Lite docs: Update guide/

Remove tfmobile/ dir

PiperOrigin-RevId: 236568927

tensorflow/lite/g3doc/_book.yaml

@@ -14,37 +14,42 @@ upper_tabs:
     other:
     - name: Guide
       contents:
-      - title: Overview
-        path: /lite/overview
-      - title: Developer guide
-        path: /lite/devguide
-      - title: Android demo app
-        path: /lite/demo_android
-      - title: iOS demo app
-        path: /lite/demo_ios
-      - break: true
-      - title: TensorFlow Lite inference
-        path: /lite/inference
-      - title: Custom operators
-        path: /lite/custom_operators
-      - title: TensorFlow Lite ops versioning
-        path: /lite/ops_versioning
-      - title: TensorFlow Lite compatibility guide
-        path: /lite/tf_ops_compatibility
-      - title: TensorFlow Lite for iOS
-        path: /lite/ios
-      - title: TensorFlow Lite for Raspberry Pi
-        path: /lite/rpi
+      - title: TensorFlow Lite guide
+        path: /lite/guide
 
-      - heading: TF Lite converter
+      - heading: Get started
       - title: Overview
+        path: /lite/guide/get_started
+      - title: Android quickstart
+        path: /lite/guide/android
+      - title: iOS quickstart
+        path: /lite/guide/ios
+      - title: TensorFlow Lite FAQ
+        path: /lite/guide/faq
+
+      - heading: Convert a model
+      - title: TensorFlow Lite converter
         path: /lite/convert/
-      - title: Python API guide
-        path: /lite/convert/python_api
       - title: Command line examples
         path: /lite/convert/cmdline_examples
       - title: Command line reference
         path: /lite/convert/cmdline_reference
+      - title: Python API
+        path: /lite/convert/python_api
+
+      - heading: Inference
+      - title: Overview
+        path: /lite/guide/inference
+      - title: Custom operators
+        path: /lite/guide/ops_custom
+      - title: Operator versions
+        path: /lite/guide/ops_version
+      - title: Operator compatibility
+        path: /lite/guide/ops_compatibility
+      - title: Select operators from TensorFlow
+        path: /lite/guide/ops_select
+      - title: List of hosted models
+        path: /lite/guide/hosted_models
 
       - heading: Performance
       - title: Best practices
@@ -63,22 +68,13 @@ upper_tabs:
       - title: Advanced GPU
         path: /lite/performance/gpu_advanced
 
-      - title: TF Mobile
-        style: accordion
-        status: deprecated
-        section:
-        - title: Overview
-          path: /lite/tfmobile/
-        - title: Building TensorFlow on Android
-          path: /lite/tfmobile/android_build
-        - title: Building TensorFlow on iOS
-          path: /lite/tfmobile/ios_build
-        - title: Integrating TensorFlow libraries
-          path: /lite/tfmobile/linking_libs
-        - title: Preparing models for mobile deployment
-          path: /lite/tfmobile/prepare_models
-        - title: Optimizing for mobile
-          path: /lite/tfmobile/optimizing
+      - heading: Build TensorFlow Lite
+      - title: Buiild for iOS
+        path: /lite/guide/build_ios
+      - title: Build for ARM64
+        path: /lite/guide/build_arm64
+      - title: Build for Raspberry Pi
+        path: /lite/guide/build_rpi
 
     - name: Examples
       contents:
@@ -89,8 +85,6 @@ upper_tabs:
       contents:
       - title: Overview
         path: /lite/models/
-      - title: Hosted models
-        path: /lite/models/hosted
       - title: Image classification
         section:
         - title: Overview

tensorflow/lite/g3doc/convert/cmdline_examples.md

@@ -1,4 +1,4 @@
-# Converter command-line examples
+# Converter command line examples
 
 This page shows how to use the TensorFlow Lite Converter in the command line.
 

tensorflow/lite/g3doc/convert/cmdline_reference.md

@@ -1,4 +1,4 @@
-# Converter command-line reference
+# Converter command line reference
 
 This page is complete reference of command-line flags used by the TensorFlow
 Lite Converter's command line starting from TensorFlow 1.9 up until the most

tensorflow/lite/g3doc/convert/index.md

@@ -1,4 +1,4 @@
-# TensorFlow Lite Converter
+# TensorFlow Lite converter
 
 TensorFlow Lite uses the optimized
 [FlatBuffer](https://google.github.io/flatbuffers/) format to represent graphs.

