# Newmu/dcgan_code

Deep Convolutional Generative Adversarial Networks

Repository: https://github.com/Newmu/dcgan_code
Canonical: https://ross.abutalabs.com/products/dcgan_code
Language: Python
License: MIT
License Family: permissive
Last push: 2019-05-08T17:50:59+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": 3936, "days_push": 2674, "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 3527, forks 689 (observed 2026-08-28T04:08:08.738128+00:00)

## What it is
Reference implementation of the DCGAN paper (Unsupervised Representation Learning with Deep Convolutional GANs) in Python. It trains convolutional generators and discriminators to synthesize images such as LSUN bedrooms and demonstrates latent-space arithmetic.

## Use cases
- train a dcgan to generate images
- reproduce the dcgan paper results
- learn how generative adversarial networks work
- generate synthetic bedroom images from lsun
- explore latent space interpolation and vector arithmetic
- use a discriminator as pretrained features for classification

## When to choose
- you want the original reference code accompanying the DCGAN paper
- you are studying historical GAN architectures and research code
- you need a minimal educational example of convolutional GAN training

## When to avoid
- you need a maintained, production-ready GAN framework
- you want modern PyTorch or TensorFlow implementations with GPU optimizations
- you need support, documentation, or recent updates - the repo is unmaintained

## Facets
- artifact type: library
- maturity: abandoned
- function: deep-learning, machine-learning, image-processing, data-generation
- domain: deep-learning, machine-learning, image-processing, artificial-intelligence
- platform: python
- tags: gan, dcgan, generative-models, research-code, theano, unsupervised-learning

## Member repositories
- Newmu/dcgan_code (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:08.738128+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 2026-08-29T18:35:09.287465+00:00, confidence not recorded.
  - readme: https://github.com/Newmu/dcgan_code (fetched 2026-08-28T04:08:08.738128+00:00, sha 6dca1f7b8cc2)
- Data as of 2026-08-30T08:39:29.467469+00:00.