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 2020/08/19 16:48:49 UTC

[GitHub] [incubator-mxnet] StevenJokes commented on issue #18931: [Development] MXNet 2.0 Update

StevenJokes commented on issue #18931:
URL: https://github.com/apache/incubator-mxnet/issues/18931#issuecomment-676540034


   I'm a newbie. I'm learning d2l [DCGAN](http://d2l.ai/chapter_generative-adversarial-networks/dcgan.html).
   And I try to translate to pytorch. Then I found it isn't same with tutorial in pytorch.org.
   Which one is right?
   My issue is here: [Maybe our DCGAN have extra nn.BatchNorm2d(ndf)?](https://github.com/d2l-ai/d2l-en/issues/1381)
   Still not finish my work: [PR](https://github.com/d2l-ai/d2l-en/pull/1309)
   
   ---
   BTW, I found `.add` in mxnet is easy to use than `.add_module` in pytorch, which must name a new layer.
   But I have another problem: After we added a layer, it will exist next time?  
   If then, how to delete or change a layer? Or, more often we just create a new structure?


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