Built and trained a deep neural network to classify traffic signs, using TensorFlow.

View the Project on GitHub

Traffic Sign Recognition

In this project, we use convolutional neural networks to classify traffic signs. We will train a model so it can decode traffic signs from natural images by using the German Traffic Sign Dataset.

After the model is trained, we will then test model program on new images of traffic signs we find on the web.

Examples of traffic sign classification

RGB images are converted to grayscale for processing

Code & Files

1. Dependencies & environment

Anaconda is used for managing my dependencies.

2. My project files

(Note: the hyperlinks only works if you are on the homepage of this GitHub reop, and if you are viewing it in “” you can be redirected by clicking the View the Project on GitHub on the top)

3. How to run the code

(1) Download German Traffic Sign Dataset: training data and test data. This is a pickled dataset in which we’ve already resized the images to 32x32. Then save them into data folder.

(2) If you using Anaconda or miniconda, activate your environment which includes the dependencies by:

source activate your-conda-environment

(2) Load jupyter notebook and then select the Traffic_Sign_Classifier.ipynb by:

jupyter notebook Traffic_Sign_Classifier.ipynb

Release History