Index
A
- age prediction / Age prediction
- AI assistant / IBM Watson services
- Amazon ML
- Analysis and Modeling of Faces and Gestures (AMFG) / Age, gender, and emotion prediction
- Android.mk file
- reference / Android.mk
- Android NDK
- installing / Installing Android NDK and SDK
- Android SDK
- installing / Installing Android NDK and SDK
- Android Studio
- TensorFlow Lite, installing / TensorFlow Lite on Android Studio
- TensorFlow Lite, downloading / TensorFlow Lite on Android Studio
- APK binary
- downloading / Downloading the APK binary
- Application.mk file
- reference / Application.mk
- artistic neural style transfer
- about / Artistic neural style transfer
- Convolutional Neural Networks (CNNs), using / Background
- VGG network / VGG network
B
- Barchart
- reference / FreeHandView for writing
- barcode scanner
- implementing / Barcode scanner
- FirebaseVisionImage object, creating / Step one: creating a FirebaseVisionImage object
- FirebaseVisionBarcodeDetector object, creating / Step two: creating a FirebaseVisionBarcodeDetector object
- barcode, detection / Step three: barcode detection
- Basic Neural Network Subroutines (BNNS) / Core ML
- bazel
- installing / Installing Bazel
- Homebrew, installing / Installing using Homebrew
- Berkeley AI Research (BAIR) / The implementation on iOS using Core ML
C
- classification / Classification
- cloud-based text recognition
- using / Cloud-based text recognition
- detector, configuring / Configuring the detector
- CNN, for age and gender prediction
- problems / CNNs for age and gender prediction
- architecture / Architecture
- network, training / Training the network
- data, initializing / Initializing the dataset
- Computer Vision and Pattern Recognition (CVPR) / Age, gender, and emotion prediction
- convex hull / Identifying the convex hull
- convolution / Finding features from an image
- Convolutional Neural Networks (CNNs)
- about / Convolutional Neural Networks , Background, Where to start when developing an ML application
- patterns, searching / Finding patterns
- features, searching from image / Finding features from an image
- features, searching in image / Finding features from an image
- pooling layer / Pooling layer
- rectified linear units (ReLU) / Rectified linear units
- local response normalization layer / Local response normalization layer
- dropout layer / Dropout layer
- fully connected layer / Fully connected layer
- for age and gender prediction / CNNs for age and gender prediction
- convolution layer / Finding features from an image
- CoreML
- about / TensorFlow Lite and Core ML, Core ML
- model, conversion / Core ML model conversion
- custom model, converting / Converting your own model into a Core ML model
- integrating, on iOS app / Core ML on an iOS app
- Core ML
- iOS, implementation / The implementation on iOS using Core ML
- reference / Limitations of building your own model
- CoreML Tools Python package
- reference / Core ML model conversion
- cost function / Linear regression - supervised learning
- cross-entropy / Training the neural network
- custom machine learning (ML) model
- building / Building your own model
- limitations / Limitations of building your own model
- personalized user experience / Personalized user experience
- better search results / Better search results
- right user, targeting / Targeting the right user
- custom TensorFlow model
- training / Training our own TensorFlow model
- TensorFlow, installing / Installing TensorFlow
- images, training / Training the images
- images, retraining / Retraining with own images
D
- Digital Signal Processing (DSP) / Core ML
- digit classifier Android application
- building / Building the Android application
- FreeHandView, for writing / FreeHandView for writing
- writing / Digit classifier
- discriminative algorithm
- versus generative algorithm / Generative versus discriminative algorithms
- dropout layer / Dropout layer
E
- emotion prediction / Age, gender, and emotion prediction
F
- face-swapping
- about / Understanding face-swapping
- steps / Steps in face-swapping
- facial key point, detection / Facial key point detection
- convex hull, identifying / Identifying the convex hull
- Delaunay triangulation / Delaunay triangulation and Voronoi diagrams
- Voronoi diagrams / Delaunay triangulation and Voronoi diagrams
- affine warp triangles, using / Affine warp triangles
- seamless cloning / Seamless cloning
- Android application, building / Building the Android application
- native face-swapper library, building / Building a native face-swapper library
- building / Building the application
- face detection
- about / Face detection
- face, tracking / Face orientation tracking
- landmarks / Landmarks
- classification / Classification
