Subscription

Explore Products

Best Sellers

New Releases

Books

Videos

Audiobooks

Learning Hub

Conferences

Free Learning

You're reading from What's New in TensorFlow 2.0 Use the new and improved features of TensorFlow to enhance machine learning and deep learning

Product type Paperback

Published in Aug 2019

Publisher Packt

ISBN-13 9781838823856

Length 202 pages

Edition 1st Edition

Languages

Python

Tools

TensorFlow

Concepts

Deep Learning

Authors (3):

Tanish Baranwal

Alizishaan Khatri

Ajay Baranwal

View More author details

Table of Contents (13) Chapters

Preface

1. Section 1: TensorFlow 2.0 - Architecture and API Changes

2. Getting Started with TensorFlow 2.0 FREE CHAPTER

3. Keras Default Integration and Eager Execution

4. Section 2: TensorFlow 2.0 - Data and Model Training Pipelines

5. Designing and Constructing Input Data Pipelines

6. Model Training and Use of TensorBoard

7. Section 3: TensorFlow 2.0 - Model Inference and Deployment and AIY

8. Model Inference Pipelines - Multi-platform Deployments

9. AIY Projects and TensorFlow Lite

10. Section 4: TensorFlow 2.0 - Migration, Summary

11. Migrating From TensorFlow 1.x to 2.0

12. Other Books You May Enjoy

Leave a review - let other readers know what you think

Running TFLite on low-power machines

TFLite's capability of being able to run on low-power and low-binary machines makes it very powerful when run on embedded Linux machines. TFLite can be run on many of the popular embedded Linux machines, and as well as on the Coral Dev Board. In this section, we will cover the building, compiling, and running of TFLite on three devices. The first device that's covered is the Coral Dev Board with the Edge TPU processor, the second device is the NVIDIA Jetson Nano, and the final one is the Raspberry Pi. The NVIDIA Jetson Nano is a small and powerful computer from NVIDIA that runs multiple neural networks in parallel in applications such as image classification, object detection, segmentation, and speech processing.

Running TFLite on an Edge...

The rest of the chapter is locked

A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.

Unlock this book and the full library FREE for 7 days

Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of

Start free trial

Renews at $19.99/month. Cancel anytime

Authors (2)

Baranwal

Ajay Baranwal works as a director at the Center for Deep Learning in Electronics Manufacturing, where he is responsible for researching and developing TensorFlow-based deep learning applications in the semiconductor and electronics manufacturing industry. Part of his role is to teach and train deep learning techniques to professionals. He has a solid history of software engineering and management, where he got hooked on deep learning. He moved to natural language understanding (NLU) to pursue deep learning further at Abzooba and built an information retrieval system for the finance sector. He has also worked at Ansys Inc. as a senior manager (engineering) and a technical fellow (data science) and introduced several ML applications.

See other products by Baranwal

Alizishaan Khatri

Alizishaan Khatri works as a machine learning engineer in Silicon Valley. He uses TensorFlow to build, design, and maintain production-grade systems that use deep learning for NLP applications. A major system he has built is a deep learning-based system for detecting offensive content in chats. Other works he has done includes text classification and named entity recognition (NER) systems for different use cases. He is passionate about sharing ideas with the community and frequently speaks at tech conferences across the globe. He holds a master's degree in computer science from the SUNY Buffalo University. His thesis proposed a solution to the problem of overfitting in deep learning. Outside of his work, he enjoys skiing and mountaineering.

See other products by Alizishaan Khatri