This project implements a Handwritten Digit Classification system using the MNIST dataset. The model is trained to recognize digits from 0–9 based on grayscale images of handwritten characters. The project demonstrates the application of deep learning techniques for image recognition tasks.

• Introduction
• Features
• Installation
• Usage
• Project Structure
• Dependencies
• Examples
• Troubleshooting
• Contributors
• License

• Classification of handwritten digits (0–9)
• Implementation in Jupyter Notebook for easy experimentation
• Deep learning model trained using standard datasets
• Visualizations of training performance and predictions

Clone the repository and install the required dependencies:

git clone https://github.com/129Ashish/Handwritten_DIGIT_Classification.git
cd Handwritten_DIGIT_Classification
pip install -r requirements.txt

Make sure you have Python 3.7+ installed.

1. Open the Jupyter Notebook:

   jupyter notebook Handwritten_DIGIT_Classification.ipynb

2. Run the cells step by step to:
   • Load and preprocess the dataset
   • Train the neural network model
   • Evaluate accuracy on test data
   • Visualize predictions

Handwritten_DIGIT_Classification/
│── Handwritten_DIGIT_Classification.ipynb  # Main notebook
│── requirements.txt                        # Project dependencies
│── README.md                               # Documentation

Main dependencies (see requirements.txt for full list):

• numpy
• matplotlib
• Pytorch (deep learning framework)
• jupyter

Install all dependencies via:

pip install -r requirements.txt

• After training, the model achieves high accuracy on the MNIST dataset.
• Example prediction output:

• Jupyter not found: Install with pip install notebook.
• Module errors: Re-run pip install -r requirements.txt.
• GPU not detected: Ensure TensorFlow GPU version and CUDA drivers are installed.

• @129Ashish

This project is licensed under the MIT License. See the LICENSE file for details..