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 2018/07/05 22:50:49 UTC

[GitHub] ThomasDelteil edited a comment on issue #11385: About loss

ThomasDelteil edited a comment on issue #11385: About loss
URL: https://github.com/apache/incubator-mxnet/issues/11385#issuecomment-402874669
 
 
   @yyl199655 for more information automatic differentiation (autograd) you can follow the Gluon Crash Course, in particular this [chapter](https://gluon-crash-course.mxnet.io/autograd.html)
   
   To expand on @szha explanation, you simply need to compute your loss function within the `with autograd.record():` scope and then you can call `loss.backward()` on your loss term to automatically compute the gradient of that loss with respect to the parameters that were used to compute it.
   
   @yyl199655 if you would want to follow up, please open a thread in https://discuss.mxnet.io, Thanks
   @szha could you please close the issue? Thanks!

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