# facebookresearch/ClassyVision

An end-to-end PyTorch framework for image and video classification

Repository: https://github.com/facebookresearch/ClassyVision
Canonical: https://ross.abutalabs.com/products/classyvision
Homepage: https://classyvision.ai
Language: Python
License: MIT
License Family: permissive
Archived: true
Last push: 2024-06-27T16:05:09+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2546, "days_push": 797, "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 1607, forks 272 (observed 2026-08-28T04:05:10.619621+00:00)

## What it is
Classy Vision is an end-to-end PyTorch framework for image and video classification, offering a modular API for computer vision research with scalable distributed training. It includes implementations of models like ResNe(X)t, EfficientNet, and Vision Transformers, but is no longer actively maintained (final stable version 0.7.0).

## Use cases
- train image classification models in pytorch
- run distributed video classification training jobs
- research computer vision model architectures like vision transformers
- fine-tune pretrained resnet or efficientnet models
- set up reproducible classification training with config files

## When to choose
- you need a modular PyTorch-based framework for image or video classification research
- you want built-in distributed training with minimal infrastructure setup
- you need reference implementations of ResNeXt, EfficientNet, RegNetZ, or Vision Transformers

## When to avoid
- you need actively maintained software with ongoing bug fixes and new PyTorch version support
- you want a general-purpose computer vision toolkit beyond classification (e.g., detection, segmentation)
- you prefer a simpler high-level API like torchvision or timm for standard training workflows

## Facets
- artifact type: framework
- maturity: abandoned
- function: machine-learning, deep-learning, image-processing, video-processing
- domain: computer-vision, deep-learning, machine-learning
- platform: python, windows
- tags: pytorch, image-classification, video-classification, computer-vision-research, distributed-training, vision-transformers, no-longer-maintained, linux, macos

## Member repositories
- facebookresearch/ClassyVision (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:10.619621+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 2026-08-30T03:51:47.674511+00:00, confidence not recorded.
  - readme: https://github.com/facebookresearch/ClassyVision (fetched 2026-08-28T04:05:10.619621+00:00, sha fa9616afa724)
  - homepage: https://classyvision.ai (fetched 2026-08-29T11:23:44.684789+00:00, sha 62df66f7aceb)
- Data as of 2026-08-30T08:39:29.467469+00:00.