# YOLOX-X

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

- Family: YOLOX (Megvii)
- Parameters: 99.1M
- GFLOPs: 141.2
- Default input size: 640px
- Detection: anchor-free · nms
- Architecture: one-stage · CSPDarknet backbone
- Weight license: Apache-2.0
- Paper-reported mAP@50-95: 51.1%
- Paper: https://arxiv.org/abs/2107.08430
- Original code: https://github.com/Megvii-BaseDetection/YOLOX

## Benchmarks (COCO val2017)

| Hardware | Runtime | mAP@50-95 | FPS | Latency (ms) | VRAM (MB) |
|---|---|---|---|---|---|
| NVIDIA Jetson Orin Nano Super 8GB | ONNX Runtime FP32 | 56.3 | 3.6 | 273.8 | - |
| NVIDIA Jetson Orin Nano Super 8GB | PyTorch FP32 | 56.3 | 3.5 | 289.6 | 505 |
| NVIDIA Jetson Orin Nano Super 8GB | TensorRT FP16 | 56.2 | 14.6 | 68.7 | - |
| NVIDIA Jetson Orin Nano Super 8GB | TensorRT FP32 | 56.3 | 6.7 | 149.3 | - |
| NVIDIA RTX 5070 Ti | ONNX Runtime FP32 | 56.3 | 41.6 | 24.0 | - |
| NVIDIA RTX 5070 Ti | PyTorch FP32 | 56.3 | 39.6 | 25.2 | 511 |
| NVIDIA RTX 5070 Ti | TensorRT FP16 | 56.3 | 72.1 | 13.9 | - |
| NVIDIA RTX 5070 Ti | TensorRT FP32 | 56.3 | 48.4 | 20.7 | - |

## Usage with LibreYOLO

```python
from libreyolo import LibreYOLO

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

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