by Rustem Feyzkhanov | Publisher: Packt Publishing | Release Date: November 2018 | ISBN: 9781789618679

Use the serverless computing approach to save time and moneyAbout This VideoSave your time by deploying deep learning models with ease using serverless infrastructuresDevelop a solid grip on AWS services (AWS Lambda, Simple Query Service, API Gateway, and Step functions) Start building deep learning APIs, followed by mastering processing pipelines and finally deployment pipelines. In DetailOne of the main problems with deep learning models is finding the right way to deploy them within the company's IT infrastructure. Serverless architecture changes the rules of the game—instead of thinking about cluster management, scalability, and query processing, it allows us to focus specifically on training the model. This course prepares you to use your own custom-trained models with AWS Lambda to achieve a simplified serverless computing approach without spending much time and money. You will use AWS services to deploy TensorFlow models without spending hours training them. You'll learn to deploy with serverless infrastructures, create APIs, process pipelines, and more. By the end of the course, you will have implemented a project that demonstrates using AWS Lambda to serve TensorFlow models.All the code and supporting files for this course are available on Github at https://github.com/PacktPublishing/Serverless-Deep-Learning-with-TensorFlow-and-AWS-Lambda

1. Chapter 1 : Beginning with Serverless and Motivation for Serverless Deep Learning
   • The Course Overview 00:03:09
   • What Is Serverless? 00:03:05
   • Why Serverless Deep Learning 00:02:55
   • Where Serverless Deep Learning Works and Where It Doesn’t Work 00:03:30
   • Example Projects That We Will Build During the Course 00:01:44
2. Chapter 2 : Start Deploying with AWS Lambda Functions
   • Introduction to AWS Lambda Functions 00:02:20
   • Creating an AWS Account and Getting Familiar with the Basics 00:02:42
   • Creating a "Hello World" AWS Lambda Function 00:03:01
   • Introduction to Serverless Framework 00:01:57
   • Installation of Serverless Framework 00:00:57
   • Deploying AWS Lambda Functions Using Serverless Framework 00:04:28
3. Chapter 3 : Start Deploying TensorFlow Models
   • General Overview of TensorFlow 00:02:52
   • Simple TensorFlow Example 00:04:22
   • Repositories for Pretrained TensorFlow Models 00:01:56
   • Image Captioning Example 00:04:05
4. Chapter 4 : Working with TensorFlow on AWS Lambda
   • Architecture of Deploying TensorFlow with AWS Lambda 00:02:53
   • General Issues with Deploying Python Libraries on AWS Lambda 00:02:06
   • Deploying TensorFlow on AWS Lambda Using Pre-existing Pack 00:03:45
   • Deploying TensorFlow Using Serverless Framework 00:04:20
5. Chapter 5 : Creating Deep Learning API
   • Introduction to API Gateway Service 00:02:58
   • Creating API Gateway Connection to AWS Lambda Using AWS Console 00:01:32
   • Creating API Gateway Connection to AWS Lambda Using Serverless Framework 00:01:57
   • Example Project – Deep Learning API 00:03:05
6. Chapter 6 : Creating Deep Learning Pipeline
   • Introduction to AWS Simple Query Service 00:02:01
   • Creating AWS SQS Connection to AWS Lambda Using AWS Console 00:01:53
   • Creating AWS SQS Connection to AWS Lambda Using Serverless Framework 00:04:17
   • Example Project – Deep Learning Pipeline 00:03:05
7. Chapter 7 : Creating Deep Learning Workflow
   • Introduction to AWS Step Functions Service 00:02:43
   • Creating AWS Step Functions Connection to AWS Lambda Using AWS Console 00:02:41
   • Creating AWS Step Functions to AWS Lambda Using Serverless Framework 00:03:07
   • Example Project - Deep Learning Workflow 00:04:23