tf.raw_ops.LearnedUnigramCandidateSampler

Generates labels for candidate sampling with a learned unigram distribution.

tf.raw_ops.LearnedUnigramCandidateSampler(
    true_classes,
    num_true,
    num_sampled,
    unique,
    range_max,
    seed=0,
    seed2=0,
    name=None
)

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.

true_classesA Tensor of type int64. A batch_size * num_true matrix, in which each row contains the IDs of the num_true target_classes in the corresponding original label.
num_trueAn int that is >= 1. Number of true labels per context.
num_sampledAn int that is >= 1. Number of candidates to randomly sample.
uniqueA bool. 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.
range_maxAn int that is >= 1. The sampler will sample integers from the interval [0, range_max).
seedAn optional int. Defaults to 0. 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.
seed2An optional int. Defaults to 0. An second seed to avoid seed collision.
nameA name for the operation (optional).

A tuple of Tensor objects (sampled_candidates, true_expected_count, sampled_expected_count).
sampled_candidatesA Tensor of type int64.
true_expected_countA Tensor of type float32.
sampled_expected_countA Tensor of type float32.