Skip to content

onnx vs weight norm #148

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

Open
Selectorrr opened this issue Mar 24, 2025 · 2 comments
Open

onnx vs weight norm #148

Selectorrr opened this issue Mar 24, 2025 · 2 comments

Comments

@Selectorrr
Copy link

Hi. @Plachtaa Thank you so much for sharing your work.
I'm trying to export this model to ONNX, but I ran into a problem that Wavenet uses weight norm in its calculations, which increases the graph complexity and model weight depending on the number of diffusion steps. Is there any way around this issue?

@Selectorrr
Copy link
Author

looks like folding weights from weight norm to Conv1d might help, but it will take time, I will check

@littlebeanhp
Copy link

looks like folding weights from weight norm to Conv1d might help, but it will take time, I will check

Have you succeeded exporting this model ? I have the same question :)

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