# hysts/pytorch_image_classification

PyTorch implementation of image classification models for CIFAR-10/CIFAR-100/MNIST/FashionMNIST/Kuzushiji-MNIST/ImageNet

Repository: https://github.com/hysts/pytorch_image_classification
Canonical: https://ross.abutalabs.com/products/pytorch_image_classification
Language: Python
License: MIT
License Family: permissive
Topics: pytorch, computer-vision, cifar10, fashion-mnist, imagenet
Archived: true
Last push: 2021-12-12T18:03:27+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3189, "days_push": 1725, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1449, forks 307 (observed 2026-08-28T04:04:45.631385+00:00)

## What it is
A PyTorch library implementing many image classification architectures (ResNet, DenseNet, WRN, PyramidNet, SENet, etc.) and augmentation techniques (Cutout, Mixup, CutMix) with training configs for CIFAR, MNIST variants, and ImageNet. It reproduces paper results with reported benchmarks.

## Use cases
- train image classification models on CIFAR-10
- reproduce results from ResNet or DenseNet papers
- benchmark data augmentation methods like Mixup and CutMix
- get baseline training code for ImageNet classification
- compare model architectures on MNIST datasets

## When to choose
- you need faithful PyTorch reproductions of classic classification papers
- you want ready-made configs and benchmark numbers for CIFAR/ImageNet experiments

## When to avoid
- you need production inference or deployment tooling
- you want actively maintained support for the latest architectures or Windows

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, computer-vision, benchmarking
- domain: computer-vision, deep-learning, image-processing, machine-learning
- platform: python
- tags: pytorch, image-classification, resnet, densenet, cifar10, imagenet, data-augmentation, research-reproducibility, linux, gpu

## Member repositories
- hysts/pytorch_image_classification (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:45.631385+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 2026-08-30T04:36:00.191972+00:00, confidence not recorded.
  - readme: https://github.com/hysts/pytorch_image_classification (fetched 2026-08-28T04:04:45.631385+00:00, sha 3352669f4f93)
- Data as of 2026-08-30T08:39:29.467469+00:00.