# FusedBatchNormV3

public final class **FusedBatchNormV3** Batch normalization.


Note that the size of 4D Tensors are defined by either "NHWC" or "NCHW".
The size of 1D Tensors matches the dimension C of the 4D Tensors.

<br />

### Nested Classes

|---|---|---|---|
| class | [FusedBatchNormV3.Options](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/core/FusedBatchNormV3.Options) || Optional attributes for `https://www.tensorflow.org/api_docs/java/org/tensorflow/op/core/FusedBatchNormV3` |

### Public Methods

|---|---|
| [Output](https://www.tensorflow.org/api_docs/java/org/tensorflow/Output)\<U\> | [batchMean](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/core/FusedBatchNormV3#batchMean())() A 1D Tensor for the computed batch mean, to be used by TensorFlow to compute the running mean. |
| [Output](https://www.tensorflow.org/api_docs/java/org/tensorflow/Output)\<U\> | [batchVariance](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/core/FusedBatchNormV3#batchVariance())() A 1D Tensor for the computed batch variance, to be used by TensorFlow to compute the running variance. |
| static \<T extends Number, U extends Number\> [FusedBatchNormV3](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/core/FusedBatchNormV3)\<T, U\> | [create](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/core/FusedBatchNormV3#create(org.tensorflow.op.Scope,%20org.tensorflow.Operand<T>,%20org.tensorflow.Operand<U>,%20org.tensorflow.Operand<U>,%20org.tensorflow.Operand<U>,%20org.tensorflow.Operand<U>,%20org.tensorflow.op.core.FusedBatchNormV3.Options...))([Scope](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/Scope) scope, [Operand](https://www.tensorflow.org/api_docs/java/org/tensorflow/Operand)\<T\> x, [Operand](https://www.tensorflow.org/api_docs/java/org/tensorflow/Operand)\<U\> scale, [Operand](https://www.tensorflow.org/api_docs/java/org/tensorflow/Operand)\<U\> offset, [Operand](https://www.tensorflow.org/api_docs/java/org/tensorflow/Operand)\<U\> mean, [Operand](https://www.tensorflow.org/api_docs/java/org/tensorflow/Operand)\<U\> variance, [Options...](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/core/FusedBatchNormV3.Options) options) Factory method to create a class wrapping a new FusedBatchNormV3 operation. |
| static [FusedBatchNormV3.Options](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/core/FusedBatchNormV3.Options) | [dataFormat](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/core/FusedBatchNormV3#dataFormat(java.lang.String))(String dataFormat) |
| static [FusedBatchNormV3.Options](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/core/FusedBatchNormV3.Options) | [epsilon](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/core/FusedBatchNormV3#epsilon(java.lang.Float))(Float epsilon) |
| static [FusedBatchNormV3.Options](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/core/FusedBatchNormV3.Options) | [exponentialAvgFactor](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/core/FusedBatchNormV3#exponentialAvgFactor(java.lang.Float))(Float exponentialAvgFactor) |
| static [FusedBatchNormV3.Options](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/core/FusedBatchNormV3.Options) | [isTraining](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/core/FusedBatchNormV3#isTraining(java.lang.Boolean))(Boolean isTraining) |
| [Output](https://www.tensorflow.org/api_docs/java/org/tensorflow/Output)\<U\> | [reserveSpace1](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/core/FusedBatchNormV3#reserveSpace1())() A 1D Tensor for the computed batch mean, to be reused in the gradient computation. |
| [Output](https://www.tensorflow.org/api_docs/java/org/tensorflow/Output)\<U\> | [reserveSpace2](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/core/FusedBatchNormV3#reserveSpace2())() A 1D Tensor for the computed batch variance (inverted variance in the cuDNN case), to be reused in the gradient computation. |
| [Output](https://www.tensorflow.org/api_docs/java/org/tensorflow/Output)\<U\> | [reserveSpace3](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/core/FusedBatchNormV3#reserveSpace3())() A 1D Tensor for some intermediate results, to be reused in the gradient computation for better efficiency. |
| [Output](https://www.tensorflow.org/api_docs/java/org/tensorflow/Output)\<T\> | [y](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/core/FusedBatchNormV3#y())() A 4D Tensor for output data. |

