DevConf.US 2021 is the 5th annual, free, Red Hat sponsored technology conference for community project and professional contributors to Free and Open Source technologies coming to Boston!
Deep learning networks, and in particular neural networks, can use large amounts of resources during and after the training phase rendering models too large or “heavy” to place on edge devices for inference. Red Hat and Intel have worked together to integrate the OpenVINO toolkit with Open Data Hub. In this presentation, we’ll show you how to use Model Optimizer from OpenVINO to create intermediate representations of existing models. Post optimization, we’ll detail how to use the intermediate representations to perform accelerated, in-notebook inference. Finally, we’ll illustrate how to deploy a serving endpoint for accelerated inference with OpenVINO Model Server.
