Skip to content

kyesh/walabot

 
 

Repository files navigation

#PLEASE READ ME FIRST !!! 😄

  • Purpose
  • Requirement
  • Before you start
  • How to build up training/validation/test data?
  • How to visualise data?
  • How to train the network?

Purpose

Detect the distance of the target.

Requirement

Hardware

  • Normal PC or laptop
  • Walabot Device (Link)

Software

  • OS: Ubuntu 14.04
  • Tensorflow 0.8.0
  • Opencv 3.0.0
  • H5PY
  • Matplotlib
  • Walabot SDK (Link)

Before you start

This project is just for entertaiment and there are several models for different purpose, such as material classification & display silhouette of target. The effect can not be guaranteed and it is not recommended to the tensorflow beginner to use it. The most important thing is "HAVING FUN!".

How to build up training/validation/test data?

  1. Execute buildAll.sh. It logs antenna's signal(tx==1) at antenna folder.The log name format is tx-rx.txt.

  2. Execute test/log5.py to create training/validation/test data. Please uncomment line 130-156 and change MODE at line 14. (training set:MODE='train', validation set:MODE='val', test set:MODE='test')

How to visualise data?

  1. Use tool/showAntenna.py

How to train the network?

  1. Execute main_location.py.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 73.4%
  • Python 19.8%
  • C++ 6.0%
  • Shell 0.8%