CLROIPoolingLayer Class Reference

Basic function to run CLROIPoolingLayerKernel. More...

#include <CLROIPoolingLayer.h>

Collaboration diagram for CLROIPoolingLayer:

Public Member Functions
void	configure (const ICLTensor *input, const ICLTensor *rois, ICLTensor *output, const ROIPoolingLayerInfo &pool_info)
	Set the input and output tensors. More...
void	configure (const CLCompileContext &compile_context, const ICLTensor *input, const ICLTensor *rois, const ICLTensor *output, const ROIPoolingLayerInfo &pool_info)
	Set the input and output tensors. More...
Public Member Functions inherited from ICLSimpleFunction
	ICLSimpleFunction (CLRuntimeContext *ctx=nullptr)
	Constructor. More...
	ICLSimpleFunction (const ICLSimpleFunction &)=delete
	Prevent instances of this class from being copied (As this class contains pointers) More...
	ICLSimpleFunction (ICLSimpleFunction &&)=default
	Default move constructor. More...
ICLSimpleFunction &	operator= (const ICLSimpleFunction &)=delete
	Prevent instances of this class from being copied (As this class contains pointers) More...
ICLSimpleFunction &	operator= (ICLSimpleFunction &&)=default
	Default move assignment operator. More...
	~ICLSimpleFunction ()
	Default destructor. More...
void	run () override final
	Run the kernels contained in the function. More...
Public Member Functions inherited from IFunction
virtual	~IFunction ()=default
	Destructor. More...
virtual void	prepare ()
	Prepare the function for executing. More...

Static Public Member Functions
static Status	validate (const ITensorInfo *input, const ITensorInfo *rois, ITensorInfo *output, const ROIPoolingLayerInfo &pool_info)
	Static function to check if given info will lead to a valid configuration of CLROIPoolingLayer. More...

Detailed Description

Basic function to run CLROIPoolingLayerKernel.

This function calls the following OpenCL kernels:

1. CLROIPoolingLayerKernel

Definition at line 43 of file CLROIPoolingLayer.h.

Member Function Documentation

configure() [1/2]

void configure	(	const CLCompileContext &	compile_context,
		const ICLTensor *	input,
		const ICLTensor *	rois,
		const ICLTensor *	output,
		const ROIPoolingLayerInfo &	pool_info
	)

Set the input and output tensors.

Parameters

[in]	compile_context	The compile context to be used.
[in]	input	Source tensor. Data types supported: F16/F32/QASYMM8
[in]	rois	ROIs tensor, it is a 2D tensor of size [5, N] (where N is the number of ROIs) containing top left and bottom right corner as coordinate of an image and batch_id of ROI [ batch_id, x1, y1, x2, y2 ]. Data types supported: U16
[out]	output	Destination tensor. Data types supported: Same as input.
[in]	pool_info	Contains pooling operation information described in ROIPoolingLayerInfo.

Note

The x and y dimensions of output tensor must be the same as pool_info 's pooled width and pooled height.

The z dimensions of output tensor and input tensor must be the same.

The fourth dimension of output tensor must be the same as the number of elements in rois array.

Definition at line 42 of file CLROIPoolingLayer.cpp.

{
    ARM_COMPUTE_LOG_PARAMS(input, rois, output, pool_info);
 
    // Configure ROI pooling kernel
    auto k = std::make_unique<CLROIPoolingLayerKernel>();
    k->configure(compile_context, input, rois, output, pool_info);
    _kernel = std::move(k);
}

References ARM_COMPUTE_LOG_PARAMS, arm_compute::test::validation::input, and arm_compute::test::validation::k.

configure() [2/2]

void configure	(	const ICLTensor *	input,
		const ICLTensor *	rois,
		ICLTensor *	output,
		const ROIPoolingLayerInfo &	pool_info
	)

Set the input and output tensors.

Valid data layouts:

• All

Valid data type configurations:

src0	src1	dst
F16	U16	F16
F32	U16	F32
QASYMM8	U16	QASYMM8

Parameters

[in]	input	Source tensor. Data types supported: F16/F32/QASYMM8
[in]	rois	ROIs tensor, it is a 2D tensor of size [5, N] (where N is the number of ROIs) containing top left and bottom right corner as coordinate of an image and batch_id of ROI [ batch_id, x1, y1, x2, y2 ]. Data types supported: U16
[out]	output	Destination tensor. Data types supported: Same as input.
[in]	pool_info	Contains pooling operation information described in ROIPoolingLayerInfo.

Note

The x and y dimensions of output tensor must be the same as pool_info 's pooled width and pooled height.

The z dimensions of output tensor and input tensor must be the same.

The fourth dimension of output tensor must be the same as the number of elements in rois array.

Definition at line 37 of file CLROIPoolingLayer.cpp.

{
    configure(CLKernelLibrary::get().get_compile_context(), input, rois, output, pool_info);
}

References CLKernelLibrary::get(), and arm_compute::test::validation::input.

validate()

Status validate ( const ITensorInfo *  input, const ITensorInfo *  rois, ITensorInfo *  output, const ROIPoolingLayerInfo &  pool_info  )

static

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

Parameters

[in]	input	Source tensor info. Data types supported: QASYMM8/F16/F32.
[in]	rois	ROIs tensor info. Data types supported: U16
[in]	output	Destination tensor info. Data types supported: Same as input.
[in]	pool_info	Contains pooling operation information described in ROIPoolingLayerInfo.

Note

The x and y dimensions of output tensor must be the same as pool_info 's pooled width and pooled height.

The z dimensions of output tensor and input tensor must be the same.

The fourth dimension of output tensor must be the same as the number of elements in rois array.

Returns

a Status

Definition at line 32 of file CLROIPoolingLayer.cpp.

{
    return CLROIPoolingLayerKernel::validate(input, rois, output, pool_info);
}

References arm_compute::test::validation::input, and CLROIPoolingLayerKernel::validate().

---

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

• arm_compute/runtime/CL/functions/CLROIPoolingLayer.h
• src/runtime/CL/functions/CLROIPoolingLayer.cpp