Package 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 Description
    DClippedPadding2D_F64​(deepboof.forward.ConfigPadding config)  

  • Method Summary

    Modifier and Type Method 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.ITensor

    createCoor, getDataType, getDimension, getShape, isShape, length

    Methods inherited from interface deepboof.forward.SpatialPadding2D

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

    Methods inherited from interface deepboof.tensors.VTensor_F64

    get, get, get, get, get, get

  • Constructor Details

    • DClippedPadding2D_F64

      public DClippedPadding2D_F64​(deepboof.forward.ConfigPadding config)

  • Method Details

    • 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)