[GitHub] szha commented on issue #11385: About loss

[GitBox <gi...@apache.org>]

szha commented on issue #11385: About loss
URL: https://github.com/apache/incubator-mxnet/issues/11385#issuecomment-400006788
 
 
   @yyl199655 if you use gluon, you can just write whatever penalty term you want using ndarray interface inside training loop. Only forward computation is needed, as long as the function is differentiable

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