# akamaster/pytorch_resnet_cifar10

Proper implementation of ResNet-s for CIFAR10/100 in pytorch that matches description of the original paper.

Repository: https://github.com/akamaster/pytorch_resnet_cifar10
Canonical: https://ross.abutalabs.com/products/pytorch_resnet_cifar10
Language: Python
License: BSD-2-Clause
License Family: permissive
Topics: resnet, resnet20, resnet32, resnet44, resnet56, resnet110, resnet1202, pytorch, resnet-cifar, cifar, torchvision-models-cifar
Last push: 2024-06-18T20:29:09+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": 3152, "days_push": 806, "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 1368, forks 341 (observed 2026-08-28T04:04:31.555233+00:00)

## What it is
A PyTorch implementation of ResNet architectures (ResNet20 through ResNet1202) for CIFAR10/CIFAR100 that faithfully matches the original paper's specifications, unlike torchvision's ImageNet-oriented models. It includes pretrained models with test errors matching or beating the paper's reported results.

## Use cases
- train resnet on cifar10 matching the original paper
- download pretrained resnet20 resnet56 for cifar10
- compare my model against paper-accurate resnet baselines on cifar
- get proper resnet implementation for cifar100 in pytorch
- reproduce resnet paper results

## When to choose
- You need paper-faithful ResNet baselines on CIFAR10/100 for fair comparison
- You want pretrained CIFAR ResNet checkpoints
- You need small ResNet variants like ResNet20 not available in torchvision

## When to avoid
- You need ResNets for ImageNet or other datasets
- You want modern architectures or training recipes
- You need validation-split-based model selection as in the paper

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: deep-learning, computer-vision, image-processing
- platform: python
- tags: resnet, cifar10, cifar100, pytorch, pretrained-models, image-classification, gpu

## Member repositories
- akamaster/pytorch_resnet_cifar10 (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:31.555233+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 2026-08-30T04:41:02.599357+00:00, confidence not recorded.
  - readme: https://github.com/akamaster/pytorch_resnet_cifar10 (fetched 2026-08-28T04:04:31.555233+00:00, sha 521b7d7a7afe)
- Data as of 2026-08-30T08:39:29.467469+00:00.