# openai/InfoGAN

Code for reproducing key results in the paper "InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets"

Repository: https://github.com/openai/InfoGAN
Canonical: https://ross.abutalabs.com/products/infogan
Homepage: https://arxiv.org/abs/1606.03657
Language: Python
License Family: other
Topics: paper
Archived: true
Last push: 2021-03-25T08:17:44+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3744, "days_push": 1987, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1069, forks 301 (observed 2026-08-28T04:03:27.778206+00:00)

## What it is
Official research code from OpenAI for reproducing results of the InfoGAN paper, an information-theoretic extension to GANs that learns disentangled representations in an unsupervised manner. It includes an MNIST experiment launcher built on an old dev version of TensorFlow.

## Use cases
- reproduce InfoGAN paper results on MNIST
- study unsupervised disentangled representation learning
- explore GAN variants with mutual information objectives
- reference implementation of information-maximizing GANs
- learn how research GAN code is structured in TensorFlow

## When to choose
- you need the exact reference implementation of the InfoGAN paper
- you are studying or extending the original InfoGAN method
- you want historical research code for academic citation or comparison

## When to avoid
- you need a maintained, production-ready GAN library
- you want to run on modern TensorFlow or PyTorch versions
- you need a permissively licensed codebase (no license is provided)
- you want to train on datasets beyond the provided MNIST example without significant rework

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning, artificial-intelligence
- platform: python
- tags: gan, infogan, research-code, paper-reproduction, tensorflow, unsupervised-learning, representation-learning, archived, docker

## Member repositories
- openai/InfoGAN (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:27.778206+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 2026-08-30T06:54:36.048850+00:00, confidence not recorded.
  - readme: https://github.com/openai/InfoGAN (fetched 2026-08-28T04:03:27.778206+00:00, sha 9e8d2f4abdfb)
  - homepage: https://arxiv.org/abs/1606.03657 (fetched 2026-08-29T12:56:57.798223+00:00, sha c4f44cc80237)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T12:56:57.810869+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T12:56:57.807342+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T12:56:57.812819+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T12:56:57.809166+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.