ONE - On-device Neural Engine
All Data Structures Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Macros Modules Pages
arm_compute::NEEmbeddingLookup Class Reference

Class to perform EmbeddingLookup operation. More...

#include <NEEmbeddingLookup.h>

Collaboration diagram for arm_compute::NEEmbeddingLookup:

Public Member Functions

void configure (const ITensor *input, ITensor *output, const ITensor *lookups)
 Set the input and output tensors.
 

Static Public Member Functions

static Status validate (const ITensorInfo *input, const ITensorInfo *output, const ITensorInfo *lookups)
 

Detailed Description

Class to perform EmbeddingLookup operation.

Definition at line 63 of file NEEmbeddingLookup.h.

Member Function Documentation

◆ configure()

void NEEmbeddingLookup::configure ( const ITensor *  input,
ITensor *  output,
const ITensor *  lookups 
)

Set the input and output tensors.

Parameters
[in]inputSource tensor. Data types supported: U8/S8/QASYMM8/U16/S16/U32/S32/F16/F32
[out]outputDestination tensor. Data types and data layouts supported: Same as input.
[in]lookupsLookups 1D tensor that values are indices into the first dimension of input. Data types supported: S32.
Returns
N/A

Definition at line 47 of file NEEmbeddingLookup.cpp.

48{
49 auto k = std::make_unique<NEEmbeddingLookupKernel>();
50 k->configure(input, output, lookups);
51 _kernel = std::move(k);
52}

◆ validate()

static Status arm_compute::NEEmbeddingLookup::validate ( const ITensorInfo *  input,
const ITensorInfo *  output,
const ITensorInfo *  lookups 
)
static

Static function to check if given info will lead to a valid configuration of NECopy

Parameters
[in]inputSource tensor info. Data types supported: U8/S8/QASYMM8/U16/S16/F16/U32/S32/F32.
[in]outputOutput tensor info. Data types supported: Same as input.
[in]outputLookups tensor info. Data types supported: S32.
Returns
a status

The documentation for this class was generated from the following files: