# wiseodd/generative-models

Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.

Repository: https://github.com/wiseodd/generative-models
Canonical: https://ross.abutalabs.com/products/wiseodd-generative-models
Homepage: http://wiseodd.github.io
Language: Python
License: Unlicense
License Family: permissive
Topics: vae, gan, pytorch, tensorflow, generative-model, machine-learning, rbm, restricted-boltzmann-machine
Last push: 2024-03-24T20:38:46+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3556, "days_push": 892, "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 7494, forks 2009 (observed 2026-08-28T04:10:00.312100+00:00)

## What it is
A collection of reference implementations of generative models including GANs, VAEs, RBMs, and Helmholtz machines in PyTorch and TensorFlow. It serves primarily as an educational resource with implementations of many GAN and VAE paper variants.

## Use cases
- learn how GANs work by reading clean implementations
- study VAE variants like conditional and denoising VAE
- compare GAN implementations in PyTorch and TensorFlow
- implement restricted Boltzmann machines with contrastive divergence
- reproduce classic generative model papers
- find a starting point for a custom GAN project

## When to choose
- you want readable, minimal implementations of classic generative models
- you are learning GANs or VAEs from a research/educational angle
- you need reference code for RBMs or the Helmholtz machine

## When to avoid
- you need a production-ready generative model library with training utilities
- you want modern architectures like diffusion models or transformers
- you need maintained, tested code with active support

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning, artificial-intelligence
- platform: python
- tags: gan, vae, rbm, pytorch, tensorflow, generative-models, educational

## Member repositories
- wiseodd/generative-models (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:00.312100+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 2026-08-29T17:37:34.233877+00:00, confidence not recorded.
  - readme: https://github.com/wiseodd/generative-models (fetched 2026-08-28T04:10:00.312100+00:00, sha 69b54cdf5b7d)
- Data as of 2026-08-30T08:39:29.467469+00:00.