tf.nn.log_uniform_candidate_sampler( true_classes, num_true, num_sampled, unique, range_max, seed=None, name=None )
See the guide: Neural Network > Candidate Sampling
Samples a set of classes using a log-uniform (Zipfian) base distribution.
This operation randomly samples a tensor of sampled classes (
sampled_candidates) from the range of integers
The elements of
sampled_candidates are drawn without replacement (if
unique=True) or with replacement (if
unique=False) from the base distribution.
The base distribution for this operation is an approximately log-uniform or Zipfian distribution:
P(class) = (log(class + 2) - log(class + 1)) / log(range_max + 1)
This sampler is useful when the target classes approximately follow such a distribution - for example, if the classes represent words in a lexicon sorted in decreasing order of frequency. If your classes are not ordered by decreasing frequency, do not use this op.
In addition, this operation returns tensors
sampled_expected_count representing the number of times each of the target classes (
true_classes) and the sampled classes (
sampled_candidates) is expected to occur in an average tensor of sampled classes. These values correspond to
Q(y|x) defined in this document. If
unique=True, then these are post-rejection probabilities and we compute them approximately.
[batch_size, num_true]. The target classes.
int. The number of target classes per training example.
int. The number of classes to randomly sample.
bool. Determines whether all sampled classes in a batch are unique.
int. The number of possible classes.
int. An operation-specific seed. Default is 0.
name: A name for the operation (optional).
sampled_candidates: A tensor of type
[num_sampled]. The sampled classes.
true_expected_count: A tensor of type
float. Same shape as
true_classes. The expected counts under the sampling distribution of each of
sampled_expected_count: A tensor of type
float. Same shape as
sampled_candidates. The expected counts under the sampling distribution of each of
© 2018 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.