Rtdetr V2 R101vd

🚀 Transformers Usable lyuwenyu RT-DETRv2_101vd

This project enables the use of lyuwenyu's RT-DETRv2_101vd with the Transformers library for object detection.

🚀 Quick Start

This project allows the use of lyuwenyu's RT-DETRv2_101vd in the Transformers library for object detection tasks.

📄 License

The project is licensed under the Apache-2.0 license.

📚 Documentation

Origin

• https://github.com/lyuwenyu/RT-DETR/tree/main/rtdetrv2_pytorch

Converter

• https://huggingface.co/jadechoghari/RT-DETRv2/tree/main
• Modification on config.json -> model_type to be usable with Transformers

Compatibility

Tested and working with:

• Transformers with RTDetrForObjectDetection, RTDetrImageProcessor, AutoModelForObjectDetection, AutoImageProcessor
• supervision with SAHI and annotators (except segmentation)

Code Example

Code example (coming soon)

Source

@misc{lv2023detrs,
      title={DETRs Beat YOLOs on Real-time Object Detection},
      author={Wenyu Lv and Shangliang Xu and Yian Zhao and Guanzhong Wang and Jinman Wei and Cheng Cui and Yuning Du and Qingqing Dang and Yi Liu},
      year={2023},
      eprint={2304.08069},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

@misc{lv2024rtdetrv2improvedbaselinebagoffreebies,
      title={RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformer}, 
      author={Wenyu Lv and Yian Zhao and Qinyao Chang and Kui Huang and Guanzhong Wang and Yi Liu},
      year={2024},
      eprint={2407.17140},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2407.17140}, 
}