#include <SimdLib.h>
Data Fields | |
| size_t | srcC |
| size_t | srcH |
| size_t | srcW |
| SimdTensorDataType | srcT |
| SimdTensorFormatType | srcF |
| size_t | dstC |
| size_t | dstH |
| size_t | dstW |
| SimdTensorDataType | dstT |
| SimdTensorFormatType | dstF |
| size_t | kernelY |
| size_t | kernelX |
| size_t | dilationY |
| size_t | dilationX |
| size_t | strideY |
| size_t | strideX |
| size_t | padY |
| size_t | padX |
| size_t | padH |
| size_t | padW |
| size_t | group |
| SimdConvolutionActivationType | activation |
Detailed Description
Describes convolution (deconvolution) parameters. It is used in SimdSynetConvolution32fInit, SimdSynetConvolution8iInit, SimdSynetDeconvolution32fInit, SimdSynetMergedConvolution32fInit and SimdSynetMergedConvolution8iInit.
Field Documentation
◆ srcC
| size_t srcC |
A number of input tensor channels.
◆ srcH
| size_t srcH |
An input tensor height.
◆ srcW
| size_t srcW |
An input tensor width.
◆ srcT
| SimdTensorDataType srcT |
An input tensor data type.
◆ srcF
| SimdTensorFormatType srcF |
An input tensor data format.
◆ dstC
| size_t dstC |
A number of output tensor channels.
◆ dstH
| size_t dstH |
An output tensor height.
◆ dstW
| size_t dstW |
An output tensor width.
◆ dstT
| SimdTensorDataType dstT |
An output tensor data type.
◆ dstF
| SimdTensorFormatType dstF |
An output tensor data format.
◆ kernelY
| size_t kernelY |
A convolution (deconvolution) kernel window height.
◆ kernelX
| size_t kernelX |
A convolution (deconvolution) kernel window width.
◆ dilationY
| size_t dilationY |
A convolution (deconvolution) dilation along Y-axis.
◆ dilationX
| size_t dilationX |
A convolution (deconvolution) dilation along X-axis.
◆ strideY
| size_t strideY |
A convolution (deconvolution) stride along Y-axis.
◆ strideX
| size_t strideX |
A convolution (deconvolution) stride along X-axis.
◆ padY
| size_t padY |
An additional zero padding of input image at the beginning of Y-axis.
◆ padX
| size_t padX |
An additional zero padding of input image at the beginning of X-axis.
◆ padH
| size_t padH |
An additional zero padding of input image at the end of Y-axis.
◆ padW
| size_t padW |
An additional zero padding of input image at the end of X-axis.
◆ group
| size_t group |
A number of convolution (deconvolution) groups.
◆ activation
| SimdConvolutionActivationType activation |
An activation function type used after convolution (deconvolution).