# HRNet/HRNet-Image-Classification

Train the HRNet model on ImageNet

Repository: https://github.com/HRNet/HRNet-Image-Classification
Canonical: https://ross.abutalabs.com/products/hrnet-image-classification
Homepage: https://jingdongwang2017.github.io/Projects/HRNet/
Language: Python
License: MIT
License Family: permissive
Topics: image-classification, imagenet, hrnets, high-resolution-net
Last push: 2021-12-02T05:55:54+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2702, "days_push": 1735, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1056, forks 219 (observed 2026-08-28T04:03:24.659255+00:00)

## What it is
Official PyTorch implementation and training code for HRNet (High-Resolution Network) image classification models on ImageNet. It provides model definitions, training scripts, and pretrained checkpoints of HRNet backbones with a classification head.

## Use cases
- train an image classification model on ImageNet
- get HRNet pretrained backbone weights for transfer learning
- use HRNet as a backbone for detection or segmentation
- compare high-resolution network accuracy against ResNet
- export HRNet models to ONNX
- find small efficient classification models with ResNet18-level cost

## When to choose
- you need a strong high-resolution backbone for downstream vision tasks like pose estimation or segmentation
- you want pretrained ImageNet weights with competitive top-1 accuracy
- you need a ResNet replacement backbone in PyTorch

## When to avoid
- you need a maintained general-purpose model zoo or modern training framework
- you want inference-only deployment without training code
- you need models beyond classification such as detection heads included out of the box

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, computer-vision
- domain: computer-vision, image-processing, deep-learning, machine-learning
- platform: python
- tags: hrnet, image-classification, imagenet, pytorch, backbone-network, pretrained-models, computer-vision, linux, gpu

## Member repositories
- HRNet/HRNet-Image-Classification (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:24.659255+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 2026-08-30T06:58:14.976985+00:00, confidence not recorded.
  - readme: https://github.com/HRNet/HRNet-Image-Classification (fetched 2026-08-28T04:03:24.659255+00:00, sha 1e406da6fe98)
  - homepage: https://jingdongwang2017.github.io/Projects/HRNet/ (fetched 2026-08-29T13:00:03.774750+00:00, sha 0b14f1d17f73)
- Data as of 2026-08-30T08:39:29.467469+00:00.