Update val.py to include the save_text option for the pose model

[jbdebelle]

In the pose/val.py script, the task is to implement a new feature called save_text. This feature enables the generation of normalized text files containing pose data. The save_one_txt function will be added to facilitate this functionality.

🛠️ PR Summary

_{Made with ❤️ by Ultralytics Actions}

🌟 Summary

Enhanced YOLO pose validation logging with TXT output and pose normalization.

📊 Key Changes

• Enabled saving pose predictions as TXT files.
• Added a function to save normalized pose coordinates to TXT, including keypoints.

🎯 Purpose & Impact

• Improve Debugging and Analysis: Users can now review YOLO pose predictions in a more accessible format (TXT), facilitating easier debugging and analysis. 🕵️‍♂️
• Enhanced Data Interpretation: Normalizing keypoints in pose predictions aids in a better understanding of the model's performance across different image dimensions. 📊
• Flexibility in Data Usage: Saving data in TXT format allows for easier integration with other analytical tools and pipelines. 🛠️

This update makes pose model predictions more transparent and manageable, benefiting researchers, developers, and hobbyists involved in computer vision projects.

[jbdebelle]

I have read the CLA Document and I sign the CLA

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 69.84%. Comparing base (fcfc44e) to head (e0c2a3c).

Additional details and impacted files

@@            Coverage Diff             @@
##             main   #10209      +/-   ##
==========================================
- Coverage   73.46%   69.84%   -3.63%     
==========================================
  Files         122      122              
  Lines       15622    15640      +18     
==========================================
- Hits        11476    10923     -553     
- Misses       4146     4717     +571     

Flag	Coverage Δ
Benchmarks	35.33% <11.11%> (-0.22%)	⬇️
GPU	37.26% <5.55%> (-0.04%)	⬇️
Tests	65.21% <100.00%> (-4.78%)	⬇️

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.

[jbdebelle]

recheck

[glenn-jocher]

Absolutely, let's recheck the matter at hand! If you're encountering any specific issues or have further details, feel free to share. Here to help! 😊

[luca-depe]

Hi @Burhan-Q! Any estimate on when this will be merged?