Allow multiple-model serving from Flask REST API

[mpromonet]

Hi,

This is a small modification to allow to serve multiple models with the flask rest api.

Best Regards,
Michel.

🛠️ PR Summary

_{Made with ❤️ by Ultralytics Actions}

🌟 Summary

Enhancement of the YOLOv5 Flask REST API to support multiple models simultaneously.

📊 Key Changes

• The REST API now allows specifying which model to use in the request URL.
• The server can load multiple models at startup based on command line arguments.
• The prediction route (predict) dynamically selects the model based on the URL.
• The hardcoded single model setup has been replaced with a flexible models dictionary.

🎯 Purpose & Impact

• Flexibility: Users can now interact with different YOLOv5 models in a single API instance, which is useful for comparing results or if different use cases require different models.
• Convenience: By allowing multiple models, users can avoid running separate instances for each model, saving resources and simplifying the interaction process.
• Customizability: The update adds the ability to specify the desired models at server startup, giving users control over which models are loaded, and adjusting for performance or resource allocation as needed.

[github-actions]

👋 Hello @mpromonet, 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

[mpromonet]

Hi @glenn-jocher ,

Thanks for cleanup, better your way.

Best Regards,
Michel.

[glenn-jocher]

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

[glenn-jocher]

@mpromonet yes by passing skip_validation=True to torch.hub.load() we bypass the need for fix #7210