# D-FINE-N

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

- Family: D-FINE (USTC)
- Parameters: 4.0M
- GFLOPs: 7.0
- Default input size: 640px
- Detection: detr · nms-free
- Architecture: transformer · HGNetv2 backbone
- Weight license: Apache-2.0
- Paper-reported mAP@50-95: 42.8%
- Paper: https://arxiv.org/abs/2410.13842
- Original code: https://github.com/Peterande/D-FINE

## Benchmarks (COCO val2017)

| Hardware | Runtime | mAP@50-95 | FPS | Latency (ms) | VRAM (MB) |
|---|---|---|---|---|---|
| NVIDIA A100 | PyTorch FP32 | 42.8 | 25.6 | 39.1 | 68 |
| NVIDIA Jetson Orin Nano Super 8GB | ONNX Runtime FP32 | 45.8 | 17.5 | 57.0 | - |
| NVIDIA Jetson Orin Nano Super 8GB | PyTorch FP32 | 45.8 | 11.7 | 85.5 | 64 |
| NVIDIA Jetson Orin Nano Super 8GB | TensorRT FP16 | 45.8 | 42.1 | 23.8 | - |
| NVIDIA Jetson Orin Nano Super 8GB | TensorRT FP32 | 45.8 | 33.5 | 29.9 | - |
| NVIDIA RTX 5070 Ti | ONNX Runtime FP32 | 45.8 | 78.9 | 12.7 | - |
| NVIDIA RTX 5070 Ti | PyTorch FP32 | 45.8 | 32.5 | 30.7 | 70 |
| NVIDIA RTX 5070 Ti | TensorRT FP16 | 45.8 | 79.7 | 12.5 | - |
| NVIDIA RTX 5070 Ti | TensorRT FP32 | 45.8 | 98.7 | 10.1 | - |

## Usage with LibreYOLO

```python
from libreyolo import LibreYOLO

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

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