21.02
|
Interface for the bounding box kernel. More...
#include <CLBoundingBoxTransformKernel.h>
Public Member Functions | |
CLBoundingBoxTransformKernel () | |
Default constructor. More... | |
CLBoundingBoxTransformKernel (const CLBoundingBoxTransformKernel &)=delete | |
Prevent instances of this class from being copied (As this class contains pointers) More... | |
CLBoundingBoxTransformKernel & | operator= (const CLBoundingBoxTransformKernel &)=delete |
Prevent instances of this class from being copied (As this class contains pointers) More... | |
CLBoundingBoxTransformKernel (CLBoundingBoxTransformKernel &&)=default | |
Allow instances of this class to be moved. More... | |
CLBoundingBoxTransformKernel & | operator= (CLBoundingBoxTransformKernel &&)=default |
Allow instances of this class to be moved. More... | |
~CLBoundingBoxTransformKernel ()=default | |
Default destructor. More... | |
void | configure (const ICLTensor *boxes, ICLTensor *pred_boxes, const ICLTensor *deltas, const BoundingBoxTransformInfo &info) |
Set the input and output tensors. More... | |
void | configure (const CLCompileContext &compile_context, const ICLTensor *boxes, ICLTensor *pred_boxes, const ICLTensor *deltas, const BoundingBoxTransformInfo &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... | |
Static Public Member Functions | |
static Status | validate (const ITensorInfo *boxes, const ITensorInfo *pred_boxes, const ITensorInfo *deltas, const BoundingBoxTransformInfo &info) |
Static function to check if given info will lead to a valid configuration of CLBoundingBoxTransform. More... | |
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 bounding box kernel.
Definition at line 34 of file CLBoundingBoxTransformKernel.h.
Default constructor.
Definition at line 87 of file CLBoundingBoxTransformKernel.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 * | boxes, |
ICLTensor * | pred_boxes, | ||
const ICLTensor * | deltas, | ||
const BoundingBoxTransformInfo & | info | ||
) |
Set the input and output tensors.
[in] | boxes | Source tensor. Bounding box proposals in pixel coordinates. Size(M, 4), format [x1, y1, x2, y2]. Data types supported: QASYMM16/F16/F32. |
[out] | pred_boxes | Destination tensor. Pixel coordinates of the transformed bounding boxes. Size (M, 4*K), format [x1, y1, x2, y2]. Data types supported: Same as input |
[in] | deltas | Bounding box translations and scales. Size (M, 4*K), format [dx, dy, dw, dh], K is the number of classes. Data types supported: QASYMM8 if input is QASYMM16, otherwise same as input |
[in] | info | Contains BoundingBox operation information described in BoundingBoxTransformInfo. |
Definition at line 92 of file CLBoundingBoxTransformKernel.cpp.
References CLKernelLibrary::get().
void configure | ( | const CLCompileContext & | compile_context, |
const ICLTensor * | boxes, | ||
ICLTensor * | pred_boxes, | ||
const ICLTensor * | deltas, | ||
const BoundingBoxTransformInfo & | info | ||
) |
Set the input and output tensors.
[in] | compile_context | The compile context to be used. |
[in] | boxes | Source tensor. Bounding box proposals in pixel coordinates. Size(M, 4), format [x1, y1, x2, y2]. Data types supported: QASYMM16/F16/F32. |
[out] | pred_boxes | Destination tensor. Pixel coordinates of the transformed bounding boxes. Size (M, 4*K), format [x1, y1, x2, y2]. Data types supported: Same as input |
[in] | deltas | Bounding box translations and scales. Size (M, 4*K), format [dx, dy, dw, dh], K is the number of classes. Data types supported: QASYMM8 if input is QASYMM16, otherwise same as input |
[in] | info | Contains BoundingBox operation information described in BoundingBoxTransformInfo. |
Definition at line 97 of file CLBoundingBoxTransformKernel.cpp.
References CLBuildOptions::add_option(), BoundingBoxTransformInfo::apply_scale(), ARM_COMPUTE_ERROR_ON, ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_THROW_ON, arm_compute::auto_init_if_empty(), BoundingBoxTransformInfo::bbox_xform_clip(), arm_compute::calculate_max_window(), ICloneable< T >::clone(), BoundingBoxTransformInfo::correct_transform_coords(), arm_compute::create_kernel(), ITensorInfo::data_type(), arm_compute::float_to_string_with_full_precision(), arm_compute::get_cl_type_from_data_type(), arm_compute::get_padding_info(), arm_compute::has_padding_changed(), BoundingBoxTransformInfo::img_height(), BoundingBoxTransformInfo::img_width(), ITensor::info(), arm_compute::test::validation::info, arm_compute::is_data_type_quantized(), kernel_name, num_elems_processed_per_iteration, UniformQuantizationInfo::offset, ITensorInfo::quantization_info(), UniformQuantizationInfo::scale, BoundingBoxTransformInfo::scale(), arm_compute::support::cpp11::to_string(), QuantizationInfo::uniform(), arm_compute::validate_arguments(), and BoundingBoxTransformInfo::weights().
|
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 162 of file CLBoundingBoxTransformKernel.cpp.
References ICLKernel::add_1D_tensor_argument(), ICLKernel::add_2D_tensor_argument(), ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, arm_compute::enqueue(), Window::first_slice_window_2D(), ICLKernel::lws_hint(), arm_compute::test::validation::reference::slice(), and IKernel::window().
|
static |
Static function to check if given info will lead to a valid configuration of CLBoundingBoxTransform.
[in] | boxes | Source tensor info. Bounding box proposals in pixel coordinates. Size(M, 4), format [x1, y1, x2, y2]. Data types supported: QASYMM16/F16/F32. |
[in] | pred_boxes | Destination tensor info. Pixel coordinates of the transformed bounding boxes. Size (M, 4*K), format [x1, y1, x2, y2]. Data types supported: Same as input |
[in] | deltas | Bounding box translations and scales. Size (M, 4*K), format [dx, dy, dw, dh], K is the number of classes. Data types supported: QASYMM8 if input is QASYMM16, otherwise same as input |
[in] | info | Contains BoundingBox operation information described in BoundingBoxTransformInfo. |
Definition at line 156 of file CLBoundingBoxTransformKernel.cpp.
References ARM_COMPUTE_RETURN_ON_ERROR, and arm_compute::validate_arguments().
Referenced by CLBoundingBoxTransform::validate(), and CLGenerateProposalsLayer::validate().