book

AI and Machine Learning for On-Device Development

by Laurence Moroney

August 2021

Intermediate to advanced

326 pages

8h 31m

English

O'Reilly Media, Inc.

Audiobook available

Read now

Unlock full access

Who Should Read This Book?Why I Wrote This BookNavigating This BookTechnology You Need to UnderstandConventions Used in This BookUsing Code ExamplesO’Reilly Online LearningHow to Contact UsAcknowledgements
What Is Artificial Intelligence?What Is Machine Learning?Moving from Traditional Programming to Machine LearningHow Can a Machine Learn?Comparing Machine Learning with Traditional ProgrammingBuilding and Using Models on MobileSummary
Using Neurons for VisionYour First Classifier: Recognizing Clothing ItemsThe Data: Fashion MNISTA Model Architecture to Parse Fashion MNISTCoding the Fashion MNIST ModelTransfer Learning for Computer VisionSummary
Building a Face Detection App on AndroidStep 1: Create the App with Android StudioStep 2: Add and Configure ML KitStep 3: Define the User InterfaceStep 4: Add the Images as AssetsStep 5: Load the UI with a Default PictureStep 6: Call the Face DetectorStep 7: Add the Bounding RectanglesBuilding a Face Detector App for iOSStep 1: Create the Project in XcodeStep 2: Using CocoaPods and PodfilesStep 3: Create the User InterfaceStep 4: Add the Application LogicSummary
Image Labeling and ClassificationStep 1: Create the App and Configure ML KitStep 2: Create the User InterfaceStep 3: Add the Images as AssetsStep 4: Load an Image to the ImageViewStep 5: Write the Button Handler CodeNext StepsObject DetectionStep 1: Create the App and Import ML KitStep 2: Create the Activity Layout XMLStep 3: Load an Image into the ImageViewStep 4: Set Up the Object Detector OptionsStep 5: Handling the Button InteractionStep 6: Draw the Bounding BoxesStep 7: Label the ObjectsDetecting and Tracking Objects in VideoExploring the LayoutThe GraphicOverlay ClassCapturing the CameraThe ObjectAnalyzer ClassThe ObjectGraphic ClassPutting It All TogetherSummary
Entity ExtractionStart Creating the AppCreate the Layout for the ActivityWrite the Entity Extraction CodePutting It All TogetherHandwriting and Other RecognitionStart the AppCreating a Drawing SurfaceParsing the Ink with ML KitSmart Reply to ConversationsStart the AppMock a ConversationGenerating a Smart ReplySummary
Image Labeling and ClassificationStep 1: Create the App in XcodeStep 2: Create the PodfileStep 3: Set Up the StoryboardStep 4: Edit the View Controller Code to Use ML KitObject Detection in iOS with ML KitStep 1: Get StartedStep 2: Create Your UI on the StoryboardStep 3: Create a Subview for AnnotationStep 4: Perform the Object DetectionStep 5: Handle the CallbackCombining Object Detection with Image ClassificationObject Detection and Tracking in VideoSummary
Entity ExtractionStep 1: Create the App and Add the ML Kit PodsStep 2: Create the Storyboard with Actions and OutletsStep 3: Allow Your View Controller to be Used for Text EntryStep 4: Initialize the ModelStep 5: Extract Entities from TextHandwriting RecognitionStep 1: Create the App and Add the ML Kit PodsStep 2: Create the Storyboard, Actions, and OutletsStep 3: Strokes, Points, and InkStep 4: Capture User InputStep 5: Initialize the ModelStep 6: Do the Ink RecognitionSmart Reply to ConversationsStep 1: Create an App and Integrate ML KitStep 2: Create Storyboard, Outlets, and ActionsStep 3: Create a Simulated ConversationStep 4: Get Smart ReplySummary
What Is TensorFlow Lite?Getting Started with TensorFlow LiteSave the ModelConvert the ModelTesting the Model with a Standalone InterpreterCreate an Android App to Host TFLiteImport the TFLite FileWrite Kotlin Code to Interface with the ModelGoing Beyond the BasicsCreate an iOS App to Host TFLiteStep 1: Create a Basic iOS AppStep 2: Add TensorFlow Lite to Your ProjectStep 3: Create the User InterfaceStep 4: Add and Initialize the Model Inference ClassStep 5: Perform the InferenceStep 6: Add the Model to Your AppStep 7: Add the UI LogicMoving Beyond “Hello World”: Processing ImagesExploring Model OptimizationQuantizationUsing Representative DataSummary
Creating a Model with TensorFlow Lite Model MakerCreating a Model with Cloud AutoMLUsing AutoML Vision EdgeCreating a Model with TensorFlow and Transfer LearningCreating Language ModelsCreate a Language Model with Model MakerSummary

