T
- data type for output()
output@Operator(group="nn") public final class LocalResponseNormalization<T extends Number> extends PrimitiveOp implements Operand<T>
The 4-D `input` tensor is treated as a 3-D array of 1-D vectors (along the last dimension), and each vector is normalized independently. Within a given vector, each component is divided by the weighted, squared sum of inputs within `depth_radius`. In detail,
sqr_sum[a, b, c, d] = sum(input[a, b, c, d - depth_radius : d + depth_radius + 1] ** 2) output = input / (bias + alpha * sqr_sum) ** beta
For details, see [Krizhevsky et al., ImageNet classification with deep convolutional neural networks (NIPS 2012)](http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks).
Modifier and Type | Class and Description |
---|---|
static class |
LocalResponseNormalization.Options
Optional attributes for
LocalResponseNormalization |
operation
Modifier and Type | Method and Description |
---|---|
static LocalResponseNormalization.Options |
alpha(Float alpha) |
Output<T> |
asOutput()
Returns the symbolic handle of a tensor.
|
static LocalResponseNormalization.Options |
beta(Float beta) |
static LocalResponseNormalization.Options |
bias(Float bias) |
static <T extends Number> |
create(Scope scope,
Operand<T> input,
LocalResponseNormalization.Options... options)
Factory method to create a class wrapping a new LocalResponseNormalization operation.
|
static LocalResponseNormalization.Options |
depthRadius(Long depthRadius) |
Output<T> |
output() |
equals, hashCode, op, toString
public static <T extends Number> LocalResponseNormalization<T> create(Scope scope, Operand<T> input, LocalResponseNormalization.Options... options)
scope
- current scopeinput
- 4-D.options
- carries optional attributes valuespublic static LocalResponseNormalization.Options depthRadius(Long depthRadius)
depthRadius
- 0-D. Half-width of the 1-D normalization window.public static LocalResponseNormalization.Options bias(Float bias)
bias
- An offset (usually positive to avoid dividing by 0).public static LocalResponseNormalization.Options alpha(Float alpha)
alpha
- A scale factor, usually positive.public static LocalResponseNormalization.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.