github.com/lyuwenyu/RT-DETR @v1.0 sqlite

English | 简体中文

RT-DETR: DETRs Beat YOLOs on Real-time Object Detection

<a href="https://github.com/lyuwenyu/RT-DETR/blob/main/LICENSE">
    <img alt="license" src="https://img.shields.io/github/license/lyuwenyu/RT-DETR">
</a>
<a href="https://github.com/lyuwenyu/RT-DETR/pulls">
    <img alt="prs" src="https://img.shields.io/github/issues-pr/lyuwenyu/RT-DETR">
</a>
<a href="https://github.com/lyuwenyu/RT-DETR/issues">
    <img alt="issues" src="https://img.shields.io/github/issues/lyuwenyu/RT-DETR?color=pink">
</a>
<a href="https://github.com/lyuwenyu/RT-DETR">
    <img alt="issues" src="https://img.shields.io/github/stars/lyuwenyu/RT-DETR">
</a>
<a href="https://arxiv.org/abs/2304.08069">
    <img alt="arXiv" src="https://img.shields.io/badge/arXiv-2304.08069-red">
</a>
<a href="mailto: lyuwenyu@foxmail.com">
    <img alt="emal" src="https://img.shields.io/badge/contact_me-email-yellow">
</a>

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

🚀 Updates

• [2024.02.27] Our work has been accepted to CVPR 2024!
• [2024.01.23] Fix difference on data augmentation with paper in rtdetr_pytorch #84.
• [2023.11.07] Add pytorch ✅ rtdetr_r34vd for requests #107, #114.
• [2023.11.05] Upgrade the logic of remap_mscoco_category to facilitate training of custom datasets, see detils in Train custom data part. #81.
• [2023.10.23] Add discussion for deployments, supported onnxruntime, TensorRT, openVINO.
• [2023.10.12] Add tuning code for pytorch version, now you can tuning rtdetr based on pretrained weights.
• [2023.09.19] Upload ✅ pytorch weights convert from paddle version.
• [2023.08.24] Release RT-DETR-R18 pretrained models on objects365. 49.2 mAP and 217 FPS.
• [2023.08.22] Upload ✅ rtdetr_pytorch source code. Please enjoy it!
• [2023.08.15] Release RT-DETR-R101 pretrained models on objects365. 56.2 mAP and 74 FPS.
• [2023.07.30] Release RT-DETR-R50 pretrained models on objects365. 55.3 mAP and 108 FPS.
• [2023.07.28] Fix some bugs, and add some comments. 1, 2.
• [2023.07.13] Upload ✅ training logs on coco.
• [2023.05.17] Release RT-DETR-R18, RT-DETR-R34, RT-DETR-R50-m（example for scaled).
• [2023.04.17] Release RT-DETR-R50, RT-DETR-R101, RT-DETR-L, RT-DETR-X.

📍 Implementations

• 🔥 RT-DETR paddle: code, weights
• 🔥 RT-DETR pytorch: code, weights

Notes: - COCO + Objects365 in the table means finetuned model on COCO using pretrained weights trained on Objects365.

💡 Introduction

We propose a Real-Time DEtection TRansformer (RT-DETR, aka RTDETR), the first real-time end-to-end object detector to our best knowledge. Our RT-DETR-R50 / R101 achieves 53.1% / 54.3% AP on COCO and 108 / 74 FPS on T4 GPU, outperforming previously advanced YOLOs in both speed and accuracy. Furthermore, RT-DETR-R50 outperforms DINO-R50 by 2.2% AP in accuracy and about 21 times in FPS. After pre-training with Objects365, RT-DETR-R50 / R101 achieves 55.3% / 56.2% AP.

🦄 Performance

🏕️ Complex Scenarios

🌋 Difficult Conditions

Citation

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={Yian Zhao and Wenyu Lv and Shangliang Xu and Jinman Wei and Guanzhong Wang and Qingqing Dang and Yi Liu and Jie Chen},
      year={2023},
      eprint={2304.08069},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}