MNIST 3 vs 7 Digit Classifier

This project focuses on classifying handwritten digits 3 and 7 from the MNIST dataset using a neural network. It's a minimal example of binary classification using PyTorch and the popular MNIST dataset.

📌 Features

• Downloads and filters MNIST data for digits 3 and 7
• Preprocessing and visualization
• Binary classification using a custom neural network
• Accuracy evaluation

📁 Project Structure

mnist-3-vs-7-classifier/
├── mnist_3_vs_7_classifier.ipynb       # Jupyter notebook with code
├── requirements.txt                    # Python dependencies
├── README.md                           # Project overview
└── .gitignore                          # Files to ignore in version control

🚀 Getting Started

1. Clone the repository

git clone https://github.com/your-username/mnist-3-vs-7-classifier.git
cd mnist-3-vs-7-classifier

2. Set up your environment (optional)

python -m venv venv
source venv/bin/activate  # or venv\Scripts\activate on Windows

3. Install dependencies

pip install -r requirements.txt

4. Launch the notebook

jupyter notebook mnist_3_vs_7_classifier.ipynb

📊 Dataset

Uses the built-in MNIST dataset from torchvision.datasets. The notebook filters for only digits 3 and 7.

🛠️ Tools Used

• Python
• PyTorch
• Matplotlib
• NumPy

📄 License

This project is licensed under the MIT License.