README.md

---
license: apache-2.0
tags:
  - kornia
  - object-detection
---

# kornia/rt_detr

Pretrained weights for **RT-DETR** (Real-Time Detection Transformer),
used by [`kornia.models.RTDETRDetector`](https://kornia.readthedocs.io/en/latest/models.html).

RT-DETR replaces traditional NMS post-processing with a transformer decoder and an
efficient hybrid encoder combining a multi-scale convolutional backbone with an
intra-scale interaction module. Weights converted from PaddleDetection. CVPR 2024.

**Original repo:** [lyuwenyu/RT-DETR](https://github.com/lyuwenyu/RT-DETR)

## Weights

| File | Backbone | COCO AP |
|------|----------|---------|
| `rtdetr_r18vd_dec3_6x_coco_from_paddle.pth` | ResNet-18D | 46.4 |
| `rtdetr_r34vd_dec4_6x_coco_from_paddle.pth` | ResNet-34D | 48.9 |
| `rtdetr_r50vd_m_6x_coco_from_paddle.pth` | ResNet-50D-M | 51.3 |
| `rtdetr_r50vd_6x_coco_from_paddle.pth` | ResNet-50D | 53.1 |
| `rtdetr_r101vd_6x_coco_from_paddle.pth` | ResNet-101D | 54.3 |

## Citation

```bibtex
@inproceedings{zhao2024rtdetr,
    title     = {{DETRs} Beat {YOLOs} on Real-time Object Detection},
    author    = {Zhao, Yian and Lv, Wenyu and Xu, Shangliang
                 and Wei, Jinman and Wang, Guanzhong and Dang, Qingqing
                 and Liu, Yi and Chen, Jie},
    booktitle = {CVPR},
    year      = {2024}
}
```