Closed lidalei closed 5 years ago
Also, this line https://github.com/basveeling/wavenet/blob/master/wavenet.py#L236 looks useless.
read paper more carefully and compare to the other implementations before your open an issue
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).
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
Shouldn't tanh_out in https://github.com/basveeling/wavenet/blob/master/wavenet.py#L226 and sigm_out in https://github.com/basveeling/wavenet/blob/master/wavenet.py#L230 share the same convolutional output instead of two independent convolutional outputs?