Update colab notebooks

[RizwanMunawar]

🛠️ PR Summary

_{Made with ❤️ by Ultralytics Actions}

🌟 Summary

This PR updates and improves Ultralytics YOLO segmentation notebooks, optimizing model training for various datasets with new examples and better configurations.

📊 Key Changes

• New Segmentation Models Added:
  • Introduced the yolo11n-seg.pt model, specifically trained for segmentation tasks.
• Updated Training Setup:
  • Adjusted training configurations, including extending training epochs for improved results (e.g., 10 epochs for carparts-seg and package-seg datasets).
• Enhanced Example Notebooks:
  • Added new segmentation tutorials, such as "Package Segmentation" and "Object Tracking in Zones," with accompanying datasets and visual examples.
• Improved Outputs & Exports:
  • Included better ONNX model exports with segmentation-specific configurations.
• Documentation Updates:
  • Refreshed the README and linked resources, including Colab notebooks, videos, and discussions for learning.

🎯 Purpose & Impact

• Purpose:
  • Expand the segmentation capabilities of YOLO models with specific pretrained models and datasets.
  • Provide clearer, more user-friendly examples for training and deploying segmentation models.
• Impact:
  • Makes segmentation tasks, such as car part or package segmentation, easier and more efficient to set up.
  • Boosts user engagement by offering ready-to-use resources for new computer vision use cases. 🚀
  • Enhances model performance and simplifies deployment workflows for beginners and experts alike.

[UltralyticsAssistant]

👋 Hello @RizwanMunawar, thank you for submitting an ultralytics/notebooks 🚀 PR! To ensure a seamless integration of your valuable contribution, please review the following checklist:

• ✅ Define a Purpose: Clearly describe the purpose of your change in the PR summary. You've provided a thorough summary and detailed key changes—great job! Please ensure you link any relevant issues from Ultralytics Notebooks Issues or state if this feature doesn't relate to an existing issue.
• ✅ Synchronize with Source: Confirm that your PR branch is synchronized with the main branch of Ultralytics Notebooks. If it is out-of-date, please update your branch via git pull or the 'Update branch' button here on GitHub.
• ✅ Ensure CI Checks Pass: Ensure that all Continuous Integration (CI) checks pass successfully for this PR. Any failures will need to be addressed before final approval.
• ✅ Update Documentation: If your changes require updates to the Ultralytics documentation, make sure these updates are included in your PR or planned for a subsequent PR.
• ✅ Add Tests: Make sure to add or update the necessary test cases for the introduced changes. If possible, provide outputs or metrics to validate the improvements added with this PR.
• ✅ Sign the CLA: If this is your first contribution to Ultralytics, please confirm that you've signed the Contributor License Agreement (CLA) by adding a comment to this PR saying, "I have read the CLA Document and I sign the CLA".
• ✅ Minimize Changes: Limit your changes to the minimum necessary for this feature addition or bug fix, ensuring clarity and cohesion. Keep an eye on optimizing any computational or memory performance aspects related to the edits.

For further assistance:

• 📚 Reference the Contributing Guide for step-by-step instructions on how to contribute efficiently.
• In case this PR introduces a bug fix (which does not appear to be the case here), make sure to include a Minimum Reproducible Example (MRE) to aid in testing and validation.

This is an automated response to facilitate your PR review process, but rest assured that an Ultralytics engineer will provide further feedback soon! If you have any questions, don't hesitate to comment below. Thank you for contributing to Ultralytics! 😊🚀

[ambitious-octopus]

all good!

[UltralyticsAssistant]

🎉✨ The PR has been merged! Huge thanks to @RizwanMunawar for spearheading this update and to @ambitious-octopus for your valuable contributions! 🚀 Your work on improving segmentation models, enhancing training configs, and creating clearer tutorial workflows will make a lasting impact on how users approach and succeed with YOLO-based segmentation tasks. 🙌

As Marcus Aurelius once said, "What we do now echoes in eternity." Your thoughtful enhancements to these tools and resources will undoubtedly empower users worldwide to take their computer vision projects to the next level. 💡 Thank you for making a difference with your contributions! ❤️