ilovepose/fast-human-pose-estimation.pytorch

Official pytorch Code for CVPR2019 paper "Fast Human Pose Estimation" https://arxiv.org/abs/1811.05419

47
/ 100
Emerging

This project helps computer vision engineers and researchers create more efficient pose estimation models. It takes existing human pose estimation models (teacher models) and uses them to improve smaller, faster student models. The output is a more accurate, compact model that can identify key points on human bodies in images or video.

398 stars. No commits in the last 6 months.

Use this if you need to deploy human pose estimation models that are smaller and faster, while maintaining high accuracy, especially when you have unlabeled image data available.

Not ideal if you are looking for an out-of-the-box application for pose estimation, or if you don't have the technical expertise to train and fine-tune machine learning models.

computer-vision human-pose-estimation model-optimization deep-learning image-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

398

Forks

67

Language

Cuda

License

MIT

Last pushed

Sep 16, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/ilovepose/fast-human-pose-estimation.pytorch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.