# mit-han-lab/gan-compression

[CVPR 2020] GAN Compression: Efficient Architectures for Interactive Conditional GANs

Repository: https://github.com/mit-han-lab/gan-compression
Canonical: https://ross.abutalabs.com/products/gan-compression
Language: Python
License: NOASSERTION
License Family: other
Topics: compression, gans, conditional-gans, pix2pix, cyclegan, gaugan, pytorch, image-to-image-translation
Last push: 2024-06-05T21:59:17+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2373, "days_push": 819, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1115, forks 149 (observed 2026-08-28T04:03:38.350703+00:00)

## What it is
A PyTorch research codebase implementing GAN Compression, a CVPR 2020 method that reduces the computation of conditional GANs like pix2pix, CycleGAN, MUNIT, and GauGAN by 9-29x via once-for-all distillation and architecture search. It includes pretrained models, training/test scripts, Colab notebooks, and an interactive demo targeting edge devices like Jetson Nano.

## Use cases
- compress a pretrained pix2pix or CycleGAN generator for faster inference
- run image-to-image translation models on edge devices like Jetson Nano
- distill a smaller student GAN from a large teacher generator
- search for efficient sub-generators under a FID or compute budget
- reproduce the GAN Compression paper results
- speed up GauGAN for interactive synthesis

## When to choose
- you need to shrink conditional GAN models for real-time or embedded deployment
- you want a research baseline for GAN distillation and once-for-all network compression
- you work with pix2pix, CycleGAN, MUNIT, or GauGAN in PyTorch

## When to avoid
- you need production-supported, well-maintained software with a permissive license
- you want to compress non-GAN models like classifiers or LLMs
- you need Windows or macOS support, since it targets Linux with GPUs

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, image-processing, deep-learning
- domain: machine-learning, computer-vision, image-processing
- platform: python
- tags: gan-compression, model-compression, knowledge-distillation, neural-architecture-search, pix2pix, cyclegan, pytorch, research-code, cvpr-2020, research, linux, gpu

## Member repositories
- mit-han-lab/gan-compression (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:38.350703+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 2026-08-30T06:42:11.416909+00:00, confidence not recorded.
  - readme: https://github.com/mit-han-lab/gan-compression (fetched 2026-08-28T04:03:38.350703+00:00, sha d95e0de314fc)
- Data as of 2026-08-30T08:39:29.467469+00:00.