Let's be clear: there isn't any "TF *or* Keras" choice to make. Keras is an API, rather than a standalone framework, and it's the official high-level API of TF (via tf.keras). You should use TF *and* Keras! A powerful combination, both easy-to-use and flexible/extensible.https://twitter.com/todddavid/status/971942826148802560 …
-
-
Will there be integration w/Edward?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Someone did a poll recently where pytorch came in as slightly more popular than TF. One of the other choices was Keras

Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Is there a plan to combine Tf Eager execution and Keras?
-
Yes, absolutely
- Show replies
New conversation -
-
-
How tf.keras is different from tensorflow estimator looks like both are api
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I’m actually waiting for the new DL4J backend.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
but then, isn‘t it time to deprecate „stand-alone keras“?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I need to come up to speed on this stuff, as our optical correlator is running AI now...
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.