Candidate Sampling Ops

Summary

Classes
tensorflow:: ops:: AllCandidateSampler	Generates labels for candidate sampling with a learned unigram distribution.
tensorflow:: ops:: ComputeAccidentalHits	Computes the ids of the positions in sampled_candidates that match true_labels.
tensorflow:: ops:: FixedUnigramCandidateSampler	Generates labels for candidate sampling with a learned unigram distribution.
tensorflow:: ops:: LearnedUnigramCandidateSampler	Generates labels for candidate sampling with a learned unigram distribution.
tensorflow:: ops:: LogUniformCandidateSampler	Generates labels for candidate sampling with a log-uniform distribution.
tensorflow:: ops:: UniformCandidateSampler	Generates labels for candidate sampling with a uniform distribution.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.

Last updated 2021-05-14 UTC.