Thanks for sharing the insights. I can confirm that you need to modify the AMI in the setup.sh file and modify the instanceID in the setup_instance.sh.
The ami-64c5cc1d instance appears to be t2.xlarge which does not have GPU (please correct me if I am wrong).
I guess for those that just want to use CPU for running deep learning algorithms this is an option but it might be more cost effective to run it on a p2 instance with GPU?
I am new to all this so let me know if I am mistaken.