Optimization Techniques with Intel’s OpenVINO to Enhance Performance on Your Existing Hardware


Date:  Tuesday, May 17 (Main Conference Day 1)

Start Time: 2:05 pm

End Time: 2:35 pm

Whether you’re using TensorFlow, PyTorch or another framework, we’ll show you optimization techniques to enhance performance on your existing hardware. With the OpenVINO Toolkit, built on the foundation of OneAPI, developers can utilize their own AI model or leverage one of the hundreds of pre-trained models available across vision and audio use cases. Learn how the Neural Network Compression Framework provides optimal model training templates for performance boosts while preserving accuracy, and how the Model Optimizer reduces complexity and makes model conversion faster. Other areas we’ll explore include auto device discovery to enable automatic load balancing and how to optimize for latency or throughput based on your workload.

Track

Session Speakers

  • Nico Galoppo is a principal AI engineer at Intel with a passion for top-to-bottom software stack optimization. His experience is with computer vision, deep learning inference, general purpose GPU compute, and media processing. In his 14 years at Intel, he has influenced the OpenCL standard, improved mixed reality graphics, and built computer vision products for stereo depth reconstruction and visual recognition. Today, he is helping Intel customers win with power-optimized AI inference on Intel hardware and driving new customer needs into the OpenVINO deep learning inference product. Nico graduated with a PhD. in Computer Science from UNC, Chapel Hill and a MSc. EE from the Katholieke Universiteit in Leuven. He grew up in Belgium feasting on mussels, fries, and chocolate. Today he lives in Portland, OR with a lovely family with two little monkeys.

  • Ryan Loney is a Technical Product Manager for OpenVINO Developer Tools at Intel. He is passionate about making AI accessible to everyone and improving our lives with technology. In his spare time, he enjoys alpine skiing, traveling, and training his dog.


Share

Optimization Techniques with Intel’s OpenVINO to Enhance Performance on Your Existing Hardware