This university course project uses a VGG-based Convolutional Neural Network (CNN) to classify images of house numbers from the Street View House Numbers (SVHN) dataset. An interactive demo is also provided using Gradio.
Use the provided requirements.txt file to install all necessary libraries:
pip install -r requirements.txt
Lauch Jupyter Notebook VGG.ipynband run each code cell in sequence, following the comments and instructions within the notebook to complete data preprocessing, model training, evaluation and gradio demo interface for real-time handwritten digit classification.