Skip to content
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

Integrate fft-conv-pytorch #9

Open
mpariente opened this issue Jan 20, 2021 · 2 comments
Open

Integrate fft-conv-pytorch #9

mpariente opened this issue Jan 20, 2021 · 2 comments

Comments

@mpariente
Copy link
Contributor

Might be much faster (and more precise) for longer FFT kernels.

See here.

@popcornell
Copy link

I see there is also a rather convenient FFTConv layer which is handy IMO. Apart from this, is it the same than torchaudiomentation convolve ?
https://github.com/asteroid-team/torch-audiomentations/blob/71c27d8206a0850640525b97a7241eb4625d755b/torch_audiomentations/utils/convolution.py#L40

@mpariente
Copy link
Contributor Author

We'd have to check both implementations more carefully. There is also an implementation in julius I believe so we'll have to choose from those options.

Note, convolve in torch-audiomentations comes from pyro, I opened an issue there to link to the original code.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants