News for hackers. Stuff that matters.
Re:MILA and the future of Theano by jbrambleDC on Friday September 29, 2017 @01:07AM (#15362841)
Thoughts on Keras on top of tensorflow?

I have not yet committed to a deep learning framework, as up until now, I was mostly either using scikit-learn or building neural networks from scratch, straight numpy (lol)

I've heard a nice thing about Keras is that it forms more of an abstraction on top of other libraries, though I could be misunderstanding.

Re:MILA and the future of Theano by ssfrr on Friday September 29, 2017 @11:00AM (#15365876)
I don't have a lot of experience, but I recently ported an RNN model from lasagne/theano to keras/tensorflow, and the latter combination was about 4x slower. Not sure whether it's keras or tensorflow causing the slowdown. The API is nice though.

I also tried to flip the keras switch to run on top of theano instead but it had issues that I didn't have time to fix, so I just stuck with the original lasagne/theano stack.