Other Functions and Classes

class tf.contrib.bayesflow.stochastic_tensor.ObservedStochasticTensor

A StochasticTensor with an observed value.


tf.contrib.bayesflow.stochastic_tensor.ObservedStochasticTensor.__init__(dist_cls, value, name=None, **dist_args) {:#ObservedStochasticTensor.init}

Construct an ObservedStochasticTensor.

ObservedStochasticTensor will instantiate a distribution from dist_cls and dist_args but use the provided value instead of sampling from the distribution. The provided value argument must be appropriately shaped to have come from the constructed distribution.

Args:
  • dist_cls: a Distribution class.
  • value: a Tensor containing the observed value
  • name: a name for this ObservedStochasticTensor and its ops.
  • **dist_args: keyword arguments to be passed through to dist_cls on construction.
Raises:
  • TypeError: if dist_cls is not a Distribution.
  • ValueError: if value is not compatible with the distribution.

tf.contrib.bayesflow.stochastic_tensor.ObservedStochasticTensor.clone(name=None, **dist_args)


tf.contrib.bayesflow.stochastic_tensor.ObservedStochasticTensor.distribution


tf.contrib.bayesflow.stochastic_tensor.ObservedStochasticTensor.dtype


tf.contrib.bayesflow.stochastic_tensor.ObservedStochasticTensor.entropy(name='entropy')


tf.contrib.bayesflow.stochastic_tensor.ObservedStochasticTensor.graph


tf.contrib.bayesflow.stochastic_tensor.ObservedStochasticTensor.input_dict


tf.contrib.bayesflow.stochastic_tensor.ObservedStochasticTensor.loss(final_loss, name=None)


tf.contrib.bayesflow.stochastic_tensor.ObservedStochasticTensor.mean(name='mean')


tf.contrib.bayesflow.stochastic_tensor.ObservedStochasticTensor.name


tf.contrib.bayesflow.stochastic_tensor.ObservedStochasticTensor.value(name='value')


tf.contrib.bayesflow.stochastic_tensor.ObservedStochasticTensor.value_type