your interest in our work. I have fixed the typo in our visualization code. There should be two returned variables for the self.bap module here.

[anandhiray]

Thanks a lot for your immediate reply. But now it gives this error.
main() File "infer.py", line 75, in main visualize(data_loader=validate_loader, net=net) File "infer.py", line 101, in visualize attention_maps = torch.max(attention_maps, dim=1, keepdim=True)[0] TypeError: max() received an invalid combination of arguments - got (tuple, keepdim=bool, dim=int), but expected one of:

• (Tensor input)
• (Tensor input, Tensor other, *, Tensor out)
• (Tensor input, int dim, bool keepdim, *, tuple of Tensors out)
• (Tensor input, name dim, bool keepdim, *, tuple of Tensors out)

Is it because of any version issue?

Thank you very much for your immediate response.

[raoyongming]

There are also two returned variables from net.visualize(X). I have fixed the bug and updated the code.

[anandhiray]

It is working great now! Thank you for your help, without which I would not have been able to do this!