Webinar: Putting a Trained ML Pipeline Behind a Web Server to Serve It
Julia Computing Webinar
When: Friday Feb 26 2021
Time: 12:00 pm - 1:00 pm US Eastern
Often in large projects, one of the key goals is to deliver a final solution to a large user base, and with the growing popularity of machine learning and data science, the final solution often looks like a machine learning pipeline. In this webinar, we will explore a simple way to deploy your trained ML models behind a webserver. We will use Dashboards.jl to make our models available over the network. You will be introduced to a basic working example of an inference pipeline and tips to scale up for larger deployments.
This webinar will be led by Dhairya Gandhi, data scientist at Julia Computing. He is responsible for developing and maintaining performant differentiable programming routines and providing core tooling through Flux.jl and Zygote.jl.