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 2018/03/28 20:39:30 UTC

[GitHub] ArmageddonKnight opened a new issue #10304: Dropout has no effect in 1-Layer FusedRNNCell

ArmageddonKnight opened a new issue #10304: Dropout has no effect in 1-Layer FusedRNNCell
URL: https://github.com/apache/incubator-mxnet/issues/10304
 
 
   https://github.com/apache/incubator-mxnet/blob/e5f6238a2b213e70ba0ca7acc5bcf5c643502561/example/rnn/word_lm/model.py#L34
   
   I saw that dropout was passed as an argument to `FusedRNNCell` in the benchmark provided. However, I personally doubt that such an argument has any effect on the training results, and the reason is because dropout will **NOT** be applied when the RNN only has one layer. 

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