The word “hacking” could be different meaning for different people, some might said that it refers to “studying the network to the every single pieces”, some might said it means cracking the network to do something good or bad.
For this article, “Hacking Deep Learning Network” could mean “Cheating DNN”. Whichever terms used, they are just to make something simple looks complicated and make some loud noises on the articles, including this. 🙂
A lot of time we need to present our idea in a more presentable form, or make our program more user friendly to others. Building a graphic user interface could help us on this.
Scilab atoms module : Scilab GUI Builder could help us to build a GUI easily, while it is not perfect yet, it serves the basic purpose on GUI building.
Image recognition could be done in several ways, depending on the requirement and the scope of recognition. In a recent article I posted at LinkedIn, Understanding Deep-Learning (CNN) with Scilab, we could see there was a parameter for the user to set in GUI in order to get the good result which I named it as “Pre-process Param”. Let’s look into details what it is all about.
First of all, I’ve to admit that I never solve a single Sudoku puzzle by hand, or pen and pencil. Secondly, I did not write the Sudoku solver in Scilab, it is done by Michael Baudin and the module is available in Scilab atoms portal. (see : https://atoms.scilab.org/toolboxes/sudoku/0.1.1).
This tutorial is the extension from previous post : Perspective Transformation – A Manual Way and we are going to used the transformed image in this tutorial.