Should I use softmax activation before crossentropy loss backward?ack

[acmilannesta]

I know nn.CrossEntropyLoss() incoporates softmax. So my model output did not add softmax layer. But when I do the loss.backward(), should I change the outputs using softmax like outputs = torch.softmax(outputs, dim=1).cpu().detach().numpy()?

[ptrblck]

As you said, you should not apply softmax on the outputs before passing it to nn.CrossEntropyLoss.

@acmilannesta

But when I do the loss.backward() , should I change the outputs using softmax like outputs = torch.softmax(outputs, dim=1).cpu().detach().numpy() ?

If you’ve calculated the loss using the raw logits and would now want to get the probabilities for debugging purposes etc., then you could of course apply the softmax afterwards.