An open API service indexing awesome lists of open source software.

https://github.com/ksdkamesh99/mnist


https://github.com/ksdkamesh99/mnist

classification digits machine-learning mnist

Last synced: 4 months ago
JSON representation

Awesome Lists containing this project

README

          

# MNIST-A Digit Classifier



Logo

## 📌 Introduction

This Machine Learning Web Application utilizes a Two-Layered Convolutional Neural Network to process the images in the notepad provided in the application.

Our Model performs fairly well with an accuracy of 99.26%. This provides a handy tool to utilize the power of Machine Learning and Artificial Intelligence in Categorical Classification Problems where time and accuracy is the paramount objective of classification.

## 🎯 About The Dataset
The MNIST database of handwritten digits, available from this page, has a training set of 60,000 examples, and a test set of 10,000 examples. It is a subset of a larger set available from NIST. The digits have been size-normalized and centered in a fixed-size image.
It is a good database for people who want to try learning techniques and pattern recognition methods on real-world data while spending minimal efforts on preprocessing and formatting.

## 🏁 Technology Stack

* [Flask](https://github.com/pallets/flask)
* [HTML](https://www.w3.org/TR/html52/)
* [CSS](https://developer.mozilla.org/en-US/docs/Web/CSS)
* [Bootstrap](https://getbootstrap.com/)
* [Tensorflow](https://www.tensorflow.org/)
* [Keras](http://keras.io/)

## 🏃‍♂️ Local Installation

1. Drop a ⭐ on the Github Repository.
2. Clone the Repo by going to your local Git Client and pushing in the command:

```sh
https://github.com/ksdkamesh99/MNIST.git
```

3. Install the Packages:
```sh
pip install -r requirements.txt
```

4. At last, push in the command:
```sh
python app.py
```

5. Go to ` http://127.0.0.1:5000/` and enjoy the application.

## 📜 LICENSE

[MIT](https://github.com/ksdkamesh99/MNIST/blob/master/LICENSE.md)