EVDAD

An EVent-Driven Anomaly Detection for Spiking Neural Networks.

Getting Started

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.

Prerequisites

• Python 3.10
• CUDA 12.3 or 12.5

Installing

A step by step series of examples that tell you how to get a development env running.

[Linux]

Clone the repo and create virtual environment.

cd $HOME
git clone git@github.com:Piotr45/evdad.git evdad
cd evdad
python -m venv evdad-venv
source evdad-venv/bin/activate

Install EVDAD and requirements via pyproject.toml.

pip install -e .
hash -r

Running the tests

pytest --cov=evdad tests/unit --cov-fail-under=35

Tutorials

• End to end training tutorials
• Inference Tutorial

Built With

• LAVA - The SNN training framework
• Hydra - Used for configs
• MLflow - Used to track training

Contributing

Please read CONTRIBUTING.md for details on our code of conduct, and the process for submitting pull requests to us.

Versioning

We use SemVer for versioning. For the versions available, see the tags on this repository.

Authors

• Piotr Baryczkowski - Initial work, framework maintenance - Piotr45

License

This project is licensed under the MIT License - see the LICENSE.md file for details

Acknowledgments

• Hat tip to creators of V2E and LAVA.