Digit Classifier

A convolutional neural network trained on MNIST data to classify images of numerical digits. Trained in Python using Keras and converted to TensorflowJS for implementation in a web demo.

This project is made up of two parts:

  1. The IPython Notebook hosted and executed on Google Colab used for training the network.

  2. The web app demo in JS. The code is available on GitHub and a live demo is hosted on Glitch to try out.

Glitch demo

Colab Notebook