org.tensorflow.op.core

Class TruncatedNormal<U extends Number>

java.lang.Object

org.tensorflow.op.PrimitiveOp

org.tensorflow.op.core.TruncatedNormal<U>

Type Parameters:

U - data type for output() output

All Implemented Interfaces:

Op, Operand<U>

@Operator
public final class TruncatedNormal<U extends Number>
extends PrimitiveOp
implements Operand<U>

Outputs random values from a truncated normal distribution.

The generated values follow a normal distribution with mean 0 and standard deviation 1, except that values whose magnitude is more than 2 standard deviations from the mean are dropped and re-picked.

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	TruncatedNormal.Options Optional attributes for TruncatedNormal

Field Summary

Fields inherited from class org.tensorflow.op.PrimitiveOp

operation

Method Summary

Modifier and Type	Method and Description
Output<U>	asOutput() Returns the symbolic handle of a tensor.
static <U extends Number,T extends Number> TruncatedNormal<U>	create(Scope scope, Operand<T> shape, Class<U> dtype, TruncatedNormal.Options... options) Factory method to create a class to wrap a new TruncatedNormal operation to the graph.
Output<U>	output() A tensor of the specified shape filled with random truncated normal values.
static TruncatedNormal.Options	seed(Long seed)
static TruncatedNormal.Options	seed2(Long seed2)

Methods inherited from class org.tensorflow.op.PrimitiveOp

equals, hashCode, toString

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Method Detail

create

public static <U extends Number,T extends Number> TruncatedNormal<U> create(Scope scope,
                                                                            Operand<T> shape,
                                                                            Class<U> dtype,
                                                                            TruncatedNormal.Options... options)

Factory method to create a class to wrap a new TruncatedNormal operation to the graph.

Parameters:

scope - current graph scope

shape - The shape of the output tensor.

dtype - The type of the output.

options - carries optional attributes values

Returns:

a new instance of TruncatedNormal

seed

public static TruncatedNormal.Options seed(Long seed)

Parameters:

seed - If either `seed` or `seed2` are set to be non-zero, the random number generator is seeded by the given seed. Otherwise, it is seeded by a random seed.

seed2

public static TruncatedNormal.Options seed2(Long seed2)

Parameters:

seed2 - A second seed to avoid seed collision.

output

public Output<U> output()

A tensor of the specified shape filled with random truncated normal values.

asOutput

public Output<U> asOutput()

Description copied from interface: Operand

Returns the symbolic handle of a 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.

Specified by:

asOutput in interface Operand<U extends Number>

See Also:

OperationBuilder.addInput(Output)