Starstruk Logo MarkStarstruk

v2.5.4

CVHub520/X-AnyLabelingv2.5.4Feb 18, 2025by CVHub520

AI Summary

This release adds YOLOv8-SAM2.1 instance segmentation model support to X-AnyLabeling while fixing several bugs related to canvas painting state management and pose data handling. The release also includes documentation improvements and removes the deprecated YOLOv8-EfficientViT-SAM model in favor of YOLOv8-SAM2.

Key Highlights

  • Added YOLOv8-SAM2.1 instance segmentation model support
  • Fixed canvas painting state management during image processing
  • Fixed pose data reset issue in pose mode to ensure correct annotation handling
  • Added documentation guide for selecting all annotation shapes
  • Removed deprecated YOLOv8-EfficientViT-SAM model (superseded by YOLOv8-SAM2)

Breaking Changes

  • YOLOv8-EfficientViT-SAM model has been removed (superseded by YOLOv8-SAM2)

New Features

  • YOLOv8-SAM2.1 instance segmentation model support in model zoo
  • Guide for selecting all annotation shapes

Full Release Notes

## Released versions

| Version | MD5                                |
|---------|------------------------------------|
| X-AnyLabeling-CPU.exe | 45a12c6784b917e5a9a498c4739ca227 |
| X-Anylabeling-Linux-CPU | c498c2e5e01d4989c23375c94bc4f6ff |

> [!NOTE]  
> For GPU acceleration and the macOS version, please consult the guide at  [this link](https://github.com/CVHub520/X-AnyLabeling/blob/main/docs/en/get_started.md).  
> If you need to use the following advanced features, please refer to the corresponding documentation to install additional dependencies.
> 
> 1. Video object tracking based on Segment-Anything-2: [Installation Guide](../../examples/interactive_video_object_segmentation/README.md)
> 2. Object proposal generation based on UPN or open_vision model: [Installation Guide](../../examples/detection/hbb/README.md)
> 3. Interactive visual-text prompting for generic vision tasks: [Installation Guide](../../examples/detection/hbb/README.md)

## Important updates

- 🚀 feat(model_zoo): Add YOLOv8-SAM2.1 instance segmentation model support by @CVHub520  in be503eb4711ab34a70d049bc2d4c42b094a389c7
- 🐛 fix(label_widget): Improve canvas painting state management during image processing by @CVHub520 in 323580b801fe4a1319c08a82d2c0227dff5eec69
- 🐛 fix(label_converter): reset pose_data for each new image in pose mode to ensure correct annotation handling (#791) by 
@CVHub520  in 29ba84e413e06b83a9118e8868bde6201b710d33
- 📝 docs: Add guide for selecting all annotation shapes (#759) by @CVHub520 and @aiyou9
 in 62542babc176cf41b785f9147763582361d56e8c
- 🗑 chore: Remove YOLOv8-EfficientViT-SAM model support as it has been superseded by YOLOv8-SAM2 by @CVHub520  in 592cacf556672bb8549e8faa99e42d9f31c1f27d

**Full Changelog**: https://github.com/CVHub520/X-AnyLabeling/compare/v2.5.3...v2.5.4