- implementing / Implementing face detection
- face detector, configuration / Face detector configuration
- face detector
- executing / Running the face detector
- FirebaseVisionImage, creating from input / Step one: creating a FirebaseVisionImage from the input
- instance, creating of FirebaseVisionFaceDetector object / Step two: creating an instance of FirebaseVisionFaceDetector object
- image detection / Step three: image detection
- information, retrieving from detected faces / Retrieving information from detected faces
- Firebase
- reference / Adding Firebase to our application
- FirebaseVisionImage, face detector
- creating, from input / Step one: creating a FirebaseVisionImage from the input
- bitmap, using / Using a bitmap
- media.Image, using / From media.Image
- creating, with ByteBuffer / From a ByteBuffer
- creating, with ByteArray / From a ByteArray
- creating, with file / From a file
- FirebaseVisionImage object, barcode scanner
- creating / Step one: creating a FirebaseVisionImage object
- creating, with bitmap / From bitmap
- creating, with media.Image / From media.Image
- creating, with ByteBuffer / From ByteBuffer
- creating, with ByteArray / From ByteArray
- creating, form file / From file
- FlatBuffers / TensorFlow Lite memory usage and performance
- food classification iOS application
- building / Building the iOS application
- fully connected layer / Fully connected layer
G
- Gaussian Mixture Models (GMM) / Age prediction
- gender prediction / Gender prediction
- Generative Adversarial Networks (GANs)
- about / Generative Adversarial Networks, Steps in GAN
- reference / Generative Adversarial Networks
- generative algorithm, versus discriminative algorithm / Generative versus discriminative algorithms
- generative algorithm
- versus discriminative algorithm / Generative versus discriminative algorithms
- Google Cloud ML
- about / Google Cloud ML
- SIGHT / Google Cloud ML
- CONVERSATION / Google Cloud ML
- LANGUAGE / Google Cloud ML
- KNOWLEDGE / Google Cloud ML
- Google Vision APIs
- reference / Google Cloud ML
- Gradient Descent / Linear regression - supervised learning
H
- Hidden Markov Models (HMM) / Age prediction
- Homebrew
- installing / Installing using Homebrew
I
- IBM Watson services / IBM Watson services
- image format parameters
- reference / From ByteBuffer
- ImageNet classification
- reference / Architecture
- images, custom TensorFlow model
- retraining / Retraining with own images
- steps parameter, training / Training steps parameter
- architecture / Architecture
- distortions / Distortions
- hyperparameters / Hyperparameters
- training script, executing / Running the training script
- model, conversion / Model conversion
- Infrastructure as a service (IaaS) / Where to start when developing an ML application
- iOS
- TensorFlow Lite / TensorFlow Lite on iOS
- implementation, with Core ML / The implementation on iOS using Core ML
- iOS app
- CoreML, integrating on / Core ML on an iOS app
L
- Labeled Faces in the Wild (LFW) / Gender prediction
- lateral inhibition / Local response normalization layer
- linear regression / Linear regression - supervised learning
- Local Binary Pattern (LBP) / Age prediction, Gender prediction
- local response normalization (LRN) / Local response normalization layer
M
- machine learning (ML)
- about / Machine learning basics, Setting up the model
- supervised learning / Supervised learning
- unsupervised learning / Unsupervised learning, Linear regression - supervised learning
- Machine learning as a Service (MLaaS) / Where to start when developing an ML application
- Magenta
- about / Setting up the model
- reference / Setting up the model
- Microsoft Azure Cognitive Services
- Vision APIs / Microsoft Azure Cognitive Services
- Speech APIs / Microsoft Azure Cognitive Services
- Knowledge APIs / Microsoft Azure Cognitive Services
- Search APIs / Microsoft Azure Cognitive Services
- Language APIs / Microsoft Azure Cognitive Services
- reference / Microsoft Azure Cognitive Services
- Million Instructions Per Second (MIPS) / Application.mk
- ML application
- developing / Where to start when developing an ML application
- IBM Watson services / IBM Watson services
- Microsoft Azure Cognitive Services / Microsoft Azure Cognitive Services
- Amazon ML / Amazon ML
- Google Cloud ML / Google Cloud ML
- ML Kit
- about / ML Kit basics
- feature set / Basic feature set
- application, building / Building the application
- Firebase, adding to application / Adding Firebase to our application
- MNIST database
- using / Understanding the MNIST database
- reference / Understanding the MNIST database
- MobileNet models
- using / MobileNet models
- dataset, building / Building the dataset
- image, retraining / Retraining of images
