# CSAILVision/semantic-segmentation-pytorch

Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset

Repository: https://github.com/CSAILVision/semantic-segmentation-pytorch
Canonical: https://ross.abutalabs.com/products/semantic-segmentation-pytorch
Homepage: http://sceneparsing.csail.mit.edu/
Language: Python
License: BSD-3-Clause
License Family: permissive
Topics: pytorch, semantic-segmentation, scene-recognition, ade20k
Last push: 2024-01-15T14:26:43+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3253, "days_push": 961, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5078, forks 1098 (observed 2026-08-28T04:09:09.496804+00:00)

## What it is
A PyTorch implementation of semantic segmentation (scene parsing) models for the MIT ADE20K dataset, including pretrained model zoo and training/evaluation tooling. It supports architectures like HRNet and multi-GPU training with synchronized batch normalization.

## Use cases
- segment images into semantic categories with pytorch
- train a scene parsing model on ADE20K
- run pixel-wise image segmentation with pretrained models
- evaluate semantic segmentation with mIoU
- try scene segmentation on my own photos
- multi-gpu training for segmentation models

## When to choose
- you need semantic segmentation on the ADE20K benchmark with pretrained weights
- you want a reference PyTorch codebase for segmentation research
- you need multi-GPU training with synchronized batch normalization

## When to avoid
- you need real-time or production-ready segmentation inference at scale
- you work with datasets other than ADE20K without adaptation effort
- you need actively developed features - the repo is in maintenance mode

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, image-processing, machine-learning, deep-learning
- domain: computer-vision, image-processing, machine-learning, deep-learning
- platform: python, windows
- tags: semantic-segmentation, scene-parsing, ade20k, pytorch, pretrained-models, hrnet, synchronized-batchnorm, gpu, linux, macos

## Member repositories
- CSAILVision/semantic-segmentation-pytorch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:09.496804+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 2026-08-29T18:02:35.857820+00:00, confidence not recorded.
  - readme: https://github.com/CSAILVision/semantic-segmentation-pytorch (fetched 2026-08-28T04:09:09.496804+00:00, sha 5eafc6808b31)
  - homepage: http://sceneparsing.csail.mit.edu/ (fetched 2026-08-29T08:57:29.580796+00:00, sha 15e2be9a5a3f)
- Data as of 2026-08-30T08:39:29.467469+00:00.