🌟 Summary
The v8.2.85
release for Ultralytics YOLO highlights the latest updates, focusing on the upcoming YOLOv10 enhancements, streamlined workflows, and improved compatibility across the platform.
📊 Key Changes
- YOLOv10 Parameter Fix: Introduced a
max_det
parameter, enhancing user control by allowing the specification of the maximum number of detections. This update is a pivotal improvement leading up to YOLOv10, aligning with ongoing efforts to optimize model configurability and performance. - GitHub Actions Update: Streamlined the publish workflow by removing the
openai
dependency and consolidating complex scripts into a single, efficient command. This significantly simplifies the release process. - INT8 Export Warning: Added a warning for automatic enforcement of
dynamic=True
during INT8 model exports to enhance compatibility, ensuring smoother user experiences with advanced export settings. - Documentation Enhancements: Improved author attribution with avatars in documentation, optimizing related tools and making contributions more visible and accessible to users.
- Explorer Tests Requirement: Updated tests to require PyTorch version 1.13 or newer, ensuring compatibility, reliability, and stability across development environments.
🎯 Purpose & Impact
- YOLOv10 Readiness: The new
max_det
parameter is a key enhancement that sets the stage for YOLOv10, giving users greater control and customization options over model outputs. - Optimized Release Workflow: The streamlined workflow reduces complexity and potential dependency issues, facilitating faster and more efficient publishing of updates.
- Enhanced Export Compatibility: The INT8 export warning for
dynamic=True
ensures compliance with optimal settings, improving export reliability and performance. - Improved Documentation: Enhanced visualization with author avatars increases transparency and improves user interaction with the documentation.
- Reliable Testing: By enforcing minimum version requirements for PyTorch, the update guarantees stable and consistent testing, enhancing overall development reliability.
These updates emphasize Ultralytics' commitment to enhancing YOLOv10's functionality, improving user control, and refining the overall development and deployment experience.
What's Changed
- Optimize docs author avatars by @glenn-jocher in #15923
- Explorer tests require torch>=1.13 by @glenn-jocher in #15930
- Update notebooks: Fix
classes_names
argument withnames
by @RizwanMunawar in #15915 - Includes warning for enforced
dynamic
during INT8 exports by @Burhan-Q in #15874 - Update publish.yml by @glenn-jocher in #15932
- Update publish.yml by @glenn-jocher in #15933
ultralytics 8.2.85
YOLOv10max_det
arg fix by @ambitious-octopus in #15917
Full Changelog: v8.2.84...v8.2.85