README.md

---
license: cc-by-nc-nd-4.0
pipeline_tag: object-detection
tags:
- yolov10
- ultralytics
- yolo
- object-detection
- pytorch
- cs2
- Counter Strike
---

Counter Strike 2 players detector

## Supported Labels

```
[ 'c', 'ch', 't', 'th' ]
```

## All models in this series

- [yoloV10n_cs2](https://huggingface.co/Vombit/yolov10n_cs2) (5.5mb)
- [yoloV10s_cs2](https://huggingface.co/Vombit/yolov10s_cs2) (15.7mb)
- [yoloV10m_cs2](https://huggingface.co/Vombit/yolov10m_cs2) (31.9mb)
- [yoloV10b_cs2](https://huggingface.co/Vombit/yolov10b_cs2) (39.7mb)
- [yoloV10l_cs2](https://huggingface.co/Vombit/yolov10l_cs2) (50.0mb)
- [yoloV10x_cs2](https://huggingface.co/Vombit/yolov10x_cs2) (61.4mb)

## How to use
```python
# load Yolo
from ultralytics import YOLO

# Load a pretrained YOLO model
model = YOLO(r'weights\yolov**_cs2.pt')

# Run inference on 'image.png' with arguments
model.predict(
    'image.png',
    save=True,
    device=0
    )
```


## Predict info

Ultralytics YOLOv8.2.90 🚀 Python-3.12.5 torch-2.3.1+cu121 CUDA:0 (NVIDIA GeForce RTX 4060, 8188MiB)

- yolov10x_cs2_fp16.engine (640x640 5 ts, 5 ths, 15.4ms)
- yolov10x_cs2.engine (640x640 5 ts, 5 ths, 19.6ms)
- yolov10x_cs2_fp16.onnx (640x640 5 ts, 5 ths, 381.7ms)
- yolov10x_cs2.onnx (640x640 5 ts, 5 ths, 369.1ms)
- yolov10x_cs2.pt (384x640 5 ts, 5 ths, 146.7ms)

## Dataset info

Data from over 120 games, where the footage has been tagged in detail.

![image/jpg](https://huggingface.co/Vombit/yolov10x_cs2/resolve/main/labels.jpg)
![image/jpg](https://huggingface.co/Vombit/yolov10x_cs2/resolve/main/labels_correlogram.jpg)


## Train info

The training took place over 150 epochs.

![image/png](https://huggingface.co/Vombit/yolov10x_cs2/resolve/main/results.png)




You can also support me with a cup of coffee: [donate](https://www.donationalerts.com/r/vombit_donation)