Bug fix: test_time_pool would be set to a non-False value #244
Conversation
This file contains hidden or 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
…oling is not available
guoriyue
pushed a commit
to guoriyue/pytorch-image-models
that referenced
this pull request
May 24, 2024
Bug fix: test_time_pool would be set to a non-False value
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Outdated suggestions cannot be applied.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.
If
args.no_test_poolis False butapply_test_time_pool()returns False because test-time pooling is not available, then the local variabletest_time_poolwould not be set to True or False but to a copy of the model. In turn, this would cause thecrop_pctto be set to 1.0 further down in the code. This bug causes the results from validate.py to be slightly different from the validation score shown during training due to the different crop rectangle (unless training happened to usecrop_pct = 1.0, of course).Also possibly the cause of this issue: #235