Style-transfer with TensorFlow
Google’s TensorFlow drew considerable attention in recent months as it enabled rapid Machine Learning development. In response, Google developed TensorFlow Lite - a solution for deploying intelligent applications on mobile and embedded devices. We will show how to use TensorFlow Lite to develop an app which transforms the style of pictures using a deep neural network. Style-transferring apps can transform summer into winter, horses into zebras, or a Monet into a Van Gogh. In this talk, we see rapid development of intelligent mobile device products which may or may not have a lasting impact.
Martin Musiol is Senior Data Scientist at IBM in Europe, co-founder of and instructor at GenerativeAI.net, and co-founder and former CTO of Storybeep a natural language processing company, working with the publishing industry in providing customer-specific newsletters. He is passionate about Machine Learning - more precisely Deep Learning architectures such as Generative Adversarial Networks (GANs) that are able to generate images, music, videos and other kinds of data. This is Generative AI and it eventually helps us in producing next-generation products.