support RGBA image in model training, validation, prediction and export

[lizongnan]

🛠️ PR Summary

_{Made with ❤️ by Ultralytics Actions}

🌟 Summary

Ultralytics introduces RGBA image support across its pipeline, enhancing visual data processing capabilities! 🎉

📊 Key Changes

• RGBA Support: New configuration option to handle RGBA (Red, Green, Blue, Alpha) images, allowing transparency in images.
• Image Channel Configuration: Adjustments to model configuration files to specify the number of image channels (now supporting 4 for RGBA images).
• Adaptive Image Loading: Modified image loading functions to dynamically support both BGR and BGRA based on configuration.
• Model Input Adjustments: Changes in model, predictor, and validator components to accommodate 4 channels for RGBA images, ensuring compatibility throughout the pipeline.
• Plotting Compatibility: Updated plotting functions to handle images with 4 channels, including adjustments for saving images in a format compatible with RGBA.

🎯 Purpose & Impact

• Enhanced Visual Data Representation: The ability to handle images with transparency opens up new avenues for richer visual data representation and processing.
• Increased Flexibility: This update provides users with more options for image formats, enhancing the toolkit’s flexibility for different use cases.
• Compatibility and Performance: Ensures seamless integration of RGBA images within the existing framework, maintaining performance and compatibility.

These changes facilitate more diverse and complex image processing tasks, catering to a broader range of applications and user needs. 🚀

[github-actions]

CLA Assistant Lite bot:
Thank you for your submission, we really appreciate it. Like many open-source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution. You can sign the CLA by just posting a Pull Request Comment same as the below format.

---

I have read the CLA Document and I sign the CLA

---

_{You can retrigger this bot by commenting recheck in this Pull Request}

[codecov]

Codecov Report

Attention: Patch coverage is 70.96774% with 9 lines in your changes are missing coverage. Please review.

Project coverage is 75.97%. Comparing base (d608565) to head (33c9174).
Report is 7 commits behind head on main.

❗ Current head 33c9174 differs from pull request most recent head b212c6d. Consider uploading reports for the commit b212c6d to get more accurate results

Files	Patch %	Lines
ultralytics/data/base.py	42.85%	4 Missing ⚠️
ultralytics/data/loaders.py	77.77%	2 Missing ⚠️
ultralytics/engine/model.py	50.00%	1 Missing ⚠️
ultralytics/engine/predictor.py	80.00%	1 Missing ⚠️
ultralytics/utils/plotting.py	75.00%	1 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main   #10036      +/-   ##
==========================================
- Coverage   75.99%   75.97%   -0.02%     
==========================================
  Files         121      121              
  Lines       15332    15349      +17     
==========================================
+ Hits        11652    11662      +10     
- Misses       3680     3687       +7     

Flag	Coverage Δ
Benchmarks	36.02% <45.16%> (-0.01%)	⬇️
GPU	37.93% <41.93%> (-0.01%)	⬇️
Tests	71.28% <64.51%> (-0.03%)	⬇️

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.