piVAE is a variational autoencoder, which learns a lower dimensional embeddings of function classes facilitating the encoding of stochastic priors.
This repository only contains the rebuild code basis for a piVAE. The concept and idea was taken from the Arxiv preprint (Mishra, Swapnil, Seth Flaxman, and Samir Bhatt. "$\pi $ VAE: Encoding stochastic process priors with variational autoencoders." arXiv preprint arXiv:2002.06873 (2020).), which can be found under the following link: https://arxiv.org/pdf/2002.06873.pdf.
This repository is an on-going project and there is no warranty for proper functioning.
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.