# chainer/chainercv

ChainerCV: a Library for Deep Learning in Computer Vision

Repository: https://github.com/chainer/chainercv
Canonical: https://ross.abutalabs.com/products/chainercv
Language: Python
License: MIT
License Family: permissive
Topics: chainer, computer-vision, neural-network, deep-learning, python, cupy, chainercv
Archived: true
Last push: 2021-07-01T16:54:50+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3488, "days_push": 1889, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1481, forks 292 (observed 2026-08-28T04:04:51.006409+00:00)

## What it is
ChainerCV is a Python library providing tools to train and run neural networks for computer vision tasks on top of the Chainer framework. It includes reference implementations of models for image classification, object detection, and semantic/instance segmentation with unified data loaders and evaluation APIs.

## Use cases
- run object detection with pretrained YOLO or Faster R-CNN models
- train image classification networks like ResNet or VGG
- perform semantic segmentation with PSPNet or DeepLab
- evaluate vision models on standard datasets
- get reproducible reference implementations of CV models

## When to choose
- you are already using the Chainer framework for deep learning
- you need well-tested reference implementations of classic vision models
- you want cohesive data loading and evaluation utilities for vision tasks

## When to avoid
- you use PyTorch or TensorFlow instead of Chainer
- you need actively developed or state-of-the-art vision models
- you require support for recent Python versions

## Facets
- artifact type: library
- maturity: maintenance
- function: deep-learning, image-processing, computer-vision, machine-learning
- domain: computer-vision, deep-learning, machine-learning
- platform: python
- tags: chainer, object-detection, semantic-segmentation, image-classification, instance-segmentation, pretrained-models, linux, gpu

## Member repositories
- chainer/chainercv (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:51.006409+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 2026-08-30T04:34:09.913266+00:00, confidence not recorded.
  - readme: https://github.com/chainer/chainercv (fetched 2026-08-28T04:04:51.006409+00:00, sha 020247852384)
- Data as of 2026-08-30T08:39:29.467469+00:00.