https://github.com/shaharband/handwritten-digit-classifier-cnn

This project implements a handwritten digit classifier based on the MNIST dataset using neural networks from TensorFlow. The classifier is built using convolutional neural networks (CNNs) to achieve high accuracy in recognizing handwritten digits.
https://github.com/shaharband/handwritten-digit-classifier-cnn

neural-network pandas tensorflow

Last synced: about 17 hours ago
JSON representation

This project implements a handwritten digit classifier based on the MNIST dataset using neural networks from TensorFlow. The classifier is built using convolutional neural networks (CNNs) to achieve high accuracy in recognizing handwritten digits.

• Host: GitHub
• URL: https://github.com/shaharband/handwritten-digit-classifier-cnn
• Owner: ShaharBand
• License: mit
• Created: 2023-03-20T11:48:02.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-05-07T18:31:26.000Z (6 months ago)
• Last Synced: 2024-11-07T10:13:54.875Z (about 17 hours ago)
• Topics: neural-network, pandas, tensorflow
• Language: Jupyter Notebook
• Homepage:
• Size: 139 KB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Handwritten Digit Classifier using TensorFlow

This project implements a handwritten digit classifier based on the MNIST dataset using neural networks from TensorFlow. The classifier is built using convolutional neural networks (CNNs) to achieve high accuracy in recognizing handwritten digits.

## 📋 Introduction

The MNIST dataset is a large collection of handwritten digits commonly used for benchmarking machine learning algorithms. 

Handwritten digit classifier based on MNIST dataset using neural networks from tensorflow.

## 🗃️ Dataset

MNIST set is a large collection of handwritten digits. It is a very popular dataset in the field of image processing. It is often used for benchmarking machine learning algorithms.

The data files train.csv and test.csv contain gray-scale images of hand-drawn digits, from zero through nine.

Each image is 28 pixels in height and 28 pixels in width, for a total of 784 pixels in total. Each pixel has a single pixel-value associated with it, indicating the lightness or darkness of that pixel, with higher numbers meaning darker. This pixel-value is an integer between 0 and 255, inclusive.

The dataset used in this analysis can be found on [Kaggle](https://www.kaggle.com/competitions/digit-recognizer/data).

## 🌱 Getting Started

To replicate this analysis, follow these steps:

1. Clone the repository:

   `https://github.com/ShaharBand/handwritten-digit-classifier-tensorflow.git`

   

2. Install the required libraries:

   `pip install requirements.txt`

   

3. Open the Jupyter Notebook `digit-recognizer.ipynb` to view the analysis steps and code.

## 📊 Results

The model achieved an accuracy of 98% on the validation set and 99% on the test set.

## 👨‍💻 Contributions:

Feel free to explore the code and contribute to further analysis or improvements!

## 💼 License

This project is licensed under the MIT License.