# facebookarchive/fb.resnet.torch

Torch implementation of ResNet from http://arxiv.org/abs/1512.03385 and training scripts

Repository: https://github.com/facebookarchive/fb.resnet.torch
Canonical: https://ross.abutalabs.com/products/fbresnettorch
Language: Lua
License: NOASSERTION
License Family: other
Archived: true
Last push: 2022-08-24T15:23:59+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3886, "days_push": 1470, "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 2360, forks 662 (observed 2026-08-28T04:06:40.869130+00:00)

## What it is
A Torch (Lua) implementation of ResNet residual networks for image classification, with training scripts for ImageNet and pretrained models from ResNet-18 to ResNet-200. The project is archived and no longer maintained, with PyTorch recommended as its successor.

## Use cases
- train a ResNet on ImageNet
- fine-tune pretrained ResNet on a custom dataset
- classify images with a pretrained ResNet model
- extract image features using ResNet
- reproduce ResNet paper results in Torch

## When to choose
- you specifically need the original Torch/Lua ResNet implementation
- you want the pretrained Torch ResNet checkpoints for research reproduction

## When to avoid
- starting any new project (use PyTorch instead)
- you need maintained code or modern GPU support
- you don't have the legacy Torch framework installed

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, gpu-computing
- domain: computer-vision, image-processing, deep-learning, machine-learning
- platform: lua
- tags: resnet, torch, imagenet, pretrained-models, archived, convolutional-networks, linux, gpu

## Member repositories
- facebookarchive/fb.resnet.torch (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:40.869130+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 2026-08-30T02:36:08.260850+00:00, confidence not recorded.
  - readme: https://github.com/facebookarchive/fb.resnet.torch (fetched 2026-08-28T04:06:40.869130+00:00, sha 7f7e4b251f59)
- Data as of 2026-08-30T08:39:29.467469+00:00.