Skip to content

Apply deep learning techniques to classify traffic signs, resulted in 91% test set accuracy.

Notifications You must be signed in to change notification settings

kevingau/CarND-Traffic-Sign-Classifier-Project

Repository files navigation

Build a Traffic Sign Recognition Program

Udacity - Self-Driving Car NanoDegree

Overview

In this project, I use what I've learned about deep neural networks and convolutional neural networks to classify traffic signs. I will train and validate a model so it can classify traffic sign images using the German Traffic Sign Dataset. After the model is trained, I will then try out the model on images of German traffic signs that I find on 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

Dataset

The dataset is provided by CarND. It's a pickled dataset which have been already resized the images to 32x32. It contains a training, validation and test set.

Result

Check the writeup for more result detail.

Source Code

https://github.com/kevingau/CarND-Traffic-Sign-Classifier-Project/blob/master/Traffic_Sign_Classifier.ipynb

About

Apply deep learning techniques to classify traffic signs, resulted in 91% test set accuracy.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published