Helper Module for Deep Learning.

API documentation of pynet.models.vae¶

Module that privides common variational networks.

pynet.models.vae.distributions	Common distributions.
pynet.models.vae.mcvae	Sparse Multi-Channel Variational Autoencoderfor the Joint Analysis of Heterogeneous Data.
pynet.models.vae.utils	Module containing VAE utilities. Code: https://github.com/YannDubs/disentangling-vae
pynet.models.vae.vae	Variational Auto-Encoder (VAE).
pynet.models.vae.moevae	Mixture of Experts VAE with similarity constraint: MoE-Sim-VAE. Reference: Mixture-of-Experts Variational Autoencoder for Clustering and Generating from Similarity-Based Representations on Single Cell Data, Andreas Kopf, arXiv 2020.
pynet.models.vae.vade	Variational Deep Embedding (VaDE).
pynet.models.vae.gmvae	Gaussian Mixture Variational Auto-Encoder (GMVAE). Two implementations are proposed: VAEGMP is an adaptation of VAE to make use of a Gaussian Mixture prior, instead of a standard Normal distribution. GMVAE is an attempt to replicate the work described in [1] and [2] [1] Gaussian Mixture VAE: Lessons in Variational Inference, Generative Models, and Deep Nets: http://ruishu.io/2016/12/25/gmvae [2] Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders Nat Dilokthanakul, arXiv 2017. Code: https://github.com/jariasf/GMVAE Code: https://github.com/mazrk7/gmvae
pynet.models.vae.pmvae	Pathway Modules Variational Auto-Encoder (pmVAE). [1] pmVAE: Learning Interpretable Single-Cell Representations with Pathway Modules, Gilles Gut, biorxiv 2021. Code: https://github.com/ratschlab/pmvae