Sasha Goodman

Where do you think it be implemented at this time? This codebase appears organized around keras layers, but for something like an RNN the dropout mask is repeated across layers...

Thanks for this awesome work! Regarding optimization, one potential issue is browser compatibility as the various browsers get on board over the coming months or (gasp!) years. Currently WebGL2 is...

Well I guess there is a 'gpu: false' setting . Didn't see that before :)

The script uses at maximum 12 mb [screenshot_robo](https://cloud.githubusercontent.com/assets/4193801/22088884/248c4bec-dd9c-11e6-9316-42585c0bfbf5.png) Prediction times are pretty snappy given this quite large network with millions of parameters. About 60 ms.

I've gotten this error also (Keras (1.1.2),Theano (0.8.2), tensorflow (0.10.0),numpy (1.11.2)). Tried both the Theano and Tensorflow model.fit calls. > Traceback (most recent call last): > File "sentiment_lstm_regression.py", line 84,...

Will do! Thank you for the feedback, it's more helpful than you think. I have a follow up question related to this and would appreciate being pointed in the right...

I'm also curious if mxnet people are in the loop.

thanks! I mentioned your implementation here: https://github.com/dmlc/mxnet/issues/3930