https://github.com/somjit101/mnist-classification-cnn

A simple study on the use of CNNs for a simple handwritten number image classification task using the Keras framework (with Tensorflow background).
https://github.com/somjit101/mnist-classification-cnn

cnn cnn-classification cnn-keras convolutional-neural-networks keras maxpool2d mnist-classification mnist-dataset neural-network neural-networks

Last synced: 27 days ago
JSON representation

A simple study on the use of CNNs for a simple handwritten number image classification task using the Keras framework (with Tensorflow background).

• Host: GitHub
• URL: https://github.com/somjit101/mnist-classification-cnn
• Owner: somjit101
• Created: 2021-09-14T14:28:27.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2021-09-15T20:01:27.000Z (over 3 years ago)
• Last Synced: 2024-11-16T03:29:39.696Z (3 months ago)
• Topics: cnn, cnn-classification, cnn-keras, convolutional-neural-networks, keras, maxpool2d, mnist-classification, mnist-dataset, neural-network, neural-networks
• Language: Jupyter Notebook
• Homepage:
• Size: 6.84 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# MNIST Classification using CNNS with Keras

A simple, exploratory study on the use of Convolutional Neural Networks (CNNs) with Keras framework (Tensorflow background) for a simple handwritten number image classification task. This project was primarily made with the purpose of learning and getting familiar with CNNs in Keras framework, which efficiently streamlines its implementation with intuitive, simple-to-use functional APIs. This eliminates the need of managing computational graphs in Tensorflow and allows us to easily play with the Neural Network Architecture. 

## Dataset 

We have used the renowned [MNIST Handwritten Digits Dataset](http://yann.lecun.com/exdb/mnist/) containing 60,000 train samples and 10,000 test samples of 28x28 grayscale images depicting numerical digits written by a huge number of human subjects.