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)

Summary

In this chapter, we gave the wonderful world of GANs a quick tour. We covered what GANs are and why they're so interesting – the way the generator and the discriminator play against each other and try to beat each other probably sounds appealing to most people. We then went through the detailed steps of how to train a basic GAN model and a more advanced image resolution enhancement model, and how to prepare them for mobile devices. Finally, we showed you how to build iOS and Android apps using the models. If you're excited about the whole process and the results, you'll definitely want to further explore GANs, a rapidly developing field where new types of GANs have been developed quickly to overcome the shortcomings of the previous models; for example, the same researchers who developed the pix2pix model which requires paired images for training,...