Mobile Deep Learning with TensorFlow Lite, ML Kit and Flutter

Singh, Anubhav, Bhadani, Rimjhim



Learn how to deploy effective deep learning solutions on cross-platform applications built using TensorFlow Lite, ML Kit, and Flutter
Key Features

  • Work through projects covering mobile vision, style transfer, speech processing, and multimedia processing
  • Cover interesting deep learning solutions for mobile
  • Build your confidence in training models, performance tuning, memory optimization, and deploying neural networks through every project

Book DescriptionDeep learning is rapidly becoming the most popular topic in the industry. This book introduces trending deep learning concepts and their use cases with an industrial and application-focused approach. You will cover a range of projects covering tasks such as mobile vision, facial recognition, smart AI assistant, augmented reality, and more.
With the help of 8-projects, you will learn to integrate deep learning processes into mobile platforms, iOS, and Android. This will help you to transform deep learning features into robust mobile apps efficiently. This book gets you hands-on with selecting the right deep learning architectures and optimizing mobile deep learning models, while following an application oriented-approach to deep learning on native mobile apps. You will later cover various pre-trained and custom-built deep learning model-based APIs such as the ML Kit through Google Firebase and Core ML. Further on, the book will take you through examples of creating custom deep learning models with the help of TensorFlow Lite using Python. Each project will demonstrate how to integrate deep learning libraries into your mobile apps, right from preparing the model through to deployment.
By the end of this book, you'll have the skills to build and deploy advanced deep learning mobile applications on both iOS and Android.
What you will learn

  • Create your own customized chatbot by extending the functionality of Google Assistant
  • Improve learning accuracy with the help of features available on mobile devices
  • Perform visual recognition tasks using image processing
  • Use augmented reality to generate captions for a camera feed
  • Authenticate users and create a mechanism to identify rare and suspicious user interactions
  • Create a chess engine based on deep reinforcement learning
  • Explore the concepts and methods involved in rolling out production-ready deep learning iOS and Android applications

Who This Book Is ForThis book is for data scientists, deep learning and computer vision engineers, and NLP engineers who want to build smart mobile apps using deep learning methods. You will also find this book useful if you want to improve your mobile app's UI by harnessing the potential of deep learning. Basic knowledge of neural networks and coding experience in Python will be beneficial to get started with this book.


學習如何在使用TensorFlow Lite、ML Kit和Flutter建立的跨平台應用程式上部署有效的深度學習解決方案


- 通過涵蓋移動視覺、風格轉換、語音處理和多媒體處理等項目來進行工作
- 涵蓋有趣的移動深度學習解決方案
- 通過每個項目來建立您在模型訓練、性能調優、內存優化和部署神經網絡方面的信心



通過8個項目的幫助,您將學習將深度學習流程整合到移動平台、iOS和Android中。這將幫助您高效地將深度學習功能轉化為強大的移動應用程序。本書將以應用導向的方式介紹在本機移動應用程序上進行深度學習的適當架構選擇和優化移動深度學習模型的方法。您還將涵蓋各種預訓練和自定義的基於深度學習模型的API,例如通過Google Firebase和Core ML的ML Kit。此外,本書還將通過使用Python和TensorFlow Lite創建自定義深度學習模型的示例來引導您。每個項目都將演示如何將深度學習庫整合到您的移動應用程序中,從準備模型到部署。



- 通過擴展Google助手的功能來創建自己定制的聊天機器人
- 利用移動設備上可用的功能提高學習準確性
- 使用圖像處理執行視覺識別任務
- 使用擴增實境為攝像頭提供標題
- 認證用戶並創建識別罕見和可疑用戶交互的機制
- 基於深度強化學習創建國際象棋引擎
- 探索在生產環境中推出可用的深度學習iOS和Android應用程序所涉及的概念和方法




Anubhav Singh is the Founder of The Code Foundation, an AI-focused startup which works on multimedia processing and natural language processing, with a goal of making AI accessible to everyone. An International Rank holder in the Cyber Olympiad, he's continuously developing software for the community in domains with roads less walked by. Anubhav is a Venkat Panchapakesan Memorial Scholarship awardee and an Intel Software Innovator. Anubhav loves talking about his learnings and is an active community speaker for Google Developer Groups all over the country and can often be found guiding learners on their journey in machine learning.

Rimjhim Bhadani is an open source lover. She has always believed in making the resources accessible to everyone at a minimal cost. She is a big fan of Mobile Application Development and has developed a number of projects most which aim to solve major and minor daily life challenges. She has been an Android mentor in Google Code-In and an Android developer for Google Summer of Code. Supporting her vision to serve the community, she is one among the six Indian students to be recognized as Google Venkat Panchapakesan Memorial Scholar and one among the three Indian students to be awarded the Grace Hopper Student Scholarship in 2019.


Anubhav Singh 是 The Code Foundation 的創辦人,該基金會是一家專注於多媒體處理和自然語言處理的人工智慧初創公司,旨在使人工智慧普及化。他在網絡奧林匹克競賽中獲得國際排名,並不斷開發軟件,致力於探索不常走的領域,他是 Venkat Panchapakesan 獎學金的獲獎者,也是 Intel 軟件創新者。Anubhav 熱衷於分享他的學習經驗,是全國各地 Google 開發者社群的活躍演講者,經常指導機器學習學習者的成長過程。

Rimjhim Bhadani 是一位開源愛好者,她一直相信以最低成本使資源對所有人都可用。她是移動應用開發的忠實粉絲,開發了許多旨在解決日常生活中重要和次要挑戰的項目。她曾擔任 Google Code-In 的 Android 導師,並參與 Google Summer of Code 的 Android 開發工作。支持她服務社群的願景,她是六位印度學生中被譽為 Google Venkat Panchapakesan 獎學金的學生之一,也是2019年三位印度學生中獲得 Grace Hopper 學生獎學金的學生之一。


  1. Introduction to Deep Learning for Mobile
  2. Mobile Vision : Face Detection using on-device models
  3. Chatbot using Actions on Google
  4. Recognizing Plant Species
  5. Live Captions Generation of Camera Feed
  6. Building Artificial Intelligence Authentication System
  7. Speech/Multimedia Processing: Generating music using AI
  8. Reinforced Neural Network based Chess Engine
  9. Building Image Super-Resolution Application
  10. Road Ahead
  11. Appendix


- 深度學習在移動設備上的介紹
- 使用設備上的模型進行人臉檢測的移動視覺
- 使用Google Actions建立聊天機器人
- 辨識植物物種
- 即時生成攝影機影像的字幕
- 建立人工智慧身份驗證系統
- 語音/多媒體處理:使用人工智慧生成音樂
- 基於強化神經網絡的國際象棋引擎
- 建立圖像超解析度應用程式
- 未來展望
- 附錄