# chainer/chainer

A flexible framework of neural networks for deep learning

Repository: https://github.com/chainer/chainer
Canonical: https://ross.abutalabs.com/products/chainer
Homepage: https://chainer.org
Language: Python
License: MIT
License Family: permissive
Topics: deep-learning, python, neural-networks, machine-learning, gpu, cuda, cudnn, numpy, cupy, chainer, neural-network
Last push: 2023-08-28T17:18:20+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 4107, "days_push": 1101, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5924, forks 1342 (observed 2026-08-28T04:09:32.382815+00:00)

## What it is
Chainer is a Python-based deep learning framework that pioneered the define-by-run approach with dynamic computational graphs and automatic differentiation. It supports CUDA/cuDNN acceleration via CuPy and is now in a maintenance phase, receiving only bug fixes.

## Use cases
- build and train neural networks in python
- train deep learning models on gpu with cuda
- define dynamic computational graphs with control flow
- run recurrent and recursive network architectures
- prototype deep learning research with define-by-run
- multi-gpu training of neural networks

## When to choose
- you need a flexible define-by-run framework with dynamic graphs
- you are maintaining an existing Chainer codebase
- you want CUDA-accelerated training with minimal code changes

## When to avoid
- you are starting a new deep learning project - PyTorch or TensorFlow are actively developed
- you need long-term community support and new features
- you need production-grade deployment tooling

## Facets
- artifact type: framework
- maturity: maintenance
- function: deep-learning, machine-learning, gpu-computing
- domain: deep-learning, machine-learning, gpu-computing
- platform: python
- tags: define-by-run, dynamic-computational-graphs, cuda, cupy, automatic-differentiation, neural-networks, linux, gpu, docker

## Member repositories
- chainer/chainer (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:32.382815+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 2026-08-29T17:50:49.756322+00:00, confidence not recorded.
  - readme: https://github.com/chainer/chainer (fetched 2026-08-28T04:09:32.382815+00:00, sha fe78c37d5af8)
  - homepage: https://chainer.org (fetched 2026-08-29T08:47:34.900606+00:00, sha d47b1c869ad6)
- Data as of 2026-08-30T08:39:29.467469+00:00.