mxnet.gluon.probability.distributions.one_hot_categorical

One-hot Categorical Distribution

Classes

OneHotCategorical(num_events[, prob, logit, ...])

Create a one-hot categorical distribution object.

class mxnet.gluon.probability.distributions.one_hot_categorical.OneHotCategorical(num_events, prob=None, logit=None, validate_args=None)

Bases: Distribution

Create a one-hot categorical distribution object.

Parameters:

• num_events (Int) – Number of events.

• prob (Tensor) – Probabilities of each event.

• logit (Tensor) – The log-odds of each event

broadcast_to(batch_shape)

Returns a new distribution instance with parameters expanded to batch_shape. This method calls numpy.broadcast_to on the parameters.

Parameters:

batch_shape (Tuple) – The batch shape of the desired distribution.

enumerate_support()

Returns a tensor that contains all values supported by a discrete distribution.

log_prob(value)

Returns the log of the probability density/mass function evaluated at value.

property mean

Returns the mean of the distribution.

sample(size=None)

Generates a shape shaped sample.

sample_n(size=None)

Generate samples of (n + parameter_shape) from the distribution.

property variance

Returns the variance of the distribution.