# AntixK/PyTorch-VAE

A Collection of Variational Autoencoders (VAE) in PyTorch.

Repository: https://github.com/AntixK/PyTorch-VAE
Canonical: https://ross.abutalabs.com/products/pytorch-vae
Language: Python
License: Apache-2.0
License Family: permissive
Topics: pytorch, pytorch-implementation, vae, vae-implementation, deep-learning, reproducible-research, paper-implementations, pytorch-vae, variational-autoencoders, architecture, beta-vae, vqvae, gumbel-softmax, celeba-dataset, iwae, wae, dfc-vae
Last push: 2025-03-21T22:00:34+00:00

## Health v2 (maintenance only)
Score: 38/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 12, release rhythm 35, longevity 100
- inputs: {"age_days": 2427, "days_push": 530, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7665, forks 1182 (observed 2026-08-28T04:10:02.267761+00:00)

## What it is
A collection of Variational Autoencoder (VAE) model implementations in PyTorch, including Beta-VAE, VQ-VAE, IWAE, WAE, and others, with a focus on reproducibility. All models are trained on the CelebA dataset for consistent comparison and use PyTorch Lightning for training.

## Use cases
- implement a VAE in pytorch
- compare different variational autoencoder architectures
- reproduce results from VAE papers
- learn how VQ-VAE or Beta-VAE works
- train a VAE on CelebA faces
- get reference code for a latent variable generative model

## When to choose
- you want clean, comparable reference implementations of many VAE variants
- you are doing research or studying generative latent-variable models
- you want a simple starting point to modify a VAE architecture

## When to avoid
- you need a production-ready or actively maintained generative modeling framework
- you want to train on datasets other than CelebA without adapting configs
- you need the latest VAE research beyond the included models

## Facets
- artifact type: library
- maturity: maintenance
- function: deep-learning, machine-learning, image-processing
- domain: deep-learning, machine-learning, image-processing
- platform: python
- tags: variational-autoencoder, pytorch-lightning, paper-implementations, generative-models, celeba, gpu

## Member repositories
- AntixK/PyTorch-VAE (main) score 38

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:02.267761+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:36:04.494861+00:00, confidence not recorded.
  - readme: https://github.com/AntixK/PyTorch-VAE (fetched 2026-08-28T04:10:02.267761+00:00, sha f8c414031536)
- Data as of 2026-08-30T08:39:29.467469+00:00.