You are viewing a plain text version of this content. The canonical link for it is here.

Posted to commits@mxnet.apache.org by GitBox <gi...@apache.org> on 2017/11/23 12:23:30 UTC

[GitHub] beeva-enriqueotero commented on issue #6179: SoftmaxOutput - how to get probabilities?

beeva-enriqueotero commented on issue #6179: SoftmaxOutput - how to get probabilities?
URL: https://github.com/apache/incubator-mxnet/issues/6179#issuecomment-346604827
 
 
   In order to apply typical crossentropy function as eval_metric you need to access to these probabilities. Otherwise training loss and validation loss will represent different metrics when using SoftmaxOutput !

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services