Skip to content

Latest commit

 

History

16 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Hand written digit guesser

This is an artificial intelligence personal project using the mnist dataset of handwritten digits to train a neural network. The user can then draw a number and the model will (try) to guess it.

Requirements

You can find the requirements here or install it with pip3 install -r requirements.txt.

Usage

To draw a number type python3 draw.py and start drawing a number, to see what the model predict press the space bar.
If you want to remove the used model and train a new model type python3 train.py.
Finally if you want to evaluate the accuracy of the model see examples of predictions type python3 evaluate.py.

About

A neural networks that recognise handwritten digits

Topics

Resources

Stars

1 star

Watchers

1 watching

Forks

Releases

Packages

Used by

Contributors

Languages