# pfnet-research/sngan_projection

GANs with spectral normalization and projection discriminator

Repository: https://github.com/pfnet-research/sngan_projection
Canonical: https://ross.abutalabs.com/products/sngan_projection
Language: Python
License: NOASSERTION
License Family: other
Last push: 2019-11-12T07:23:14+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": 3134, "days_push": 2486, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1103, forks 201 (observed 2026-08-28T04:03:36.074508+00:00)

## What it is
Official Chainer implementation of GANs using spectral normalization and projection discriminators for conditional image generation on ImageNet. It includes training scripts, preprocessing utilities, and pretrained models from the associated ICLR 2018 papers.

## Use cases
- train a conditional GAN on ImageNet
- reproduce SNGAN and projection cGAN paper results
- generate class-conditional images with pretrained models
- study spectral normalization implementations
- interpolate between image categories with a GAN

## When to choose
- you need the reference implementation of spectral normalization or projection discriminator GANs
- you want to reproduce the ICLR 2018 SNGAN/cGAN paper experiments
- you work with Chainer and want pretrained ImageNet GAN models

## When to avoid
- you need PyTorch or TensorFlow implementations
- you want actively maintained code for production use
- you lack a GPU or the ImageNet dataset

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing
- domain: machine-learning, deep-learning, computer-vision, image-processing
- platform: python
- tags: gan, spectral-normalization, projection-discriminator, chainer, conditional-generation, imagenet, research-code, gpu, linux

## Member repositories
- pfnet-research/sngan_projection (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:36.074508+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 2026-08-30T06:45:34.152840+00:00, confidence not recorded.
  - readme: https://github.com/pfnet-research/sngan_projection (fetched 2026-08-28T04:03:36.074508+00:00, sha cf296de7f5d1)
- Data as of 2026-08-30T08:39:29.467469+00:00.