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.
Optional attributes (see
Outputsampled_candidates: A vector of length num_sampled, in which each element is the ID of a sampled candidate.
Outputtrue_expected_count: 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.
Outputsampled_expected_count: 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.
|Constructors and Destructors|
|Public static functions|
Optional attribute setters for LearnedUnigramCandidateSampler.
LearnedUnigramCandidateSampler( const ::tensorflow::Scope & scope, ::tensorflow::Input true_classes, int64 num_true, int64 num_sampled, bool unique, int64 range_max )
LearnedUnigramCandidateSampler( const ::tensorflow::Scope & scope, ::tensorflow::Input true_classes, int64 num_true, int64 num_sampled, bool unique, int64 range_max, const LearnedUnigramCandidateSampler::Attrs & attrs )
Attrs Seed( int64 x )
Attrs Seed2( int64 x )
© 2017 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.