Devang Aggarwal, and Akhila Vidiyala from Intel join Cassie Breviu to talk about Intel OpenVINO + ONNX Runtime. We'll look at how you can optimize large BERT models with the power of Optimum, OpenVINO™, ONNX Runtime, and Azure! Chapters: 00:00 AI Show Begins 00:20 Welcome and Introductions 01:35 Intro to OpenVINO Execution Provider 03:04 Demo - Object detection with YOLOv7 09:41 The Architecture - how it works 11:00 Optimezation tools overview 11:33 Optimum Intel overview 13:15 What is the AI Workflow? 14:31 Demo - Quantization Aware Training Using AzureML 20:25 In review 21:54 Wrap Resources: https://aka.ms/ML/TutorialsDemos https://aka.ms/AIML/OpenSource/Blogs https://aka.ms/AzureMLModels https://aka.ms/OpenVINOAzure/Blog Watch on-demand at https://aka.ms/AIShow Subscribe to the AI Show: https://aka.ms/AIShowsubscribe AI Show Live Playlist: https://aka.ms/AIShowPlaylist Join us every other Friday, for an AI Show livestream on YouTube https://aka.ms/AIShowLive