WHY USE DOCKER ?

WE NEED TO INSTALL THE DOCKER SOFTWARE THAT IS ABLE TO HOST THE 

DOCKER IMAGE

LOAD THE PRE CONFIGURED DOCKER IMAGE INTO THE DOCKER SOFTWARE.

MANAGE THE DOCKER IMAGE BY DOCKER SOFTWARE INSTALLED.

FOR EVERY OS WE HAVE DOCKER SOFTWARE THAT CAN HOST ANY DOCKER IMAGE

SAME DOCKER IMAGE CAN BE LOADED ON DIFFERENT OS HAVING THEIR VERSION OF

DOCKER SOFTWARE INTALLED ON THEM. 

DOCKER IS LIKE A LIGHT WEIGHT VM ON YOUR MAIN OS

DOCKER IS LIKE A LIGHT WEIGH  MINI OS ON YOUR MAIN OS

WE RUN OUR APPLICATION IN THAT VM/MINI OS.

WE INSTALL ALL THE DEPENDENCIES OF APPLICATION IN THAT MINI OS/VM

THIS MINI OS/VM IS EASILY SHIPABLE TO NEW MACHINES

ON NEW MACHINES WE DO NOT NEED TO WORRY ABOUT THE

1- DEPENDENCIES OF APPLICATION AS THEY ARE PRE PACKAGED IN DOCKER

2- CONFIGURAITONS OF THE APPLICATION AS THEY ARE THERE AND MAPPED 

    TO THE DEPENDICES INSIDE CONTAINER.

SO WE SHIP THE APPLICATION WITH ALL ITS ENVIROMENT TO THE NEW OS.

WE DO NOT HAVE TO INSTALL DEPEDENCES ON TARGET MACHIN OS

WE DO NOT AHVE TO MAP THE CONFIGURAIOTN TO THE NEW INSTALLED DEPEDENCIES

WE DO NOT HAVE TO WORRRY ABOUT THE DEPEDENCESI VERSIONS ON THE TARGET MACHINE

WE DO NOT HAVE WORRY ABOUT CONFLICST OF DEPENDEIS

WE DNOT HAVE WORRY ABOUT THE UPGRATDATION AND DOWN GRADATION OF DEPENDECNCES.

Before you start

Make sure you have 

Python

OpenFace

DLIB

installed. 

You can either install them manually or 

use a preconfigured docker image 

that has everying already installed:

docker pull bamos/openface

docker run -p 9000:9000 -p 8000:8000 -t -i bamos/openface /bin/bash

cd /root/openface

Step 1

Make a folder called /training-images/ somewhere on your computer.

Step 2

Make a subfolder for each person you want to recognize. For example:

/training-images/will-ferrell/

/training-images/chad-smith/

/training-images/jimmy-fallon/

Step 3

Copy all your images of each person into the correct sub-folders

Step 4

Run the openface scripts from inside the openface root directory:

First, do >>>>pose detection and >>>>alignment:

./util/align-dlib.py ./training-images/ align outerEyesAndNose ./aligned-images/ --size 96

Second, generate the >>>>>>representations from the aligned images:

./batch-represent/main.lua -outDir ./generated-embeddings/ -data ./aligned-images/

When you are done, the ./generated-embeddings/ folder will contain a csv file 

with the embeddings for each image.