Gridiron AI Football Detection Model

This is a YOLOv8 model trained to detect football players and positions using the presnaps-large-model dataset.

Model Details

Model Type: YOLOv8
Task: Object Detection
Domain: Sports Analytics
Dataset: presnaps-large-model
Base Architecture: YOLOv8m

Dataset

This model was trained on the presnaps-large-model dataset from Roboflow Universe, which contains annotated football images for player and position detection.

Usage

from ultralytics import YOLO

# Load model
model = YOLO('best.pt')

# Run inference
results = model('path/to/football_image.jpg')
results[0].show()

Training Details

Epochs: 50
Image Size: 640
Batch Size: 16
Device: NVIDIA A100
Optimizer: AdamW
Learning Rate: Auto

Performance

Citation

If you use this model, please cite both this work and the original dataset:

This Model

@misc{gridiron-ai-football-detector,
  title={Gridiron AI Football Detection Model},
  author={[Your Name]},
  year={2025},
  url={https://huggingface.co/lmarte17/gridiron-ai-football-detector}
}

Original Dataset

@misc{presnaps-large-model_dataset,
  title = { presnaps-large-model Dataset },
  type = { Open Source Dataset },
  author = { Boilermake 2025 },
  howpublished = { \\url{ https://universe.roboflow.com/boilermake-2025/presnaps-large-model } },
  url = { https://universe.roboflow.com/boilermake-2025/presnaps-large-model },
  journal = { Roboflow Universe },
  publisher = { Roboflow },
  year = { 2025 },
  month = { feb },
  note = { visited on 2025-06-16 }
}

Acknowledgments

Thanks to Boilermake 2025 for creating and sharing the presnaps-large-model dataset
Built using Ultralytics YOLOv8
Dataset hosted on Roboflow Universe

License

This model is released under the MIT License. Please also respect the license terms of the original dataset.