Skip to content

Using FCN and an Attention layer to recognize Hyperdimensional images

Notifications You must be signed in to change notification settings

CheezBallzPi/hyperspec-fcn

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

43 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

HyperSpectral FCN

This is an implementation of FCN and Attention layers to recognize HyperSpectral images.

Prerequisites

  • Python 3
    • Keras
  • An Nvidia GPU (Not required but recommended)
  • A Hyperspectral image (currently only Pavia University Dataset works)

Setup

Anaconda is recommended for Python and its prerequisites. This implementation uses Python 3 so be sure to install the right one. You can install Anaconda from here.

The models are currently made to train from the Pavia University dataset. Put this image in data/pavia.

Training

To train this model, run solve.py.

Todo

  • Add the Attention Layer
  • Visualization

About

Using FCN and an Attention layer to recognize Hyperdimensional images

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages