tf.contrib.distributions.Mixture

class tf.contrib.distributions.Mixture

Mixture distribution.

The Mixture object implements batched mixture distributions. The mixture model is defined by a Categorical distribution (the mixture) and a python list of Distribution objects.

Methods supported include log_prob, prob, mean, sample, and entropy_lower_bound.

Links:

https://www.tensorflow.org/versions/master/api_docs/python/contrib.distributions.html#Mixture

doc_TensorFlow

2016-10-14 12:56:16

Comments

Popular Articles

tf.contrib.distributions.Mixture.dtype tf.contrib.distributions.Mixture.dtype The DType of Tensors handled by this Distribution.

tf.contrib.distributions.Mixture.__init__() tf.contrib.distributions.Mixture.__init__(cat, components, validate_args=False, allow_nan_stats=True, name='Mixture') Initialize a Mixture distribut

tf.contrib.distributions.Mixture.mean() tf.contrib.distributions.Mixture.mean(name='mean') Mean.

tf.contrib.distributions.Mixture.cat tf.contrib.distributions.Mixture.cat

tf.contrib.distributions.Mixture.mode() tf.contrib.distributions.Mixture.mode(name='mode') Mode.