MNIST-Digit-Recognizer

MNIST Digit Recognizer with 99.72% Accuracy using Keras

Scoring done on Kaggle ( https://www.kaggle.com/mukultiwari )

Dataset

The dataset used for the project is 'The MNIST database of handwritten digits' has a training set of 60,000 examples, and a test set of 10,000 examples.

Download Link

http://yann.lecun.com/exdb/mnist/

Prerequisites

This project requires Python 2 with Numpy, Scipy, Keras, Tensorflow, Pandas, Matplotlib libraries installed.

To set up python on windows you can use Anaconda

https://medium.com/@GalarnykMichael/install-python-on-windows-anaconda-c63c7c3d1444

Built With

KERAS - https://keras.io/

ANACONDA - https://conda.io/docs/index.html

JUPYTER NOTEBOOK - http://jupyter.org/