[zerostar07]

While we are at it, which framework is the easiest to tweak at the low-level, e.g. create modified LSTMs etc ?

[laingc]

Pytorch, by a mile.

If I had to summarise the frameworks in a few words, they would be: Keras for speed, Tensorflow for production, Pytorch for research.

[mlthoughts2018]

I would say keras or mxnet for speed and production. PyTorch for research. By this point there are hardly any cases when it’s worth it to descend to lower TensorFlow levels.

[pdyck]

Keras only offers standard layers but you can implement your own LSTM layer and use it with Keras. This way you can take advantage of all the other features