This project creates and train a deep convolutional neural network to classify traffic signs. It uses the German Traffic Sign Dataset. Additionally the model is tested on images of German traffic signs found on the web and from pictures taken in my neighbourhood.
The deliverables for the project are:
- Ipython notebook with code
- HTML output of the code
- A writeup report (markdown)
Check out the writeup for a detailed discussion on steps, challenges and results encountered in this project.
The goals / steps of this project are the following:
- Load the data set
- Explore, summarize and visualize the data set
- Design, train and test a model architecture
- Use the model to make predictions on new images
- Analyze the softmax probabilities of the new images
- Summarize the results with a written report
This project requires Python3 will the following dependencies:
A pickled version of the German Traffic Sign Dataset with images resized to 32x32 is available here.
For dataset augmentation, run python data_augmentation.py