Add --half support for OpenVINO exports

[djmmoss]

This PR enables exporting OpenVINO models with the FP16 data type.

Size and Accuracy comparison between OpenVINO FP32 and FP16 versions of yolov5n6:

🛠️ PR Summary

_{Made with ❤️ by Ultralytics Actions}

🌟 Summary

Enhancements to model exporting for OpenVINO with FP16 support.

📊 Key Changes

• Added a half parameter to export_openvino function to allow exporting models in FP16 precision.
• Included --data_type argument in the OpenVINO Model Optimizer command to support FP16 or FP32 during export.
• Adjusted assertion to allow --half usage with OpenVINO (xml) export.

🎯 Purpose & Impact

• 🚀 Purpose: To enable YOLOv5 models to be exported for OpenVINO in a more memory-efficient FP16 format, when compatible hardware is available.
• 💻 Impact for Users: Users can now reduce the computational requirements of their YOLOv5 models when deploying to hardware supporting FP16, potentially improving performance. This change is particularly beneficial for edge computing scenarios where resources are limited.

[github-actions]

👋 Hello @djmmoss, 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 upstream/master. If your PR is behind upstream/master an automatic GitHub Actions merge may be attempted by writing /rebase in a new comment, 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 merge 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

[glenn-jocher]

@djmmoss it works! Verified no accuracy loss also:

[glenn-jocher]

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