Class AllCandidateSampler

java.lang.Object

org.tensorflow.op.RawOp

org.tensorflow.op.random.AllCandidateSampler

All Implemented Interfaces:

Op

@Operator(group="random")
public final class AllCandidateSampler
extends RawOp

Generates labels for candidate sampling with a learned unigram distribution. See explanations of candidate sampling and the data formats at go/candidate-sampling.

For each batch, this op picks a single set of sampled candidate labels.

The advantages of sampling candidates per-batch are simplicity and the possibility of efficient dense matrix multiplication. The disadvantage is that the sampled candidates must be chosen independently of the context and of the true labels.

Nested Class Summary

Nested Classes

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

Field Summary

Fields

Modifier and Type	Field	Description
static final String	OP_NAME	The name of this op, as known by TensorFlow core engine

Fields inherited from class RawOp

operation

Constructor Summary

Constructors

Constructor	Description
AllCandidateSampler(Operation operation)

Method Summary

Modifier and Type	Method	Description
static AllCandidateSampler	create(Scope scope, Operand<TInt64> trueClasses, Long numTrue, Long numSampled, Boolean unique, AllCandidateSampler.Options... options)	Factory method to create a class wrapping a new AllCandidateSampler operation.
Output<TInt64>	sampledCandidates()	Gets sampledCandidates.
Output<TFloat32>	sampledExpectedCount()	Gets sampledExpectedCount.
static AllCandidateSampler.Options	seed(Long seed)	Sets the seed option.
static AllCandidateSampler.Options	seed2(Long seed2)	Sets the seed2 option.
Output<TFloat32>	trueExpectedCount()	Gets trueExpectedCount.

Methods inherited from class RawOp

equals, hashCode, op, toString

Methods inherited from class Object

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

Methods inherited from interface Op

env

Field Details

OP_NAME

public static final String OP_NAME

The name of this op, as known by TensorFlow core engine

See Also:

• Constant Field Values

Constructor Details

AllCandidateSampler

public AllCandidateSampler(Operation operation)

Method Details

create

@Endpoint(describeByClass=true)
public static AllCandidateSampler create(Scope scope,
 Operand<TInt64> trueClasses,
 Long numTrue,
 Long numSampled,
 Boolean unique,
 AllCandidateSampler.Options... options)

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

Parameters:

scope - current scope

trueClasses - A batch_size * num_true matrix, in which each row contains the IDs of the num_true target_classes in the corresponding original label.

numTrue - Number of true labels per context.

numSampled - Number of candidates to produce.

unique - If unique is true, we sample with rejection, so that all sampled candidates in a batch are unique. This requires some approximation to estimate the post-rejection sampling probabilities.

options - carries optional attribute values

Returns:

a new instance of AllCandidateSampler

seed

public static AllCandidateSampler.Options seed(Long seed)

Sets the seed option.

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.

Returns:

this Options instance.

seed2

public static AllCandidateSampler.Options seed2(Long seed2)

Sets the seed2 option.

Parameters:

seed2 - An second seed to avoid seed collision.

Returns:

this Options instance.

sampledCandidates

public Output<TInt64> sampledCandidates()

Gets sampledCandidates. A vector of length num_sampled, in which each element is the ID of a sampled candidate.

Returns:

sampledCandidates.

trueExpectedCount

public Output<TFloat32> trueExpectedCount()

Gets trueExpectedCount. A batch_size * num_true matrix, representing the number of times each candidate is expected to occur in a batch of sampled candidates. If unique=true, then this is a probability.

Returns:

trueExpectedCount.

sampledExpectedCount

public Output<TFloat32> sampledExpectedCount()

Gets sampledExpectedCount. A vector of length num_sampled, for each sampled candidate representing the number of times the candidate is expected to occur in a batch of sampled candidates. If unique=true, then this is a probability.

Returns:

sampledExpectedCount.