Implement automatic class weight calculation for imbalanced distributions

[AjibolaPy]

This pull request addresses #2703, introducing automatic class weight calculation for imbalanced datasets in the YOLOv8 project, specifically in the classification trainer. It improves model performance by dynamically determining class weights based on dataset analysis. Underrepresented classes receive higher weights, while overrepresented classes receive lower weights. Manual weight adjustments are no longer needed, streamlining the workflow and enhancing classification effectiveness. Thorough testing confirms significant improvements.

🛠️ PR Summary

_{Made with ❤️ by Ultralytics Actions}

📊 Key Changes

• A new function class_weight has been implemented for automatic class weight calculation.
• This function is integrated into the training process to handle class imbalance issues.
• Manual class weight input is also accommodated as an option.

🎯 Purpose & Impact

• The purpose is to improve model training where there is an imbalance in class distributions within the dataset.
• Automatically computed class weights help to give minority classes more weight in the loss computation, potentially improving model accuracy on such classes.
• Users dealing with imbalanced datasets will benefit from this update, as it can improve fairness and generalization of the model.

🌟 Summary

"New feature to automatically calculate class weights for imbalanced datasets during model training, promoting better performance for minority classes." 🏋️‍♂️📈

[github-actions]

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

[github-actions]

👋 Hello @AjibolaPy, thank you for submitting a 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!

[AjibolaPy]

I have read the CLA Document and I sign the CLA

[AjibolaPy]

I have read the CLA Document and I sign the CLA

[AjibolaPy]

removed unused imports

[AjibolaPy]

removed unused imports

[AjibolaPy]

removed unused import

[AjibolaPy]

removed block "#"

[AjibolaPy]

removed class_weight arg

[AjibolaPy]

merging