21.02
|
Interface for the ROI pooling layer kernel. More...
#include <CLROIPoolingLayerKernel.h>
Public Member Functions | |
CLROIPoolingLayerKernel () | |
Default constructor. More... | |
CLROIPoolingLayerKernel (const CLROIPoolingLayerKernel &)=delete | |
Prevent instances of this class from being copied (As this class contains pointers) More... | |
CLROIPoolingLayerKernel & | operator= (const CLROIPoolingLayerKernel &)=delete |
Prevent instances of this class from being copied (As this class contains pointers) More... | |
CLROIPoolingLayerKernel (CLROIPoolingLayerKernel &&)=default | |
Allow instances of this class to be moved. More... | |
CLROIPoolingLayerKernel & | operator= (CLROIPoolingLayerKernel &&)=default |
Allow instances of this class to be moved. More... | |
~CLROIPoolingLayerKernel ()=default | |
Default destructor. More... | |
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, ICLTensor *output, const ROIPoolingLayerInfo &pool_info) |
Set the input and output tensors. More... | |
void | run (const Window &window, cl::CommandQueue &queue) override |
Enqueue the OpenCL kernel to process the given window on the passed OpenCL command queue. More... | |
Public Member Functions inherited from ICLKernel | |
ICLKernel () | |
Constructor. More... | |
cl::Kernel & | kernel () |
Returns a reference to the OpenCL kernel of this object. More... | |
template<typename T > | |
void | add_1D_array_argument (unsigned int &idx, const ICLArray< T > *array, const Strides &strides, unsigned int num_dimensions, const Window &window) |
Add the passed 1D array's parameters to the object's kernel's arguments starting from the index idx. More... | |
void | add_1D_tensor_argument (unsigned int &idx, const ICLTensor *tensor, const Window &window) |
Add the passed 1D tensor's parameters to the object's kernel's arguments starting from the index idx. More... | |
void | add_1D_tensor_argument_if (bool cond, unsigned int &idx, const ICLTensor *tensor, const Window &window) |
Add the passed 1D tensor's parameters to the object's kernel's arguments starting from the index idx if the condition is true. More... | |
void | add_2D_tensor_argument (unsigned int &idx, const ICLTensor *tensor, const Window &window) |
Add the passed 2D tensor's parameters to the object's kernel's arguments starting from the index idx. More... | |
void | add_2D_tensor_argument_if (bool cond, unsigned int &idx, const ICLTensor *tensor, const Window &window) |
Add the passed 2D tensor's parameters to the object's kernel's arguments starting from the index idx if the condition is true. More... | |
void | add_3D_tensor_argument (unsigned int &idx, const ICLTensor *tensor, const Window &window) |
Add the passed 3D tensor's parameters to the object's kernel's arguments starting from the index idx. More... | |
void | add_4D_tensor_argument (unsigned int &idx, const ICLTensor *tensor, const Window &window) |
Add the passed 4D tensor's parameters to the object's kernel's arguments starting from the index idx. More... | |
virtual void | run_op (ITensorPack &tensors, const Window &window, cl::CommandQueue &queue) |
Enqueue the OpenCL kernel to process the given window on the passed OpenCL command queue. More... | |
template<typename T > | |
void | add_argument (unsigned int &idx, T value) |
Add the passed parameters to the object's kernel's arguments starting from the index idx. More... | |
void | set_lws_hint (const cl::NDRange &lws_hint) |
Set the Local-Workgroup-Size hint. More... | |
cl::NDRange | lws_hint () const |
Return the Local-Workgroup-Size hint. More... | |
void | set_wbsm_hint (const cl_int &wbsm_hint) |
Set the workgroup batch size modifier hint. More... | |
cl_int | wbsm_hint () const |
Return the workgroup batch size modifier hint. More... | |
const std::string & | config_id () const |
Get the configuration ID. More... | |
void | set_target (GPUTarget target) |
Set the targeted GPU architecture. More... | |
void | set_target (cl::Device &device) |
Set the targeted GPU architecture according to the CL device. More... | |
GPUTarget | get_target () const |
Get the targeted GPU architecture. More... | |
size_t | get_max_workgroup_size () |
Get the maximum workgroup size for the device the CLKernelLibrary uses. More... | |
template<unsigned int dimension_size> | |
void | add_tensor_argument (unsigned &idx, const ICLTensor *tensor, const Window &window) |
template<typename T , unsigned int dimension_size> | |
void | add_array_argument (unsigned &idx, const ICLArray< T > *array, const Strides &strides, unsigned int num_dimensions, const Window &window) |
Add the passed array's parameters to the object's kernel's arguments starting from the index idx. 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 Window & | window () const |
The maximum window the kernel can be executed on. More... | |
Additional Inherited Members | |
Static Public Member Functions inherited from ICLKernel | |
static constexpr unsigned int | num_arguments_per_1D_array () |
Returns the number of arguments enqueued per 1D array object. More... | |
static constexpr unsigned int | num_arguments_per_1D_tensor () |
Returns the number of arguments enqueued per 1D tensor object. More... | |
static constexpr unsigned int | num_arguments_per_2D_tensor () |
Returns the number of arguments enqueued per 2D tensor object. More... | |
static constexpr unsigned int | num_arguments_per_3D_tensor () |
Returns the number of arguments enqueued per 3D tensor object. More... | |
static constexpr unsigned int | num_arguments_per_4D_tensor () |
Returns the number of arguments enqueued per 4D tensor object. More... | |
static cl::NDRange | gws_from_window (const Window &window) |
Get the global work size given an execution window. More... | |
Interface for the ROI pooling layer kernel.
