Book Image

Intelligent Mobile Projects with TensorFlow

By : Jeff Tang
Book Image

Intelligent Mobile Projects with TensorFlow

By: Jeff Tang

Overview of this book

As a developer, you always need to keep an eye out and be ready for what will be trending soon, while also focusing on what's trending currently. So, what's better than learning about the integration of the best of both worlds, the present and the future? Artificial Intelligence (AI) is widely regarded as the next big thing after mobile, and Google's TensorFlow is the leading open source machine learning framework, the hottest branch of AI. This book covers more than 10 complete iOS, Android, and Raspberry Pi apps powered by TensorFlow and built from scratch, running all kinds of cool TensorFlow models offline on-device: from computer vision, speech and language processing to generative adversarial networks and AlphaZero-like deep reinforcement learning. You’ll learn how to use or retrain existing TensorFlow models, build your own models, and develop intelligent mobile apps running those TensorFlow models. You'll learn how to quickly build such apps with step-by-step tutorials and how to avoid many pitfalls in the process with lots of hard-earned troubleshooting tips.
Table of Contents (14 chapters)

Final words

So it's about time to say Goodbye. In this book, we started with three pre-trained TensorFlow models of image classification, object detection, and neural-style transfer, and discussed in detail how we can retrain the models and use them in iOS and Android apps. Then we covered three interesting models from the TensorFlow tutorials built with Python —audio recognition, image captioning, and quick drawing—and showed how to retrain and run the models on mobile.

After that, we developed RNN models from scratch for stock price prediction in TensorFlow and Keras, two GAN models for digit recognition and pixel translation, and an AlphaZero-like model for Connect 4, along with complete iOS and Android apps using all those TensorFlow models. We then covered how to use TensorFlow Lite, as well as Apple's Core ML with standard machine learning models...