Sort by confidence and remove excess boxes without explicit if

[developer0hye]

It is related to #10502.
Signed-off-by: Yonghye Kwon developer.0hye@gmail.com

🛠️ PR Summary

_{Made with ❤️ by Ultralytics Actions}

🌟 Summary

Optimization of Non-Max Suppression (NMS) in YOLOv5 object detection.

📊 Key Changes

• Simplified the sorting of detection boxes based on confidence score.
• Removed excess boxes beyond a maximum threshold (max_nms) in one line of code.

🎯 Purpose & Impact

• Purpose: To streamline the box sorting process within NMS and improve code readability.
• Impact: This change can potentially speed up the NMS step in object detection, leading to faster inference times. It also makes the codebase easier to understand and maintain for developers. Users can expect slightly quicker results without compromising accuracy when detecting objects in images. 🚀

[glenn-jocher]

@developer0hye PR is merged. Thank you for your contributions to YOLOv5 🚀 and Vision AI ⭐