Deploying an ML Model with Cloud Run

30 minutes
  • 4 Learning Objectives

About this Hands-on Lab

Deploying a trained machine learning (ML) model to the cloud increases availability and performance. In this hands-on lab, you’ll learn how to take the code from a pre-trained ML model, containerize the application, store that container in a registry, and then deploy the stored container on Google Cloud Run.

Learning Objectives

Successfully complete this lab by achieving the following learning objectives:

Enable APIs

Enable the Cloud Build and Cloud Run APIs.

Retrieve the Working Files
  1. Activate the Cloud Shell.
  2. Clone the desired repository.
  3. Change directory to the working files.
Containerize the App and Store the Disk Image

Use the appropriate gcloud command invoking Cloud Build to containerize the web app and then store the resulting disk image in Container Registry.

Deploy the Disk Image to Cloud Run

In Cloud Shell, execute the proper command to deploy the stored disk image to Cloud Run.

Additional Resources

Your team is preparing to take advantage of the power and availability of cloud computing when making predictions from their trained ML models. You have been asked to take a pre-trained model and deploy it to Cloud Run for testing purposes.


Access the GitHub repo for the lab to obtain the needed code.

Deploy to the us-east1 region.

What are Hands-on Labs

Hands-on Labs are real environments created by industry experts to help you learn. These environments help you gain knowledge and experience, practice without compromising your system, test without risk, destroy without fear, and let you learn from your mistakes. Hands-on Labs: practice your skills before delivering in the real world.

Sign In
Welcome Back!

Psst…this one if you’ve been moved to ACG!

Get Started
Who’s going to be learning?