This repository contains a Python project that implements a Convolutional Neural Network (CNN) to classify images of Saudi Riyal banknotes into seven denominations: 10, 100, 200, 5, 5 Polymer, 50, and 500 SR. Utilizing PyTorch, the project encompasses the complete workflow from data loading and preprocessing to model training and evaluation.
- Data Handling: The project includes scripts for loading and transforming image data into a suitable format for neural network training using PyTorch's DataLoader.
- Model Training: It details the process of splitting the dataset into training and testing sets, configuring a neural network model, and conducting training sessions with performance metrics.
- Evaluation: After training, the model's effectiveness is assessed through its accuracy and a detailed classification report providing insights into its performance across different classes.
- Visualization: The repository demonstrates how to use the trained model to predict on new images and visualize the outputs with confidence scores, enhancing interpretability of the results.