# leoxiaobin/deep-high-resolution-net.pytorch

The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

Repository: https://github.com/leoxiaobin/deep-high-resolution-net.pytorch
Canonical: https://ross.abutalabs.com/products/deep-high-resolution-netpytorch
Homepage: https://jingdongwang2017.github.io/Projects/HRNet/PoseEstimation.html
Language: Cuda
License: MIT
License Family: permissive
Topics: human-pose-estimation, deep-learning, coco-keypoints-detection, mpii-dataset, mpii, mscoco-keypoint, deep-high-resolution-net, high-resolution-net
Last push: 2024-08-30T23:46:48+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": 2746, "days_push": 733, "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 4480, forks 922 (observed 2026-08-28T04:08:51.114344+00:00)

## What it is
Official PyTorch implementation of HRNet (Deep High-Resolution Representation Learning for Human Pose Estimation, CVPR 2019), which maintains high-resolution representations throughout the network for accurate keypoint prediction. It includes training, testing, demo, and visualization code with pretrained models for COCO and MPII pose estimation benchmarks.

## Use cases
- detect human body keypoints in images
- train a pose estimation model on COCO or MPII
- run pose estimation inference with pretrained HRNet weights
- benchmark keypoint detection models
- use HRNet as a backbone for other vision tasks
- estimate human poses from photos or video frames

## When to choose
- you need accurate top-down human pose estimation with a proven architecture
- you want official pretrained models and reproducible benchmark results on COCO/MPII
- you're doing research on keypoint detection or pose tracking

## When to avoid
- you need real-time pose estimation on edge devices or mobile
- you want a maintained library with frequent updates and modern PyTorch practices
- you need bottom-up multi-person pose estimation (see HigherHRNet instead)

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning
- platform: python
- tags: human-pose-estimation, hrnet, keypoint-detection, pytorch, cvpr-2019, coco, mpii, research-code, gpu, linux, cuda

## Member repositories
- leoxiaobin/deep-high-resolution-net.pytorch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:51.114344+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 2026-08-29T18:20:33.153650+00:00, confidence not recorded.
  - readme: https://github.com/leoxiaobin/deep-high-resolution-net.pytorch (fetched 2026-08-28T04:08:51.114344+00:00, sha 1b51e332e658)
  - homepage: https://jingdongwang2017.github.io/Projects/HRNet/PoseEstimation.html (fetched 2026-08-29T09:06:50.339939+00:00, sha 722e0dbbf3ad)
- Data as of 2026-08-30T08:39:29.467469+00:00.