The Intel® Distribution of OpenVINO™ toolkit enables high-performance, deep learning deployments.
In this session, software specialists Zoe Cayetano, Anna Belova, and Dmitry Temnov discuss optimization best practices to maximize your deep learning metrics, including throughput, accuracy, and latency.
You will:
- Get an understanding of the different optimization metrics that are important in deep learning
- Learn about the available tools and techniques to optimize your deep learning applications within Intel® Distribution of OpenVINO™ toolkit
- See a demo of how to use the Deep Learning Workbench (DL Workbench) to visually fine-tune your models
- Explore benchmarking resources to test on your own applications
- And more
Get started
- Download the latest version of the Intel® Distribution of OpenVINO™ toolkit
- Find out more about DL Workbench, a web-based graphical environment for visualizing, fine-tuning, and comparing performance of deep learning models