👓 Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLO 👓

💻 Blog by Jack Clark |📜 Paper

Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLO
Julian Moosmann ¹, [🧑🏻‍🚀 Pietro Bonazzi](https://linkedin.com/in/pietrobonazzi)¹, Yawei Li¹, Sizhen Bian ¹, Philipp Mayer¹ , Luca Benini ¹ , Michele Magno¹

¹ ETH Zurich, Switzerland

✉️ Citation ❤️

Our codebase is based on Ultralytics. If you find our work useful please use this citation :

@misc{moosmann2023ultraefficient,
      title={Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLO}, 
      author={Julian Moosmann* and Pietro Bonazzi* and Yawei Li and Sizhen Bian and Philipp Mayer and Luca Benini and Michele Magno},
      year={2023},
      eprint={2311.01057},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

🚀 TL;DR quickstart 🚀

Create the environment

Create the environment:

python3.10 -m venv venv
source venv/bin/activate
pip install torch==2.0.0+cu117 torchvision==0.15.1+cu117 torchaudio==2.0.1 --index-url https://download.pytorch.org/whl/cu117 
pip install -r requirements.txt 

Training & Evaluation

python a_train_export.py