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

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

adam-optimizer batch-normalization deep-learning dropout-keras grid-search hyperparameter-tuning image-classification keras mnist mnist-classification neural-network sgd-optimizer tensorflow

Last synced: 21 days ago
JSON representation

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

• Host: GitHub
• URL: https://github.com/somjit101/mnist-classification-keras
• Owner: somjit101
• Created: 2021-09-15T20:03:32.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2021-09-17T19:20:47.000Z (over 3 years ago)
• Last Synced: 2024-11-16T03:29:38.024Z (3 months ago)
• Topics: adam-optimizer, batch-normalization, deep-learning, dropout-keras, grid-search, hyperparameter-tuning, image-classification, keras, mnist, mnist-classification, neural-network, sgd-optimizer, tensorflow
• Language: Jupyter Notebook
• Homepage:
• Size: 567 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# MNIST-Classification-Keras

A simple, exploratory study on the use of Deep Neural Networks (DNNs) 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 Multi-layered Perceptrons, training and performance testing 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.