pixel-rnn-tensorflow
pixel-rnn-tensorflow copied to clipboard
Shouldn't we use tanh instead of sigmoid with this implementation?
https://github.com/carpedm20/pixel-rnn-tensorflow/blob/1d98c28c62ed9c9584a342b63e4612dd9e5ae688/ops.py#L315
I have found at L315 that we have used the sigmoid function either to calculate the new inputs g, is that possible? Shouldn't we use the tanh instead?
Thank you