# facebookresearch/multipathnet

A Torch implementation of the object detection network from "A MultiPath Network for Object Detection" (https://arxiv.org/abs/1604.02135)

Repository: https://github.com/facebookresearch/multipathnet
Canonical: https://ross.abutalabs.com/products/multipathnet
Language: Lua
License: NOASSERTION
License Family: other
Archived: true
Last push: 2019-03-22T18:15:44+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": 3667, "days_push": 2721, "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 1331, forks 275 (observed 2026-08-28T04:04:24.277440+00:00)

## What it is
A Torch-7 implementation of the MultiPath Network for object detection from the BMVC 2016 paper by Facebook AI Research, also supporting Fast R-CNN training. It provides training and evaluation code on datasets like MSCOCO and PASCAL VOC using GPU acceleration.

## Use cases
- train an object detection model in Torch
- reproduce MultiPath Network object detection results
- train Fast R-CNN on COCO or PASCAL VOC
- run object detection research on GPU with Lua Torch
- evaluate object detection models with COCO API

## When to choose
- you need the exact MultiPath Network implementation from the paper
- your stack is Torch-7/Lua and you want Fast R-CNN style training
- you're studying or extending Facebook Research's 2016 detection code

## When to avoid
- you want modern, maintained object detection tooling (use PyTorch-based Detectron2, MMDetection, or Ultralytics)
- you don't have an NVIDIA GPU or Linux environment
- you can't work with the deprecated Torch-7 ecosystem

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning
- platform: lua
- tags: object-detection, torch7, fast-rcnn, multipath-network, research-code, coco, pascal-voc, research, linux, gpu

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

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:24.277440+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 2026-08-30T04:45:15.802155+00:00, confidence not recorded.
  - readme: https://github.com/facebookresearch/multipathnet (fetched 2026-08-28T04:04:24.277440+00:00, sha d6ae2bcea6b5)
- Data as of 2026-08-30T08:39:29.467469+00:00.