Please note: You will need an AWS account to complete this course. Your AWS account will be charged as per your usage. Please make sure that you are able to access Sagemaker within your AWS account. If your AWS account is new, you may need to ask AWS support for access to certain resources. You should be familiar with python programming, and AWS before starting this hands on project. We use a Sagemaker P type instance in this project, and if you don't have access to this instance type, please contact AWS support and request access. In this 2-hour long project-based course, you will learn how to train and deploy a Semantic Segmentation model using Amazon Sagemaker. Sagemaker provides a number of machine learning algorithms ready to be used for solving a number of tasks. We will use the semantic segmentation algorithm from Sagemaker to create, train and deploy a model that will be able to segment images of dogs and cats from the popular IIIT-Oxford Pets Dataset into 3 unique pixel values. That is, each pixel of an input image would be classified as either foreground (pet), background (not a pet), or unclassified (transition between foreground and background). Since this is a practical, project-based course, we will not dive in the theory behind deep learning based semantic segmentation, but will focus purely on training and deploying a model with Sagemaker. You will also need to have some experience with Amazon Web Services (AWS).
Python programming, conceptual understanding of deep learning, and previous experience with AWS is required.