Bridging Models to AndroidBuilding an Image Classification App from a Model Maker OutputUsing a Model Maker Output with ML KitUsing Language ModelsCreating an Android App for Language ClassificationSummary
Bridging Models to iOSA Custom Model Image ClassifierStep 1: Create the App and Add the TensorFlow Lite PodStep 2: Create the UI and Image AssetsStep 3: Load and Navigate Through the Image AssetsStep 4: Load the ModelStep 5: Convert an Image to an Input TensorStep 6: Get Inference for the TensorUse a Custom Model in ML KitBuilding an App for Natural Language Processing in SwiftStep 1: Load the VocabStep 2: Convert the Sentence to a SequenceStep 3: Extend Array to Handle Unsafe DataStep 4: Copy the Array to a Data BufferStep 5: Run Inference on the Data and Process the ResultsSummary
Why Use Firebase Custom Model Hosting?Create Multiple Model VersionsUsing Firebase Model HostingStep 1: Create a Firebase ProjectStep 2: Use Custom Model HostingStep 3: Create a Basic Android AppStep 4: Add Firebase to the AppStep 5: Get the Model from Firebase Model HostingStep 6: Use Remote ConfigurationStep 7: Read Remote Configuration in Your AppNext StepsSummary
A Core ML Image Classifier Built Using Create MLMaking a Core ML App That Uses a Create ML ModelAdd the MLModel FileRun the InferenceUsing Create ML to Build a Text ClassifierUse the Model in an AppSummary
Installing TensorFlow ServingInstalling Using DockerInstalling Directly on LinuxBuilding and Serving a ModelAccessing a Server Model from AndroidAccessing a Server Model from iOSSummary
Ethics, Fairness, and Privacy with Responsible AIResponsibly Defining Your ProblemAvoiding Bias in Your DataBuilding and Training Your ModelEvaluating Your ModelGoogle’s AI PrinciplesSummary

Content preview from AI and Machine Learning for On-Device Development

Chapter 11. Using Custom Models in iOS

In Chapter 9, you looked at various scenarios for creating custom models using TensorFlow Lite Model Maker, Cloud AutoML Vision Edge, and TensorFlow using transfer learning. In this chapter, you’ll take a look at how to integrate these into an iOS app. We’ll focus on two scenarios: image recognition and text classification. If you’ve landed here after reading Chapter 10, our discussions will be very similar, because it’s not always as easy as just dropping a model into your app and it just works. With Android, models created with TensorFlow Lite Model Maker shipped with metadata and a task library that made integration much easier. With iOS, you don’t have the same level of support, and passing data into a model and parsing the results back will involve you getting very low level in dealing with converting your internal datatypes into the underlying tensors the model understands. After you’re done with this chapter, you’ll understand the basics on how to do that, but your scenarios may differ greatly, depending on your data! One exception to this will be if you are using a custom model type that is supported by ML Kit; we’ll explore how to use the ML Kit APIs in iOS to handle a custom model.

Bridging Models to iOS

When you train a model and convert it into TensorFlow Lite’s TFLite format, you’ll have a binary blob that you add to your app as an asset. Your app will load this into the TensorFlow Lite interpreter, and you’ll have to code for ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Start your free trial

AI for Healthcare with Keras and Tensorflow 2.0: Design, Develop, and Deploy Machine Learning Models Using Healthcare Data

Anshik

Publisher Resources

ISBN: 9781098101732Errata Page Supplemental Content

AI and Machine Learning for On-Device Development

by Laurence Moroney

Chapter 11. Using Custom Models in iOS

Bridging Models to iOS

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

You might also like

AI for Healthcare with Keras and Tensorflow 2.0: Design, Develop, and Deploy Machine Learning Models Using Healthcare Data

Machine Learning with Core ML

Practical Simulations for Machine Learning

Automated Deep Learning Using Neural Network Intelligence: Develop and Design PyTorch and TensorFlow Models Using Python

Publisher Resources

Chapter 11. Using Custom Models in iOS

Bridging Models to iOS

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,and much more.

You might also like

AI for Healthcare with Keras and Tensorflow 2.0: Design, Develop, and Deploy Machine Learning Models Using Healthcare Data

Machine Learning with Core ML

Practical Simulations for Machine Learning

Automated Deep Learning Using Neural Network Intelligence: Develop and Design PyTorch and TensorFlow Models Using Python

Publisher Resources

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.