Compute Library
 19.11
NEDequantizationLayerKernel Class Reference

Interface for the dequantization layer kernel. More...

#include <NEDequantizationLayerKernel.h>

Collaboration diagram for NEDequantizationLayerKernel:
[legend]

Public Member Functions

const char * name () const override
 Name of the kernel. More...
 
 NEDequantizationLayerKernel ()
 Default constructor. More...
 
 NEDequantizationLayerKernel (const NEDequantizationLayerKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
NEDequantizationLayerKerneloperator= (const NEDequantizationLayerKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
 NEDequantizationLayerKernel (NEDequantizationLayerKernel &&)=default
 Default Move Constructor. More...
 
NEDequantizationLayerKerneloperator= (NEDequantizationLayerKernel &&)=default
 Default move assignment operator. More...
 
 ~NEDequantizationLayerKernel ()=default
 Default destructor. More...
 
void configure (const ITensor *input, ITensor *output)
 Set input, output tensors. More...
 
void run (const Window &window, const ThreadInfo &info) override
 Execute the kernel on the passed window. More...
 
- Public Member Functions inherited from ICPPKernel
virtual ~ICPPKernel ()=default
 Default destructor. More...
 
- Public Member Functions inherited from IKernel
 IKernel ()
 Constructor. More...
 
virtual ~IKernel ()=default
 Destructor. More...
 
virtual bool is_parallelisable () const
 Indicates whether or not the kernel is parallelisable. More...
 
virtual BorderSize border_size () const
 The size of the border for that kernel. More...
 
const Windowwindow () const
 The maximum window the kernel can be executed on. More...
 

Static Public Member Functions

static Status validate (const ITensorInfo *input, const ITensorInfo *output)
 Static function to check if given info will lead to a valid configuration of NEDequantizationLayerKernel. More...
 

Detailed Description

Interface for the dequantization layer kernel.

Definition at line 34 of file NEDequantizationLayerKernel.h.

Constructor & Destructor Documentation

◆ NEDequantizationLayerKernel() [1/3]

Default constructor.

Definition at line 360 of file NEDequantizationLayerKernel.cpp.

361  : _input(nullptr), _output(nullptr)
362 {
363 }

◆ NEDequantizationLayerKernel() [2/3]

Prevent instances of this class from being copied (As this class contains pointers)

◆ NEDequantizationLayerKernel() [3/3]

Default Move Constructor.

◆ ~NEDequantizationLayerKernel()

Default destructor.

Member Function Documentation

◆ configure()

void configure ( const ITensor input,
ITensor output 
)

Set input, output tensors.

Parameters
[in]inputSource tensor. Data type supported: QASYMM8/QSYMM8_PER_CHANNEL/QSYMM8/QSYMM16.
[out]outputDestination tensor with the same dimensions of input. Data type supported: F16/F32.

Definition at line 365 of file NEDequantizationLayerKernel.cpp.

366 {
368  ARM_COMPUTE_ERROR_THROW_ON(validate_arguments(input->info(), output->info()));
369 
370  _input = input;
371  _output = output;
372 
373  // Configure kernel window
374  auto win_config = validate_and_configure_window(input->info(), output->info());
375 
376  ARM_COMPUTE_ERROR_THROW_ON(std::get<0>(win_config));
377 
378  INEKernel::configure(std::get<1>(win_config));
379 }
#define ARM_COMPUTE_ERROR_THROW_ON(status)
Definition: Error.h:455
#define ARM_COMPUTE_ERROR_ON_NULLPTR(...)
Definition: Validate.h:161

References ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_THROW_ON, ITensor::info(), and arm_compute::test::validation::input.

Referenced by NEGenerateProposalsLayer::configure().

◆ name()

const char* name ( ) const
inlineoverridevirtual

Name of the kernel.

Returns
Kernel name

Implements ICPPKernel.

Definition at line 37 of file NEDequantizationLayerKernel.h.

38  {
39  return "NEDequantizationLayerKernel";
40  }

◆ operator=() [1/2]

Prevent instances of this class from being copied (As this class contains pointers)

◆ operator=() [2/2]

Default move assignment operator.

◆ run()

void run ( const Window window,
const ThreadInfo info 
)
overridevirtual

Execute the kernel on the passed window.

Warning
If is_parallelisable() returns false then the passed window must be equal to window()
Note
The window has to be a region within the window returned by the window() method
The width of the window has to be a multiple of num_elems_processed_per_iteration().
Parameters
[in]windowRegion on which to execute the kernel. (Must be a region of the window returned by window())
[in]infoInfo about executing thread and CPU.

Implements ICPPKernel.

Definition at line 388 of file NEDequantizationLayerKernel.cpp.

389 {
393 
394  switch(_output->info()->data_type())
395  {
396  case DataType::F32:
397  run_dequantization_core<float>(_input, _output, window);
398  break;
399 #ifdef __ARM_FEATURE_FP16_VECTOR_ARITHMETIC
400  case DataType::F16:
401  run_dequantization_core<float16_t>(_input, _output, window);
402  break;
403 #endif /* __ARM_FEATURE_FP16_VECTOR_ARITHMETIC */
404  default:
405  ARM_COMPUTE_ERROR("Unsupported data type.");
406  }
407 }
const Window & window() const
The maximum window the kernel can be executed on.
Definition: IKernel.cpp:28
#define ARM_COMPUTE_ERROR(msg)
Print the given message then throw an std::runtime_error.
Definition: Error.h:352
virtual DataType data_type() const =0
Data type used for each element of the tensor.
1 channel, 1 F32 per channel
1 channel, 1 F16 per channel
#define ARM_COMPUTE_UNUSED(...)
To avoid unused variables warnings.
Definition: Error.h:152
virtual ITensorInfo * info() const =0
Interface to be implemented by the child class to return the tensor's metadata.
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)
Definition: Validate.h:205
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
Definition: Validate.h:941

References ARM_COMPUTE_ERROR, ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, ARM_COMPUTE_UNUSED, ITensorInfo::data_type(), arm_compute::F16, arm_compute::F32, ITensor::info(), arm_compute::test::validation::info, and IKernel::window().

◆ validate()

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

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

Parameters
[in]inputInput tensor info. Data types supported: QASYMM8/QSYMM8_PER_CHANNEL/QSYMM8/QSYMM16.
[in]outputOutput tensor info. Data types supported: F16/F32.
Returns
a status

Definition at line 381 of file NEDequantizationLayerKernel.cpp.

382 {
383  ARM_COMPUTE_RETURN_ON_ERROR(validate_arguments(input, output));
384  ARM_COMPUTE_RETURN_ON_ERROR(std::get<0>(validate_and_configure_window(input->clone().get(), output->clone().get())));
385  return Status{};
386 }
#define ARM_COMPUTE_RETURN_ON_ERROR(status)
Checks if a status contains an error and returns it.
Definition: Error.h:204

References ARM_COMPUTE_RETURN_ON_ERROR, ICloneable< T >::clone(), and arm_compute::test::validation::input.

Referenced by NEDequantizationLayer::validate(), and NEGenerateProposalsLayer::validate().


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