LocalResponseNormalizationGrad

public final class LocalResponseNormalizationGrad

Gradients for Local Response Normalization.

Nested Classes

class LocalResponseNormalizationGrad.Options Optional attributes for LocalResponseNormalizationGrad

Constants

String OP_NAME The name of this op, as known by TensorFlow core engine

Public Methods

static LocalResponseNormalizationGrad.Options
alpha (Float alpha)
Output <T>
asOutput ()
Returns the symbolic handle of the tensor.
static LocalResponseNormalizationGrad.Options
beta (Float beta)
static LocalResponseNormalizationGrad.Options
bias (Float bias)
static <T extends TNumber > LocalResponseNormalizationGrad <T>
create ( Scope scope, Operand <T> inputGrads, Operand <T> inputImage, Operand <T> outputImage, Options... options)
Factory method to create a class wrapping a new LocalResponseNormalizationGrad operation.
static LocalResponseNormalizationGrad.Options
depthRadius (Long depthRadius)
Output <T>
output ()
The gradients for LRN.

Inherited Methods

Constants

public static final String OP_NAME

The name of this op, as known by TensorFlow core engine

Constant Value: "LRNGrad"

Public Methods

public static LocalResponseNormalizationGrad.Options alpha (Float alpha)

Parameters
alpha A scale factor, usually positive.

public Output <T> asOutput ()

Returns the symbolic handle of the tensor.

Inputs to TensorFlow operations are outputs of another TensorFlow operation. This method is used to obtain a symbolic handle that represents the computation of the input.

public static LocalResponseNormalizationGrad.Options beta (Float beta)

Parameters
beta An exponent.

public static LocalResponseNormalizationGrad.Options bias (Float bias)

Parameters
bias An offset (usually > 0 to avoid dividing by 0).

public static LocalResponseNormalizationGrad <T> create ( Scope scope, Operand <T> inputGrads, Operand <T> inputImage, Operand <T> outputImage, Options... options)

Factory method to create a class wrapping a new LocalResponseNormalizationGrad operation.

Parameters
scope current scope
inputGrads 4-D with shape `[batch, height, width, channels]`.
inputImage 4-D with shape `[batch, height, width, channels]`.
outputImage 4-D with shape `[batch, height, width, channels]`.
options carries optional attributes values
Returns
  • a new instance of LocalResponseNormalizationGrad

public static LocalResponseNormalizationGrad.Options depthRadius (Long depthRadius)

Parameters
depthRadius A depth radius.

public Output <T> output ()

The gradients for LRN.