- model conversion, from GraphDef to TFLite / Model conversion from GraphDef to TFLite
- Gender model / Gender model
- Emotion model / Emotion model
- Android application, building / Building the Android application
- Monet
- reference / Setting up the model
- about / Setting up the model
- MXNet converter
- reference / Core ML model conversion
N
- Native Development Kit (NDK) / Building the Android application
- native face-swapper library
- building / Building a native face-swapper library
- reference / Building a native face-swapper library
- Android.mk / Android.mk
- Application.mk / Application.mk
- face-swapping logic, applying / Applying face-swapping logic
- natural language processing (NLP) / Core ML, Where to start when developing an ML application
- NDK Archives
- reference / Installing Android NDK and SDK
- neural network
- training / Training the neural network
- digit classifier Android application, building / Building the Android application
- Neural Networks API (NNAPI) / TensorFlow Lite
- non-photo realistic rendering / Layers in the VGG network
O
- on-device text recognition
- creating / On-device text recognition
- text, detecting on device / Detecting text on a device
- OpenCV 3.0.0 version
- reference / Building the Android application
- Optical Character Recognition (OCR) / Convolutional Neural Networks , Text recognition
P
- Platform as a service (PaaS) / Where to start when developing an ML application
- pooling / Pooling layer
R
- receptive field / Convolutional Neural Networks
- rectified linear units (ReLU) / Rectified linear units
S
- SavedModel
- converting, into TensorFlow Lite / Converting SavedModel into TensorFlow Lite format
- strategies / Strategies
- seamless cloning
- about / Seamless cloning
- NORMAL_CLONE / Seamless cloning
- MIXED_CLONE / Seamless cloning
- FEATURE_EXCHANGE / Seamless cloning
- Software as a service (SaaS) / Where to start when developing an ML application
- style transfer / Setting up the model
- style transfer Android applications
- model, setting up / Setting up the model
- custom model, training / Training your own model
- building / Building the application
- camera, setting up / Setting up the camera and an image picker
- image picker, setting up / Setting up the camera and an image picker
- style transfer applications
- building / Building the applications
- reference / Building the applications
- TensorFlow-to-Core ML conversion / TensorFlow-to-Core ML conversion
- building, for iOS / iOS application
- building, for Android / Android application
- supervised learning / Supervised learning
- Support Vector Machine (SVM) / Age prediction
T
- TensorFlow-to-Core ML library
- reference / Building the applications
- TensorFlow converter
- reference / Core ML model conversion
- TensorFlow Lite
- about / TensorFlow Lite and Core ML, TensorFlow Lite
- architecture / TensorFlow Lite
- supported platforms / Supported platforms
- memory usage / TensorFlow Lite memory usage and performance
- performance, improving / TensorFlow Lite memory usage and performance
- using / Hands-on with TensorFlow Lite
- SavedModel, converting / Converting SavedModel into TensorFlow Lite format
- TensorFlow Lite, on Android
- demo app, using / TensorFlow Lite on Android
- APK binary, donwloading / Downloading the APK binary
- installing / TensorFlow Lite on Android Studio
- downloading / TensorFlow Lite on Android Studio
- demo app, building from source / Building the TensorFlow Lite demo app from the source
- bazel, installing / Installing Bazel
- Android NDK, installing / Installing Android NDK and SDK
- Android SDK, installing / Installing Android NDK and SDK
- TensorFlow Lite, on iOS
- demo app, building / TensorFlow Lite on iOS, Building the iOS demo app
- prerequisites / Prerequisites
- Tensorflow Lite models
- reference / Limitations of building your own model
- TensorFlow Lite Optimizing Converter (TOCO) / Training the neural network
- TensorFlow model
- building / Building the TensorFlow model
- text recognition
- building / Text recognition
- on-device text recognition / On-device text recognition
- cloud-based text recognition / Cloud-based text recognition
- transfer learning
- about / Transfer learning
- approaches / Approaches in transfer learning
U
- Uniform Resource Identifier (URI) / From a file
- unsupervised learning
- about / Unsupervised learning
- user experience (UX) / Personalized user experience
- user interface (UI) layout / Building the Android application
V
- VGG TensorFlow model
- reference / Layers in the VGG network
- Visual Geometry Group (VGG) network
- about / Background, VGG network
- layers / Layers in the VGG network
- Voronoi diagrams
- reference / Delaunay triangulation and Voronoi diagrams
W
- Watson Studio / IBM Watson services