Skip to content

GrahlmanMatthew/Colour-SOFM

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Colour-SOFM

A self-organizing feature map which is trained on a random three-dimensional (RGB) input space.

Compilation

To compile you will need to first install the MinGW C++ compiler. Once you have done so, simply run the following command from a Bash command line:

g++ main.cpp -o SOFM.exe pixel.h  user-input.h -I CImg/ -lgdi32 -Wl,--stack,100000000

Learning Parameters

When executed, the program will prompt the user for:

  • The height of the SOFM
  • The width of the SOFM
  • The number of epochs to train the SOFM over
  • The neighbourhood radius for the SOFM update function
  • The learning rate

Input Space

The SOFM is trained on a three dimensional input space of pixels with randomized RGB values. Initially, the SOFM will look similar to the image below.

Output

The output of the SOFM is saved to the "SOFM-TRAINED.bmp" file and will look similar to the following:

About

A self-organizing feature map which is trained on a random three-dimensional (RGB) input space.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages