In the documentation -> installation -> EC2, it says "The best way to do this is through Docker. We have a public AMI with the preliminary CUDA drivers installed: ami-c12f86a1. Start a P2/G2 GPU instance with this AMI and run the nvidia-docker command above to get started." I am trying to launch a instance, the first step is to choose an AMI and I cannot find this public AMI. Should I just choose Ubuntu and use the installation guide for Ubuntu? Thanks!