Course Overview
This course covers accelerating AI deployment with OpenVINO™ toolkit. Learn to optimize AI inference across business units, from cloud to edge devices. Topics include: converting PyTorch/TensorFlow models to optimized Intel IR format, deploying across CPUs/GPUs/NPUs with unified code, using Neural Network Compression Framework for resource-constrained devices, and implementing OpenVINO Model Server for scalable production environments. Features hands-on examples and enterprise-grade solutions.
Share With
Chapter Overview
AI deployment expanded from cloud to edge devices with limited power. OpenVINO™ is an open-source toolkit converting models to Intel's IR format for efficient deployment across CPUs, GPUs, NPUs. Features Auto Plugin for optimal hardware selection & "develop once, deploy anywhere" philosophy.