Subscription

Explore Products

Best Sellers

New Releases

Books

Videos

Audiobooks

Learning Hub

Conferences

Free Learning

You're reading from Intelligent Mobile Projects with TensorFlow Build 10+ Artificial Intelligence apps using TensorFlow Mobile and Lite for iOS, Android, and Raspberry Pi

Product type Paperback

Published in May 2018

Publisher Packt

ISBN-13 9781788834544

Length 404 pages

Edition 1st Edition

Languages

Python

Tools

Android

Concepts

Artificial Intelligence

Author (1):

Jeff Tang

View More author details

Table of Contents (14) Chapters

Preface

1. Getting Started with Mobile TensorFlow FREE CHAPTER

2. Classifying Images with Transfer Learning

3. Detecting Objects and Their Locations

4. Transforming Pictures with Amazing Art Styles

5. Understanding Simple Speech Commands

6. Describing Images in Natural Language

7. Recognizing Drawing with CNN and LSTM

8. Predicting Stock Price with RNN

9. Generating and Enhancing Images with GAN

10. Building an AlphaZero-like Mobile Game App

11. Using TensorFlow Lite and Core ML on Mobile

12. Developing TensorFlow Apps on Raspberry Pi

13. Other Books You May Enjoy

Leave a review - let other readers know what you think

Using the GAN models in iOS

If you try to use the TensorFlow pod in your iOS app and load the gan_mnist.pb file, you'll get an error:

Could not create TensorFlow Graph: Invalid argument: No OpKernel was registered to support Op 'RandomStandardNormal' with these attrs. Registered devices: [CPU], Registered kernels:
 <no registered kernels>
[[Node: z_1/RandomStandardNormal = RandomStandardNormal[T=DT_INT32, _output_shapes=[[50,100]], dtype=DT_FLOAT, seed=0, seed2=0](z_1/shape)]]

Make sure your tensorflow/contrib/makefile/tf_op_files.txt file has tensorflow/core/kernels/random_op.cc, which implements the RandomStandardNormal operation, and the libtensorflow-core.a is built with tensorflow/contrib/makefile/build_all_ios.sh after the line is added to tf_op_files.txt.

Furthermore, if you try to load the pix2pix_transformed_memmapped.pb even in the custom TensorFlow...

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 (1)

Tang

Gibson Tang grew up loving technology after getting his hands on an old Apple II when he was still a young kid. Since then, he has never stopped keeping pace with technology, and after he coded his first "Hello World" program, he has been hooked on programming ever since. Following his studies at Nanyang Polytechnic and Singapore Institute of Management and serving a 6-year stint in the Republic of Singapore Navy (RSN), he honed his development skills creating software and games for Yahoo! and other Fortune 500 companies. In 2010, he founded Azukisoft Pte Ltd in Singapore to focus on mobile application development. Since then, he has developed countless mobile applications and games for start-ups and big companies both in USA and Singapore. Apart from programming, he indulges in various hobbies such as soccer, computer games, and jogging in order to get his regular dose of Vitamin D and to see the sun once in a while. Occasionally, he would be on Steam or Battle.net blowing off some steam by slaying monsters and killer robots after a day of programming.

See other products by Tang