Note: All images in this directory, unless specified otherwise, are licensed under CC BY-NC 4.0.
| Figure number | Description | Notes |
|---|---|---|
| 13-1 | Not Hotdog app listing on the Apple App Store | |
| 13-2 | High-level architecture of the TensorFlow Lite ecosystem | |
| 13-3 | Start screen of Android Studio | |
| 13-4 | Android Studio “Open Existing Project” screen in the TensorFlow repository | |
| 13-5 | System information screen on an Android phone; select the About Phone option here | |
| 13-6 | The About Phone screen on an Android device | |
| 13-7 | The System information screen showing “Developer options” enabled | |
| 13-8 | “Developer options” screen on an Android device with USB debugging enabled | |
| 13-9 | Allow USB debugging on the displayed alert | |
| 13-10 | Debug toolbar in Android Studio | |
| 13-11 | Select the phone from the deployment target selection screen | |
| 13-12 | The app up-and-running app, showing real-time predictions | |
| 13-13 | Home page of Google Cloud Firebase | |
| 13-14 | The Project Overview screen on Google Cloud Firebase | |
| 13-15 | App creation screen on Firebase | |
| 13-16 | The ML Kit custom models tab | |
| 13-17 | Uploading a TensorFlow Lite model file to Firebase | |
| 13-18 | Currently uploaded custom models to Firebase | |
| 13-19 | A/B testing screen in Firebase where we can create an experiment | |
| 13-20 | The Basics section of the screen to create a remote configuration experiment | |
| 13-21 | The Targeting section of the Remote Config screen | |
| 13-22 | The Variants section of the Remote Config screen | |
| 13-23 | Analytics available when setting up an A/B testing experiment | |
| 13-24 | Performance of Fritz SDK’s object detection functionality on different mobile devices, relative to the iPhone X | Copyright reserved with Fritz.ai |
| 13-25 | Mobile AI app development life cycle | |
| 13-26 | The feedback cycle of an incorrect prediction, generating more training data, leading to an improved model | |
| 13-27 | The self-evolving model cycle | |
| 13-28 | Snap It feature from Lose It! showing multiple suggestions for a scanned food item | |
| 13-29 | Portrait effect on Pixel 3, which achieves separation between foreground and background using blurring | |
| 13-30 | Face contour points identified by ML Kit | |
| 13-31 | An input image (left) is broken down into its three components layers (R, G, B). The output mask of the previous frame ithen | appended with these components |
