Pull Request #61 refactored by Sourcery.

Since the original Pull Request was opened as a fork in a contributor's
repository, we are unable to create a Pull Request branching from it.

To incorporate these changes, you can either:

1. Merge this Pull Request instead of the original, or

2. Ask your contributor to locally incorporate these commits and push them to
   the original Pull Request

   Incorporate changes via command line

   git fetch https://github.com/ultralytics/JSON2YOLO pull/61/head
   git merge --ff-only FETCH_HEAD
   git push

NOTE: As code is pushed to the original Pull Request, Sourcery will
re-run and update (force-push) this Pull Request with new refactorings as
necessary. If Sourcery finds no refactorings at any point, this Pull Request
will be closed automatically.

See our documentation here.

Help us improve this pull request!

🛠️ PR Summary

_{Made with ❤️ by Ultralytics Actions}

📊 Key Changes

• Added the ability to convert COCO RLE (Run Length Encoding) formatted annotations to YOLOv5/v8 segmentation format.
• Implemented functions to support keypoints in annotations, including flip indices and merging multiple contours.
• Introduced utility functions for various transformations like converting masks to polygons, RLE to polygon, and more.

🎯 Purpose & Impact

The purpose of these changes is to enhance the JSON2YOLO conversion tool to support more complex annotation formats used in computer vision datasets, especially keypoints and segmentation masks. 🌐 This will allow developers and researchers who use the YOLO format for object detection and instance segmentation tasks to work with a broader range of datasets that may contain different types of annotations. For non-experts, these features make it easier to convert datasets without needing an in-depth understanding of annotation formats, potentially accelerating their AI/ML projects.

🌟 Summary

Now you can convert COCO dataset annotations with keypoints and segmentation to the YOLO format in a snap! 🎉 This update makes your data transformation tasks much simpler and supports more types of computer vision training escapades. 🚀