Overview

The following describes the media data processing APIs. The APIs of different versions cannot be used together.

• Media data processing operator API: The definition of this API is more suitable for AI frameworks. The input and output data is based on tensor parameters and can be asynchronously executed on streams. In addition, this API can be collaboratively processed with the NN operator on the same stream.
• Media data processing V2 APIs: The APIs are applicable to computer vision processing applications. The input and output data is based on image parameters and supports multiple image formats such as YUV420 and RGB, providing richer and more flexible parameter configuration capabilities.
• Media data processing V1 APIs: The media APIs are not evolved and are replaced by the preceding two sets of APIs.