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?

-- 
You are receiving this because you authored the thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/incubator-mxnet/issues/18931#issuecomment-676540034

Reply via email to