Deploying Deep Learning models on the Edge (Android, IOS, ...)
Submitted by A Naveen Kumar (@4nonymou5) on Friday, 5 July 2019
Session type: Full talk of 40 mins
The ability to train the task specific deep learning models is very easy these
days, with the wide range of available libraries and documentation around it. But,
the difficulty lies in bringing it to production ready mode. Especially, if the
application concentrates on Mobile platform. Though there are existing wrappers of certain libraries to make them work, but,
as of now, they are slow and use up almost the entire memory space of the
In this talk, I would like to explain, what can be done to make things faster and
how to make models with reduced size. The aim of this talk is to provide insights
on what would be the difficulties which lie ahead and how to build your own
libraries in both iOS and Android.
What is Deep Learning ?
5 mins, introduction and explanation
What are the difficulties faced to push them into mobile production ?
How to solve it in IOS ?
How to solve it in Android ?
How to solve it on other edge devices ?
Generic Idea of creating deep learning models and there deployement.
I am a member of the data science team at Here Maps - Automating Maps. Over the years, I have had the chance to work on various aspects of Deep Learning, one such scenario was running the models on mobile. We made an app named Flo, which got featured by Apple on their twitter page for using AI and their framework to make it run faster. Currently, I am working on making perception modules run on the edge devices.