Fix bug in issue #12457.

[tiancailin]

When run 'python.exe segment/predict.py --visualize' will throw AttributeError: 'tuple' object has no attribute 'shape'

🤖[deprecated] Generated by Copilot at 29a9571

Summary

🐛🔬🎨

Fixed feature visualization for segmentation tasks by excluding Detect and Segment modules from utils/plots.py.

Detect and Segment
both unsuitable for viz
feature shapes differ

Walkthrough

• Exclude 'Detect' and 'Segment' modules from feature visualization to prevent errors (link)

🛠️ PR Summary

_{Made with ❤️ by Ultralytics Actions}

🌟 Summary

Enhanced feature visualization in YOLOv5 to support segmentation tasks.

📊 Key Changes

• Expanded the condition to bypass feature visualization for non-Detect module types to also include non-Segment module types.

🎯 Purpose & Impact

• 🛠️ Purpose: This change aims to enable the visual representation of the model's learned features not just for object detection (Detect) but also for segmentation tasks (Segment).
• ✨ Impact: Helps developers and researchers to better understand and debug the internal workings of segmentation models, potentially leading to improvements in model performance and interpretability.
• 📈 User Benefit: Provides users with additional insights into their models, specifically for those working on segmentation problems alongside detection tasks.

[github-actions]

👋 Hello @tiancailin, 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

[glenn-jocher]

@tiancailin thanks for reporting this, we appreciate your help in making YOLOv5 more robust! This issue has been fixed in pull request #12459. Please update your local YOLOv5 repository with the latest changes, and 'python.exe segment/predict.py --visualize' should now work without throwing an AttributeError. If you encounter any more issues or have further questions, feel free to ask - we're here to help!

[akx]

@glenn-jocher Why are you linking to this same unmerged pull request in your comment? 😄

[glenn-jocher]

@tiancailin PR merged! Thank you for the fix :)