This is a cross-post of a Google AI Huddle event. Please RSVP either here or there (https://www.meetup.com/Google-AI-Huddle-Seattle/events/264703186/)
This is a great opportunity for you to learn about how to deploy ML models to cloud, mobile and IoT!
5:30 - 6:15 networking
6:15 - 6:45 presentation #1
6:45 - 7:00 presentation #2
7:00 - 7:30 Q&A
7:30- 8:00 networking
Speaker: Andrew Ferlitsch, Google Cloud AI/Developer Relations
We are going to talk about tackling problems moving into large scale production. Topics covered: Subclassing in tf.Keras, Pre-stems for adapting existing models, deconvoltuions for learning upsampling, distributed batch prediction and warmup techniques.
This talk will be a combination of presentation, live coding and "unscripted" interaction with the attendees. Feel free to interrupt, ask questions, or just share your experiences with others on the topics that are raised.
Title: Deploy ML models to Mobile & IoT
Speaker: Margaret Maynard-Reid, ML GDE
This talk covers the various options of deploying ML models to the edge: from ready-made APIs to training your own custom models. An overview of the end-to-end process of model training, conversion and deploying to mobile / embedded devices. Discussion of the new features of TensorFlow Lite in TensorFlow 2.0.
Who is this presentation for?
ML Practitioners and leads tackling the transition from going from development stage to "large-scale" production.
Level: Intermediate to Advanced
- Experienced with TF 1.X and tf.Keras
- Experienced with ML development phase
- Transitioning or in Production deployment phase
Andrew Ferlitsch is an expert on computer vision and deep learning at Google Cloud AI Developer Relations, and formerly a principal research scientist for 20 years at Sharp Corporation of Japan, where he has 114 issued US patents and worked on emerging technologies: telepresence, augmented reality, digital signage, and autonomous vehicles. Currently in his present role, he reaches out to developer communities, corporations and universities, teaching Deep Learning and evangelizing Google's AI technologies.
Margaret Maynard-Reid is a Google Developer Expert (GDE) for Machine Learning. She is 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. She is passionate about community building and helping others get started with AI/ML. She leads GDG Seattle and Seattle Data/Analytics/ML.