As research continues in the development of self-driving cars, one of the key challenges is computer vision, allowing these cars to develop an understanding of their environment from digital images. In particular, this involves the ability to recognize and distinguish road signs – stop signs, speed limit signs, yield signs, and more.
In this project, we will use TensorFlow to build a neural network to classify road signs based on an image of those signs. To do so, we’ll need a labeled dataset: a collection of images that have already been categorized by the road sign represented in them.
Several such data sets exist, but for this project, we’ll use the German Traffic Sign Recognition Benchmark (GTSRB) dataset, which contains thousands of images of 43 different kinds of road signs.
Project is built with:
- Python version: 3.9.12
- pipenv version: 2022.7.4
git clone https://github.com/JackyZzZz/traffic.git
cd traffic
Download the data set for this project and unzip it. Move the resulting gtsrb directory inside of your traffic directory.
pip3 install -r requirements.txt
Simply run this command.
python traffic.py /full/path/to/dataset/
This software is inspired by and developed on the existed prompt by Harvard CSCI E-80