Package org.tensorflow.op.random

Class LogUniformCandidateSampler

java.lang.Object

org.tensorflow.op.PrimitiveOp

org.tensorflow.op.random.LogUniformCandidateSampler

All Implemented Interfaces:

Op

@Operator(group="random")
public final class LogUniformCandidateSampler
extends PrimitiveOp

Generates labels for candidate sampling with a log-uniform 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	LogUniformCandidateSampler.Options	Optional attributes for LogUniformCandidateSampler

Field Summary

Fields inherited from class org.tensorflow.op.PrimitiveOp

operation

Method Summary

Modifier and Type	Method	Description
static LogUniformCandidateSampler	create(Scope scope, Operand<java.lang.Long> trueClasses, java.lang.Long numTrue, java.lang.Long numSampled, java.lang.Boolean unique, java.lang.Long rangeMax, LogUniformCandidateSampler.Options... options)	Factory method to create a class to wrap a new LogUniformCandidateSampler operation to the graph.
Output<java.lang.Long>	sampledCandidates()	A vector of length num_sampled, in which each element is the ID of a sampled candidate.
Output<java.lang.Float>	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.
static LogUniformCandidateSampler.Options	seed(java.lang.Long seed)
static LogUniformCandidateSampler.Options	seed2(java.lang.Long seed2)
Output<java.lang.Float>	trueExpectedCount()	A batch_size * num_true matrix, representing the number of times each candidate is expected to occur in a batch of sampled candidates.

Methods inherited from class java.lang.Object

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

Methods inherited from class org.tensorflow.op.PrimitiveOp

equals, hashCode, toString

Method Detail

create

public static LogUniformCandidateSampler create(Scope scope,
                                                Operand<java.lang.Long> trueClasses,
                                                java.lang.Long numTrue,
                                                java.lang.Long numSampled,
                                                java.lang.Boolean unique,
                                                java.lang.Long rangeMax,
                                                LogUniformCandidateSampler.Options... options)

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

Parameters:

scope - current graph 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 randomly sample.

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.

rangeMax - The sampler will sample integers from the interval [0, range_max).

options - carries optional attributes values

Returns:

a new instance of LogUniformCandidateSampler

seed

public static LogUniformCandidateSampler.Options seed(java.lang.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 LogUniformCandidateSampler.Options seed2(java.lang.Long seed2)

Parameters:

seed2 - An second seed to avoid seed collision.

sampledCandidates

public Output<java.lang.Long> sampledCandidates()

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

trueExpectedCount

public Output<java.lang.Float> 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.

sampledExpectedCount

public Output<java.lang.Float> 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.