Skip to content

Latest commit

 

History

History
38 lines (29 loc) · 1.44 KB

README.md

File metadata and controls

38 lines (29 loc) · 1.44 KB
Raw

EMNIST Digit Predictor

Description:

This is an application that displays a 14x14 grid which the user can draw on. As the user draws a prediction is made for which digit is being displayed.

The model used to make the predictions is made using DL4J and trained with the EMNIST digits dataset.

See: https://www.nist.gov/itl/products-and-services/emnist-dataset

Features

  • Java, JavaFX, JUnit, Maven
  • Neural Network Model using DL4J
  • Custom, Responsive GUI
  • Reset and Save Buttons

Demo:

Examples:

To Do:

  • Basic GUI and Functionality.
  • Real-Time Prediction
  • Create Nueral Network Model on Launch
  • Improve Splash Screen
  • Implement Unit Testing
  • Improve Overall Style and Layout
  • Containerize the Application (Docker)
  • Refactor, Refactor, Refactor...

For the things we have to learn before we can do them, we learn by doing them.