Compute Library
17.10
|
Basic function to simulate a normalization layer. More...
#include <NENormalizationLayer.h>
Public Member Functions | |
NENormalizationLayer (std::shared_ptr< IMemoryManager > memory_manager=nullptr) | |
Default constructor. More... | |
void | configure (const ITensor *input, ITensor *output, NormalizationLayerInfo norm_info) |
Set the input and output tensors. More... | |
void | run () override |
Run the kernels contained in the function. More... | |
![]() | |
virtual | ~IFunction ()=default |
Destructor. More... | |
Basic function to simulate a normalization layer.
This function calls the following NEON kernels:
Definition at line 50 of file NENormalizationLayer.h.
NENormalizationLayer | ( | std::shared_ptr< IMemoryManager > | memory_manager = nullptr | ) |
Default constructor.
void configure | ( | const ITensor * | input, |
ITensor * | output, | ||
NormalizationLayerInfo | norm_info | ||
) |
Set the input and output tensors.
[in] | input | Source tensor. 3 lower dims represent a single input with dimensions [width, height, IFM], and an optional 4th dimension for batch of inputs. Data type supported: QS8/F16/F32 |
[out] | output | Destination with the same dimensions, data type and number of channels of input |
[in] | norm_info | Normalization layer information like the normalization type, normalization size and other parameters. |
|
overridevirtual |
Run the kernels contained in the function.
For NEON kernels:
For OpenCL kernels:
Implements IFunction.