Should tanh_out and sigm_out in residual_block share the same convolutional output about wavenet HOT 4 CLOSED

Also, this line https://github.com/basveeling/wavenet/blob/master/wavenet.py#L236 looks useless.

from wavenet.

read paper more carefully and compare to the other implementations before your open an issue

from wavenet.

Which message are you replying to? The paper says it uses a new kind of activation function. Using two convolutional layers and combining them afterwards is not equivalent to that. I will read the paper again and come back later (on a holiday).

from wavenet.

Hi Dalei,

If you believe that the gated activation is implemented incorrectly, please feel free to submit a pull request with some evidence that your proposed implementation is more faithful to the paper.

Thanks,

Bas

from wavenet.