# tensorlayer/HyperPose

Library for Fast and Flexible Human Pose Estimation

Repository: https://github.com/tensorlayer/HyperPose
Canonical: https://ross.abutalabs.com/products/hyperpose
Homepage: https://hyperpose.readthedocs.io
Language: Python
License Family: other
Topics: tensorlayer, tensorflow, openpose, pose-estimation, computer-vision, distributed-training, tensorrt, mobilenet, neural-networks
Last push: 2023-03-25T01:16:28+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2930, "days_push": 1258, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1264, forks 271 (observed 2026-08-28T04:04:10.533685+00:00)

## What it is
HyperPose is a library for building high-performance custom human pose estimation applications. It combines a C++ inference engine with TensorRT and pipeline parallelism for real-time speed, plus Python APIs for training and customizing pose estimation models.

## Use cases
- estimate human poses from video in real time
- train a custom pose estimation model on my own dataset
- speed up openpose inference with tensorrt
- run pose estimation on multiple gpus
- benchmark pose estimation models against openpose

## When to choose
- you need real-time human pose estimation with high FPS on CPU or GPU
- you want to train or customize pose estimation architectures like OpenPose or PifPaf

## When to avoid
- you need a maintained project with active development or a clear license file
- you work outside pose estimation or need Windows-first deployment

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning
- platform: python, cpp
- tags: pose-estimation, openpose, tensorrt, human-pose, tensorflow, real-time-inference, linux, gpu, docker

## Member repositories
- tensorlayer/HyperPose (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:10.533685+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 2026-08-30T05:04:04.411193+00:00, confidence not recorded.
  - readme: https://github.com/tensorlayer/HyperPose (fetched 2026-08-28T04:04:10.533685+00:00, sha 7cd2ab6d5ebb)
  - registry_pypi: https://pypi.org/pypi/hyperpose/json (fetched 2026-08-29T12:16:51.965603+00:00, sha 2d392d7a19e7)
- Data as of 2026-08-30T08:39:29.467469+00:00.