21.08
|
Interface for the kernel to run a depthwise convolution native on a tensor. More...
#include <CpuDepthwiseConv2dNativeKernel.h>
Public Member Functions | |
CpuDepthwiseConv2dNativeKernel ()=default | |
ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE (CpuDepthwiseConv2dNativeKernel) | |
void | configure (const ITensorInfo *src, const ITensorInfo *weights, const ITensorInfo *biases, ITensorInfo *dst, const ConvolutionInfo &info) |
Initialize the function's source, destination and parameters. More... | |
void | run_op (ITensorPack &tensors, const Window &window, const ThreadInfo &info) override |
Execute the kernel on the passed window. More... | |
const char * | name () const override |
Name of the kernel. More... | |
![]() | |
virtual | ~ICPPKernel ()=default |
Default destructor. More... | |
virtual void | run (const Window &window, const ThreadInfo &info) |
Execute the kernel on the passed window. 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... | |
![]() | |
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... | |
bool | is_window_configured () const |
Function to check if the embedded window of this kernel has been configured. More... | |
Static Public Member Functions | |
static Status | validate (const ITensorInfo *src, const ITensorInfo *weights, const ITensorInfo *biases, const ITensorInfo *dst, const ConvolutionInfo &info) |
Static function to check if given info will lead to a valid configuration. More... | |
Interface for the kernel to run a depthwise convolution native on a tensor.
Definition at line 43 of file CpuDepthwiseConv2dNativeKernel.h.
|
default |
ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE | ( | CpuDepthwiseConv2dNativeKernel | ) |
void configure | ( | const ITensorInfo * | src, |
const ITensorInfo * | weights, | ||
const ITensorInfo * | biases, | ||
ITensorInfo * | dst, | ||
const ConvolutionInfo & | info | ||
) |
Initialize the function's source, destination and parameters.
[in] | src | Source tensor. DataType supported: QASYMM8/QASYMM8_SIGNED/F16/F32. |
[in] | weights | Weights tensor. This is a 3D tensor with dimensions [IFM, W, H]. Data type supported: Same as src or QASYMM8/QASYMM8_SIGNED/QSYMM8_PER_CHANNEL when src is QASYMM8/QASYMM8_SIGNED. |
[in] | biases | Biases tensor. A 1D tensor with dimensions [IFM]. Must be nullptr if not needed. Data type supported: Same as src , S32 when src is QASYMM8/QASYMM8_SIGNED. |
[out] | dst | Destination tensor. Data type supported: Same as src . |
[in] | info | Depthwise convolution meta-data. |
Definition at line 806 of file CpuDepthwiseConv2dNativeKernel.cpp.
References ARM_COMPUTE_ERROR, ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_THROW_ON, arm_compute::auto_init_if_empty(), arm_compute::calculate_max_window(), arm_compute::quantization::calculate_quantized_multiplier(), ICloneable< T >::clone(), arm_compute::misc::shape_calculator::compute_depthwise_convolution_shape(), ITensorInfo::data_type(), ConvolutionInfo::depth_multiplier, ConvolutionInfo::dilation, ITensorInfo::dimension(), arm_compute::F16, arm_compute::F32, arm_compute::is_data_type_quantized(), arm_compute::is_data_type_quantized_per_channel(), arm_compute::test::validation::output_shape, ConvolutionInfo::pad_stride_info, arm_compute::QASYMM8, arm_compute::QASYMM8_SIGNED, arm_compute::QSYMM8_PER_CHANNEL, ITensorInfo::quantization_info(), UniformQuantizationInfo::scale, QuantizationInfo::scale(), and QuantizationInfo::uniform().
|
overridevirtual |
Name of the kernel.
Implements ICPPKernel.
Definition at line 944 of file CpuDepthwiseConv2dNativeKernel.cpp.
|
overridevirtual |
Execute the kernel on the passed window.
[in] | tensors | A vector containing the tensors to operate on. |
[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 930 of file CpuDepthwiseConv2dNativeKernel.cpp.
References arm_compute::ACL_DST, arm_compute::ACL_SRC_0, arm_compute::ACL_SRC_1, arm_compute::ACL_SRC_2, ARM_COMPUTE_ERROR_ON, ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, ARM_COMPUTE_UNUSED, ITensorPack::get_const_tensor(), ITensorPack::get_tensor(), and IKernel::window().
|
static |
Static function to check if given info will lead to a valid configuration.
Similar to CpuDepthwiseConv2dNativeKernel::configure()
Definition at line 880 of file CpuDepthwiseConv2dNativeKernel.cpp.
References ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, ARM_COMPUTE_RETURN_ON_ERROR, ITensorInfo::data_type(), arm_compute::test::validation::dst, ITensor::info(), arm_compute::is_data_type_quantized_per_channel(), arm_compute::test::validation::src, and IKernel::window().