Improve resizing by basing it on input image #37
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
Improves faceboxes test scores on major benchmarks PASCAL: 97.05% -> 97.28% AFW: 98.55% -> 98.83%
This was referenced Jul 25, 2019
Closed
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Outdated suggestions cannot be applied.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.
Improves faceboxes test scores on major benchmarks
PASCAL: 97.05% -> 97.28%
AFW: 98.55% -> 98.83%
I really didn't like these magic numbers for each dataset, so instead I targeted a min face size of ~15-20 pixels between eyes as it is trained which is met by 800 pixels image. This corresponds to an optimal score in the benchmarks, with least resizing.