Hyperbolic learning tutorial code

Code for the tutorial "Hyperbolic Learning in Action" at AMLD 2025.

Usage

Environment

To facilitate environment setup, it is strongly recommeded to run the tutorial on Google Colab or Kaggle. If you wish to execute the code locally, you are welcome to do so, but it will be impossible to provide individual support for everyone during the tutorial.

Local installation

Using a clean virtual environment is highly recommended.

The HypLL library used in this tutorial requires python>=3.10. Lower python versions may seem to work at first, but could lead to unexpected errors in the last part of the tutorial.

1. Open a shell and clone the repository

   git clone https://github.com/Digital-Dermatology/hyperbolic-learning-tutorial-code.git
   

2. Change directory to within the repository

   cd hyperbolic-learning-tutorial-code
   

3. Install jupyter-lab if needed, e.g. with pip

   pip install --upgrade pip jupyterlab
   

4. [Optional] Requirements can be installed directly from the notebook or prior to opening it, e.g. with

   pip install -r requirements.txt
   

5. Open a notebook engine such as jupyter-lab

   jupyter-lab
   

6. Select the notebooks folder and open tutorial.ipynb.
7. Follow the instructions and enjoy.