# bearpaw/pytorch-classification

Classification with PyTorch.

Repository: https://github.com/bearpaw/pytorch-classification
Canonical: https://ross.abutalabs.com/products/pytorch-classification
Language: Python
License: MIT
License Family: permissive
Topics: classification, cifar10, cifar100, imagenet, pytorch, resnet, resnext, wide-residual-networks, wrn, densenet, preresnet
Last push: 2024-06-18T02:36:02+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3402, "days_push": 807, "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 1738, forks 555 (observed 2026-08-28T04:05:29.997092+00:00)

## What it is
A PyTorch library providing a unified interface for training image classification models on CIFAR-10/100 and ImageNet. It includes implementations of popular architectures like ResNet, PreResNet, Wide ResNet, ResNeXt, and DenseNet, with pretrained models and training logs.

## Use cases
- train a resnet on cifar-10
- benchmark wide residual networks on cifar-100
- train densenet on imagenet
- get pretrained classification models for pytorch
- compare image classification architectures
- reproduce resnext training results

## When to choose
- you need a unified codebase to train and compare many CNN architectures on CIFAR or ImageNet
- you want reference accuracy numbers and pretrained checkpoints for classic vision models

## When to avoid
- you need modern vision transformers or the latest architectures
- you want a maintained production inference library rather than research training code

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

## Member repositories
- bearpaw/pytorch-classification (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:29.997092+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 2026-08-30T03:30:35.770004+00:00, confidence not recorded.
  - readme: https://github.com/bearpaw/pytorch-classification (fetched 2026-08-28T04:05:29.997092+00:00, sha cc10c11a2288)
- Data as of 2026-08-30T08:39:29.467469+00:00.