Feeds: iCal | RSS | JSON | CSV (as of 06/06/2020)
Login | Need an account?

Meetup: Deploy Deep Learning models as Microservices using Open Source tools

Setup Time:
15 minutes
Thursday, February 20, 2020 at 06:00pm
Thursday, February 20, 2020 at 08:00pm
Teardown Time:
15 minutes
Estimated size:
Main Space

Powering your application with deep learning is no walk in the park, but is certainly attainable with some tricks and good practice. Serving a deep learning model on a production system demands the model to be stable, reproducible, capable of isolation and to behave as a stand-alone package. One possible solution to this is a containerized microservice.

Ideally, serving deep learning microservices should be quick and efficient, without having to dive deep into the underlying algorithms and their implementation. Too good to be true? Not anymore! Together, we will demystify the process of developing, training, and deploying deep learning models as a web microservice using Model Asset Exchange, an open source framework developed in Python at the IBM Center for Open Source Data and AI Technologies (CODAIT).

We will kick off with an overview of how deep learning models are best published as Docker Images on DockerHub, and are best prepared for deployment in local or cloud environments using Kubernetes or Docker. We highlight the following benefits of such an approach: Standardized REST API implementation and application-friendly output format (JSON) Abstracting out the complex pre and post-processing portions of the model inputs and outputs.

We will walk you through some super cool applications such as automatic image cropping, age estimation from videos/webcam and Veremin - a video theremin. All these applications and the framework itself are open sources and we conclude by inviting contributions and opening the gates for you to be a part of this amazing initiative!


Member RSVP

Hacker Dojo members may login to reserve space in the event room up to 48 hours before the event.

Member RSVP does not imply event registration if applicable.