tensorlayer/HyperPose

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

1264 stars · 271 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity maintenance

machine-learning computer-vision image-processing computer-vision deep-learning machine-learning python cpp pose-estimation openpose tensorrt human-pose tensorflow real-time-inference linux gpu docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="tensorlayer/HyperPose")