# RT-DETRv2-R18

> RT-DETRv2-R18: transformer object detector from the RT-DETRv2 family. Available in LibreYOLO, the MIT-licensed open-source library (free for commercial use).

- Family: RT-DETRv2 (Baidu)
- Parameters: 20.0M
- GFLOPs: 60.0
- Default input size: 640px
- Detection: detr · nms-free
- Architecture: transformer · PResNet backbone
- Weight license: Apache-2.0
- Paper-reported mAP@50-95: 48.1%
- Paper: https://arxiv.org/abs/2407.17140
- Original code: https://github.com/lyuwenyu/RT-DETR/tree/main/rtdetrv2_pytorch

## Benchmarks (COCO val2017)

| Hardware | Runtime | mAP@50-95 | FPS | Latency (ms) | VRAM (MB) |
|---|---|---|---|---|---|
| NVIDIA Jetson Orin Nano Super 8GB | ONNX Runtime FP32 | 50.8 | 9.7 | 103.5 | - |
| NVIDIA Jetson Orin Nano Super 8GB | PyTorch FP32 | 50.8 | 10.3 | 97.4 | 155 |
| NVIDIA Jetson Orin Nano Super 8GB | TensorRT FP16 | 50.8 | 39.9 | 25.1 | - |
| NVIDIA Jetson Orin Nano Super 8GB | TensorRT FP32 | 50.7 | 22.3 | 44.8 | - |
| NVIDIA RTX 5070 Ti | ONNX Runtime FP32 | 50.8 | 97.1 | 10.3 | - |
| NVIDIA RTX 5070 Ti | PyTorch FP32 | 50.8 | 51.1 | 19.6 | 169 |
| NVIDIA RTX 5070 Ti | TensorRT FP16 | 50.8 | 117.8 | 8.5 | - |
| NVIDIA RTX 5070 Ti | TensorRT FP32 | 50.7 | 125.5 | 8.0 | - |
| Raspberry Pi 5 | ONNX Runtime FP32 | 50.8 | 1.3 | 791.2 | - |
| Raspberry Pi 5 | PyTorch FP32 | 50.8 | 0.8 | 1244.5 | - |

## Usage with LibreYOLO

```python
from libreyolo import LibreYOLO

model = LibreYOLO("LibreRTDETRv2r18.pt")
result = model("image.jpg", conf=0.25, iou=0.45)
```

Source: https://www.visionanalysis.org/model/rtdetrv2-r18. Benchmarks produced with LibreYOLO (https://github.com/Libre-YOLO/libreyolo).