# Tramac/awesome-semantic-segmentation-pytorch

Semantic Segmentation on PyTorch (include FCN, PSPNet, Deeplabv3, Deeplabv3+, DANet, DenseASPP, BiSeNet, EncNet, DUNet, ICNet, ENet, OCNet, CCNet, PSANet, CGNet, ESPNet, LEDNet, DFANet)

Repository: https://github.com/Tramac/awesome-semantic-segmentation-pytorch
Canonical: https://ross.abutalabs.com/products/awesome-semantic-segmentation-pytorch
Language: Python
License: Apache-2.0
License Family: permissive
Topics: semantic-segmentation, pytorch
Last push: 2023-01-04T08:24:27+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": 2733, "days_push": 1337, "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 3069, forks 581 (observed 2026-08-28T04:07:41.506799+00:00)

## What it is
A PyTorch library providing concise, modifiable reference implementations of many semantic segmentation models such as FCN, PSPNet, DeepLabv3+, BiSeNet, and DANet. It includes training, evaluation, and demo scripts with single- and multi-GPU support.

## Use cases
- train semantic segmentation models on pascal voc
- implement deeplabv3+ in pytorch
- compare segmentation model architectures
- run a segmentation demo on an image
- evaluate segmentation models on multiple gpus
- learn how semantic segmentation networks work

## When to choose
- you want readable, modifiable reference code for classic segmentation models
- you need to train or benchmark many segmentation architectures in one codebase
- you are studying or reproducing segmentation papers

## When to avoid
- you need a production-ready, actively maintained segmentation toolkit
- you want the latest transformer-based segmentation models
- you need pretrained models for many datasets out of the box

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, computer-vision
- domain: computer-vision, deep-learning, machine-learning
- platform: python, cross-platform
- tags: semantic-segmentation, pytorch, fcn, pspnet, deeplabv3, bisenet, reference-implementation, gpu, linux

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

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:41.506799+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 2026-08-30T07:28:09.860057+00:00, confidence not recorded.
  - readme: https://github.com/Tramac/awesome-semantic-segmentation-pytorch (fetched 2026-08-28T04:07:41.506799+00:00, sha f0150382b300)
- Data as of 2026-08-30T08:39:29.467469+00:00.