Handwritten Digit Recognition

This project implements a simple neural network using PyTorch for recognizing handwritten digits from the MNIST dataset. The model is trained to classify digits ranging from 0 to 9.

Features

• Load and preprocess the MNIST dataset.
• Define and train a neural network.
• Evaluate the model on a test dataset.
• Save the trained model for future use.

Getting Started

Prerequisites

Make sure you have the following libraries installed:

• torch
• torchvision

You can install them using pip:

pip install torch torchvision

MNIST Dataset

The MNIST dataset is a large database of handwritten digits that is commonly used for training various image processing systems. It contains the following:

• Training Set: 60,000 images of handwritten digits.
• Test Set: 10,000 images of handwritten digits.
• Image Size: 28x28 pixels.
• Color: Grayscale.
• Classes: 10 classes (digits 0-9).

Example images from the MNIST dataset:

Characteristics of the MNIST Dataset

1. Digit Classes: The dataset includes digits from 0 to 9.
2. Image Format: Each image is a 28x28 pixel grayscale image.
3. Training and Test Sets:
   • The training set contains 60,000 images.
   • The test set contains 10,000 images.
4. Normalization: Images are often normalized to have pixel values between 0 and 1 before being fed into the neural network.

The dataset is well-suited for benchmarking machine learning algorithms as it is simple enough to allow for quick prototyping and testing, yet it provides a robust challenge for image classification tasks.