### Inherited Methods

From class [org.tensorflow.op.PrimitiveOp](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/PrimitiveOp)

|---|---|
| final boolean | [equals](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/PrimitiveOp#equals(java.lang.Object))(Object obj) |
| final int | [hashCode](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/PrimitiveOp#hashCode())() |
| [Operation](https://www.tensorflow.org/api_docs/java/org/tensorflow/Operation) | [op](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/PrimitiveOp#op())() Returns the underlying `https://www.tensorflow.org/api_docs/java/org/tensorflow/Operation` |
| final String | [toString](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/PrimitiveOp#toString())() |

From class java.lang.Object

|---|---|
| boolean | equals(Object arg0) |
| final Class\<?\> | getClass() |
| int | hashCode() |
| final void | notify() |
| final void | notifyAll() |
| String | toString() |
| final void | wait(long arg0, int arg1) |
| final void | wait(long arg0) |
| final void | wait() |

## Public Methods

#### public [Output](https://www.tensorflow.org/api_docs/java/org/tensorflow/Output)\<U\>
**batchMean**
()

A 1D Tensor for the computed batch mean, to be used by TensorFlow
to compute the running mean.

#### public [Output](https://www.tensorflow.org/api_docs/java/org/tensorflow/Output)\<U\>
**batchVariance**
()

A 1D Tensor for the computed batch variance, to be used by
TensorFlow to compute the running variance.

#### public static [FusedBatchNormV3](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/core/FusedBatchNormV3)\<T, U\>
**create**
([Scope](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/Scope) scope, [Operand](https://www.tensorflow.org/api_docs/java/org/tensorflow/Operand)\<T\> x, [Operand](https://www.tensorflow.org/api_docs/java/org/tensorflow/Operand)\<U\> scale, [Operand](https://www.tensorflow.org/api_docs/java/org/tensorflow/Operand)\<U\> offset, [Operand](https://www.tensorflow.org/api_docs/java/org/tensorflow/Operand)\<U\> mean, [Operand](https://www.tensorflow.org/api_docs/java/org/tensorflow/Operand)\<U\> variance, [Options...](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/core/FusedBatchNormV3.Options) options)

Factory method to create a class wrapping a new FusedBatchNormV3 operation.

##### Parameters

| scope | current scope |
| x | A 4D Tensor for input data. |
| scale | A 1D Tensor for scaling factor, to scale the normalized x. |
| offset | A 1D Tensor for offset, to shift to the normalized x. |
| mean | A 1D Tensor for population mean. Used for inference only; must be empty for training. |
| variance | A 1D Tensor for population variance. Used for inference only; must be empty for training. |
| options | carries optional attributes values |
|---|---|

##### Returns

- a new instance of FusedBatchNormV3

#### public static [FusedBatchNormV3.Options](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/core/FusedBatchNormV3.Options)
**dataFormat**
(String dataFormat)

<br />

##### Parameters

| dataFormat | The data format for x and y. Either "NHWC" (default) or "NCHW". |
|---|---|

#### public static [FusedBatchNormV3.Options](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/core/FusedBatchNormV3.Options)
**epsilon**
(Float epsilon)

<br />

##### Parameters

| epsilon | A small float number added to the variance of x. |
|---|---|

#### public static [FusedBatchNormV3.Options](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/core/FusedBatchNormV3.Options)
**exponentialAvgFactor**
(Float exponentialAvgFactor)

<br />

#### public static [FusedBatchNormV3.Options](https://www.tensorflow.org/api_docs/java/org/tensorflow/op/core/FusedBatchNormV3.Options)
**isTraining**
(Boolean isTraining)

<br />

##### Parameters

| isTraining | A bool value to indicate the operation is for training (default) or inference. |
|---|---|

#### public [Output](https://www.tensorflow.org/api_docs/java/org/tensorflow/Output)\<U\>
**reserveSpace1**
()

A 1D Tensor for the computed batch mean, to be reused
in the gradient computation.

#### public [Output](https://www.tensorflow.org/api_docs/java/org/tensorflow/Output)\<U\>
**reserveSpace2**
()

A 1D Tensor for the computed batch variance (inverted variance
in the cuDNN case), to be reused in the gradient computation.

#### public [Output](https://www.tensorflow.org/api_docs/java/org/tensorflow/Output)\<U\>
**reserveSpace3**
()

A 1D Tensor for some intermediate results, to be reused in the gradient
computation for better efficiency.

#### public [Output](https://www.tensorflow.org/api_docs/java/org/tensorflow/Output)\<T\>
**y**
()

A 4D Tensor for output data.