Fix TFLite Segment mask rows 1-4 normalization

[charlesollion]

Update autobackend.py: fix ndim ==3 for tflite to exclude mask tensor
fixes #9385

🛠️ PR Summary

_{Made with ❤️ by Ultralytics Actions}

🌟 Summary

Improved tensor handling for non-classification tasks in neural network backend.

📊 Key Changes

• Adjusted condition for handling tensor dimensions in callbacks: the code now precisely targets tensors with exactly 3 dimensions instead of more than 2.

🎯 Purpose & Impact

• Enhanced precision: This change aims to exclude 4-dimensional tasks (like masks) from a normalization process meant for non-classification tasks, improving the accuracy for object detection and segmentation models.
• Better compatibility: Ensures the neural network backend processes only relevant data shapes, leading to fewer errors and potentially faster inference times.
• Impact: Users working with non-classification tasks (e.g., object detection) may notice improved model performance and accuracy due to more precise data handling.

[github-actions]

CLA Assistant Lite bot All Contributors have signed the CLA. ✅

[github-actions]

👋 Hello @charlesollion, thank you for submitting an Ultralytics YOLOv8 🚀 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/ultralytics main 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 main locally.
• ✅ Verify all YOLOv8 Continuous Integration (CI) checks are passing.
• ✅ Update YOLOv8 Docs for any new or updated features.
• ✅ 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

See our Contributing Guide for details and let us know if you have any questions!

[codecov]

Codecov Report

Attention: Patch coverage is 0% with 1 lines in your changes are missing coverage. Please review.

Project coverage is 38.85%. Comparing base (30a867b) to head (02f2bfd).

❗ Current head 02f2bfd differs from pull request most recent head 211135a. Consider uploading reports for the commit 211135a to get more accurate results

Files	Patch %	Lines
ultralytics/nn/autobackend.py	0.00%	1 Missing ⚠️

Additional details and impacted files

@@           Coverage Diff           @@
##             main    #9405   +/-   ##
=======================================
  Coverage   38.85%   38.85%           
=======================================
  Files         117      117           
  Lines       14850    14850           
=======================================
  Hits         5770     5770           
  Misses       9080     9080           

Flag	Coverage Δ
GPU	38.85% <0.00%> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[charlesollion]

I have read the CLA Document and I hereby sign the CLA

[glenn-jocher]

@charlesollion thank you for signing the CLA! Your contribution is immensely valuable to the YOLOv8 community. 🌟 If you have any more questions or need further assistance as you contribute, feel free to reach out. Happy coding! 👩‍💻👨‍💻

[glenn-jocher]

@charlesollion thanks! It looks like the CLA message may not have worked. Can you try again with this message:

I have read the CLA Document and I sign the CLA

[charlesollion]

I have read the CLA Document and I sign the CLA

[glenn-jocher]

@charlesollion PR merged! Thank you for catching this hard-to-find bug and submitting this fix. Let us know if you spot any other bugs or areas for improvement :)