Skip to content

Convolutional Neural Network Digit recognizer implemented using TensorFlow.js and p5.js

License

Notifications You must be signed in to change notification settings

HarivardhanR/digitsclassifier

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Getting Started

Webpage

You can train,test Convolutional Neural Network here. The webpage contains the following buttons guess,train,test and clear.

Guess button

The model outputs the digit you drew on the canvas.It also outputs the probability of other numbers it thinks the digit is,darker the digit's corresponding cirle higher the probability.

Clear button

clears the canvas.

Test button

Used to test how well the Neural network has been trained.Testing of model is done with 1000 images.

Train button

Used to train the model.Training of model is done with 10,000 images.More the Train images the better the model's outputs.

NOTE : training with more number of images in low-end PC may take a long time.

Built with

  • p5.js. p5.js a JS client-side library for creating graphic and interactive experiences, based on the core principles of Processing.
  • tensorflow.js. TensorFlow.js is a JavaScript Library for training and deploying machine learning models in the browser.

License

This project is licensed under the MIT License - see the LICENSE file for details

About

Convolutional Neural Network Digit recognizer implemented using TensorFlow.js and p5.js

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published