Skip to content
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

feature: add scripts/aux_swa.py #252

Merged
merged 2 commits into from
Jan 31, 2022
Merged

Conversation

YuriCat
Copy link
Contributor

@YuriCat YuriCat commented Jan 25, 2022

Should we change the script name?

ed, length = int(sys.argv[1]), int(sys.argv[2])
step = 1
if len(sys.argv) >= 4:
step
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

fixed

@ikki407
Copy link
Member

ikki407 commented Jan 26, 2022

I like just swa.py or stochastic_weighted_averaging.py.

@ikki407
Copy link
Member

ikki407 commented Jan 26, 2022

Do we need to update the parameters of batch normalization after weight parameter updates? If not, I think, the SWA model is saved with the BN parameters of the first loaded model, since the swa_model.update_parameters() doesn't update the BN params, right?

@ikki407 ikki407 merged commit 0123390 into DeNA:develop Jan 31, 2022
@YuriCat YuriCat deleted the feature/add_swa_script branch February 11, 2022 17:56
This pull request was closed.
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

Successfully merging this pull request may close these issues.

2 participants