CIFAR10 Image Classification

This project demonstrates various machine learning methods for image classification based on the CIFAR10 dataset.

Table of Contents

• Introduction
• Installation
• Usage
• Results
• Contributing
• License

Introduction

The CIFAR10 dataset consists of 60,000 32x32 color images in 10 different classes. This project explores several machine learning and deep learning techniques for classifying these images.

Installation

Clone the repository:

git clone https://github.com/your-username/CIFAR10-Image-Classification.git
cd CIFAR10-Image-Classification

Install the required packages:

pip install -r requirements.txt

Usage

Take ResMacNet as example: Run the train.py first:

train.py

Evaluate the model then:

test.py

Results

The following table shows the accuracy achieved by different models:

Model	Accuracy
EasyNet	54.65%
Res-MacNet	81.3%

Contributing

Feel free to fork this repository and submit pull requests. For major changes, please open an issue first to discuss what you would like to change.

License

MIT