About this Document - 2.0 English

Vitis AI Library User Guide (UG1354)

Document ID
UG1354
Release Date
2022-01-20
Version
2.0 English

Related Libraries

The following Vitis™ AI Libraries are related to this document.
Table 1. Vitis AI Library Packet List
No Package Name Version
1 vitis_ai_library_r2.0.0_video.tar.gz r2.0.0
2 vitis_ai_library_r2.0.0_image.tar.gz r2.0.0
3 vitis-ai-runtime-2.0.0.tar.gz r2.0.0
4 vitis_ai_2021.2-r2.0.0.tar.gz r2.0.0
6 alveo_xclbin-2.0.0.tar.gz r2.0.0
7 sdk-2021.2.0.0.sh 2021.2

Intended Audience

The target users of Vitis AI libraries are as follows:

  • Users who want to use Xilinx models to quickly build applications.
  • Users who use their own models that are retrained by their own data under the Vitis AI library support network list.
  • Users who have custom models, similar to the model supported by the Vitis AI libraries, and use Vitis AI’s post-processing library.
Note: If you have custom models that are completely different from the models supported by the Vitis AI Library or have special post-processing parts, you can use the samples and libraries' implementation for reference.

Document Navigation

This document describes how to install, use, and develop with the Vitis AI Library.

  • Introduction is an introduction to the Vitis AI Library. This chapter provides a clear understanding of the Vitis AI Library in general, its framework, supported networks, and supported hardware platforms.
  • Installation describes how to install the Vitis AI Library and run the examples. The information in this chapter will help you to quickly set up the host and target environments, compile, and execute the Vitis AI Library-related examples.
  • Libraries and Samples describes each model library supported by the Vitis AI Library. This chapter provides an understanding of the model libraries supported by the Vitis AI Library, the purpose of each library, how to test the library with images or videos, and how to test the performance of the library.
  • Programming Examples describes how to develop applications with the Vitis AI Library. This chapter provides an understanding of the following:
    • Development using Vitis API
    • Development using your models
    • Customizing pre-processing
    • Using the configuration file as pre-processing and post-processing parameters
    • Using the post-processing library in the Vitis AI Library
    • Implementing your post-processing code
    • Using the xdputil tool for dpu and xmodel debug
    • Custom operator implementation and registration
  • Application Demos describes how to set up a test environment and run the application demos. There are two application demos provided with the Vitis AI Library.
  • Programming APIs describes how to find the programming APIs.
  • Performance describes the performance of the Vitis AI Library on different boards.