In this project, I used Python and TensorFlow to classify traffic signs. Dataset used: German Traffic Sign Dataset. This dataset has more than 50,000 images of 43 classes. I was able to reach a +99% validation accuracy, and a 97.3% testing accuracy.
I'll explain each step in details below.
The pickled data is a dictionary with 4 key/value pairs:
In this step, we will apply several preprocessing steps to the input images to achieve the best…