deepboof.impl.backward.standard

Class DClippedPadding2D_F64

java.lang.Object

deepboof.BaseTensor

deepboof.impl.forward.standard.BaseSpatialPadding2D<deepboof.tensors.Tensor_F64>

deepboof.forward.SpatialPadding2D_F64

deepboof.impl.forward.standard.ClippedPadding2D_F64

deepboof.impl.backward.standard.DClippedPadding2D_F64

All Implemented Interfaces:

DSpatialPadding2D<deepboof.tensors.Tensor_F64>, DSpatialPadding2D_F64, deepboof.forward.ClippedPadding2D<deepboof.tensors.Tensor_F64>, deepboof.forward.SpatialPadding2D<deepboof.tensors.Tensor_F64>, deepboof.ITensor, deepboof.tensors.VTensor_F64, deepboof.VTensor

public class DClippedPadding2D_F64
extends deepboof.impl.forward.standard.ClippedPadding2D_F64
implements DSpatialPadding2D<deepboof.tensors.Tensor_F64>, DSpatialPadding2D_F64

Backwards implementation of ClippedPadding2D_F64.

Field Summary

Fields inherited from class deepboof.impl.forward.standard.BaseSpatialPadding2D

COL0, COL1, config, input, ROW0, ROW1

Fields inherited from class deepboof.BaseTensor

shape

Constructor Summary

Constructors

Constructor and Description
DClippedPadding2D_F64(deepboof.forward.ConfigPadding config)

Method Summary

Modifier and Type	Method and Description
void	backwardsChannel(deepboof.tensors.Tensor_F64 gradientPadded, int batch, int channel, deepboof.tensors.Tensor_F64 gradientInput) Compute the gradient of the input image from the gradient of the padded image for a specific mini-batch and channel of the input tensor.
void	backwardsImage(deepboof.tensors.Tensor_F64 gradientPadded, int batch, deepboof.tensors.Tensor_F64 gradientInput) Compute the gradient of the input image from the gradient of the padded image for a specific mini-batch and channel of the input tensor.

Methods inherited from class deepboof.impl.forward.standard.ClippedPadding2D_F64

borderGet, getClippingOffsetCol, getClippingOffsetRow, getTensorType, isClipped

Methods inherited from class deepboof.forward.SpatialPadding2D_F64

get, get, get, get, get, get, getDataType

Methods inherited from class deepboof.impl.forward.standard.BaseSpatialPadding2D

checkBackwardsShapeChannel, checkBackwardsShapeImage, getPaddingCol0, getPaddingCol1, getPaddingRow0, getPaddingRow1, setInput, shapeGivenInput

Methods inherited from class deepboof.BaseTensor

createCoor, getDimension, getShape, isShape, length

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface deepboof.forward.SpatialPadding2D

getClippingOffsetCol, getClippingOffsetRow, getPaddingCol0, getPaddingCol1, getPaddingRow0, getPaddingRow1, getTensorType, isClipped, setInput, shapeGivenInput

Methods inherited from interface deepboof.ITensor

createCoor, getDataType, getDimension, getShape, isShape, length

Methods inherited from interface deepboof.tensors.VTensor_F64

get, get, get, get, get, get

Constructor Detail

DClippedPadding2D_F64

public DClippedPadding2D_F64(deepboof.forward.ConfigPadding config)

Method Detail

backwardsChannel

public void backwardsChannel(deepboof.tensors.Tensor_F64 gradientPadded,
                             int batch,
                             int channel,
                             deepboof.tensors.Tensor_F64 gradientInput)

Description copied from interface: DSpatialPadding2D

Compute the gradient of the input image from the gradient of the padded image for a specific mini-batch and channel of the input tensor.

Specified by:

backwardsChannel in interface DSpatialPadding2D<deepboof.tensors.Tensor_F64>

Parameters:

gradientPadded - (Input) Gradient of padded image at specific mini-batch and channel. (H, W)

batch - (Input) mini-batch.

channel - (Input) Channel.

gradientInput - (Output) Output 4D spatial tensor. Only elements used to compute the channel are modified. (N, C, H, W)

backwardsImage

public void backwardsImage(deepboof.tensors.Tensor_F64 gradientPadded,
                           int batch,
                           deepboof.tensors.Tensor_F64 gradientInput)

Description copied from interface: DSpatialPadding2D

Compute the gradient of the input image from the gradient of the padded image for a specific mini-batch and channel of the input tensor.

Specified by:

backwardsImage in interface DSpatialPadding2D<deepboof.tensors.Tensor_F64>

Parameters:

gradientPadded - (Input) Gradient of padded image at specific mini-batch. (C, H, W)

batch - (Input) mini-batch.

gradientInput - (Output) Output 4D spatial tensor. Only elements used to compute the image are modified. (N, C, H, W)