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

Backend FFT functions are not differentiable #31

Open
phernst opened this issue Nov 22, 2021 · 1 comment
Open

Backend FFT functions are not differentiable #31

phernst opened this issue Nov 22, 2021 · 1 comment

Comments

@phernst
Copy link

phernst commented Nov 22, 2021

The functions cuda_backend.rfft and cuda_backend.irfft don't implement a backward pass, so their gradient can't be computed. This makes BaseRadon.filter_sinogram unusable for network trainings.

Is there a reason why you don't use torch.fft.rfft and torch.fft.irfft?

@phernst
Copy link
Author

phernst commented Nov 22, 2021

Oh, this is probably related to #22

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

1 participant