Definition at line 36 of file CLROIPoolingLayerKernel.h.
Default constructor.
Definition at line 70 of file CLROIPoolingLayerKernel.cpp.
|
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.
void configure | ( | const ICLTensor * | input, |
const ICLTensor * | rois, | ||
ICLTensor * | output, | ||
const ROIPoolingLayerInfo & | pool_info | ||
) |
Set the input and output tensors.
[in] | input | Source tensor. Data types supported: F16/F32. |
[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. |
output
tensor must be the same as pool_info
's pooled width and pooled height. output
tensor and input
tensor must be the same. output
tensor must be the same as the number of elements in rois
array. Definition at line 75 of file CLROIPoolingLayerKernel.cpp.
References CLKernelLibrary::get().
void configure | ( | const CLCompileContext & | compile_context, |
const ICLTensor * | input, | ||
const ICLTensor * | rois, | ||
ICLTensor * | output, | ||
const ROIPoolingLayerInfo & | pool_info | ||
) |
Set the input and output tensors.
[in] | compile_context | The compile context to be used. |
[in] | input | Source tensor. Data types supported: F16/F32. |
[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. |
output
tensor must be the same as pool_info
's pooled width and pooled height. output
tensor and input
tensor must be the same. output
tensor must be the same as the number of elements in rois
array. Definition at line 80 of file CLROIPoolingLayerKernel.cpp.
References ARM_COMPUTE_ERROR_ON, ARM_COMPUTE_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN, ARM_COMPUTE_ERROR_ON_F16_UNSUPPORTED, ARM_COMPUTE_ERROR_ON_MISMATCHING_DATA_TYPES, ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_THROW_ON, arm_compute::create_kernel(), ITensorInfo::data_type(), ITensorInfo::dimension(), Window::DimX, Window::DimY, Window::DimZ, arm_compute::F16, arm_compute::F32, arm_compute::get_cl_type_from_data_type(), arm_compute::get_data_size_from_data_type(), ITensor::info(), arm_compute::test::validation::input, kernel_name, ICLKernel::num_arguments_per_1D_array(), ICLKernel::num_arguments_per_3D_tensor(), ITensorInfo::num_dimensions(), ROIPoolingLayerInfo::pooled_height(), ROIPoolingLayerInfo::pooled_width(), ROIPoolingLayerInfo::spatial_scale(), ITensorInfo::strides_in_bytes(), arm_compute::support::cpp11::to_string(), ITensorInfo::total_size(), and arm_compute::U16.
|
delete |
Prevent instances of this class from being copied (As this class contains pointers)
|
default |
Allow instances of this class to be moved.
|
overridevirtual |
Enqueue the OpenCL kernel to process the given window on the passed OpenCL command queue.
[in] | window | Region on which to execute the kernel. (Must be a valid region of the window returned by window()). |
[in,out] | queue | Command queue on which to enqueue the kernel. |
Reimplemented from ICLKernel.
Definition at line 134 of file CLROIPoolingLayerKernel.cpp.
References ICLKernel::add_2D_tensor_argument(), ICLKernel::add_3D_tensor_argument(), ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, ITensorInfo::dimension(), Window::DimX, Window::DimZ, arm_compute::enqueue(), Window::first_slice_window_3D(), ITensor::info(), ICLKernel::lws_hint(), Window::set(), Window::set_dimension_step(), arm_compute::test::validation::reference::slice(), ITensorInfo::strides_in_bytes(), and IKernel::window().