In practice, users have many different application requirements, but it basically falls into three categories. The first is to use the ready-made models provided by Vitis AI Library to quickly build their own applications, and the second is to use users’ own custom models which are similar to the models in the AI Library and the last is to use new models that are totally different from the models in the AI Library. This chapter describes the detailed development steps for the first two cases. For the third case, users can also use the AI Library’s samples and libraries implementation for reference. Therefore, this chapter describes the following contents:
- How to customize pre-processing
- How to use the configuration file as pre-processing and post-processing parameter
- How to use the AI Library's post-processing library
- How to implement user post-processing code
The following figure shows the relationships of the various AI Library APIs and their corresponding example. And there are three kinds of APIs in this release.
- Vitis AI API_0
- AI Library API_1
- AI Library API_2
