v2.5.1

CVHub520/X-AnyLabelingv2.5.1Jan 1, 2025by CVHub520

AI Summary

X-AnyLabeling v2.5.1 is a minor release focused on bug fixes, model support additions, and performance optimizations. Key updates include adding Hyper-YOLO model support, Florence-2 CPU support, and optimizing batch inference efficiency, along with several bug fixes for RAM model preprocessing and config path issues.

Key Highlights

Added support for Hyper-YOLO model
Optimized inference efficiency for batch task execution (run_all_images)
Added CPU support for Florence-2 with optimized model loading
Fixed GBK codec decoding error in RAM model loading
Fixed dtype casting issue in RAM model preprocessing
Improved MacOS dark mode visibility

New Features

Hyper-YOLO model support
Florence-2 CPU support and optimized model loading
Batch task execution optimization for faster inference

Full Release Notes

## Released versions

| Version | MD5                                |
|---------|------------------------------------|
| X-AnyLabeling-CPU.exe | 9f45a1b7fb6f9c530b47ff7e46a95989 |
| X-Anylabeling-Linux-CPU | 752fb67594b9ab7e0b00f97e37d3c50e |

> [!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: [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(run_all_images): optimize inference efficiency during batch task execution by @chevydream in 900602e4e22ab56da1b713de6d364662656b38f6
- 🚀 feat(model): add support for Hyper-YOLO by @CVHub520 in 51b8cb2e5334ba0e91c4b611463c3e2687e02180
- 🚀 feat(Florence-2): add CPU support and optimize model loading by @CVHub520 in 3d6239a06d9f2eacbe80b603f1786d8cf5e11338
- 🐛 fix(RAM): GBK codec decoding error in model loading process by @CVHub520 in 8f7840db7ca4e562fb247f4390b18862cbe12017
- 🐛 fix(RAM): correct dtype casting in RAM model preprocessing by @CVHub520 in 9a6a03678f2f1141e58a07ac850a51d0ff477783
- 🐛 fix(config): correct text_encoder_type path in open_vision.yaml by @CVHub520 in 64db73c83c10674810eddc152e61628965b1c0a7
- 🎨 style(MacOS): improve visibility in dark mode by @CVHub520  in 5c71187705bc17d621cc3dad3a0d7f98bfd72f54
- 📚 docs(OpenVision): update README with new installation instructions by @CVHub520 in 4628963fcd22c4b1d990f65f9de13963573fb34c

**Full Changelog**: https://github.com/CVHub520/X-AnyLabeling/compare/v2.5.0...v2.5.1