# goodfeli/adversarial

Code and hyperparameters for the paper "Generative Adversarial Networks"

Repository: https://github.com/goodfeli/adversarial
Canonical: https://ross.abutalabs.com/products/adversarial
Language: Python
License: BSD-3-Clause
License Family: permissive
Last push: 2020-05-25T03:31:19+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 4468, "days_push": 2291, "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 4078, forks 1098 (observed 2026-08-28T04:08:34.377222+00:00)

## What it is
Reference implementation of the original 2014 'Generative Adversarial Networks' paper by Goodfellow et al., containing training code, YAML configs, and hyperparameters built on Theano and Pylearn2. It is academic research code with no support, unit tests, or maintenance.

## Use cases
- reproduce the original GAN paper experiments
- study the first GAN implementation and its hyperparameters
- compare modern GAN implementations against the original
- learn how GANs were trained in 2014 with Theano and Pylearn2
- estimate model log-likelihood with the Parzen density technique

## When to choose
- you need the exact original GAN code and hyperparameters for citation or historical study
- you are doing research on the provenance or reproduction of the original GAN paper

## When to avoid
- you want to train GANs in production or on modern hardware
- you need maintained, documented, or tested software
- your project uses PyTorch, TensorFlow, or JAX instead of Theano and Pylearn2

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning, artificial-intelligence
- platform: python
- tags: generative-adversarial-networks, gan, research-code, theano, pylearn2, reference-implementation, gpu

## Member repositories
- goodfeli/adversarial (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:34.377222+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 2026-08-29T18:23:26.685410+00:00, confidence not recorded.
  - readme: https://github.com/goodfeli/adversarial (fetched 2026-08-28T04:08:34.377222+00:00, sha d5e1d8455172)
- Data as of 2026-08-30T08:39:29.467469+00:00.