Amazon SageMaker: Build an Object Detection Model Using Images Labeled with Ground Truth

In this course we’ll join Dr. Denis Batalov, worldwide AI/ML Tech Leader, as he shows you how to implement a machine learning pipeline using Amazon SageMaker and Amazon SageMaker Ground Truth. First you will create a labeled dataset, then you’ll create a training job to train your object detection model, and finally you will use Amazon SageMaker to create and update your model.

Intended Audience

This course is intended for:

• Developers and data scientists who want to create machine learning pipelines with Amazon SageMaker using the Sagemaker SDK and python.
• Developers and data scientists who want to use Amazon SageMaker Ground Truth to create their own labeled datasets.

Course Objectives

In this course, you will learn how to:

• Train a machine learning model using images labeled by Amazon SageMaker Ground Truth
• Use Amazon SageMaker Ground Truth to identify the exact location of bees on individual images in a dataset
• Train the object detection model using Amazon SageMaker in-built algorithms
• Use an automated hyperparameter tuning job to find an optimal set of hyperparameters

Prerequisites

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

• A basic understanding Amazon SageMaker (https://aws.amazon.com/sagemaker/)
• A basic understanding of the python programming language with various libraries like Pandas, NumPy, SageMaker, and Boto3

Delivery Method

This course is delivered through:

• Digital training

Duration

• 70 minutes

Course Outline

This course covers the following concepts:

• Downloading data
• Running a labeling job
• Training a model
• Deploying a model
• Hyperparameters/automated model tuning
• Examining hyperparameter optimization results
• Replacing a machine learning production model