Agreed, good work is never over. Plus everything is iterative in nature, including improvements. Francois, the community got your back. Always happy to help!
Glad to hear :) We're now working hard on extensions ranging from hyperparameter tuning, autoML, preprocessing layers, easier distribution, easier deployment, and more. Work is never over.https://twitter.com/A_K_Nain/status/1144615884855500800 …
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thanks François for your great contribution in
#deeplearning domain. Do you have any idea of supporting#Tf2 in#Keras. I've know that tf.keras may be better option and I'm utilizing it in my projects and packages, but some of other package is only written in pure Keras. -
Multi-backend Keras will support TF2, in fact you can already check out the branch `tf-2` which does just that. However if you want to use TF2 features I would strongly recommend switching to tf.keras.
- Show replies
New conversation -
-
-
Keras is awesome
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Great!! do tuner and autokeras run experiments in parallel? any integration with kubeflow/katib to distribute across nodes?
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.