OBB: update metrics

[Laughing-q]

Thank you 🙏 for your contribution to Ultralytics 🚀! Your effort in enhancing our repositories is greatly appreciated. To streamline the process and assist us in integrating your Pull Request (PR) effectively, please follow these steps:

1. Check for Existing Contributions: Before submitting, kindly explore existing PRs to ensure your contribution is unique and complementary.

2. Link Related Issues: If your PR addresses an open issue, please link it in your submission. This helps us better understand the context and impact of your contribution.

3. Elaborate Your Changes: Clearly articulate the purpose of your PR. Whether it's a bug fix or a new feature, a detailed description aids in a smoother integration process.

4. Ultralytics Contributor License Agreement (CLA): To uphold the quality and integrity of our project, we require all contributors to sign the CLA. Please confirm your agreement by commenting below:

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

For more detailed guidance and best practices on contributing, refer to our ✅ Contributing Guide. Your adherence to these guidelines ensures a faster and more effective review process.

🛠️ PR Summary

_{Made with ❤️ by Ultralytics Actions}

🌟 Summary

Improved accuracy for YOLOv8 OBB models and updated dataset recommendations.

📊 Key Changes

• Increased mAP (mean Average Precision) results for YOLOv8n-obb and YOLOv8s-obb models.
• Updated the default dataset in the example code for OBB validators to dota8.yaml.
• Adjusted an error message for clarity when incorrectly training an OBB model on a detection dataset.

🎯 Purpose & Impact

• Enhanced performance: The improved mAP values indicate that the models perform better in object detection tasks, which is a significant benefit for users needing high accuracy.
• Clearer guidance: The use of a more appropriate default dataset (dota8.yaml) in code examples helps prevent user errors when training models.
• The updated error message provides clearer instructions and helps users troubleshoot and correct their training setup more easily.

[sentry-io]

🔍 Existing Issues For Review

Your pull request is modifying functions with the following pre-existing issues:

📄 File: ultralytics/utils/loss.py

Function	Unhandled Issue
__call__	RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 1127 but got size 576 for tensor... ... Event Count: 13
__call__	RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (w... ... Event Count: 5
__call__	TypeError: ERROR ❌ segment dataset incorrectly formatted or not a segment dataset. ... Event Count: 5
__call__	TypeError: cross_entropy_loss(): argument 'input' (position 1) must be Tensor, not list ... Event Count: 5
__call__	TypeError: ERROR ❌ OBB dataset incorrectly formatted or not a OBB dataset. ultralyt... Event Count: 5

---

_{Did you find this useful? React with a 👍 or 👎}

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Comparison is base (cf50bd9) 77.23% compared to head (927586a) 74.48%.

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #7593      +/-   ##
==========================================
- Coverage   77.23%   74.48%   -2.76%     
==========================================
  Files         117      117              
  Lines       14327    14327              
==========================================
- Hits        11065    10671     -394     
- Misses       3262     3656     +394     

Flag	Coverage Δ
Benchmarks	?
GPU	39.60% <ø> (ø)
Tests	72.37% <ø> (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.

[glenn-jocher]

@Laughing-q thanks, looks good!