Abstract

Develop Scalable IVA Applications using DeepStream

Learn how to create AI-based video analytics applications using DeepStream to transform video into valuable insights. Understanding video requires multi-stream decoding/encoding, scaling, color space conversion, tracking, and multi-stage inference. DeepStream SDK allows developers to focus on core deep learning development, while offering the best system level software optimization and performance. By attending this, you'll learn how to: .....


Speaker: Adam Henryk Grzywaczweski
Type:

DLI Instructor-Led Training

Date: Thursday - October 18, 2018 03:30 PM - 05:30 PM
Location: Hall C2
Topics: Deep Learning and AI, Intelligent Video Analytics
Industry: Defense

 

Learn how to create AI-based video analytics applications using DeepStream to transform video into valuable insights. Understanding video requires multi-stream decoding/encoding, scaling, color space conversion, tracking, and multi-stage inference. DeepStream SDK allows developers to focus on core deep learning development, while offering the best system level software optimization and performance. By attending this, you'll learn how to: 1. Build modular and scalable multi-stream applications using heterogenous concurrent neural networks for video analytics 2. Utilize hardware accelerated multi-media processing and optimized memory management for high stream density and throughput 3. Utilize included sample code and pre-trained models for image classification, understanding, categorization and filtering. Prerequisites: Experience with C++