Process

Function Usage

Receives the model inference output tensors and outputs the text generation result. During subsequent execution, Init needs to be executed first.

Prototype

1
virtual APP_ERROR TextGenerationPostProcessBase::Process(const std::vector<TensorBase>& tensors, std::vector<TextsInfo>& textsInfos, const std::map<std::string, std::shared_ptr<void>> &configParamMap = {});

Parameters

Parameter

Input/Output

Description

tensors

Input

Input tensors for model postprocessing.

textsInfos

Output

Output text generation result.

configParamMap

Input

(Optional) Other parameters.

Response Parameters

Data Structure

Description

APP_ERROR

For details about the returned error codes, see APP_ERROR Description.