Discussions>softmax_cross_entropy_with_logits issue with keras>

softmax_cross_entropy_with_logits issue with keras

I'm using Keras with TensorFlow backend and using cross-entropy as the loss function. I saw that TensorFlow requires pre softmax as an input for the loss, but I put the output of the softmax in Keras.
What is the right way to use it?

2 votesNN215.00
1 Answers
JW326.00
2

I usually create the inverse function of the output, so I can design my network with softmax of sigmoid but will use the inverse version of it when I need to pass them to the loss function.

In general, cross-entropy with logits works better than with softmax output. Also, the mixed-precision regime almost always requires you to use loss with the logits version.

Reply
Couldn't find what you were looking for?and we will find an expert to answer.
How helpful was this page?