That sort of makes sense. When it comes to basic Python language questions there is (not always, but) often one right way to do it. Whereas with something like TensorFlow even its creators are still groping around in the dark on a lot of questions.
-
-
-
You mean in terms of how to design their library?
-
I think they could start by writing the documentation to actually reflect what the code does. Especially those who release their weights pretending like it's open science. It's not open if nobody knows what the hell you did. Often they didn't even do what's in the preprint!
End of conversation
New conversation -
-
-
Try Keras
-
Tell me more...

-
It is a high level wrapper on tensorflow and needs minimal code to work. Released by google. It was used in multiple demos in open data science conference. See this for example:https://youtu.be/j_pJmXJwMLA
-
Thanks. I don't think that would work for me right now because of what I am doing being something very specific.
End of conversation
New conversation -
-
-
I'm just waiting for the wrapper of the wrapper of
#tensorflow which finally makes it plug/play. Or perhaps we need another wrapper to plug that into it...Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Slightly related, :-), https://xkcd.com/979/
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.
