NVIDIA TAO Toolkit and Deep Stream SDK

di Anand Vemula (Autore)

Anand Vemula, 2024

This audiobook is narrated by a digital voice. Part 1: Introduction to Vision AI and Deep Learning Lays the groundwork for computer vision and deep learning concepts. Explains how these technologies are used in real-world applications. Introduces NVIDIA TAO and DeepStream, your one-stop shop for vision AI development. Part 2: NVIDIA TAO Toolkit - Your Vision AI Training Companion Guides you through setting up and navigating the user-friendly TAO interface. Explains how to prepare your data for efficient model training. Covers techniques for leveraging pre-trained models and adding new classes. Dives into model training optimization and explores methods for reducing model size for deployment. Teaches you how to export your trained models for seamless integration with DeepStream. Part 3: NVIDIA DeepStream SDK - Unleashing Your Vision AI in Real-Time Unveils the core functionalities and architecture of DeepStream for real-time video analytics. Explains how DeepStream leverages GStreamer, a powerful framework, for efficient data processing. Provides step-by-step guidance on building real-time video analytics pipelines using DeepStream. Explores various DeepStream plugins for common tasks like decoding, inference, and displaying results. Demonstrates how to integrate your TAO models into DeepStream pipelines for real-world applications. Part 4: Deployment and Optimization - Taking Your DeepStream Applications to the Real World Explores different deployment options for your DeepStream applications, from edge devices to cloud servers.

• Autore: Anand Vemula
• Durata in (hh:mm:ss): 00:28:39
• Anno edizione: 2024
• Editore: Anand Vemula
• EAN: 9798882392085

Testo in en