Training is very slow about classical-piano-composer

[mehrzeller]

you can use CuDNNLSTM instead :
from keras.layers import CuDNNLSTM
instead of
from keras.layers import LSTM
don't forget to change all your LSTM statements in the source code

[kevaday]

Also, I tried using your text generating LSTM but it's also very slow on my GPU, it takes about 1 hour to do one epoch. Shouldn't my GPU be a lot faster at training?

[kevaday]

Thanks mehrzeller,
actually, it's a coincidence because I was just looking at the keras recurrent layers site and just saw that there's such thing
but thanks anyways

[victor-felicitas]

For new Keras versions specifying CuDNNLSTM is obsolete.
Training is slow because with recurrent_dropout >0 CUDNN can not be used.

From Keras documentation:
"The requirements to use the cuDNN implementation are:
activation == tanh
recurrent_activation == sigmoid
recurrent_dropout == 0
unroll is False
use_bias is True
Inputs, if use masking, are strictly right-padded.
Eager execution is enabled in the outermost context."

I suggest changing the model by adding dropout layer instead, after each LSTM layer