Gluon: Keras for MXnet. But why? Thestraightdope: Data Science from Scratch for DLhttps://twitter.com/AnimaAnandkumar/status/918717678721699840 …
It is much more than keras. you can easily define new architectures. you can obtain symbolic graphs. check out the tutorials.
-
-
My bad. Tutorials look very cool! So the most compelling novelty wrt pytorch is the hybridization b/w dynamic and symbolic graphs?
-
Same question here. Tutorials look amazing! Dataloaders, net definitions, arrays etc. look like pytorch. What are the specific benefits?
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.