You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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?
The text was updated successfully, but these errors were encountered:
The functions
cuda_backend.rfft
andcuda_backend.irfft
don't implement a backward pass, so their gradient can't be computed. This makesBaseRadon.filter_sinogram
unusable for network trainings.Is there a reason why you don't use
torch.fft.rfft
andtorch.fft.irfft
?The text was updated successfully, but these errors were encountered: