# ajbrock/BigGAN-PyTorch

The author's officially unofficial PyTorch BigGAN implementation.

Repository: https://github.com/ajbrock/BigGAN-PyTorch
Canonical: https://ross.abutalabs.com/products/biggan-pytorch
Language: Python
License: MIT
License Family: permissive
Topics: biggan, pytorch, deep-learning, neural-networks, gans, dogball
Last push: 2023-07-19T17:08:51+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": 2782, "days_push": 1141, "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 2923, forks 488 (observed 2026-08-28T04:07:30.317340+00:00)

## What it is
A PyTorch implementation of BigGAN for large-scale high-fidelity image synthesis, written by the paper's first author. It supports multi-GPU training with gradient accumulation, FID evaluation, and pretrained model sampling.

## Use cases
- train a BigGAN on ImageNet
- generate high-fidelity images with a GAN
- reproduce BigGAN paper results in PyTorch
- sample images from pretrained BigGAN weights
- compute FID metrics for GAN evaluation
- experiment with truncation and latent interpolations

## When to choose
- you need a faithful BigGAN implementation for research
- you have multiple GPUs and want to train large-scale GANs
- you want pretrained BigGAN weights for sampling or fine-tuning

## When to avoid
- you need a maintained, up-to-date framework (code targets PyTorch 1.0.1)
- you want simple, single-GPU GAN training
- you need a general-purpose generative model library rather than BigGAN specifically

## Facets
- artifact type: library
- maturity: maintenance
- function: deep-learning, machine-learning, image-processing, gpu-computing
- domain: deep-learning, machine-learning, image-processing
- platform: python
- tags: gan, biggan, pytorch, image-synthesis, generative-models, research-code, gpu, linux

## Member repositories
- ajbrock/BigGAN-PyTorch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:30.317340+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 2026-08-30T07:33:44.603551+00:00, confidence not recorded.
  - readme: https://github.com/ajbrock/BigGAN-PyTorch (fetched 2026-08-28T04:07:30.317340+00:00, sha 6d4afeaca629)
- Data as of 2026-08-30T08:39:29.467469+00:00.