Google Cloud

Geometric Deep Learning for face segmentation

Spring 2020 · 27 minutes · Paul Berg, Bilel Debbabi

Python Tensorflow Google Cloud

Study state of the arts models in the field of geometric deep learning. And then apply, by training models on a face segmentation dataset. We provide our fork of both the PointNet and PointNet++ models.

Google Compute Engine SSH Tunnel

01/09/2020 · 1 minute

TLDR You can create a ssh tunnel from your virtual machine to your local machine by running the following command on your local machine: $ gcloud compute ssh <INSTANCE-NAME> -- \ -N -L <LOCAL-PORT>:localhost:<REMOTE-PORT> Example For example, if you are training a neural network using tensorflow on your virtual machine named instance-1. To monitor the training, you would launch tensorboard on the remote machine: