@Namespace(value="tensorflow::ops") @NoOffset public static class tensorflow.LRN extends Pointer
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).
Arguments:
* scope: A Scope object
* input: 4-D.
Optional attributes (see Attrs):
* depth_radius: 0-D. Half-width of the 1-D normalization window.
* bias: An offset (usually positive to avoid dividing by 0).
* alpha: A scale factor, usually positive.
* beta: An exponent.
Returns:
* Output: The output tensor.| Modifier and Type | Class and Description |
|---|---|
static class |
tensorflow.LRN.Attrs
Optional attribute setters for LRN
|
Pointer.CustomDeallocator, Pointer.Deallocator, Pointer.NativeDeallocator| Constructor and Description |
|---|
LRN(Pointer p)
Pointer cast constructor.
|
LRN(tensorflow.Scope scope,
tensorflow.Input input) |
LRN(tensorflow.Scope scope,
tensorflow.Input input,
tensorflow.LRN.Attrs attrs) |
| Modifier and Type | Method and Description |
|---|---|
static tensorflow.LRN.Attrs |
Alpha(float x) |
tensorflow.Input |
asInput() |
tensorflow.Output |
asOutput() |
static tensorflow.LRN.Attrs |
Beta(float x) |
static tensorflow.LRN.Attrs |
Bias(float x) |
static tensorflow.LRN.Attrs |
DepthRadius(long x) |
tensorflow.Node |
node() |
tensorflow.Operation |
operation() |
tensorflow.LRN |
operation(tensorflow.Operation operation) |
tensorflow.Output |
output() |
tensorflow.LRN |
output(tensorflow.Output output) |
address, asBuffer, asByteBuffer, availablePhysicalBytes, calloc, capacity, capacity, close, deallocate, deallocate, deallocateReferences, deallocator, deallocator, equals, fill, formatBytes, free, hashCode, isNull, limit, limit, malloc, maxBytes, maxPhysicalBytes, memchr, memcmp, memcpy, memmove, memset, offsetof, parseBytes, physicalBytes, position, position, put, realloc, setNull, sizeof, toString, totalBytes, totalPhysicalBytes, withDeallocator, zeropublic LRN(Pointer p)
Pointer.Pointer(Pointer).public LRN(@Const @ByRef tensorflow.Scope scope, @ByVal tensorflow.Input input)
public LRN(@Const @ByRef tensorflow.Scope scope, @ByVal tensorflow.Input input, @Const @ByRef tensorflow.LRN.Attrs attrs)
@ByVal @Name(value="operator tensorflow::Output") public tensorflow.Output asOutput()
@ByVal @Name(value="operator tensorflow::Input") public tensorflow.Input asInput()
public tensorflow.Node node()
@ByVal public static tensorflow.LRN.Attrs DepthRadius(@Cast(value="tensorflow::int64") long x)
@ByVal public static tensorflow.LRN.Attrs Bias(float x)
@ByVal public static tensorflow.LRN.Attrs Alpha(float x)
@ByVal public static tensorflow.LRN.Attrs Beta(float x)
@ByRef public tensorflow.Operation operation()
public tensorflow.LRN operation(tensorflow.Operation operation)
@ByRef public tensorflow.Output output()
public tensorflow.LRN output(tensorflow.Output output)
Copyright © 2019. All rights reserved.