CIFAR-10 Image Classification using CNN

This project demonstrates the use of a Convolutional Neural Network (CNN) to classify images from the CIFAR-10 dataset. It includes data preprocessing, CNN model architecture, training, evaluation, and feature visualization.

🔍 Project Overview

• Dataset: CIFAR-10 (32x32 RGB images, 10 classes)
• Model: 4-layer CNN with max-pooling and dropout
• Final Accuracy: ~82.6% (Training), ~80.7% (Validation)

📓 Notebook

You can view the full implementation on Kaggle here:
👉 Open on Kaggle

📊 Visual Results

• Feature maps of convolutional layers
• Learned filters from the first Conv2D layer
• Model architecture diagram

📄 Report

The detailed report explaining each step is included as report.pdf.

📁 Folder Structure

• notebook.ipynb – Full code
• report.pdf – Final report