Put open source to work
July 16–17, 2018: Training & Tutorials
July 18–19, 2018: Conference
Portland, OR

Serverless deep learning; or, How to port your TensorFlow model to AWS Lambda

Rustem Feyzkhanov (Instrumental)
4:15pm4:55pm Wednesday, July 18, 2018
Tags: tensorflow
Level: Beginner
Average rating: ***..
(3.00, 1 rating)

Who is this presentation for?

  • Data engineers, data scientists, and DevOps engineers

Prerequisite knowledge

  • A basic understanding of AWS, TensorFlow, and Keras

What you'll learn

  • Explore an image recognition tool that ports TensorFlow to AWS Lambda
  • Learn how to architect serverless ML in your cloud pipeline
  • Understand whether serverless ML/DL is right for your use case and challenges you may encounter along the way

Description

This year TensorFlow 1.4 was released. Rustem Feyzkhanov explains how he ported it to AWS Lambda and built an image recognition tool. The tool is cheaper than almost any alternatives: one run (recognition of one picture) will cost $0.00005. It’s also very scalable (a thousand functions can be run in parallel) and integrates into cloud infrastructure.

Topics include:

  • How to determine if serverless ML/DL is right for you or your company
  • How to architect serverless ML in your cloud pipeline
  • How to port your model to a serverless architecture
  • Challenges when using serverless ML
Photo of Rustem Feyzkhanov

Rustem Feyzkhanov

Instrumental

Rustem Feyzkhanov is a machine learning engineer at Instrumental, where he creates analytical models for the manufacturing industry. Rustem is passionate about serverless infrastructure (and AI deployments on it) and is the author of the course and book Serverless Deep Learning with TensorFlow and AWS Lambda.

Comments on this page are now closed.

Comments

Picture of Rustem Feyzkhanov
Rustem Feyzkhanov | MACHINE LEARNING ENGINEER
07/18/2018 12:33am PDT

Link to the presentation: http://bit.ly/2L72P2y