tensorflow/lite/g3doc/demo_android.md → tensorflow/lite/g3doc/guide/android.md

@@ -1,5 +1,4 @@
-
-# Android Demo App
+# Android quickstart
 
 An example Android application using TensorFLow Lite is available
 [on GitHub](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/java/demo).

tensorflow/lite/g3doc/linux_aarch64.md → tensorflow/lite/g3doc/guide/build_arm64.md

@@ -1,4 +1,4 @@
-# TensorFlow Lite for generic ARM64 boards
+# Build TensorFlow Lite for ARM64 boards
 
 ## Cross compiling
 

tensorflow/lite/g3doc/rpi.md → tensorflow/lite/g3doc/guide/build_rpi.md

@@ -1,4 +1,4 @@
-# TensorFlow Lite for Raspberry Pi
+# Build TensorFlow Lite for Raspberry Pi
 
 ## Cross compiling
 

tensorflow/lite/g3doc/devguide.md → tensorflow/lite/g3doc/guide/get_started.md

@@ -1,4 +1,4 @@
-# TF Lite Developer Guide
+# Get started with TensorFlow Lite
 
 Using a TensorFlow Lite model in your mobile app requires multiple
 considerations: you must choose a pre-trained or custom model, convert the model

tensorflow/lite/g3doc/overview.md → tensorflow/lite/g3doc/guide/index.md

@@ -1,5 +1,5 @@
 
-# Introduction to TensorFlow Lite
+# TensorFlow Lite guide
 
 TensorFlow Lite is TensorFlow’s lightweight solution for mobile and embedded
 devices. It enables on-device machine learning inference with low latency and a

tensorflow/lite/g3doc/inference.md → tensorflow/lite/g3doc/guide/inference.md

@@ -1,4 +1,4 @@
-# TensorFlow Lite Inference
+# TensorFlow Lite inference
 
 [TOC]
 

tensorflow/lite/g3doc/demo_ios.md → tensorflow/lite/g3doc/guide/ios.md

@@ -1,4 +1,4 @@
-# iOS Demo App
+# iOS quickstart
 
 This tutorial provides a simple iOS mobile application to classify images using
 the iOS device camera. In this tutorial, you will download the demo application

tensorflow/lite/g3doc/tf_ops_compatibility.md → tensorflow/lite/g3doc/guide/ops_compatibility.md

@@ -1,4 +1,4 @@
-# TensorFlow Lite & TensorFlow Compatibility Guide
+# TensorFlow Lite and TensorFlow operator compatibility
 
 TensorFlow Lite supports a number of TensorFlow operations used in common
 inference models. As they are processed by the TensorFlow Lite Optimizing

tensorflow/lite/g3doc/using_select_tf_ops.md → tensorflow/lite/g3doc/guide/ops_select.md

@@ -1,4 +1,6 @@
-# [Experimental] Using TensorFlow Lite with select TensorFlow ops
+# Select TensorFlow operators to use in TensorFlow Lite
+
+Caution: This feature is experimental.
 
 The TensorFlow Lite builtin op library has grown rapidly, and will continue to
 grow, but there remains a long tail of TensorFlow ops that are not yet natively
@@ -196,9 +198,7 @@ Python support is actively under development.
 
 When using a mixture of both builtin and select TensorFlow ops, all of the same
 TensorFlow Lite optimizations and optimized builtin kernels will be be available
-and usable with the converted model. For the TensorFlow ops, performance should
-generally be comparable to that of
-[TensorFlow Mobile](https://www.tensorflow.org/lite/tfmobile/).
+and usable with the converted model.
 
 The following table describes the average time taken to run inference on
 MobileNet on a Pixel 2. The listed times are an average of 100 runs. These

tensorflow/lite/g3doc/ops_versioning.md → tensorflow/lite/g3doc/guide/ops_version.md

@@ -1,5 +1,4 @@
-
-# TensorFlow Lite Ops Versioning
+# TensorFlow Lite operator versions
 
 This document describes TensorFlow Lite's op versioning schema. Op
 versioning enables developers to add new functionalities and parameters into

tensorflow/lite/g3doc/performance/benchmarks.md

@@ -1,5 +1,4 @@
-
-# Performance
+# Performance benchmarks
 
 This document lists TensorFlow Lite performance benchmarks when running well
 known models on some Android and iOS devices.

tensorflow/lite/g3doc/performance/gpu.md

@@ -1,4 +1,4 @@
-# TensorFlow Lite GPU Delegate Tutorial
+# TensorFlow Lite GPU delegate
 
 [TensorFlow Lite](https://www.tensorflow.org/lite) supports several hardware
 accelerators. This document describes how to preview the experimental GPU backend using the