21.02
|
Interface for the kernel to run an arbitrary size convolution on a tensor. More...
#include <NEConvolution.h>
Public Member Functions | |
const char * | name () const override |
Name of the kernel. More... | |
NEConvolutionKernel () | |
Default constructor. More... | |
NEConvolutionKernel (const NEConvolutionKernel &)=delete | |
Prevent instances of this class from being copied (As this class contains pointers). More... | |
NEConvolutionKernel & | operator= (const NEConvolutionKernel &)=delete |
Prevent instances of this class from being copied (As this class contains pointers). More... | |
NEConvolutionKernel (NEConvolutionKernel &&)=default | |
Allow instances of this class to be moved. More... | |
NEConvolutionKernel & | operator= (NEConvolutionKernel &&)=default |
Allow instances of this class to be moved. More... | |
~NEConvolutionKernel ()=default | |
Default destructor. More... | |
void | configure (const ITensor *input, ITensor *output, const int16_t *conv, uint32_t scale, bool border_undefined) |
Initialise the kernel's input, output and border mode. More... | |
void | run (const Window &window, const ThreadInfo &info) override |
Execute the kernel on the passed window. More... | |
BorderSize | border_size () const override |
The size of the border for that kernel. More... | |
Public Member Functions inherited from ICPPSimpleKernel | |
ICPPSimpleKernel () | |
Constructor. More... | |
ICPPSimpleKernel (const ICPPSimpleKernel &)=delete | |
Prevent instances of this class from being copied (As this class contains pointers) More... | |
ICPPSimpleKernel & | operator= (const ICPPSimpleKernel &)=delete |
Prevent instances of this class from being copied (As this class contains pointers) More... | |
ICPPSimpleKernel (ICPPSimpleKernel &&)=default | |
Allow instances of this class to be moved. More... | |
ICPPSimpleKernel & | operator= (ICPPSimpleKernel &&)=default |
Allow instances of this class to be moved. More... | |
~ICPPSimpleKernel ()=default | |
Default destructor. More... | |
Public Member Functions inherited from ICPPKernel | |
virtual | ~ICPPKernel ()=default |
Default destructor. More... | |
virtual void | run_nd (const Window &window, const ThreadInfo &info, const Window &thread_locator) |
legacy compatibility layer for implemantions which do not support thread_locator In these cases we simply narrow the interface down the legacy version More... | |
virtual void | run_op (ITensorPack &tensors, const Window &window, const ThreadInfo &info) |
Execute the kernel on the passed window. 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... | |
const Window & | window () const |
The maximum window the kernel can be executed on. More... | |
Interface for the kernel to run an arbitrary size convolution on a tensor.
(Currently supports 3x3, 5x5, 7x7 and 9x9). The client can supply a convolution matrix \( C_{m,n} \).
\begin{eqnarray} k_0 &=& \frac{m}{2} \\ l_0 &=& \frac{n}{2} \\ sum &=& \sum_{k=0,l=0}^{k=m-1,l=n-1} input(x+k-k_0, y+l-l_0) C_{k,l} \end{eqnarray}
Definition at line 42 of file NEConvolution.h.
Default constructor.
Definition at line 314 of file NEConvolutionKernel.cpp.
Referenced by NEConvolutionKernel< matrix_size >::name().
|
delete |
Prevent instances of this class from being copied (As this class contains pointers).
|
default |
Allow instances of this class to be moved.
|
default |
Default destructor.
Referenced by NEConvolutionKernel< matrix_size >::name().
|
overridevirtual |
The size of the border for that kernel.
Reimplemented from IKernel.
Definition at line 320 of file NEConvolutionKernel.cpp.
Referenced by NEConvolutionKernel< matrix_size >::configure(), NEConvolutionKernel< matrix_size >::name(), NESeparableConvolutionHorKernel< matrix_size >::name(), NESeparableConvolutionVertKernel< matrix_size >::name(), and NEConvolutionRectangleKernel::name().
void configure | ( | const ITensor * | input, |
ITensor * | output, | ||
const int16_t * | conv, | ||
uint32_t | scale, | ||
bool | border_undefined | ||
) |
Initialise the kernel's input, output and border mode.
[in] | input | Source tensor. Data type supported: U8. |
[out] | output | Destination tensor. Data types supported: U8, S16. |
[in] | conv | Convolution matrix to apply to the input tensor. |
[in] | scale | Scale of the convolution matrix. If 0 is passed, it will be set to the sum of the coefficients of the convolution or 1 if they add up to 0. |
[in] | border_undefined | True if the border mode is undefined. False if it's replicate or constant. |
Definition at line 326 of file NEConvolutionKernel.cpp.
References ARM_COMPUTE_ERROR_ON, ARM_COMPUTE_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN, ARM_COMPUTE_ERROR_ON_MISMATCHING_SHAPES, ARM_COMPUTE_ERROR_ON_NULLPTR, NEConvolutionKernel< matrix_size >::border_size(), arm_compute::calculate_matrix_scale(), arm_compute::calculate_max_window(), arm_compute::execute_window_loop(), ITensor::info(), arm_compute::test::validation::input, BorderSize::left, num_elems_processed_per_iteration, Iterator::ptr(), arm_compute::S16, arm_compute::test::validation::scale, arm_compute::set_shape_if_empty(), arm_compute::detail::store_results(), ITensorInfo::tensor_shape(), BorderSize::top, arm_compute::U8, arm_compute::update_window_and_padding(), and ITensorInfo::valid_region().
Referenced by NEConvolutionKernel< matrix_size >::name(), NESeparableConvolutionHorKernel< matrix_size >::name(), NESeparableConvolutionVertKernel< matrix_size >::name(), and NEConvolutionRectangleKernel::name().
|
inlineoverridevirtual |
Name of the kernel.
Implements ICPPKernel.
Definition at line 58 of file NEConvolutionKernel.h.
References NEConvolutionKernel< matrix_size >::border_size(), NEConvolutionKernel< matrix_size >::configure(), arm_compute::test::validation::info, arm_compute::test::validation::input, NEConvolutionKernel< matrix_size >::NEConvolutionKernel(), NEConvolutionKernel< matrix_size >::operator=(), NEConvolutionKernel< matrix_size >::run(), arm_compute::test::validation::scale, IKernel::window(), and NEConvolutionKernel< matrix_size >::~NEConvolutionKernel().
|
delete |
Prevent instances of this class from being copied (As this class contains pointers).
Referenced by NEConvolutionKernel< matrix_size >::name(), NESeparableConvolutionHorKernel< matrix_size >::name(), NESeparableConvolutionVertKernel< matrix_size >::name(), and NEConvolutionRectangleKernel::name().
|
default |
Allow instances of this class to be moved.
|
overridevirtual |
Execute the kernel on the passed window.
[in] | window | Region on which to execute the kernel. (Must be a region of the window returned by window()) |
[in] | info | Info about executing thread and CPU. |
Reimplemented from ICPPKernel.
Definition at line 626 of file NEConvolutionKernel.cpp.
References ARM_COMPUTE_ERROR, ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, ARM_COMPUTE_UNUSED, arm_compute::S16, arm_compute::U8, and IKernel::window().
Referenced by NEConvolutionKernel< matrix_size >::name(), NESeparableConvolutionHorKernel< matrix_size >::name(), NESeparableConvolutionVertKernel< matrix_size >::name(), and NEConvolutionRectangleKernel::name().