Allow multi_label option for NMS with PyTorch Hub

[jeanbmar]

🛠️ PR Summary

_{Made with ❤️ by Ultralytics Actions}

🌟 Summary

Enhanced Non-Maximum Suppression (NMS) with multi-label support in YOLOv5.

📊 Key Changes

• Added a new parameter multi_label to the AutoShape class.
• Updated the forward method to use the new multi_label parameter during NMS.

🎯 Purpose & Impact

• 🎯 Purpose: To allow each detected bounding box to have multiple class labels assigned during the NMS process, enhancing the model's ability to recognize multiple objects within the same region.
• 🔍 Impact: Users will benefit from more versatile object detection, particularly in images where objects of different categories overlap. This update may also improve the model's overall accuracy and performance in complex scenarios.

[github-actions]

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

• ✅ Verify your PR is up-to-date with origin/master. If your PR is behind origin/master an automatic GitHub actions rebase may be attempted by including the /rebase command in a comment body, or by running the following code, replacing 'feature' with the name of your local branch:

git remote add upstream https://github.com/ultralytics/yolov5.git
git fetch upstream
git checkout feature  # <----- replace 'feature' with local branch name
git rebase upstream/master
git push -u origin -f

• ✅ Verify all 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

[jeanbmar]

Thank you for the quick review and merge!