# HRNet/HRNet-Semantic-Segmentation

The OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919

Repository: https://github.com/HRNet/HRNet-Semantic-Segmentation
Canonical: https://ross.abutalabs.com/products/hrnet-semantic-segmentation
Language: Python
License: NOASSERTION
License Family: other
Topics: segmentation, semantic-segmentation, cityscapes, pascal-context, lip, high-resolution, high-resolution-net, hrnets, transformer, segmentation-transformer
Last push: 2022-11-17T13:07:10+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": 2703, "days_push": 1385, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3331, forks 695 (observed 2026-08-28T04:07:56.610441+00:00)

## What it is
Official PyTorch implementation of HRNet (High-Resolution Network) and the Segmentation Transformer (OCR) approach for semantic segmentation. It provides pretrained models and training/evaluation code achieving state-of-the-art results on benchmarks like Cityscapes, PASCAL-Context, LIP, ADE20K, and COCO-Stuff.

## Use cases
- train a semantic segmentation model on Cityscapes
- segment images into per-pixel class labels with HRNet
- use pretrained HRNet weights for scene parsing
- reproduce state-of-the-art OCR segmentation results
- benchmark segmentation models on ADE20K or PASCAL-Context
- human part segmentation with LIP dataset

## When to choose
- you need high-accuracy semantic segmentation with strong multi-scale representations
- you want a research-grade PyTorch codebase with pretrained HRNet checkpoints
- you are benchmarking on standard segmentation datasets like Cityscapes or ADE20K

## When to avoid
- you need a lightweight model for real-time or mobile inference
- you want a maintained production framework rather than research code
- you need segmentation support outside PyTorch

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, image-processing, deep-learning, machine-learning
- platform: python
- tags: semantic-segmentation, hrnet, pytorch, transformer, cityscapes, computer-vision-models, research-code, linux, gpu

## Member repositories
- HRNet/HRNet-Semantic-Segmentation (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:56.610441+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 2026-08-29T18:41:42.182310+00:00, confidence not recorded.
  - readme: https://github.com/HRNet/HRNet-Semantic-Segmentation (fetched 2026-08-28T04:07:56.610441+00:00, sha 740206057e82)
- Data as of 2026-08-30T08:39:29.467469+00:00.