Daniil-Osokin/lightweight-human-pose-estimation.pytorch
A PyTorch implementation of lightweight OpenPose for real-time 2D multi-person human pose estimation running on CPU.
Not currently ranked — collecting fresh signals.
star history
This repository provides training and inference code for human pose estimation based on the lightweight OpenPose approach. It detects human skeletons consisting of 18 keypoints (ears, eyes, nose, joints) and their connections in images. The model is optimized for real-time CPU inference with minimal accuracy loss compared to the original OpenPose. The implementation achieves 40% AP on the COCO 2017 Keypoint Detection validation set using single-scale inference.
Frequently asked
- What is Daniil-Osokin/lightweight-human-pose-estimation.pytorch?
- A PyTorch implementation of lightweight OpenPose for real-time 2D multi-person human pose estimation running on CPU.
- Is lightweight-human-pose-estimation.pytorch open source?
- Yes — Daniil-Osokin/lightweight-human-pose-estimation.pytorch is open source, released under the Apache-2.0 license.
- What language is lightweight-human-pose-estimation.pytorch written in?
- Daniil-Osokin/lightweight-human-pose-estimation.pytorch is primarily written in Python.
- How popular is lightweight-human-pose-estimation.pytorch?
- Daniil-Osokin/lightweight-human-pose-estimation.pytorch has 2.2k stars on GitHub.
- Where can I find lightweight-human-pose-estimation.pytorch?
- Daniil-Osokin/lightweight-human-pose-estimation.pytorch is on GitHub at https://github.com/Daniil-Osokin/lightweight-human-pose-estimation.pytorch.