# dmlc/gluon-cv

Gluon CV Toolkit

Repository: https://github.com/dmlc/gluon-cv
Canonical: https://ross.abutalabs.com/products/gluon-cv
Homepage: http://gluon-cv.mxnet.io
Language: Python
License: Apache-2.0
License Family: permissive
Topics: deep-learning, computer-vision, neural-network, gluon, mxnet, machine-learning, image-classification, object-detection, semantic-segmentation, gan, person-reid, action-recognition, pose-estimation
Last push: 2024-11-25T15:30:52+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": 3111, "days_push": 646, "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 5916, forks 1205 (observed 2026-08-28T04:09:32.241247+00:00)

## What it is
GluonCV is a deep learning toolkit providing state-of-the-art computer vision model implementations with 170+ pre-trained models. It supports both MXNet and PyTorch backends and covers image classification, object detection, segmentation, pose estimation, and action recognition.

## Use cases
- run image classification with pretrained models
- train an object detection model on custom data
- semantic segmentation of images
- human pose estimation
- video action recognition
- reproduce SOTA results from research papers
- export models for mobile deployment

## When to choose
- you need pretrained computer vision models with a simple one-line API
- you want training scripts to reproduce published SOTA results
- you work with MXNet or want dual PyTorch/MXNet support

## When to avoid
- you need actively maintained tooling - MXNet is retired and development has shifted to AutoGluon and other projects
- you need tasks beyond the supported vision applications
- you want the latest model architectures, which appear faster in timm or MMDetection

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, computer-vision
- domain: computer-vision, deep-learning, machine-learning, image-processing
- platform: python, windows
- tags: model-zoo, pretrained-models, mxnet, pytorch, object-detection, semantic-segmentation, pose-estimation, action-recognition, image-classification, linux, macos, gpu

## Member repositories
- dmlc/gluon-cv (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:32.241247+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 2026-08-29T17:51:15.144498+00:00, confidence not recorded.
  - readme: https://github.com/dmlc/gluon-cv (fetched 2026-08-28T04:09:32.241247+00:00, sha c085a9d17474)
  - homepage: http://gluon-cv.mxnet.io (fetched 2026-08-29T08:46:38.880887+00:00, sha fcaf3f72b135)
  - site_page: https://cv.gluon.ai/install.html (fetched 2026-08-29T08:46:38.884271+00:00, sha 134ab4058b05)
- Data as of 2026-08-30T08:39:29.467469+00:00.