# victoresque/pytorch-template

PyTorch deep learning projects made easy.

Repository: https://github.com/victoresque/pytorch-template
Canonical: https://ross.abutalabs.com/products/pytorch-template
Language: Python
License: MIT
License Family: permissive
Last push: 2024-06-04T05:59:13+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3096, "days_push": 820, "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 5119, forks 1098 (observed 2026-08-28T04:09:10.874808+00:00)

## What it is
A PyTorch project template providing a clear folder structure, JSON config files, CLI overrides, checkpointing, and abstract base classes for trainers, data loaders, and models. It ships with an MNIST example and a script to scaffold new deep learning projects.

## Use cases
- scaffold a new pytorch deep learning project
- organize my pytorch training code with configs and checkpoints
- template for reproducible deep learning experiments
- start a pytorch project with trainer and data loader base classes
- set up tensorboard logging for pytorch training

## When to choose
- starting a new PyTorch research or experiment project from scratch
- you want a lightweight, readable structure without heavy framework lock-in
- you need config-driven training with checkpoint resume out of the box

## When to avoid
- you need a full-featured experiment framework like PyTorch Lightning or Hydra
- your project is not PyTorch-based
- you need actively maintained features or recent PyTorch API support

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning, developer-tools, logging, configuration-management
- domain: deep-learning, machine-learning, developer-tools, tutorials
- platform: python, cross-platform
- tags: pytorch, project-template, boilerplate, training-pipeline, mnist-example, tensorboard

## Member repositories
- victoresque/pytorch-template (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:10.874808+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 2026-08-29T18:02:06.443028+00:00, confidence not recorded.
  - readme: https://github.com/victoresque/pytorch-template (fetched 2026-08-28T04:09:10.874808+00:00, sha b3034025f182)
- Data as of 2026-08-30T08:39:29.467469+00:00.