Project: Build a Traffic Sign Recognition Program

Overview

This project demonstrates the performance of the LeNet architecture to classify images. You will train and validate a model so it can classify traffic sign images using the German Traffic Sign Dataset. After the model is trained, The model is tested through several images downloaded from the web.

The Project

The goals / steps of this project are the following:

• Load the data set
• Explore, summarize and visualize the data set
• Design, train and test a model architecture
• Use the model to make predictions on new images
• Analyze the softmax probabilities of the new images
• Summarize the results with a written report

Dependencies

This lab requires:

• CarND Term1 Starter Kit

Python libraries required:

• matplotlib
• cv2
• numoy
• pickle
• tensorflow
• sklearn

Instructions

• Make sure that the pickled dataset of the traffic sign images is located in the same directory as the python code.
• Make sure that the python libraries listed above are installed on your python environment.
• open the 'Traffic_Sign_Classifier-final.ipynb' file.
• Run the code cells from top to bottom.