keypoint support for map#3348
Open
SebastianJanampa wants to merge 2 commits intoLightning-AI:masterfrom
Open
Conversation
SebastianJanampa
requested review from
SkafteNicki,
justusschock and
lantiga
as code owners
for more information, see https://pre-commit.ci
Author
|
The unittests checks fail because the repo does not have the JSON files I use to test the mAP for keypoints |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do?
Fixes #1361
Before submitting
PR review
This PR adds support for the human pose keypoint estimation metric (mAP). The only problem I found is that it will only work for COCO keypoints (17 keypoints) because tor torchmetrics relies on pycocotools. A solution could be to migrate or incorporate xtcocotools to support other keypoint datasets (e.g., CrowdPose).
I added additional tests to verify that the keypoint estimation works correctly, though I am not sure these tests are sufficient (this is my first PR, so I apologize if I am missing anything). Also, I created two JSON files, but I don't know how to upload them since torchmetrics downloads all the testing JSON files from an AWS account.
Did you have fun?
Yeap 😃
Make sure you had fun coding 🙃
📚 Documentation preview 📚: https://torchmetrics--3348.org.readthedocs.build/en/3348/