# facebookresearch/deepmask

Torch implementation of DeepMask and SharpMask

Repository: https://github.com/facebookresearch/deepmask
Canonical: https://ross.abutalabs.com/products/deepmask
Language: Lua
License: NOASSERTION
License Family: other
Archived: true
Last push: 2019-01-16T17:21:51+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3724, "days_push": 2786, "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 3099, forks 499 (observed 2026-08-28T04:07:43.517807+00:00)

## What it is
A Torch (Lua) implementation of the DeepMask and SharpMask object proposal algorithms from Facebook AI Research. It generates class-agnostic object segmentation masks for images, usable as a first stage for object detection pipelines.

## Use cases
- generate object segmentation proposals for images
- run pretrained DeepMask/SharpMask models on COCO images
- produce class-agnostic masks as input to object detection
- reproduce research results from the DeepMask and SharpMask papers
- compare mask proposal quality with top-down refinement

## When to choose
- you need to reproduce DeepMask/SharpMask research results
- you are already working in the Torch (Lua) ecosystem
- you need object proposals for a detection pipeline built around these models

## When to avoid
- you want a maintained library with active support
- you prefer PyTorch or modern deep learning frameworks
- you need fast inference in production
- you work on Windows or without an NVIDIA GPU

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, image-processing
- platform: lua
- tags: object-proposals, instance-segmentation, torch, deepmask, sharpmask, research-code, linux, macos, gpu

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

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:43.517807+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 2026-08-29T18:46:21.819472+00:00, confidence not recorded.
  - readme: https://github.com/facebookresearch/deepmask (fetched 2026-08-28T04:07:43.517807+00:00, sha 6487feba4f0d)
- Data as of 2026-08-30T08:39:29.467469+00:00.