# xiaoyufenfei/Efficient-Segmentation-Networks

Lightweight models for real-time semantic segmentationon PyTorch (include SQNet, LinkNet, SegNet, UNet, ENet, ERFNet, EDANet, ESPNet, ESPNetv2, LEDNet, ESNet, FSSNet, CGNet, DABNet, Fast-SCNN, ContextNet, FPENet, etc.)

Repository: https://github.com/xiaoyufenfei/Efficient-Segmentation-Networks
Canonical: https://ross.abutalabs.com/products/efficient-segmentation-networks
Language: Python
License: MIT
License Family: permissive
Topics: pytorch, real-time-semantic-segmentation, camvid, cityscapes, computer-vision, scene-understanding, segmentation, efficient-segmentation-networks, semantic-segmentation-models, image-segmentation, neural-networks, lightweight-semantic-segmentation, driving-scene-understanding, semantic-segmentation
Last push: 2024-07-25T10:16:24+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2522, "days_push": 769, "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 1008, forks 167 (observed 2026-08-28T04:03:12.716665+00:00)

## What it is
A PyTorch reference implementation collection of lightweight, real-time semantic segmentation models such as ENet, ERFNet, LEDNet, Fast-SCNN, and CGNet. It includes training and evaluation scripts for datasets like Cityscapes and CamVid.

## Use cases
- run real-time semantic segmentation on driving scenes
- train lightweight segmentation models on cityscapes
- compare efficient encoder-decoder segmentation architectures
- deploy fast image segmentation on edge devices
- benchmark real-time segmentation networks in pytorch

## When to choose
- you need ready-to-use PyTorch implementations of many real-time segmentation models in one repo
- you want to train or benchmark lightweight segmentation networks on Cityscapes or CamVid

## When to avoid
- you need state-of-the-art heavy segmentation models like Mask2Former or SAM
- you need production-grade tooling like MMSegmentation with configs and model zoo

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, computer-vision
- domain: computer-vision, machine-learning, deep-learning, autonomous-vehicles
- platform: python, cross-platform
- tags: semantic-segmentation, pytorch, real-time-segmentation, lightweight-models, cityscapes, camvid, scene-understanding, gpu

## Member repositories
- xiaoyufenfei/Efficient-Segmentation-Networks (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:12.716665+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 2026-08-30T07:12:22.831955+00:00, confidence not recorded.
  - readme: https://github.com/xiaoyufenfei/Efficient-Segmentation-Networks (fetched 2026-08-28T04:03:12.716665+00:00, sha a7642cf7345c)
- Data as of 2026-08-30T08:39:29.467469+00:00.