In this project, I applied what I've learned about deep neural networks and convolutional neural networks to classify traffic signs. I trained and validated a model so it can classify traffic sign images using the German Traffic Sign Dataset. After the model was trained, I then tried out the model on images of German traffic signs that I randomly found on the web.
I also created a detailed writeup of the project.
To meet the project's specifications, three files were of outmost importance:
- the Ipython notebook with the code
- the code exported as an html file
- a writeup report either as a markdown or pdf file
The achieved goals / steps of this project are the following:
- Loading the data set
- Exploring, summarizing and visualizing the data set
- Designing, training and testing a model architecture
- Using the model to make predictions on new images
- Analyzing the softmax probabilities of the new images
- Summarizing the results with a written report
This lab requires:
The lab environment can be created with CarND Term1 Starter Kit. Click here for the details.