AMP check improvements backup YOLOv5n pretrained #7959
Merged
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Outdated suggestions cannot be applied.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.
More robust and faster, removes tolerance parameter.
EDIT: will not work for non-pretrained models...
π οΈ PR Summary
Made with β€οΈ by Ultralytics Actions
π Summary
Enhanced PyTorch Automatic Mixed Precision (AMP) testing for accuracy and compatibility.
π Key Changes
amp_allclose
for more robust comparison.DetectMultiBackend
into the AMP checking process to support more model types.π― Purpose & Impact
DetectMultiBackend
during AMP validation expands compatibility, which benefits users who work with different types of models, enhancing the utility of YOLOv5 across a wider range of environments.