You're reading from Learn TensorFlow Enterprise Build, manage, and scale machine learning workloads seamlessly using Google's TensorFlow Enterprise

Product type Paperback

Published in Nov 2020

Publisher Packt

ISBN-13 9781800209145

Length 314 pages

Edition 1st Edition

Languages

Python

Tools

TensorFlow

Concepts

Artificial Intelligence

Author (1):

KC Tung

View More author details

Table of Contents (15) Chapters

Preface

1. Section 1 – TensorFlow Enterprise Services and Features

2. Chapter 1: Overview of TensorFlow Enterprise FREE CHAPTER

3. Chapter 2: Running TensorFlow Enterprise in Google AI Platform

4. Section 2 – Data Preprocessing and Modeling

5. Chapter 3: Data Preparation and Manipulation Techniques

6. Chapter 4: Reusable Models and Scalable Data Pipelines

7. Section 3 – Scaling and Tuning ML Works

8. Chapter 5: Training at Scale

9. Chapter 6: Hyperparameter Tuning

10. Section 4 – Model Optimization and Deployment

11. Chapter 7: Model Optimization

12. Chapter 8: Best Practices for Model Training and Performance

13. Chapter 9: Serving a TensorFlow Model

14. Other Books You May Enjoy

Leave a review - let other readers know what you think

Chapter 4: Reusable Models and Scalable Data Pipelines

In this chapter, you will learn different ways of using scalable data ingestion pipelines with pre-made model elements in TensorFlow Enterprise's high-level API's. These options provide the flexibility to suit different requirements or styles for building, training, and deploying models. Armed with this knowledge, you will be able to make informed choices and understand trade-offs among different model development approaches. The three major approaches are TensorFlow Hub, the TensorFlow Estimators API, and the TensorFlow Keras API.

TensorFlow Hub is a library of open source machine learning models. TensorFlow Estimators and tf.keras APIs are wrappers that can be regarded as high-level elements that can be configured and reused as building blocks in a model. In terms of the amount of coding required, TensorFlow Hub models require the least amount of extra coding, while Estimator and Keras APIs are building blocks at...