Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Squashed changes with YoloNASPose & Loss #1512

Merged

Conversation

BloodAxe
Copy link
Contributor

@BloodAxe BloodAxe commented Oct 9, 2023

This PR adds following components of YoloNASPose

  • YoloNASPose model itself
  • N/S/M/L variants and corresponding classes
  • YoloNASPose loss and collate fn
  • Exportable pose estimation interface

…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
Copy link
Contributor

@Louis-Dupont Louis-Dupont left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Here's some comments, but I'm still reviewing

Base automatically changed from feature/SG-1060-yolo-nas-pose-release to master October 11, 2023 07:16
Copy link
Contributor

@Louis-Dupont Louis-Dupont left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@BloodAxe BloodAxe merged commit 3a19f85 into master Oct 13, 2023
3 checks passed
@BloodAxe BloodAxe deleted the feature/SG-1060-yolo-nas-pose-release-add-model-and-loss branch October 13, 2023 08:31
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants