CMU-Perceptual-Computing-Lab/openpose_train
Training repository for OpenPose
This is a specialized tool for developers working with computer vision models. It provides the underlying code to train and experiment with models for real-time multi-person human pose estimation. Developers can use this to take existing image and video datasets and create or fine-tune models that can identify body, hand, face, and foot keypoints.
612 stars. No commits in the last 6 months.
Use this if you are a computer vision developer who needs to train or customize models for real-time human pose estimation, building on the OpenPose framework.
Not ideal if you are looking for an out-of-the-box application for pose estimation; this is a highly experimental training toolkit, not a production-ready solution.
Stars
612
Forks
186
Language
Python
License
—
Category
Last pushed
Nov 19, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/CMU-Perceptual-Computing-Lab/openpose_train"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
talmolab/sleap
A deep learning framework for multi-animal pose tracking.
kennymckormick/pyskl
A toolbox for skeleton-based action recognition.
open-mmlab/mmaction2
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
jgraving/DeepPoseKit
a toolkit for pose estimation using deep learning
DenisTome/Lifting-from-the-Deep-release
Implementation of "Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image"