@fchollet Congratulations, and thanks for all your hard work over the years.
Keras 1.0 is now released. Announcement: http://blog.keras.io/introducing-keras-10.html … Code: https://github.com/fchollet/keras Get started: http://keras.io/getting-started/functional-api-guide/ …
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
@fchollet Great work!Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
@fchollet Great job! Unfortunately I still did not have time to work on the scan-based RNNs for TensorFlow. -
@seaandsailor we'll including it later! In any case, it's important work. - Show replies
New conversation -
-
-
@fchollet Thanks this is amazing!Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
@fchollet Awesome! Great work! Can you post / talk a bit about the 25% faster RNNs? Does it work for stateful RNNs too? -
@EdwardRaffML RNNs now have a `unroll=True/False` argument which will unroll the network in Theano. Only viable for short sequences though. - Show replies
New conversation -
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
.
@fchollet Wohoooo! Congrats Francois! This is awesome.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.