# aaron-xichen/pytorch-playground

Base pretrained models and datasets in pytorch (MNIST, SVHN, CIFAR10, CIFAR100, STL10, AlexNet, VGG16, VGG19, ResNet, Inception, SqueezeNet)

Repository: https://github.com/aaron-xichen/pytorch-playground
Canonical: https://ross.abutalabs.com/products/pytorch-playground
Language: Python
License: MIT
License Family: permissive
Topics: pytorch-tutorial, pytorch-tutorials, pytorch, quantization
Last push: 2022-11-22T04:06:41+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": 3414, "days_push": 1380, "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 2716, forks 619 (observed 2026-08-28T04:07:12.114734+00:00)

## What it is
A PyTorch playground providing pretrained models and dataset loaders for popular benchmarks like MNIST, SVHN, CIFAR10/100, STL10, and ImageNet architectures (AlexNet, VGG, ResNet, Inception, SqueezeNet). It also includes a demo for quantizing models to lower bit-widths using linear, minmax, and non-linear methods.

## Use cases
- learn pytorch with pretrained models on mnist and cifar
- download pretrained models for image classification benchmarks
- quantize a model to 8-bit or lower precision
- train an mlp on mnist as a pytorch beginner
- evaluate quantization accuracy tradeoffs on standard datasets
- set up a quick imagenet validation pipeline

## When to choose
- you are a pytorch beginner wanting ready-made models and dataset loaders
- you need pretrained checkpoints for small vision benchmarks
- you want to experiment with low-bit quantization methods

## When to avoid
- you need production-grade training frameworks or modern architectures like transformers
- you require actively maintained code with recent pytorch compatibility
- you work outside image classification domains

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning, benchmarking, data-science
- domain: deep-learning, machine-learning, computer-vision, tutorials
- platform: python, cross-platform
- tags: pytorch, pretrained-models, quantization, image-classification, mnist, cifar, tutorial, model-zoo, gpu

## Member repositories
- aaron-xichen/pytorch-playground (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:12.114734+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 2026-08-30T02:15:21.493169+00:00, confidence not recorded.
  - readme: https://github.com/aaron-xichen/pytorch-playground (fetched 2026-08-28T04:07:12.114734+00:00, sha 4a78fe414471)
- Data as of 2026-08-30T08:39:29.467469+00:00.