I see this as a convergence in DL high level API (for the better). Hope that ONNX can do the same for the serialized models!
The folks at AWS have developed a MXNet backend for Keras, with extensive feature coverage and great performance. Hopefully we can merge it into core Keras in the future (some technical blockers there). For now it exists as a fork:https://github.com/awslabs/keras-apache-mxnet …
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Build a Keras for PyTorch!
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
We need build the backend for paddlepaddle now!
@BaiduResearchThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Good news.. Keras has been getting more popular..
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.