NEDepthConvertLayer Class Reference

Basic function to run cpu::kernels::CpuCastKernel. More...

#include <NEDepthConvertLayer.h>

Collaboration diagram for NEDepthConvertLayer:

Public Member Functions
	NEDepthConvertLayer ()
	Constructor. More...
	~NEDepthConvertLayer ()
	Destructor. More...
	NEDepthConvertLayer (const NEDepthConvertLayer &)=delete
	Prevent instances of this class from being copied (As this class contains pointers) More...
	NEDepthConvertLayer (NEDepthConvertLayer &&)
	Default move constructor. More...
NEDepthConvertLayer &	operator= (const NEDepthConvertLayer &)=delete
	Prevent instances of this class from being copied (As this class contains pointers) More...
NEDepthConvertLayer &	operator= (NEDepthConvertLayer &&)
	Default move assignment operator. More...
void	configure (const ITensor *input, ITensor *output, ConvertPolicy policy, uint32_t shift=0)
	Initialize the function's source, destination. More...
void	run () override
	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 *output, ConvertPolicy policy, uint32_t shift=0)
	Static function to check if given info will lead to a valid configuration of NEDepthConvertLayer. More...

Detailed Description

Basic function to run cpu::kernels::CpuCastKernel.

Definition at line 39 of file NEDepthConvertLayer.h.

Constructor & Destructor Documentation

NEDepthConvertLayer() [1/3]

NEDepthConvertLayer

(

)

Constructor.

Definition at line 40 of file NEDepthConvertLayer.cpp.

References NEDepthConvertLayer::operator=(), and NEDepthConvertLayer::~NEDepthConvertLayer().

    : _impl(std::make_unique<Impl>())
{
}

~NEDepthConvertLayer()

~NEDepthConvertLayer ( )

default

Destructor.

Referenced by NEDepthConvertLayer::NEDepthConvertLayer().

NEDepthConvertLayer() [2/3]

NEDepthConvertLayer ( const NEDepthConvertLayer &  )

delete

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

NEDepthConvertLayer() [3/3]

NEDepthConvertLayer ( NEDepthConvertLayer &&  )

default

Default move constructor.

Member Function Documentation

configure()

void configure	(	const ITensor *	input,
		ITensor *	output,
		ConvertPolicy	policy,
		uint32_t	shift = 0
	)

Initialize the function's source, destination.

Valid data layouts:

• All

Valid data type configurations:

src	dst
QASYMM8	F16, F32
U8	U16, S16, S32
U16	U8, U32
S16	U8, S32
BFLOAT16	F32
F16	QASYMM8, F32
F32	QASYMM8, F16, BFLOAT16

Input data type must be different than output data type.

Parameters

[in]	input	The input tensor to convert. Data types supported: QASYMM8/U8/U16/S16/BFLOAT16/F16/F32.
[out]	output	The output tensor. Data types supported: QASYMM8/U8/U16/S16/U32/S32/BFLOAT16/F16/F32.
[in]	policy	Conversion policy.
[in]	shift	(Optional) Value for down/up conversions. Must be 0 <= shift < 8.

Definition at line 48 of file NEDepthConvertLayer.cpp.

References ARM_COMPUTE_ERROR_ON, ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_UNUSED, and arm_compute::test::validation::input.

{
    ARM_COMPUTE_UNUSED(shift);

    _impl->src = input;
    _impl->dst = output;

    ARM_COMPUTE_ERROR_ON_NULLPTR(_impl->src, _impl->dst);
    ARM_COMPUTE_ERROR_ON(shift != 0);

    _impl->op = std::make_unique<cpu::CpuCast>();
    _impl->op->configure(_impl->src->info(), _impl->dst->info(), policy);
}

operator=() [1/2]

NEDepthConvertLayer& operator= ( const NEDepthConvertLayer &  )

delete

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

Referenced by NEDepthConvertLayer::NEDepthConvertLayer().

operator=() [2/2]

NEDepthConvertLayer & operator= ( NEDepthConvertLayer &&  )

default

Default move assignment operator.

run()

void run ( )

overridevirtual

Run the kernels contained in the function.

For CPU kernels:

• Multi-threading is used for the kernels which are parallelisable.
• By default std::thread::hardware_concurrency() threads are used.

Note

CPPScheduler::set_num_threads() can be used to manually set the number of threads

For OpenCL kernels:

• All the kernels are enqueued on the queue associated with CLScheduler.
• The queue is then flushed.

Note

The function will not block until the kernels are executed. It is the user's responsibility to wait.

Will call prepare() on first run if hasn't been done

Implements IFunction.

Definition at line 68 of file NEDepthConvertLayer.cpp.

References arm_compute::ACL_DST, arm_compute::ACL_SRC, and arm_compute::test::validation::pack.

{
    ITensorPack pack = { { ACL_SRC, _impl->src }, { ACL_DST, _impl->dst } };
    _impl->op->run(pack);
}

validate()

Status validate ( const ITensorInfo *  input, const ITensorInfo *  output, ConvertPolicy  policy, uint32_t  shift = 0  )

static

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

Parameters

[in]	input	Source tensor info. Data types supported: QASYMM8/U8/U16/S16/BFLOAT16/F16/F32.
[in]	output	Destination tensor info. Data type supported: QASYMM8/U8/U16/S16/U32/S32/BFLOAT16/F16/F32.
[in]	policy	Conversion policy.
[in]	shift	(Optional) Value for down/up conversions. Must be 0 <= shift < 8.

Returns

a status

Definition at line 62 of file NEDepthConvertLayer.cpp.

References ARM_COMPUTE_RETURN_ERROR_ON, and CpuCast::validate().

Referenced by arm_compute::test::validation::DATA_TEST_CASE().

{
    ARM_COMPUTE_RETURN_ERROR_ON(shift != 0);
    return cpu::CpuCast::validate(input, output, policy);
}

---

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

• arm_compute/runtime/NEON/functions/NEDepthConvertLayer.h
• src/runtime/NEON/functions/NEDepthConvertLayer.cpp