Compute Library
18.05
|
Basic function to execute a generic depthwise convolution. More...
#include <NEDepthwiseConvolutionLayer.h>
Public Member Functions | |
NEDepthwiseConvolutionLayer () | |
Default constructor. More... | |
NEDepthwiseConvolutionLayer (const NEDepthwiseConvolutionLayer &)=delete | |
Prevent instances of this class from being copied (As this class contains pointers) More... | |
NEDepthwiseConvolutionLayer (NEDepthwiseConvolutionLayer &&)=default | |
Default move constructor. More... | |
NEDepthwiseConvolutionLayer & | operator= (const NEDepthwiseConvolutionLayer &)=delete |
Prevent instances of this class from being copied (As this class contains pointers) More... | |
NEDepthwiseConvolutionLayer & | operator= (NEDepthwiseConvolutionLayer &&)=default |
Default move assignment operator. More... | |
void | configure (ITensor *input, const ITensor *weights, const ITensor *biases, ITensor *output, const PadStrideInfo &conv_info, unsigned int depth_multiplier=1) |
Initialize the function's source, destination, weights and convolution information. 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... | |
Basic function to execute a generic depthwise convolution.
This function calls the following NEON kernels:
Definition at line 98 of file NEDepthwiseConvolutionLayer.h.
Default constructor.
|
delete |
Prevent instances of this class from being copied (As this class contains pointers)
|
default |
Default move constructor.
void configure | ( | ITensor * | input, |
const ITensor * | weights, | ||
const ITensor * | biases, | ||
ITensor * | output, | ||
const PadStrideInfo & | conv_info, | ||
unsigned int | depth_multiplier = 1 |
||
) |
Initialize the function's source, destination, weights and convolution information.
[in,out] | input | Source tensor. Data type supported: QASYMM8/F32. (Written to only for border filling). |
[out] | output | Destination tensor. Data type supported: same as input . |
[in] | weights | Weights tensor. These are 3D tensors with shape [kernel_x, kernel_y, IFM]. Data type supported: Same as input . |
[in] | biases | (Optional) Biases tensor. A 1D tensor with shape [IFM]. Must be nullptr if not needed. Data type supported: Same as input , S32 when input is QASYMM8. |
[in] | conv_info | Padding and stride information to use for the convolution. |
[in] | depth_multiplier | (Optional) Multiplier to apply to the input's depth in order to retrieve the output's depth. Defaults to 1. |
|
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 NEON kernels:
For OpenCL kernels:
Implements IFunction.