🛑 Traffic Sign Classification using CNN

This project focuses on building a deep learning model to classify traffic signs using Convolutional Neural Networks (CNNs). The model is trained on the German Traffic Sign Recognition Benchmark (GTSRB) dataset and achieves accurate recognition across 43 traffic sign categories.

---

📘 Project Overview

Traffic sign recognition is a crucial component in autonomous driving systems. The goal of this project is to:

• Preprocess and augment traffic sign images.
• Train a CNN model from scratch.
• Compare performance with transfer learning (MobileNetV2 / VGG16).
• Evaluate, visualize, and deploy the final trained model.

---

🧱 Project Structure

⚙️ Step-by-Step Roadmap

1️⃣ Import Libraries

Import all necessary libraries for deep learning, data preprocessing, and visualization.

2️⃣ Load Dataset

Load the GTSRB dataset which contains images of 43 traffic sign classes.

3️⃣ Preprocess Data

Use ImageDataGenerator for data normalization and augmentation.

4️⃣ Build CNN Model

Design a CNN architecture suitable for traffic sign recognition.

5️⃣ Train the Model

Train the CNN on training data and validate on validation data.

6️⃣ Evaluate the Model

Compute accuracy on the test set and visualize model performance.

7️⃣ Compare with Pretrained Model (Transfer Learning)

Use MobileNetV2 or VGG16 for better accuracy through fine-tuning.

Save and Deploy the Model

Save the trained CNN or transfer learning model for deployment.