agoila / udacity-carnd-p2 Goto Github PK

In this project, we will use what we've learned about deep neural networks and convolutional neural networks to classify traffic signs. We will train and validate a model so it can classify traffic sign images using the German Traffic Sign Dataset. After the model is trained, we will then try out our model on images of German traffic signs that we find on the web.

Here's the Ipython notebook for this project. The HTML file is available here

Check out my writeup for this project. The images downloaded from the web can be found here as test1.jpg, test2.jpg etc.

The TensorBoard logdir is located here. To run TensorBoard from your command prompt, just type:

tensorboard --logdir="./logs/train/1"

The writeup has been written following the guidelines here.

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

The original post on this project by Udacity can be found here