# kuangliu/pytorch-cifar

95.47% on CIFAR10 with PyTorch

Repository: https://github.com/kuangliu/pytorch-cifar
Canonical: https://ross.abutalabs.com/products/pytorch-cifar
Language: Python
License: MIT
License Family: permissive
Topics: pytorch
Last push: 2023-02-24T10:06:53+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": 3511, "days_push": 1286, "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 6423, forks 2167 (observed 2026-08-28T04:09:43.342092+00:00)

## What it is
A PyTorch reference repository for training image classification models on the CIFAR10 dataset, with implementations of many popular architectures like ResNet, DenseNet, and DLA. It serves as a well-known baseline benchmark achieving up to 95.47% accuracy.

## Use cases
- train image classifiers on cifar10 with pytorch
- compare accuracy of different cnn architectures
- learn how to implement resnet in pytorch
- get a baseline for image classification experiments
- find reference pytorch model implementations

## When to choose
- you want clean, minimal PyTorch implementations of common CNN architectures
- you need CIFAR10 accuracy baselines for research comparisons
- you are learning PyTorch image classification

## When to avoid
- you need production-grade training pipelines with distributed training or experiment tracking
- you need datasets other than CIFAR10
- you need the latest training techniques like mixup or modern optimizers

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning, benchmarking
- domain: deep-learning, computer-vision, image-processing, tutorials
- platform: python, cross-platform
- tags: pytorch, cifar10, image-classification, model-zoo, reference-implementation, gpu

## Member repositories
- kuangliu/pytorch-cifar (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:43.342092+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 2026-08-29T17:44:53.585064+00:00, confidence not recorded.
  - readme: https://github.com/kuangliu/pytorch-cifar (fetched 2026-08-28T04:09:43.342092+00:00, sha 5e6cbde3f442)
- Data as of 2026-08-30T08:39:29.467469+00:00.