An end-to-end image classifier for the German Traffic Signs dataset using Tensorflow and Convolutional Neural Networks. The link to download the dataset is here: http://benchmark.ini.rub.de/

This project requires Python 3.5 and the following Python libraries installed:

• Jupyter
• NumPy
• SciPy
• scikit-learn
• TensorFlow

Run this command at the terminal prompt to install OpenCV. Useful for image processing:

• conda install -c https://conda.anaconda.org/menpo opencv3

Dataset

1. Download the dataset. You can download the pickled dataset in which we've already resized the images to 32x32 here.

2. Clone the project and start the notebook.

git clone https://github.com/udacity/traffic-signs
cd traffic-signs
jupyter notebook Traffic_Signs_Recognition.ipynb

3. Follow the instructions in the Traffic_Signs_Recognition.ipynb notebook.