# szagoruyko/wide-residual-networks

3.8% and 18.3% on CIFAR-10 and CIFAR-100

Repository: https://github.com/szagoruyko/wide-residual-networks
Canonical: https://ross.abutalabs.com/products/wide-residual-networks
Homepage: http://arxiv.org/abs/1605.07146
Language: Lua
License: BSD-2-Clause
License Family: permissive
Last push: 2019-08-20T08:37:42+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": 3760, "days_push": 2570, "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 1315, forks 301 (observed 2026-08-28T04:04:20.600417+00:00)

## What it is
Reference implementation of Wide Residual Networks (WRN), a ResNet variant that trades depth for width to train faster and achieve state-of-the-art CIFAR, SVHN, COCO, and ImageNet results. Written in Lua for the Torch framework, with pretrained models later integrated into torchvision.

## Use cases
- train wide residual networks on CIFAR-10 and CIFAR-100
- reproduce BMVC 2016 WRN paper results
- get a faster alternative to very deep ResNets for image classification
- benchmark new architectures against WRN baselines
- load pretrained WRN ImageNet models via PyTorch Hub

## When to choose
- you need the original WRN training code for research reproduction
- you want a strong, fast image classification baseline on CIFAR/SVHN
- you are studying residual network architecture design

## When to avoid
- you need actively maintained code - the repo is legacy Torch/Lua and no longer developed
- you want pretrained WRNs in a modern framework - use torchvision's wide_resnet50_2 instead
- you need production deployment tooling

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing
- domain: deep-learning, computer-vision, machine-learning
- platform: lua
- tags: residual-networks, cifar, torch, research-code, image-classification, gpu

## Member repositories
- szagoruyko/wide-residual-networks (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:20.600417+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 2026-08-30T04:48:43.595986+00:00, confidence not recorded.
  - readme: https://github.com/szagoruyko/wide-residual-networks (fetched 2026-08-28T04:04:20.600417+00:00, sha 71c6763c2d53)
  - homepage: http://arxiv.org/abs/1605.07146 (fetched 2026-08-29T12:07:16.389051+00:00, sha e7352f94da47)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T12:07:16.398519+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T12:07:16.402347+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T12:07:16.404468+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T12:07:16.400410+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.