Deploying models to production with TensorFlow model server

62 RSVP'ed

About this event

Talk Abstract

How to serve TensorFlow models over HTTP and HTTPS. How we can essentially follow the main steps of putting a model into production, package it and make it ready for deployment, upload it somewhere in the cloud, make an API, and most importantly have no downtime while you are updating the model and doing version numbering efficiently. We plan to cover all these which are the steps required to deploy a model in the wild and how TensorFlow simplifies them for a developer. We will show how applications could access the model maybe through web or cloud calls. We will also show how one could make this deployment to auto-scale using GCP Cloud functions and/or Kubernetes

Speaker Bio

Rishit Dagli is a 10-grade student and is a past TED-X and Ted-Ed speaker. He is an AI and Cloud enthusiast and is also a Google Certified Mobile site developer. He has often represented India in international level Hackathons and competitions and also won a few. He most recently represented the country and won the International Hackathon on Blockchain and IoT by IET. While free, he loves to conduct research and has written 7 research papers in the field of AI and Robotics and Mathematics. He also loves writing technical blogs and has written quite a few of them in the past. With this, he was also awarded the Smartest Techno Kid Award in 2017. He has also given quite a few talks in other communities and colleges. He also was among the top 10 winners for Palo Alto Networking Challenge with GCP. Besides this, he also manages the communities Kotlin Mumbai and Mozilla Mumbai.

Social Media Links
LinkedIn :
Twitter :
GitHub :