deepboof.forward

Interface SpatialPadding2D<T extends Tensor<T>>

All Superinterfaces:

ITensor, VTensor

All Known Subinterfaces:

ClippedPadding2D<T>, ConstantPadding2D<T>

All Known Implementing Classes:

BaseSpatialPadding2D, ClippedPadding2D_F32, ClippedPadding2D_F64, ConstantPadding2D_F32, ConstantPadding2D_F64, SpatialPadding2D_F32, SpatialPadding2D_F64

public interface SpatialPadding2D<T extends Tensor<T>>
extends VTensor

Interface for all virtual 2D spatial padding implementation. Virtual padding contains a reference to the original input tensor which is going to be padded and on the fly will generate the values for elements which are not explicitly contained in the input tensor. This can reduce memory consumption and is more simplistic to implement for more complex padding methods.

Clipped padding is a special case. In this situation only pixels contained inside the original image should be processed.

Method Summary

Modifier and Type	Method and Description
int	getClippingOffsetCol(int paddedCol) Returns how far away the column is from the clipping border.
int	getClippingOffsetRow(int paddedRow) Returns how far away the row is from the clipping border.
int	getPaddingCol0() Returns the lower-extent padding along the tensor's columns.
int	getPaddingCol1() Returns the upper-extent padding along the tensor's columns.
int	getPaddingRow0() Returns the lower-extent padding along the tensor's rows.
int	getPaddingRow1() Returns the upper-extent padding along the tensor's rows.
java.lang.Class<T>	getTensorType() Returns the type of input tensor it can process
boolean	isClipped() Returns true if this is a clipped border or false of it is not.
void	setInput(T input) Spatial tensor that padding is being added around
int[]	shapeGivenInput(int... inputShape) Returns what the tensor's shape will be when given can input tensor with the spcified shape.

Methods inherited from interface deepboof.ITensor

createCoor, getDataType, getDimension, getShape, isShape, length

Method Detail

setInput

void setInput(T input)

Spatial tensor that padding is being added around

Parameters:

input - The input tensor

getClippingOffsetRow

int getClippingOffsetRow(int paddedRow)

Returns how far away the row is from the clipping border. 0 if it is inside the image. Positive is below the lower extent and negative if above upper extent.

Parameters:

paddedRow - Row in padded coordinates

Returns:

offset

getClippingOffsetCol

int getClippingOffsetCol(int paddedCol)

Returns how far away the column is from the clipping border. 0 if it is inside the image. Positive is below the lower extent and negative if above upper extent.

Parameters:

paddedCol - Column in padded coordinates

Returns:

offset

getPaddingRow0

int getPaddingRow0()

Returns the lower-extent padding along the tensor's rows.

Returns:

padding

getPaddingCol0

int getPaddingCol0()

Returns the lower-extent padding along the tensor's columns.

Returns:

padding

getPaddingRow1

int getPaddingRow1()

Returns the upper-extent padding along the tensor's rows.

Returns:

padding

getPaddingCol1

int getPaddingCol1()

Returns the upper-extent padding along the tensor's columns.

Returns:

padding

shapeGivenInput

int[] shapeGivenInput(int... inputShape)

Returns what the tensor's shape will be when given can input tensor with the spcified shape.

Parameters:

inputShape - Input spatial tensor. 3-DOF with no mini-batch or 4-DOF with mini-batch

Returns:

Tensor's shape

isClipped

boolean isClipped()

Returns true if this is a clipped border or false of it is not.

Returns:

if clipped or not

getTensorType

java.lang.Class<T> getTensorType()

Returns the type of input tensor it can process

Returns:

Type of tensor