Introduce sample-centric keypoint transforms #1492
Merged
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
BloodAxe
requested review from
shaydeci,
ofrimasad and
Louis-Dupont
as code owners
Louis-Dupont
reviewed
Oct 3, 2023
src/super_gradients/training/transforms/keypoints/abstract_keypoints_transform.py
Outdated
Show resolved
Hide resolved
src/super_gradients/training/transforms/keypoints/keypoints_compose.py
Outdated
Show resolved
Hide resolved
src/super_gradients/training/transforms/keypoints/keypoints_compose.py
Outdated
Show resolved
Hide resolved
src/super_gradients/training/transforms/keypoints/keypoints_compose.py
Outdated
Show resolved
Hide resolved
src/super_gradients/training/transforms/keypoints/keypoints_image_normalize.py
Show resolved
Hide resolved
src/super_gradients/training/transforms/keypoints/keypoints_random_affine.py
Outdated
Show resolved
Hide resolved
src/super_gradients/training/transforms/keypoints/keypoints_random_affine.py
Outdated
Show resolved
Hide resolved
src/super_gradients/training/transforms/keypoints/keypoints_random_affine.py
Outdated
Show resolved
Hide resolved
src/super_gradients/training/transforms/keypoints/keypoints_random_horisontal_flip.py
Outdated
Show resolved
Hide resolved
src/super_gradients/training/transforms/keypoints/keypoints_rescale.py
Outdated
Show resolved
Hide resolved
shaydeci
suggested changes
Oct 3, 2023
src/super_gradients/recipes/dataset_params/coco_pose_estimation_dataset_params.yaml
Outdated
Show resolved
Hide resolved
src/super_gradients/training/transforms/keypoints/keypoints_image_standardize.py
Outdated
Show resolved
Hide resolved
src/super_gradients/training/transforms/keypoints/keypoints_mixup.py
Outdated
Show resolved
Hide resolved
src/super_gradients/training/transforms/keypoints/keypoints_mosaic.py
Outdated
Show resolved
Hide resolved
src/super_gradients/training/transforms/keypoints/keypoints_mosaic.py
Outdated
Show resolved
Hide resolved
…lease' into feature/SG-1060-yolo-nas-pose-release
# Conflicts: # src/super_gradients/recipes/dataset_params/coco_pose_estimation_dataset_params.yaml
…1506) * Cherry pick changes to post-prediction, visualization and metric * Remove unwanted references to new datasets * Remove YoloNASPoseCollateFN * Fixed unit test * Improve clarify of bbox format by giving it more explicit name and added a bunch of docstrings * Improve variable names
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.
What this PR does:
PoseEstimationSamplethat holds all information about a single dataset samplePoseEstimationSampleas well as existing API that pass a tuple (image,mask,boxes,...)paths are still working fine.
New transforms:
Sanity checks:
We can merge this PR as is to master or we can 'fake approve' this PR (If everyone is good with the concept) and I will keep adding yolo-nas pose stuff on top of it (Through PR to this branch)