Skip to content

MAISI load_unet func misses the load of scale_factor for finetune training #1935

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
shengzhang90 opened this issue Feb 1, 2025 · 1 comment
Assignees

Comments

@shengzhang90
Copy link

Hi,

During the training with scripts/diff_model_train.py file.

Sometimes, the calculate_scale_factor func will output the result of "scale_factor=nan", could you please set and fix the "scale_factor" parameter in certain json file?

Also, for the finetune training, could you please load the "scale_factor" in load_unet func since you have save the "scale_factor" in the save_checkpoint func. Thanks a lot.

@Can-Zhao
Copy link
Contributor

Yes, that is helpful! Thank you! We will modify it

@Can-Zhao Can-Zhao marked this as a duplicate of #1960 Mar 21, 2025
@Can-Zhao Can-Zhao self-assigned this Mar 21, 2025
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