21.08
|
Descriptor used by the direct convolution layer output stage kernels. More...
#include <KernelDescriptors.h>
Data Fields | |
int32_t | result_fixedpoint_multiplier { 0 } |
Result output stage multiplier used for quantizing. More... | |
int32_t | result_shift { 0 } |
Result output stage shift used for quantizing. More... | |
int32_t | result_offset_after_shift { 0 } |
Result offset used for quantizing. More... | |
DataType | output_data_type { DataType::UNKNOWN } |
Output tensor data type to use if the output is not initialized. More... | |
Descriptor used by the direct convolution layer output stage kernels.
Definition at line 117 of file KernelDescriptors.h.
DataType output_data_type { DataType::UNKNOWN } |
Output tensor data type to use if the output is not initialized.
Definition at line 122 of file KernelDescriptors.h.
Referenced by CpuDirectConv2dOutputStageKernel::configure().
int32_t result_fixedpoint_multiplier { 0 } |
Result output stage multiplier used for quantizing.
Definition at line 119 of file KernelDescriptors.h.
Referenced by CpuDirectConv2dOutputStageKernel::configure().
int32_t result_offset_after_shift { 0 } |
Result offset used for quantizing.
Definition at line 121 of file KernelDescriptors.h.
Referenced by CpuDirectConv2dOutputStageKernel::configure().
int32_t result_shift { 0 } |
Result output stage shift used for quantizing.
Definition at line 120 of file KernelDescriptors.h.
Referenced by CpuDirectConv2dOutputStageKernel::configure().