Skip to content
This repository has been archived by the owner on Oct 31, 2023. It is now read-only.

Question about the implemented of SpectralConvergengeLoss #150

Open
mcw519 opened this issue Apr 6, 2023 · 0 comments
Open

Question about the implemented of SpectralConvergengeLoss #150

mcw519 opened this issue Apr 6, 2023 · 0 comments

Comments

@mcw519
Copy link

mcw519 commented Apr 6, 2023

Does the norm calculation include the batch dimension is reasonable, or should be calculated for each utterance then sum/mean the losses across batch dimension?

denoiser/denoiser/stft_loss.py

Line 51 in f98f16c

return torch.norm(y_mag - x_mag, p="fro") / torch.norm(y_mag, p="fro")

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@mcw519