add option to save metrics to csv

[geezacoleman]

This is just a small change in val.py to make saving/downstream analysis of metrics easier. It doesn't appear to be covered elsewhere from what I've checked. I was comparing quite a few different models with changes in parameters and needed an automated way of comparing performance.

It includes a flag --save-metrics to save all metrics produced in val.py to a csv. Somewhat related to #5341

Signed-off-by: Guy Coleman 51358498+geezacoleman@users.noreply.github.com

🛠️ PR Summary

_{Made with ❤️ by Ultralytics Actions}

🌟 Summary

Improvement in model evaluation with CSV metrics export.

📊 Key Changes

• Importing of the csv module in val.py.
• Addition of save_metrics argument to enable saving of evaluation metrics in CSV format.
• Creation of code blocks that compile evaluation metrics into a CSV-friendly list.
• Writing the compiled metrics into a CSV file at the specified output path (metrics.csv).

🎯 Purpose & Impact

• Purpose: To allow users to save detailed model evaluation metrics such as precision (P), recall (R), mean Average Precision at 0.5 IoU (mAP50), and mAP at 0.5:0.95 IoU (mAP50-95) into a CSV file for easier analysis and reporting.
• Impact: Users can now easily compare metrics across different models and share results without needing to parse console logs or custom scripts. This feature enhances the transparency and accessibility of model evaluation for both casual users and ML researchers or engineers. 📈🔍

[github-actions]

👋 Hello @geezacoleman, 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

[github-actions]

This pull request has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions YOLOv5 🚀 and Vision AI ⭐.

[github-actions]

👋 Hello there! We wanted to let you know that we've decided to close this pull request due to inactivity. We appreciate the effort you put into contributing to our project, but unfortunately, not all contributions are suitable or aligned with our product roadmap.

We hope you understand our decision, and please don't let it discourage you from contributing to open source projects in the future. We value all of our community members and their contributions, and we encourage you to keep exploring new projects and ways to get involved.

For additional resources and information, please see the links below:

• Docs: https://docs.ultralytics.com
• HUB: https://hub.ultralytics.com
• Community: https://community.ultralytics.com

Thank you for your contributions to YOLO 🚀 and Vision AI ⭐