24.02.1
|
Basic function to run a quantization layer using cpu::CpuQuantize. More...
#include <NEQuantizationLayer.h>
Public Member Functions | |
NEQuantizationLayer () | |
~NEQuantizationLayer () | |
Default Destructor. More... | |
NEQuantizationLayer (const NEQuantizationLayer &)=delete | |
Prevent instances of this class from being copied (As this class contains pointers) More... | |
NEQuantizationLayer (NEQuantizationLayer &&)=default | |
Default move constructor. More... | |
NEQuantizationLayer & | operator= (const NEQuantizationLayer &)=delete |
Prevent instances of this class from being copied (As this class contains pointers) More... | |
NEQuantizationLayer & | operator= (NEQuantizationLayer &&)=default |
Default move assignment operator. More... | |
void | configure (const ITensor *input, ITensor *output) |
Set the input and output tensors. More... | |
void | run () override |
Run the kernels contained in the function. More... | |
Public Member Functions inherited from IFunction | |
virtual | ~IFunction ()=default |
Destructor. More... | |
virtual void | prepare () |
Prepare the function for executing. More... | |
Static Public Member Functions | |
static Status | validate (const ITensorInfo *input, const ITensorInfo *output) |
Static function to check if given info will lead to a valid configuration of NEQuantizationLayer. More... | |
Basic function to run a quantization layer using cpu::CpuQuantize.
Definition at line 39 of file NEQuantizationLayer.h.
Definition at line 41 of file NEQuantizationLayer.cpp.
|
default |
Default Destructor.
|
delete |
Prevent instances of this class from being copied (As this class contains pointers)
|
default |
Default move constructor.
Set the input and output tensors.
Valid data layouts:
Valid data type configurations:
src | dst |
---|---|
QASYMM8 | QASYMM8, QASYMM8_SIGNED, QASYMM16 |
QASYMM8_SIGNED | QASYMM8, QASYMM8_SIGNED, QASYMM16 |
F16 | QASYMM8, QASYMM8_SIGNED, QASYMM16 |
F32 | QASYMM8, QASYMM8_SIGNED, QASYMM16 |
[in] | input | Source tensor. The dimensions over the third will be interpreted as batches. Data types supported: QASYMM8/QASYMM8_SIGNED/F32/F16. |
[out] | output | Destination tensor with the same dimensions of input. Data types supported: QASYMM8/QASYMM8_SIGNED/QASYMM16 |
Definition at line 51 of file NEQuantizationLayer.cpp.
References ITensor::info(), and arm_compute::test::validation::input.
Referenced by NEGenerateProposalsLayer::configure(), NELSTMLayerQuantized::configure(), NEQLSTMLayer::configure(), and main().
|
delete |
Prevent instances of this class from being copied (As this class contains pointers)
|
default |
Default move assignment operator.
|
overridevirtual |
Run the kernels contained in the function.
For CPU kernels:
For OpenCL kernels:
Implements IFunction.
Definition at line 59 of file NEQuantizationLayer.cpp.
References arm_compute::ACL_DST, arm_compute::ACL_SRC, ITensorPack::add_tensor(), and arm_compute::test::validation::pack.
Referenced by main(), NEQLSTMLayer::prepare(), NEGenerateProposalsLayer::run(), and NELSTMLayerQuantized::run().
|
static |
Static function to check if given info will lead to a valid configuration of NEQuantizationLayer.
[in] | input | Input tensor info. The dimensions over the third will be interpreted as batches. Data types supported: QASYMM8/QASYMM8_SIGNED/F32/F16. |
[in] | output | Output tensor info. Data types supported: QASYMM8/QASYMM8_SIGNED/QASYMM16 |
Definition at line 46 of file NEQuantizationLayer.cpp.
References arm_compute::test::validation::input, and CpuQuantize::validate().
Referenced by NEGenerateProposalsLayer::validate(), and NELSTMLayerQuantized::validate().