# jcjohnson/pytorch-examples

Simple examples to introduce PyTorch

Repository: https://github.com/jcjohnson/pytorch-examples
Canonical: https://ross.abutalabs.com/products/pytorch-examples
Language: Python
License: MIT
License Family: permissive
Last push: 2022-02-20T08:38:11+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": 3509, "days_push": 1655, "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 4906, forks 920 (observed 2026-08-28T04:09:02.233160+00:00)

## What it is
A collection of self-contained Python examples that introduce PyTorch fundamentals, from numpy baselines to tensors, autograd, nn modules, and custom modules. It teaches core concepts using a simple fully-connected ReLU network trained with gradient descent.

## Use cases
- learn pytorch basics
- understand how autograd works
- examples of training a neural network in pytorch
- compare numpy and pytorch implementations
- learn to define custom autograd functions
- introduction to nn and optim modules

## When to choose
- you are new to PyTorch and want minimal, self-contained examples
- you want to understand what happens under the hood of nn and optim
- you prefer learning by reading small scripts rather than large frameworks

## When to avoid
- you need production-ready or up-to-date PyTorch 2.x patterns
- you want comprehensive tutorials on CNNs, RNNs, or transformers
- you need maintained course material with active support

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: deep-learning, machine-learning, tutorials
- platform: python, cross-platform
- tags: pytorch, tutorials, examples, neural-networks, autograd, education

## Member repositories
- jcjohnson/pytorch-examples (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:02.233160+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 2026-08-29T18:18:06.814159+00:00, confidence not recorded.
  - readme: https://github.com/jcjohnson/pytorch-examples (fetched 2026-08-28T04:09:02.233160+00:00, sha f2d2e4be73f6)
- Data as of 2026-08-30T08:39:29.467469+00:00.