Homework 3: Shoe Pair Classification

In this Homework, we will be building a convolutional neural network (CNN) to predict whether two shoes are from the same pair or from two different pairs. This task has real-world applications, such as assisting visually impaired individuals to gain more independence.

This project was done together with Chanel Michaeli.

Table of Contents

• Dataset
• Convolutional Architectures
• Files and Directory Structure
• Usage
• Contributing

Dataset

The dataset for this assignment consists of a collection of shoe images labeled as either "same pair" or "different pairs." The images are provided in a structured format that allows us to train our CNN model for classification. The dataset will be provided to you separately or can be downloaded from [link to dataset].

Convolutional Architectures

In this assignment, we will explore and implement two different convolutional architectures for the shoe pair classification task. These architectures will be designed to extract meaningful features from the input images and make accurate predictions. We will experiment with different network configurations, layer sizes, and activation functions to optimize the model's performance.

Files and Directory Structure

This repository contains the following files:

• main.py: The main Python script that contains the code for training and evaluating the CNN model.
• data.py: A Python script that handles the loading and preprocessing of the dataset.
• model.py: A Python script that defines the architecture of the CNN model.
• utils.py: A Python script that provides utility functions for data preprocessing and model evaluation.
• requirements.txt: A file listing the required Python packages and their versions.

Usage

To use the code and reproduce the results of this assignment, follow these steps:

1. Clone the repository: git clone https://github.com/NoamAtias/Machine_Learning_Image_Classification.git
2. Install the required packages: pip install -r requirements.txt
3. Run the main.py script to train and evaluate the CNN model: python main.py

Please ensure that you have the necessary computing resources and dependencies installed to run the code successfully.

Contributing

Contributions to this repository are welcome. If you have any suggestions, improvements, or bug fixes, please submit a pull request or open an issue.