# YOLOv9-T

> YOLOv9-T: one-stage object detector from the YOLOv9 family. Available in LibreYOLO, the MIT-licensed open-source library (free for commercial use).

- Family: YOLOv9 (Academia Sinica)
- Parameters: 2.0M
- GFLOPs: 4.0
- Default input size: 640px
- Detection: anchor-free · nms
- Architecture: one-stage · GELAN backbone
- Weight license: MIT
- Paper-reported mAP@50-95: 38.3%
- Paper: https://arxiv.org/abs/2402.13616
- Original code: https://github.com/MultimediaTechLab/YOLO

## Benchmarks (COCO val2017)

| Hardware | Runtime | mAP@50-95 | FPS | Latency (ms) | VRAM (MB) |
|---|---|---|---|---|---|
| NVIDIA Jetson Orin Nano Super 8GB | ONNX Runtime FP32 | 41.8 | 18.6 | 53.8 | - |
| NVIDIA Jetson Orin Nano Super 8GB | PyTorch FP32 | 41.8 | 9.9 | 101.2 | 47 |
| NVIDIA Jetson Orin Nano Super 8GB | TensorRT FP16 | 41.8 | 34.3 | 29.1 | - |
| NVIDIA Jetson Orin Nano Super 8GB | TensorRT FP32 | 41.8 | 27.8 | 36.0 | - |
| NVIDIA RTX 5070 Ti | ONNX Runtime FP32 | 41.8 | 52.1 | 19.2 | - |
| NVIDIA RTX 5070 Ti | PyTorch FP32 | 41.8 | 31.9 | 31.3 | 48 |
| NVIDIA RTX 5070 Ti | TensorRT FP16 | 41.8 | 59.0 | 17.0 | - |
| NVIDIA RTX 5070 Ti | TensorRT FP32 | 41.8 | 72.0 | 13.9 | - |
| Raspberry Pi 5 | PyTorch FP32 | 41.4 | 2.9 | 346.3 | - |

## Usage with LibreYOLO

```python
from libreyolo import LibreYOLO

model = LibreYOLO("LibreYOLO9t.pt")
result = model("image.jpg", conf=0.25, iou=0.45)
```

Source: https://www.visionanalysis.org/model/yolov9t. Benchmarks produced with LibreYOLO (https://github.com/Libre-YOLO/libreyolo).