GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → ZexinChen → FastPose

ZexinChen / FastPose

Licence: other
pytorch realtime multi person keypoint estimation

Programming Languages

Jupyter Notebook
11667 projects
python
139335 projects - #7 most used programming language
shell
77523 projects

Labels

real-timeaccelerationcomputer-visionrealtimepytorchdeeplearninghuman-pose-estimationpose-estimationmodel-compressionopenpose

Projects that are alternatives of or similar to FastPose

Openpose
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
Stars: ✭ 22,892 (+63488.89%)
Mutual labels:  real-time, human-pose-estimation, pose-estimation, openpose
Gccpm Look Into Person Cvpr19.pytorch
Fast and accurate single-person pose estimation, ranked 10th at CVPR'19 LIP challenge. Contains implementation of "Global Context for Convolutional Pose Machines" paper.
Stars: ✭ 137 (+280.56%)
Mutual labels:  real-time, human-pose-estimation, pose-estimation
Tf Pose Estimation
Deep Pose Estimation implemented using Tensorflow with Custom Architectures for fast inference.
Stars: ✭ 3,856 (+10611.11%)
Mutual labels:  realtime, human-pose-estimation, pose-estimation
rmpe dataset server
Realtime Multi-Person Pose Estimation data server. Used as a training and validation data provider in training process.
Stars: ✭ 14 (-61.11%)
Mutual labels:  realtime, human-pose-estimation, pose-estimation
Alphapose
Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System
Stars: ✭ 5,697 (+15725%)
Mutual labels:  realtime, human-pose-estimation, pose-estimation
Poseflow
PoseFlow: Efficient Online Pose Tracking (BMVC'18)
Stars: ✭ 330 (+816.67%)
Mutual labels:  real-time, realtime, pose-estimation
Mobilepose Pytorch
Light-weight Single Person Pose Estimator
Stars: ✭ 427 (+1086.11%)
Mutual labels:  real-time, realtime, pose-estimation
Keras realtime multi Person pose estimation
Keras version of Realtime Multi-Person Pose Estimation project
Stars: ✭ 728 (+1922.22%)
Mutual labels:  real-time, human-pose-estimation, pose-estimation
posture recognition
Posture recognition based on common camera
Stars: ✭ 91 (+152.78%)
Mutual labels:  human-pose-estimation, pose-estimation, openpose
OpenPoseDotNet
OpenPose wrapper written in C++ and C# for Windows
Stars: ✭ 55 (+52.78%)
Mutual labels:  human-pose-estimation, openpose
Real Time Ml Project
A curated list of applied machine learning and data science notebooks and libraries across different industries.
Stars: ✭ 143 (+297.22%)
Mutual labels:  real-time, deeplearning
Deepstream pose estimation
This is a sample DeepStream application to demonstrate a human pose estimation pipeline.
Stars: ✭ 168 (+366.67%)
Mutual labels:  real-time, human-pose-estimation
Aws Mobile Appsync Events Starter React Native
GraphQL starter application with Realtime and Offline functionality using AWS AppSync
Stars: ✭ 134 (+272.22%)
Mutual labels:  real-time, realtime
Dop
JavaScript implementation for Distributed Object Protocol
Stars: ✭ 163 (+352.78%)
Mutual labels:  real-time, realtime
Kepler
The open source full-stack geosocial network platform
Stars: ✭ 125 (+247.22%)
Mutual labels:  real-time, realtime
Opentok Ios Sdk Samples
Example applications that use the OpenTok iOS SDK
Stars: ✭ 186 (+416.67%)
Mutual labels:  real-time, realtime
A2j
Code for paper "A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image". ICCV2019
Stars: ✭ 190 (+427.78%)
Mutual labels:  real-time, pose-estimation
Laravel Parse
A Parse SDK bridge for Laravel 5
Stars: ✭ 116 (+222.22%)
Mutual labels:  real-time, realtime
Hope
Source code of CVPR 2020 paper, "HOPE-Net: A Graph-based Model for Hand-Object Pose Estimation"
Stars: ✭ 184 (+411.11%)
Mutual labels:  real-time, pose-estimation
Mocapnet
We present MocapNET2, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned neural networks that regress the 3D human pose by also allowing for the decomposition of the body to an upper and lower kinematic hierarchy. This permits the recovery of the human pose even in the case of significant occlusions. (c) An efficient Inverse Kinematics solver that refines the neural-network-based solution providing 3D human pose estimations that are consistent with the limb sizes of a target person (if known). All the above yield a 33% accuracy improvement on the Human 3.6 Million (H3.6M) dataset compared to the baseline method (MocapNET) while maintaining real-time performance (70 fps in CPU-only execution).
Stars: ✭ 194 (+438.89%)
Mutual labels:  real-time, pose-estimation
View All Similar Projects ➔

FastPose

FastPose is a small and fast multi-person pose estimator which use middle point to do the keypoint grouping. It is the 46% smaller and 47% faster (forward time) than OpenPose (without using existing model compression and acceleration methods like MobileNet, Quantization, etc). For more detail, please refer to the technical report.

Installation

  1. Get the code.
git clone https://github.com/ZexinChen/FastPose.git
  1. Install pytorch 0.4.0 and other dependencies.
pip install -r requirements.txt
  1. Download the models manually: fastpose.pth (Google Drive | Baidu pan). Place it into ./network/weights .

Demo

You can run the code in the ./picture_demo.ipynb to see the demo of your own image by changing test_image path

Training

  1. Prepare COCO dataset:
    a. Download COCO.json (Google Drive | Baidu pan | Dropbox). Place it into ./data/coco/ .
    b. Download mask.tar.gz (Google Drive | Baidu pan). Untar it into ./data/coco/ .
    c. Download COCO dataset (2014)
bash ./training/getData.sh

The data folder should as followed:

-data
   -coco
      -COCO.json
      -mask
      -annotations
      -images
         -train2014
         -val2014
  1. Run the training script. The default should work fine.
CUDA_VISILBE_DIVECES=0,1 python3 train.py

Contributors

FastPose is developed and maintained by Zexin Chen and Yuliang Xiu. Some codes is brought from pytorch-version OpenPose. Thanks to the original authors.

License

FastPose is freely available for free non-commercial use, and may be redistributed under these conditions. For commercial queries, contact Cewu Lu

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].