Softmax in the evaluation stage

Open saeedizadi opened this issue 8 years ago • 1 comments

Hi,

I've found that you are explicitly applying log_softmax in your criterion.py file. Isn't is necessary to explicitly apply the softmax function on the output of the network in the evaluation stage? that is, before getting the maximum index for each class?

Thanks

Jul 18 '17 01:07 saeedizadi

Hey,

yes, I think you are right. Could you test what happens if you add F.log_softmax(labels) here and make a PR out of it?

Jul 18 '17 06:07 bodokaiser