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. |
Parent topic: TextGenerationPostProcessBase