README.md

---
language:
- en
- es
base_model: onnx-community/yolov10b
---
# Counter Strike 2 players detector

### Supported Labels
[ "none", "ct_body", "ct_head", "t_body", "t_head" ]

### models
YOLOv10b

## How to use
```
from ultralytics import YOLO

# Load a pretrained YOLO model
model = YOLO(r'weights\yolov10b_cs2.pt')

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

# Labels
![labels.jpg](https://cdn-uploads.huggingface.co/production/uploads/62e1c9b42e4cab6e39dafc97/C8USpCXU6KN8VQ2vjub_Q.jpeg)
# Results
![results.png](https://cdn-uploads.huggingface.co/production/uploads/62e1c9b42e4cab6e39dafc97/X9ZL01yd9UIo-u4sYnHN8.png)
# Predict
![train_batch0.jpg](https://cdn-uploads.huggingface.co/production/uploads/62e1c9b42e4cab6e39dafc97/gZQHxDe4hYYw8oz3NgNnv.jpeg)
```
YOLOv10b summary (fused): 383 layers, 20,418,862 parameters, 0 gradients, 98.0 GFLOPs
                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 3/3 [00:02<00:00,  1.44it/s]
                   all         90        215      0.908      0.757       0.85      0.635
               ct_body         41         45      0.914      0.911      0.953      0.819
               ct_head         43         47      0.909      0.639      0.735      0.465
                t_body         54         60      0.932      0.921      0.964      0.781
                t_head         56         63      0.877      0.556      0.748      0.476
```

# others models YOLOv10s
https://huggingface.co/ChitoParedes/cs2-yolov10s