Skip to content

This is my attempt to identify handwritten digits in the MNIST dataset using Convolutional Neural Networks. It is implemented in Keras with backend as Theano.

Notifications You must be signed in to change notification settings

msrdinesh/MNIST-Handwriting-Recognition-using-Keras

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 

Repository files navigation

Try making changes in the code and improve the accuracy!

Things to install:

0. Dependencies
 sudo apt-get install python-pip (Python Package Installer)
pip install --user numpy
pip install --user matplotlib
pip install --user ipython[notebook] (Tool for sharing python projects in an interactive format)
 
1. Jupyter Notebook
 python -m pip install jupyter jupyter notebook

2. Theano (using as Backend)
pip install git+https://github.com/Theano/Theano.git@e891fb3

3. Keras
pip install git+https://github.com/fchollet/keras.git@1e58b89

Alt Text

About

This is my attempt to identify handwritten digits in the MNIST dataset using Convolutional Neural Networks. It is implemented in Keras with backend as Theano.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published