Machine Learning: Model Deployment Using Blue/Green Method

Languages Available: Español (Latinoamérica) | Français | Bahasa Indonesia | Italiano | 日本語 | 한국어 | Português (Brasil) | 中文（简体)

In this lab, you’ll create a machine learning model for housing price predictions and then deploy that model for real-time inferencing. You’ll interact with the model through a the Jupyter notebook and push test data to the endpoint. You’ll then train and deploy a new model using an alternate algorithm. Finally, create a new endpoint configuration and shift all traffic from the blue environment to the green.

Level

Advanced

Duration

2 Hours 0 Minutes

Course Objectives

In this course, you will learn how to:

• Deploy a machine learning model using Amazon Sagemaker
• Update a model to use a different algorithm
• Deploy an updated model using a blue/green deployment method

Intended Audience

This course is intended for:

• Architects
• DevOps Engineers
• Systems Operators

Prerequisites

We recommend that attendees of this course have the following prerequisites:

• Access to a notebook computer with Wi-Fi running Microsoft Windows, Mac OS X, or Linux (Ubuntu, SuSE, or Red Hat). The lab environment is not accessible using an iPad or tablet device, but you can use these devices to access the student guide
• For Microsoft Windows users: administrator access to the computer
• An internet browser such as Chrome, Firefox, or Internet Explorer 9 (previous versions of Internet Explorer are not supported)
  
  

Course Outline

• Task 1: Review and complete the provided exercise notebook