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
- Activate the Cloud Shell.
- Clone the desired repository.
- Change directory to the working files.
- Containerize the App and Store the Disk Image
Use the appropriate
gcloudcommand 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.
