# IgorSusmelj/pytorch-styleguide

An unofficial styleguide and best practices summary for PyTorch

Repository: https://github.com/IgorSusmelj/pytorch-styleguide
Canonical: https://ross.abutalabs.com/products/pytorch-styleguide
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: pytorch, styleguide, best-practices
Last push: 2021-12-28T17:41:46+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": 2698, "days_push": 1709, "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 2017, forks 174 (observed 2026-08-28T04:06:06.033092+00:00)

## What it is
An unofficial styleguide and best-practices document for writing PyTorch code, based on over a year of deep learning experience from a research and startup perspective. It covers Python style conventions, PyTorch tips, workflow recommendations, and reusable code snippets for common building blocks.

## Use cases
- learn pytorch best practices
- how should I structure my pytorch project
- python naming conventions for deep learning code
- pytorch training loop style guide
- set up vs code for remote pytorch development
- code snippets for pytorch losses and layers
- improve my deep learning workflow

## When to choose
- you are starting a new PyTorch project and want conventions to follow
- you want curated code snippets for common PyTorch building blocks like attention or perceptual loss
- you are onboarding a team to a shared PyTorch coding style

## When to avoid
- you need an official or exhaustively maintained PyTorch reference
- you need runnable software or a library rather than a document
- you work primarily with other frameworks like TensorFlow or JAX

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: documentation, deep-learning, machine-learning
- domain: deep-learning, machine-learning, tutorials, developer-tools
- platform: python
- tags: pytorch, styleguide, best-practices, coding-standards

## Member repositories
- IgorSusmelj/pytorch-styleguide (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:06.033092+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 2026-08-30T03:00:29.286226+00:00, confidence not recorded.
  - readme: https://github.com/IgorSusmelj/pytorch-styleguide (fetched 2026-08-28T04:06:06.033092+00:00, sha cd534f586772)
- Data as of 2026-08-30T08:39:29.467469+00:00.