🖼️ CIFAR-10 Image Classification

---

📌 Overview

This project builds an image classification system using the CIFAR-10 dataset.
We compare two approaches:

• A Basic Convolutional Neural Network (CNN).
• An Enhanced CNN with Dropout, BatchNorm, and Data Augmentation.

---

🗂 Dataset

Source: CIFAR-10 Dataset
Structure:

• 60,000 color images (32x32 pixels, RGB)
• 50,000 training images + 10,000 testing images
• 10 categories: airplane, automobile, bird, cat, deer, dog, frog, horse, ship, truck

---

🛠 Tech Stack

• Python 3.x
• TensorFlow / Keras → Deep learning models
• NumPy → Numerical operations
• Matplotlib / Seaborn → Visualization
• scikit-learn → Evaluation metrics
• Jupyter Notebook → Development environment

---

📍 Project Steps

1. Data Loading & Preprocessing

   • Normalize pixel values
   • Apply Data Augmentation

2. Model 1: Basic CNN

   • Simple Conv + MaxPooling layers
   • Dense layers for classification

3. Model 2: Enhanced CNN

   • Deeper architecture
   • Dropout + Batch Normalization
   • Data Augmentation

4. Evaluation

   • Accuracy, Precision, Recall, F1-score
   • Confusion Matrix
   • Training vs Validation curves

5. Visualization

   • Example predictions (correct vs incorrect)
   • Confusion matrix heatmap

---

🚀 How to Run

# Clone the repository
git clone https://github.com/RehanShaikh-ai/cifar-10-image-classification.git
cd cifar-10-image-classification

# Install dependencies
pip install -r requirements.txt

# Run Jupyter Notebook

---

👤 Author

Rehan Abdul Gani Shaikh Aspiring Data Scientist | B.Tech Student

🔗 Connect with me: LinkedIn

📬 Email: rehansk.3107@gmail.com