Apply SIoU on Bounding Box IoU metrics as default

[rodsei]

• SIoU method on metrics/bbox_iou
• applying SIoU as default metric on bounding box loss

🛠️ PR Summary

_{Made with ❤️ by Ultralytics Actions}

🌟 Summary

Incorporating SIoU (Scaled IoU) Loss into YOLOv5 prediction and bounding box calculations.

📊 Key Changes

• Replaced CIoU (Complete IoU) with SIoU (Scaled IoU) in IoU loss calculations for object detection.
• Extended the bbox_iou function to support SIoU loss computation.
• Implemented the SIoU loss mathematical formula according to the referenced research paper.

🎯 Purpose & Impact

• 🎯 Purpose: To improve the performance of YOLOv5 by integrating a more advanced IoU loss computation that could better differentiate between bounding boxes and address scale invariance.
• 🚀 Impact: Users may experience improved object detection accuracy, especially in cases where scaling differences are significant, potentially leading to more precise and scalable object detection models.

[github-actions]

👋 Hello @rodsei, thank you for submitting a YOLOv5 🚀 PR! To allow your work to be integrated as seamlessly as possible, we advise you to:

• ✅ Verify your PR is up-to-date with ultralytics/yolov5 master branch. If your PR is behind you can update your code by clicking the 'Update branch' button or by running git pull and git merge master locally.
• ✅ Verify all YOLOv5 Continuous Integration (CI) checks are passing.
• ✅ Reduce changes to the absolute minimum required for your bug fix or feature addition. "It is not daily increase but daily decrease, hack away the unessential. The closer to the source, the less wastage there is." — Bruce Lee