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 2019/12/27 08:12:17 UTC

[GitHub] [incubator-mxnet] zixuanweeei commented on issue #17184: Weight tied cannot be used with weight sharing

zixuanweeei commented on issue #17184: Weight tied cannot be used with weight sharing
URL: https://github.com/apache/incubator-mxnet/issues/17184#issuecomment-569217439
 
 
   According to the class `AWDRNN(train.AWDRNN)`, `tie_weights` boolean value means that *Whether to tie the weight matrices of output dense layer and input embedding layer*. So there is no bias param in a embeddings table, right? And output dense should be defined with `no_bias=True`.  Does it make sense?

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to 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