Skip to content

bestat/lighttrack

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

32 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

lighttrack

Clone from https://github.com/Guanghan/lighttrack.

環境構築

GPU必須。

Prerequisites

$ conda create -n lighttrack python=3.7
$ conda activate lighttrack
$ conda install tensorflow-gpu=1.14 pillow=6.2.1
$ conda install -c conda-forge tqdm setproctitle matplotlib
$ conda install -c anaconda cython

condaで入らないものはpipでいれる。pipのバージョンが3.7であることに注意して、

$ pip install opencv-python==4.2.0 pyyaml==5.3
$ pip install torch==1.4.0 torchvision==0.5.0

Getting Started

元のREADMEに従う。

About

LightTrack: A Generic Framework for Online Top-Down Human Pose Tracking

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 96.5%
  • Cuda 1.6%
  • C++ 1.1%
  • Other 0.8%