h-bo / rt-detr Goto Github PK

English | 简体中文

This is the official implementation of the paper "DETRs Beat YOLOs on Real-time Object Detection".

• [2023.07.13] Upload rtdetr training logs.

• Release RT-DETR-R50, RT-DETR-R101
• Release RT-DETR-R50-m（example for scaled)
• Release RT-DETR-R34, RT-DETR-R18
• Release RT-DETR-L, RT-DETR-X

• rtdetr-paddle
• rtdetr-pytorch

We propose a Real-Time DEtection TRansformer (RT-DETR), the first real-time end-to-end object detector to our best knowledge. Our RT-DETR-L achieves 53.0% AP on COCO val2017 and 114 FPS on T4 GPU, while RT-DETR-X achieves 54.8% AP and 74 FPS, outperforming all YOLO detectors of the same scale in both speed and accuracy. Furthermore, our RT-DETR-R50 achieves 53.1% AP and 108 FPS, outperforming DINO-Deformable-DETR-R50 by 2.2% AP in accuracy and by about 21 times in FPS.

If you use RT-DETR in your work, please use the following BibTeX entries:

@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}
}