Search icon CANCEL
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Conferences
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Machine Learning Projects for Mobile Applications

You're reading from   Machine Learning Projects for Mobile Applications Build Android and iOS applications using TensorFlow Lite and Core ML

Arrow left icon
Product type Paperback
Published in Oct 2018
Publisher Packt
ISBN-13 9781788994590
Length 246 pages
Edition 1st Edition
Languages
Tools
Arrow right icon
Author (1):
Arrow left icon
Karthikeyan NG Karthikeyan NG
Author Profile Icon Karthikeyan NG
Karthikeyan NG
Arrow right icon
View More author details
Toc

Building the applications

Here comes the app building section of the chapter. When building this application, we are going to use fast style transfers on pre-trained models. We can also use customized models with adjustments to make the app work on the iOS platform. 

The following are two examples on style transfer implementation that use TensorFlow: https://github.com/titu1994/Neural-Style-Transfer and https://github.com/yining1023/fast_style_transfer_in_ML5/.

As a consequence of this, we are going to make use of the TensorFlow-to-Core ML library 1.1.0+ in this tutorial. The GitHub link to this is as follows: https://github.com/tf-coreml/tf-coreml, and the dependencies are listed as follows:

  • tensorflow >= 1.5.0
  • coremltools >= 0.8
  • numpy >= 1.6.2
  • protobuf >= 3.1.0
  • six >= 1.10.0

To get the latest version of the TensorFlow-to-Core ML converter...

lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
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
Renews at $19.99/month. Cancel anytime