Ultralytics Release v8.3.34 Announcement
We’re thrilled to announce the release of Ultralytics YOLO version 8.3.34! This update brings improvements especially focused on enhancing the accuracy and reliability of predictive processes in modern machine learning workflows. Here’s a comprehensive overview:
Summary
The update to version 8.3.34 focuses on improving prediction reliability in the FastSAM model and enhances various internal systems to optimize workflows and accuracy. 
Key Changes
- Enhanced prompt method to handle cases with empty predictions effectively for
FastSAM. - Updated GitHub Actions to use uv for dependency installation, reducing potential Python packaging issues.
- Improved project name handling in training setups to fix issues with special characters, ensuring compatibility with systems like W&B.
- Revised
v8_transformsfunction with better hyperparameter handling using Namespace. - Enhanced dataset configuration for
RT-DETRwith new parameters likefraction,single_cls, andclassesto better align withYOLOdataset management. - Refined object counting method in heatmaps to use centroids instead of bounding boxes for improved accuracy.
What’s Changed
- Update Actions with
uvinstalls by@glenn-jocherin #17620 - Fix
v8_transformsdocstring example by@Y-T-Gin #17630 - Fix W&B project name separator compatibility by
@ArcPenin #17627 - Update Slack usage to v2 by
@glenn-jocherin #17631 - Add
fraction,single_clsandclassestoRTDETRDatasetby@Y-T-Gin #17633 - Heatmaps bug fix by
@RizwanMunawarin #17634 - ultralytics 8.3.34
FastSAMnon-detection fix by@peterchamin #17628
New Contributors
@ArcPenmade their first contribution in #17627@peterchammade their first contribution in #17628