hands-on lab

Machine Learning - Training Custom Models

Difficulty: Beginner
Duration: Up to 3 hours
Students: 2,503
Rating: 3.9/5
Get guided in a real environmentPractice with a step-by-step scenario in a real, provisioned environment.
Learn and validateUse validations to check your solutions every step of the way.
See resultsTrack your knowledge and monitor your progress.

Description

Machine learning is the process of teaching a computer system how to make predictions through experience. In order for a computer to understand a model must be created on an initial set of data. This lab is aimed at machine learning beginners who want to understand how to train custom models. After completing this lab you will understand how to create a machine learning model based on a categorized set of images. Additionally, you will gain familiarity with Amazon Rekognition, and basic Python concepts for interacting with the sample model.

Learning Objectives

Upon completion of this lab you will be able to:

  • Understand machine learning model training over a set of images concepts
  • Utilizing Python to interact with the Amazon Rekognition Models to classify images

Intended Audience

This lab is intended for:

  • Individuals starting out with machine learning
  • Anyone interested in training custom models and/or image classification

Prerequisites

You should possess:

  • A basic understanding of Python

Updates

March 18th, 2024 - Updated the AWS console instructions

April 18th, 2023 - Updated instruction to address the Jupyter interface experience

January 13th, 2023 - Added instructions to address the Jupyter interface experience.

December 21st, 2021 - Added instructions to reflect the latest Jupyter interface experience.

June 16th, 2020 - Added instructions on how to clean up the Rekognition model and project.

Covered topics

Lab steps

Logging In to the Amazon Web Services Console
Opening the Lab's Jupyter Notebook