Update June 12, 2018: The book has been officially published and the complete source code is available here. I’m honored to have Pete Warden, the lead of Google TensorFlow mobile team as one technical reviewer of the book, and Aurélien Géron, the best-seller author of Hands-On Machine Learning with Scikit-Learn and TensorFlow, as the Foreword author who kindly writes about my book - “This is going to be a super popular book. It’s such an important topic, and it’s hard to get good reliable information.”

I’ve been working like crazy since December on a book of building mobile AI apps with TensorFlow 1.4/1.5/1.6. Early Access to the book, with 14-day free trial, is now available. Also available on Amazon for pre-order. Completed book chapters so far include fully updated, much improved, and step-by-step tutorials of using the TensorFlow image classification, object detection, neural style transfer, audio recognition, image captioning, drawing classification, stock price prediction with RNN, generating and enhancing images with GAN, and reinforcement learning models to build both iOS and Android apps.

The book also includes extensive in-depth tips that will save you a lot of time and frustration:

  • How to find out the right input and output node names of a model;
  • How to transform and optimize a model the right way;
  • How to build your customized TensorFlow library to fix all kinds of possible errors when using a model;
  • How to write code in iOS and Android to use a simple or complicated TensorFlow model and see the magic happens;
  • How to use Objective-C or Swift to develop your mobile TensorFlow iOS app;
  • How to add TensorFlow to your new iOS and Android apps or existing apps.

“Access cutting-edge content as it’s created” or wait a few more months to start learning to build all kinds of TensorFlow-powered mobile AI apps that can run anytime, anywhere like never before.