public interface SpatialConvolve2D<T extends Tensor<T>> extends Function<T>
| Modifier and Type | Method and Description |
|---|---|
void |
forward(T input,
T output)
Applies forward spacial convolution.
|
ConfigConvolve2D |
getConfiguration()
Returns configuration of spacial parameters
|
SpatialPadding2D<T> |
getPadding()
Returns the padding
|
void |
setParameters(java.util.List<T> parameters)
See
forward(T, T) for a description of parameters. |
getOutputShape, getParameters, getParameterShapes, getTensorType, initializevoid forward(T input, T output)
Input shape = (N, C, H, W) Outputs shape = (N, F, H', W') Weight shape = (F, C, HH, WW) Bias shape = (F,) ------------------------------------------------- N = Size of mini-batch C = Number of channels in input image H = Height of input image W = With of input image F = Number of kernels or channels in output H' = Height of output image. H' = 1 + (H + padY0 + padY1 - HH) / periodY W' = Width of output image. W' = 1 + (W + padX0 + padX1 - WW) / periodX HH = Height of kernel WW = Width of kernel
void setParameters(java.util.List<T> parameters)
forward(T, T) for a description of parameters.setParameters in interface Function<T extends Tensor<T>>parameters - Two tensors. Weights = (F, C, HH, WW), bias = (F,)ConfigConvolve2D getConfiguration()
SpatialPadding2D<T> getPadding()