# fastai/fastbook

The fastai book, published as Jupyter Notebooks

Repository: https://github.com/fastai/fastbook
Canonical: https://ross.abutalabs.com/products/fastbook
Language: Jupyter Notebook
License: NOASSERTION
License Family: other
Topics: notebooks, fastai, deep-learning, machine-learning, data-science, python, book
Last push: 2024-08-16T14:38:24+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2378, "days_push": 747, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 25242, forks 9470 (observed 2026-08-28T04:11:38.081339+00:00)

## What it is
The fastai book, 'Deep Learning for Coders', published as a collection of Jupyter Notebooks covering deep learning with fastai and PyTorch. It serves as the material for the fast.ai MOOC and is runnable in Google Colab or locally.

## Use cases
- learn deep learning from scratch
- study fastai and PyTorch with hands-on notebooks
- follow the fast.ai course material
- understand computer vision and NLP basics
- run deep learning tutorials in Google Colab
- prepare for building deep learning models in production

## When to choose
- you want a practical, code-first introduction to deep learning
- you are taking the fast.ai course and need the notebooks
- you prefer learning via runnable Jupyter notebooks
- you want free access to a well-regarded deep learning textbook

## When to avoid
- you need a redistributable or commercially usable textbook (prose is copyright-restricted)
- you want a math-heavy theoretical treatment rather than a top-down practical approach
- you need a maintained software library rather than learning material

## Facets
- artifact type: learning-resource
- maturity: stable
- function: deep-learning, machine-learning, data-science, nlp, computer-vision
- domain: deep-learning, machine-learning, data-science, tutorials
- platform: python, cross-platform
- tags: jupyter-notebooks, fastai, pytorch, book, mooc, educational, web-server

## Member repositories
- fastai/fastbook (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:38.081339+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 2026-08-29T16:56:04.824608+00:00, confidence not recorded.
  - readme: https://github.com/fastai/fastbook (fetched 2026-08-28T04:11:38.081339+00:00, sha bc09adfb3153)
  - registry_pypi: https://pypi.org/pypi/fastbook/json (fetched 2026-08-29T07:52:54.946231+00:00, sha 26e3706c3dca)
- Data as of 2026-08-30T08:39:29.467469+00:00.