NVIDIA DeepStream SDK API Reference

Welcome to the NVIDIA DeepStream SDK API Reference.

The NVIDIA DeepStream SDK provides a framework for constructing GPU-accelerated video analytics applications running on NVIDIA^® AGX Xavier™ platforms.

Documentation is preliminary and subject to change.

API Documentation

This API Documentation describes the NVIDIA APIs that you can use to customize aspects of your device's behavior. To provide unified API documentation, the API content of this volume was generated from code comments.

Warning

The API content represents the set of public APIs you can use directly. Some APIs are not documented and we advise you do not use them directly. Using undocumented APIs can lead to incompatibility when upgrading to later releases.

The APIs included in this documentation are logically grouped into a hierarchy of modules. Header files that contribute to the same capability are grouped into a single, high-level module. Each high-level module may be further broken down into functional subcategories. To view the modules in this documentation, click the API Modules tab.

Browser Known Issues

Users may experience issue related to opening some of the included documents.

• Internet Explorer — When you open the References and the Development Guide, you must select Allow Blocked Content in response to the message:

  Internet
      Explorer restricted this webpage from running scripts or ActiveX
      controls.

  Those documents use JavaScript and ActiveX controls to provide navigation and search features. By default, Internet Explorer disables those features.

• Internet Explorer 8 — there are known issues with launching Adobe Acrobat PDFs from HTML pages. You can configure IE to use Acrobat Reader to open PDF files. First close IE, and then open Acrobat Reader. Under Edit > Preferences, select Internet and then clear the Display PDF in Browser option. Now restart IE.

Notice

ALL NVIDIA DESIGN SPECIFICATIONS, REFERENCE BOARDS, FILES, DRAWINGS, DIAGNOSTICS, LISTS, AND OTHER DOCUMENTS (TOGETHER AND SEPARATELY, "MATERIALS") ARE BEING PROVIDED "AS IS." NVIDIA MAKES NO WARRANTIES, EXPRESS, IMPLIED, STATUTORY, OR OTHERWISE WITH RESPECT TO THE MATERIALS, AND ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OR CONDITION OF TITLE, MERCHANTABILITY, SATISFACTORY QUALITY, FITNESS FOR A PARTICULAR PURPOSE AND ON-INFRINGEMENT, ARE HEREBY EXCLUDED TO THE MAXIMUM EXTENT PERMITTED BY LAW.

Information furnished is believed to be accurate and reliable. However, NVIDIA Corporation assumes no responsibility for the consequences of use of such information or for any infringement of patents or other rights of third parties that may result from its use. No license is granted by implication or otherwise under any patent or patent rights of NVIDIA Corporation. Specifications mentioned in this publication are subject to change without notice. This publication supersedes and replaces all information previously supplied. NVIDIA Corporation products are not authorized for use as critical components in life support devices or systems without express written approval of NVIDIA Corporation.

Trademarks

NVIDIA, the NVIDIA logo, CUDA, Tegra, and TensorRT are trademarks or registered trademarks of NVIDIA Corporation in the United States and other countries. Other company and product names may be trademarks of the respective companies with which they are associated.

Copyright

© 2024 by NVIDIA Corporation. All rights reserved.