Deep learning for Android with TensorFlow

Margaret Maynard-Reid (Tiny Peppers)

2:30pm–3:10pm Thursday, October 31, 2019

Location: Grand Ballroom H

Mobile & Edge

Who is this presentation for?

ML engineers and AI researchers who would like to deploy models to Android

Level

Intermediate

Description

If you’re interested in making intelligent apps with the most popular deep learning framework, TensorFlow, join Margaret Maynard-Reid to learn your various options from using ready-made APIs to training your own custom models. You’ll learn the end-to-end process of how to train a model with TensorFlow high-level API tf.Keras, convert it to a TensorFlow Lite model, and deploy it to Android.

You’ll get an introduction to tf.Keras and TensorFlow Lite; learn how to integrate ML Kit, a Mobile SDK powered by TensorFlow Lite; transfer learning with a pretrained model (using tf.Keras or TensorFlow Hub); and train a model from scratch and deploy it to Android for inference.

Prerequisite knowledge

A basic understanding of TensorFlow and deep learning (useful but not required)

What you'll learn

Get an introduction to TensorFlow, TensorFlow Lite, and ML Kit
Learn how to integrate ML Kit, a Mobile SDK powered by TensorFlow Lite; transfer learning with a pretrained model (using tf.Keras or TensorFlow Hub); and train a model from scratch and deploy it to Android for inference

Margaret Maynard-Reid

Tiny Peppers

Margaret Maynard-Reid is a machine learning engineer and Google Developer Expert (GDE) at Tiny Peppers, and she’s a contributor to the open source ML framework TensorFlow. She writes blog posts and speaks at conferences about on-device ML, deep learning, computer vision, TensorFlow, and Android. Margaret is passionate about community building and helping others get started with AI and ML. She’s a community leader of GDG Seattle and Seattle Data/Analytics/Machine Learning Meetup.