v1.0.0

CVHub520/X-AnyLabelingv1.0.0Oct 25, 2023by CVHub520

AI Summary

This is the v1.0.0 release of X-AnyLabeling, a labeling tool that introduces rotation box support and integrates several state-of-the-art models including YOLOv5-OBB for oriented bounding box detection, GroundingDINO for zero-shot object detection, and Recognize Anything for image tagging.

Key Highlights

Added rotation box feature for labeling rotated objects
Integrated YOLOv5-OBB supporting DroneVehicle and DOTA datasets (v1.0/v1.5/v2.0)
Added GroundingDINO for zero-shot object detection capabilities
Integrated Recognize Anything model for image tagging
Released new executables for Windows (CPU/GPU) and Linux (CPU/GPU)

New Features

Rotation box labeling feature
YOLOv5-OBB support with DroneVehicle and DOTA dataset models
GroundingDINO zero-shot object detection integration
Recognize Anything (Tag2Text) image tagging model

Full Release Notes

## New versions

- X-AnyLabeling-CPU.exe [md5 | 1831f151c9140b9b126626094b6cd160]
- X-AnyLabeling-GPU.exe [md5 | adefc07059626ad3fc86f1e0b2be70a4]
- X-Anylabeling-Linux-CPU [md5 | 6f14401502fa19e9917a6dc44517df06]
- X-Anylabeling-Linux-GPU [md5 | b39f74af52b95b6f24020e8c9d26bab5]

## New feature
  - 🆕🆕🆕 Add a new feature for rotation box.
  - 🚀🚀🚀 Support [YOLOv5-OBB](https://github.com/hukaixuan19970627/yolov5_obb) with [DroneVehicle](https://github.com/VisDrone/DroneVehicle) and [DOTA](https://captain-whu.github.io/DOTA/index.html)-v1.0/v1.5/v2.0 model.
  - 🔥🔥🔥 SOTA Zero-Shot Object Detection - [GroundingDINO](https://github.com/wenyi5608/GroundingDINO) is released.
  - 🙌🙌🙌 SOTA Image Tagging Model - [Recognize Anything](https://github.com/xinyu1205/Tag2Text) is released.