New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
tf.signal is differentiable #22
Comments
I think you were trying to say that it does not support a trainable basis? That's true, but it's still differentiable so you can incorporate it into a network and backpropagate through it (e.g. to add a spectral loss to model that generates time-domain waveforms -- as in Parallel WaveNet) |
Nice job on this repo and the paper by the way :). |
Thanks for pointing it out. You are right, I was talking about the trainable basis. I will fix the paper now. |
Hi Ryan, I have removed the claim that |
Thanks a lot for updating it! |
Hi. Can I ask what is meant by trainable basis? |
Hi there,
I'm the author of Tensorflow's
tf.signal
package. Your paper says thattf.signal
does not support gradients, however this is not true. All operations intf.signal
are fully differentiable and come with GPU and TPU support. Could you please update your paper on arXiv to correct this?The text was updated successfully, but these errors were encountered: