T
- data type for output()
outputpublic final class LocalResponseNormalizationGrad<T extends Number> extends PrimitiveOp implements Operand<T>
Modifier and Type | Class and Description |
---|---|
static class |
LocalResponseNormalizationGrad.Options
Optional attributes for
LocalResponseNormalizationGrad |
operation
Modifier and Type | Method and Description |
---|---|
static LocalResponseNormalizationGrad.Options |
alpha(Float alpha) |
Output<T> |
asOutput()
Returns the symbolic handle of a tensor.
|
static LocalResponseNormalizationGrad.Options |
beta(Float beta) |
static LocalResponseNormalizationGrad.Options |
bias(Float bias) |
static <T extends Number> |
create(Scope scope,
Operand<T> inputGrads,
Operand<T> inputImage,
Operand<T> outputImage,
LocalResponseNormalizationGrad.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.
|
equals, hashCode, op, toString
public static <T extends Number> LocalResponseNormalizationGrad<T> create(Scope scope, Operand<T> inputGrads, Operand<T> inputImage, Operand<T> outputImage, LocalResponseNormalizationGrad.Options... options)
scope
- current scopeinputGrads
- 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 valuespublic static LocalResponseNormalizationGrad.Options depthRadius(Long depthRadius)
depthRadius
- A depth radius.public static LocalResponseNormalizationGrad.Options bias(Float bias)
bias
- An offset (usually > 0 to avoid dividing by 0).public static LocalResponseNormalizationGrad.Options alpha(Float alpha)
alpha
- A scale factor, usually positive.public static LocalResponseNormalizationGrad.Options beta(Float beta)
beta
- An exponent.public Output<T> asOutput()
Operand
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.
asOutput
in interface Operand<T extends Number>
OperationBuilder.addInput(Output)
Copyright © 2022. All rights reserved.