-
Notifications
You must be signed in to change notification settings - Fork 965
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
Improve averaging checkpoints and creating model #2135
Conversation
Job PR-2135-1167dd7 is done. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM. Thanks for fixing this. We need to rerun our experiments with larger backbones since the average state becomes float64. @Raldir
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thank you for the fix, LGTM.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The fix and refactor look great! Thanks!
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM, thanks!
create_model
intocreate_model
andcreate_fusion_model
to improve modularization.create_model
is only in charge of creating a single model, which will be used in creating models in the siamese matcher.By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.