Load weights on segmentation/train.py when using --resume and --test-only flags #3285
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
datumbox
commented
Jan 24, 2021
| optimizer.load_state_dict(checkpoint['optimizer']) | ||
| lr_scheduler.load_state_dict(checkpoint['lr_scheduler']) | ||
| args.start_epoch = checkpoint['epoch'] + 1 | ||
| model_without_ddp.load_state_dict(checkpoint['model'], strict=not args.test_only) |
There was a problem hiding this comment.
strict=False required to avoid having to configure auxiliary classifiers
| args.start_epoch = checkpoint['epoch'] + 1 | ||
| model_without_ddp.load_state_dict(checkpoint['model'], strict=not args.test_only) | ||
| if not args.test_only: | ||
| optimizer.load_state_dict(checkpoint['optimizer']) |
There was a problem hiding this comment.
We avoid loading the weights of other objects if in test-only mode. Similar to the above, this is done to avoid having to handle auxiliary classifiers.
fmassa
approved these changes
Jan 25, 2021
facebook-github-bot
pushed a commit
that referenced
this pull request
Feb 1, 2021
Summary: Co-authored-by: Francisco Massa <fvsmassa@gmail.com> Reviewed By: datumbox Differential Revision: D26156373 fbshipit-source-id: 83f22c90477ca2da8db176d2455a70ca302d17d1
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
A good way to verify the accuracy of a specific epoch checkpoint on the evaluation dataset is to execute:
This is supported on both the classification and detection reference scripts but not on segmentation. More specifically on segmentation, the specified weights are not loaded and thus we report the accuracy of randomly initialized weights. This PR fixes this.