# tjwei/GANotebooks

wgan, wgan2(improved, gp), infogan, and dcgan implementation in  lasagne, keras, pytorch

Repository: https://github.com/tjwei/GANotebooks
Canonical: https://ross.abutalabs.com/products/ganotebooks
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: wgan, wgan-gp, infogan, lasagne, keras, pytorch, tensorflow, pix2pix, dcgan, dragan, cyclegan
Last push: 2018-02-11T07:24:06+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": 3554, "days_push": 3125, "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 1484, forks 362 (observed 2026-08-28T04:04:51.285650+00:00)

## What it is
A collection of Jupyter notebook implementations of generative adversarial networks, including WGAN, improved WGAN-GP, InfoGAN, DCGAN, CycleGAN, pix2pix, and DRAGAN, written in Lasagne, Keras, and PyTorch. It serves as educational reference code with sample results for image-to-image translation and image generation tasks.

## Use cases
- learn how GANs are implemented from scratch
- study WGAN and WGAN-GP implementations
- understand InfoGAN on MNIST
- implement pix2pix image-to-image translation
- run CycleGAN for unpaired image translation
- compare GAN implementations across Keras, Lasagne, and PyTorch
- generate anime faces with a GAN

## When to choose
- you want readable notebook-style reference implementations of classic GAN variants
- you are learning generative adversarial networks and want to see multiple frameworks side by side
- you need example code for WGAN, InfoGAN, CycleGAN, or pix2pix

## When to avoid
- you need a maintained production-ready GAN library
- you want modern architectures like diffusion models or StyleGAN
- you require support for recent versions of TensorFlow, Keras, or PyTorch
- you need documentation beyond the notebooks themselves

## Facets
- artifact type: learning-resource
- maturity: abandoned
- function: machine-learning, deep-learning, image-processing
- domain: deep-learning, machine-learning, image-processing
- platform: python
- tags: gan, wgan, wgan-gp, infogan, dcgan, cyclegan, pix2pix, dragan, keras, lasagne, pytorch, jupyter-notebooks, generative-models, gpu

## Member repositories
- tjwei/GANotebooks (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:51.285650+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 2026-08-30T04:34:01.218820+00:00, confidence not recorded.
  - readme: https://github.com/tjwei/GANotebooks (fetched 2026-08-28T04:04:51.285650+00:00, sha 2b2969031629)
- Data as of 2026-08-30T08:39:29.467469+00:00.