About Outputs

[longlongvip]

I read your code carefully. In train.py, I'm not sure what outputs means. Is it the output of the model FC layer or the Softmax layer?
Because if it's the output of the FC layer, then it's contradictory to _ predicted = outputs.max (1), and if it's the output of the Softmax layer, it's contradictory to loss = criterion (outputs, y). What's going on?
Please take the precious time to help me, because I urgently need to get the correct conclusion and thank you for your help.

[yu4u]

The output of the model is logits (the output of the FC layer), not that of softmax.

Please refer to https://pytorch.org/docs/stable/torch.html#torch.max

outputs.max(1) is the same as torch.max(outputs, 1).