BatchVector

Function Usage

Combine batches into a tensor. This function calls BatchConcat and BatchStack to perform batch combination. The keepDims parameter is used to control the function to be called.

Prototype

static APP_ERROR TensorBase::BatchVector(const std::vector<TensorBase> &inputs, TensorBase &output, const bool &keepDims = false);

Parameters

Parameter	Input/Output	Description
inputs	Input	For a multi-batch model, the TensorBase object list is used as the input. The list size cannot exceed 1024.
output	Output	A TensorBase object is output after the batches are combined.
keepDims	Input	Parameter that retains the multidimensional feature. true indicates that the internal BatchConcat function is called to retain the multidimensional feature. false indicates that the internal BatchStack function is not called to retain the multidimensional feature.

Parameter

Input/Output

Description

inputs

Input

For a multi-batch model, the TensorBase object list is used as the input. The list size cannot exceed 1024.

output

Output

A TensorBase object is output after the batches are combined.

keepDims

Input

Parameter that retains the multidimensional feature.

true indicates that the internal BatchConcat function is called to retain the multidimensional feature.
false indicates that the internal BatchStack function is not called to retain the multidimensional feature.

Response Parameters

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

Parent topic: TensorBase