#328 · Primary category： Computer Vision
HyperPose
Library for Fast and Flexible Human Pose Estimation
Project last updated：03/25/23
GitHub Stars
1.3K
Forks
271
Contributors
18
License
Other
Why we included this project
HyperPose pairs a high-level Python API for building and customizing pose estimation models with a C++ inference engine that runs them fast on CPUs and GPUs. The engine relies on TensorRT and hybrid CPU/GPU scheduling, which the maintainers report can reach up to 10x the frame rate of OpenPose, TF-Pose, or OpenPifPaf, so it suits applications where latency matters. You can adjust training, evaluation, and pre/post-processing from Python without touching the C++ internals, which makes the library a practical baseline for a custom pose application instead of a research demo you have to rewire yourself.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)