8000 size mismatch · Issue #111 · yxlllc/DDSP-SVC · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

size mismatch #111

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.

Sign up for GitHub

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

Jump to bottom
Open
curious-ai-developer opened this issue Feb 12, 2024 · 4 comments
Open

size mismatch #111

curious-ai-developer opened this issue Feb 12, 2024 · 4 comments

Comments

@curious-ai-developer
Copy link

Hi,

I tried training model 5 but got an error for training. Error is:
size mismatch for ddsp_model.window: copying a param with shape torch.size([1024]) from checkpoint, the shape in current model is torch.size([2048])
size mismatch for ddsp_model.unit2ctrl.denseout
Then I ran for model 4 and it works.
What is the problem with model 5?
What are the benefits of model 5?
@yxlllc
Copy link
Owner
yxlllc commented Feb 13, 2024

Check whether the configuration file or pre-trained model used is correct

@Y-Kitaro
Copy link

I got the same error . You start training without using ‘model0.pt’ or try using this 'model0.pt'
https://github.com/yxlllc/DDSP-SVC/releases/tag/5.0

@curious-ai-developer
Copy link
Author

I used pre trained model for training. I still have the problem as Y-Kitaro. Should I change configuration file? Which yaml? How?

@Y-Kitaro
Copy link

I started learning without changing the settings in 'config/diffusion-fast.yaml'.
I think your win_length setting or pre-trained model is wrong.
V5.0 'model_0.pt' has the sa 5A6B me file name, but the contents are different.

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

No branches or pull requests
3 participants
@yxlllc @Y-Kitaro @curious-ai-developer
0