Book Image

Machine Learning with Core ML

Book Image

Machine Learning with Core ML

Overview of this book

Core ML is a popular framework by Apple, with APIs designed to support various machine learning tasks. It allows you to train your machine learning models and then integrate them into your iOS apps. Machine Learning with Core ML is a fun and practical guide that not only demystifies Core ML but also sheds light on machine learning. In this book, you’ll walk through realistic and interesting examples of machine learning in the context of mobile platforms (specifically iOS). You’ll learn to implement Core ML for visual-based applications using the principles of transfer learning and neural networks. Having got to grips with the basics, you’ll discover a series of seven examples, each providing a new use-case that uncovers how machine learning can be applied along with the related concepts. By the end of the book, you will have the skills required to put machine learning to work in their own applications, using the Core ML APIs

Related Content you might be interested in

Current Title:

Small book image
Machine Learning with Core ML
Jun, 2018 | 378 pages
Small book image
Machine Learning Projects for Mobile Applications
Karthikeyan NG
Oct, 2018 | 246 pages
Small book image
Machine Learning with Swift
Oleksandr Baiev | Alexander Sosnovshchenko
Feb, 2018 | 378 pages
Small book image
Machine Learning for Mobile
Avinash Venkateswarlu | Revathi Gopalakrishnan
Dec, 2018 | 274 pages
Table of Contents (16 chapters)
Title Page
Title Page
Packt Upsell
Packt Upsell
Contributors
Contributors
Preface
Preface
Free Chapter
1
Introduction to Machine Learning
Introduction to Machine Learning
What is machine learning?
A brief tour of ML algorithms
A typical ML workflow 
Summary
2
Introduction to Apple Core ML
Introduction to Apple Core ML
Difference between training and inference
Inference on the edge
A brief introduction to Core ML
Learning algorithms 
Considerations 
Summary
3
Recognizing Objects in the World
Recognizing Objects in the World
Understanding images
Recognizing objects in the world
Performing inference 
Summary 
4
Emotion Detection with CNNs
Emotion Detection with CNNs
Facial expressions
Input data and preprocessing 
Bringing it all together
Summary 
5
Locating Objects in the World
Locating Objects in the World
Object localization and object detection 
Converting Keras Tiny YOLO to Core ML
Making it easier to find photos
Optimizing with batches
Summary
6
Creating Art with Style Transfer
Creating Art with Style Transfer
Transferring style from one image to another 
A faster way to transfer style
Converting a Keras model to Core ML
Building custom layers in Swift
Reducing your model's weight
Summary
7
Assisted Drawing with CNNs
Assisted Drawing with CNNs
Towards intelligent interfaces 
Drawing
Recognizing the user's sketch
Summary 
8
Assisted Drawing with RNNs
Assisted Drawing with RNNs
Assisted drawing 
Recurrent Neural Networks for drawing classification
Input data and preprocessing 
Bringing it all together
Summary 
9
Object Segmentation Using CNNs
Object Segmentation Using CNNs
Classifying pixels 
Data to drive the desired effect – action shots
Building the photo effects application
Working with probabilistic results
Summary
10
An Introduction to Create ML
An Introduction to Create ML
A typical workflow 
Preparing the data
Creating and training a model
Closing thoughts
Summary
Other Books You May Enjoy
Other Books You May Enjoy
Leave a review - let other readers know what you think
Index
Index

Recurrent Neural Networks for drawing classification

The model used in this chapter was trained on the dataset used in Google's AI experiment Quick, Draw!

Quick, Draw! is a game where players are challenged to draw a given object to see whether the computer can recognize it; an extract of the data is shown as follows:

The technique was inspired from the work done on handwritten recognition (Google Translate), where, rather than looking at the image as a whole, the team worked with data features describing how the characters were drawn. This is illustrated in the following image:

Source: https://experiments.withgoogle.com/ai/quick-draw

The hypothesis here is that there exists some consistent pattern of how people draw certain types of objects; but to discover those patterns, we would need a lot of data, which we do have. The dataset consists of over 50 million drawings across 345 categories obtained cleverly, from the players of the Quick, Draw! game. Each sample is described with timestamped...

Previous Section
End of Section 3
Next Section