# facebookresearch/ResNeXt

Implementation of a classification framework from the paper Aggregated Residual Transformations for Deep Neural Networks

Repository: https://github.com/facebookresearch/ResNeXt
Canonical: https://ross.abutalabs.com/products/resnext
Language: Lua
License: NOASSERTION
License Family: other
Archived: true
Last push: 2020-01-14T19:58:44+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3522, "days_push": 2423, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1924, forks 291 (observed 2026-08-28T04:05:55.419773+00:00)

## What it is
A Torch (Lua) implementation of the ResNeXt architecture from the paper 'Aggregated Residual Transformations for Deep Neural Networks', built on top of fb.resnet.torch. It provides a training framework for image classification on ImageNet along with pretrained models.

## Use cases
- train a ResNeXt model on ImageNet
- reproduce results from the ResNeXt paper
- classify images with a pretrained ResNeXt network
- experiment with cardinality in residual network architectures
- fine-tune ResNeXt on a custom image classification dataset

## When to choose
- you specifically need the original ResNeXt implementation in Torch
- you are reproducing the paper's ImageNet results
- you are researching aggregated residual transformations

## When to avoid
- you want a modern PyTorch or TensorFlow implementation
- you are starting a new project (Torch is deprecated)
- you need active maintenance or recent GPU support

## Facets
- artifact type: library
- maturity: abandoned
- function: deep-learning, machine-learning, image-processing
- domain: deep-learning, computer-vision, image-processing, machine-learning
- platform: lua
- tags: resnext, image-classification, torch, convolutional-networks, imagenet, research-code, residual-networks, gpu, linux

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

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:55.419773+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 2026-08-30T03:09:34.374403+00:00, confidence not recorded.
  - readme: https://github.com/facebookresearch/ResNeXt (fetched 2026-08-28T04:05:55.419773+00:00, sha 985938b49b91)
- Data as of 2026-08-30T08:39:29.467469+00:00.