A replication of "SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows", implemented as the final project for the "Generative Neural Networks" class of the University of Heidelberg, 2024.
The repository contains the following:
├── assets # relevant PDFs
├── report # source code for the report
├── notebooks # Jupyter notebooks
├── saves # save states for MNIST
└── survae # source code
- install the requirements (
pip install -r requirements.txt
) - open and run any notebook in
notebooks/
To run all of the tests, use the following command:
python3 -m survae.test