Traffic signs recognition is needed in autonomous vehicles to drive safely. In this project, I created a deep model in Tensorflow using Convolutional Neural Networks to classify traffic signs. The model was trained and validated using the German Traffic Sign Dataset. After the model was trained, it was tried out on images of German traffic signs found on the web.
This project requires:
The enviroment can be created with CarND Term1 Starter Kit. Click here for the details.
The German Traffic Sign Dataset used in this project is automatically downloaded in the Juputer Notebook.
Open the Jupyter notebook Traffic_Sign_Classifier.ipynb and run. This notebook is self-contained. Please note that the training time might be a lot if run on a CPU.