# carpedm20/DCGAN-tensorflow

A tensorflow implementation of "Deep Convolutional Generative Adversarial Networks"

Repository: https://github.com/carpedm20/DCGAN-tensorflow
Canonical: https://ross.abutalabs.com/products/dcgan-tensorflow
Homepage: http://carpedm20.github.io/faces/
Language: JavaScript
License: MIT
License Family: permissive
Topics: tensorflow, dcgan, gan, generative-model
Last push: 2021-01-06T05:38:06+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": 3919, "days_push": 2065, "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 7177, forks 2581 (observed 2026-08-28T04:09:56.427919+00:00)

## What it is
A TensorFlow implementation of Deep Convolutional Generative Adversarial Networks (DCGAN) for generating images such as faces and digits. It includes training scripts, dataset download helpers, and support for custom image datasets.

## Use cases
- generate realistic face images with a gan
- train a dcgan on my own image dataset
- reproduce the dcgan paper in tensorflow
- generate handwritten mnist digits with a gan
- learn how generative adversarial networks are implemented
- create ai-generated profile pictures

## When to choose
- you want a simple, well-known reference implementation of DCGAN
- you are studying or teaching how GANs work from readable code
- you need to train an image generator on MNIST, CelebA, or a custom image folder

## When to avoid
- you need modern TensorFlow 2.x or PyTorch support - the code targets TensorFlow 0.12
- you need production-grade, actively maintained GAN tooling
- you want the latest GAN architectures beyond DCGAN

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

## Member repositories
- carpedm20/DCGAN-tensorflow (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:56.427919+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 2026-08-29T17:39:55.806023+00:00, confidence not recorded.
  - readme: https://github.com/carpedm20/DCGAN-tensorflow (fetched 2026-08-28T04:09:56.427919+00:00, sha 59ab442fa8f7)
  - homepage: http://carpedm20.github.io/faces/ (fetched 2026-08-29T08:35:25.420755+00:00, sha 3aa7c7fc80c7)
- Data as of 2026-08-30T08:39:29.467469+00:00.