Deploy function seems really good, also the fact that it doesn't add any overhead
Here's a new open-source package for hyperparameter search for Keras models: https://github.com/autonomio/talos (no affiliation with the authors, I just thought it was cool)
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Any advantages with respect to Hyperas?
-
Thanks for sharing, by the way!
End of conversation
New conversation -
-
-
That's pretty much the same API as hyperopt, but it only works with Keras models and supports fewer optimization algorithms. still good to have more tooling, I guess.
-
Yep I’m using hyperopt with fasttext
#python but I like the idea to keep this Keras tooling as simpler as possibile. - Show replies
New conversation -
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
English translation?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Always good to read specific comments fr experienced users trying out new tools like this, thanks!
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Seems to lack generator capability, which is a common issue for those of us using git hub repos for image based deep learning : fit(x,y) works but fit_generator foes not. I wish I understood enough to fix. I do not.
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.