https://github.com/sudarshanc00/mnist-digit-classification
This project uses a machine learning model to classify handwritten digits (0-9) from the MNIST dataset, a popular collection of grayscale images for image classification benchmarking. It includes a Jupyter Notebook to train a neural network, enabling accurate recognition and classification of digits.
https://github.com/sudarshanc00/mnist-digit-classification
jupyter-notebook matplotlib numpy python tensorflow
Last synced: 5 months ago
JSON representation
This project uses a machine learning model to classify handwritten digits (0-9) from the MNIST dataset, a popular collection of grayscale images for image classification benchmarking. It includes a Jupyter Notebook to train a neural network, enabling accurate recognition and classification of digits.
- Host: GitHub
- URL: https://github.com/sudarshanc00/mnist-digit-classification
- Owner: SudarshanC00
- Created: 2024-06-24T14:53:33.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-11-18T08:37:11.000Z (about 1 year ago)
- Last Synced: 2025-04-03T05:16:39.183Z (10 months ago)
- Topics: jupyter-notebook, matplotlib, numpy, python, tensorflow
- Language: Jupyter Notebook
- Homepage:
- Size: 96.7 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# MNIST Digit Classification
## Overview
This project implements a machine learning model to classify handwritten digits (0-9) using the MNIST dataset. The MNIST dataset is a collection of grayscale images of handwritten digits, widely used for benchmarking image classification models. This project provides a Jupyter Notebook that trains a neural network to recognize and classify digits with high accuracy.
## Features
- **Data Loading and Preprocessing**: Loads and preprocesses the MNIST dataset to prepare it for model training.
- **Model Training**: Trains a neural network on the MNIST data for digit classification.
- **Evaluation**: Evaluates the model’s performance and displays accuracy metrics.
## File Structure
- **MNIST.ipynb**: Jupyter Notebook containing code to load, preprocess, train, and evaluate a digit classification model using the MNIST dataset.
## Installation
1. Clone this repository:
```bash
git clone https://github.com/SudarshanC00/MNIST-Digit-Classification.git
```
2. Navigate to the project directory:
```bash
cd MNIST-Digit-Classification
```
3. Install dependencies (e.g., TensorFlow, Keras, etc.):
```bash
pip install -r requirements.txt
```
## Usage
1. Open the Jupyter Notebook:
```bash
jupyter notebook MNIST.ipynb
```
2. Run the cells in the notebook to:
- Load and preprocess the MNIST data.
- Define and train the neural network model.
- Evaluate the model's performance and view accuracy metrics.
## Model Details
- **Dataset**: MNIST dataset containing 60,000 training images and 10,000 test images of handwritten digits.
- **Model Architecture**: A neural network suitable for image classification tasks, optimized for the MNIST dataset.
- **Evaluation Metrics**: Accuracy and loss metrics are used to evaluate model performance.
## Dependencies
- **Jupyter Notebook**: To run and explore the code interactively.
- **TensorFlow/Keras**: For building and training the neural network model.
- **NumPy**: For handling numerical data.
- **Matplotlib**: For visualizing data and model performance.
## License
This project is licensed under the MIT License.