An extension of the PyTorch library containing various tools for performing deep learning in hyperbolic space.
Contents:
Visit our documentation for tutorials and more.
The Hyperbolic Learning Library was written for Python 3.10+ and PyTorch 1.11+.
It's recommended to have a working PyTorch installation before setting up HypLL:
- PyTorch installation instructions.
Start by setting up a Python virtual environment:
python -venv .env
Activate the virtual environment on Linux and MacOs:
source .env/bin/activate
Or on Windows:
.env/Scripts/activate
Finally, install HypLL from PyPI.
pip install hypll
If you would like to cite this project, please use the following bibtex entry
@article{spengler2023hypll,
title={HypLL: The Hyperbolic Learning Library},
author={van Spengler, Max and Wirth, Philipp and Mettes, Pascal},
journal={arXiv preprint arXiv:2306.06154},
year={2023}
}