#458 · Primary category： Computer Vision
keras_Realtime_Multi-Person_Pose_Estimation
Keras version of Realtime Multi-Person Pose Estimation project
Project last updated：12/10/19
GitHub Stars
783
Forks
364
Contributors
6
License
Other
Why we included this project
This is a Keras port of the CVPR 2017 realtime multi-person pose estimation project, which locates the body joints of everyone in an image in a single forward pass. The author reworked the original Caffe implementation to drop the separate C++ server, and the repo includes scripts for converting the pretrained Caffe weights and running inference directly. It also walks through training and shows sample heatmap and part affinity field visualizations, which makes it a handy way to see how the architecture works. One caveat: the project is deprecated and won't run on TensorFlow 2.0, and the author points to a newer TensorFlow-based successor. Treat it as a reference for understanding the approach rather than something to build on.
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)