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 2017/12/12 08:04:12 UTC

[GitHub] helloworldlxb opened a new issue #9032: Why does a tanh activation layer generates values greater than 1?

helloworldlxb opened a new issue #9032: Why does a tanh activation layer generates values greater than 1?
URL: https://github.com/apache/incubator-mxnet/issues/9032
 
 
   ## Description
   I trained a CNN model with a tanh activation layer. However, when the model is applied to the validation set, the values after the activation layer may be greater than 1.
   
   ## Environment info (Required)
   MxNet 0.12.0 with Nvidia Tesla K80
   Ubuntu 14.04
   
   Package used (Python/R/Scala/Julia):
   Python
   

----------------------------------------------------------------
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