LostTech.TensorFlow : API Documentation

Type NegativeBinomial

Namespace tensorflow.contrib.distributions

Parent Distribution

Interfaces INegativeBinomial

NegativeBinomial distribution.

The NegativeBinomial distribution is related to the experiment of performing Bernoulli trials in sequence. Given a Bernoulli trial with probability `p` of success, the NegativeBinomial distribution represents the distribution over the number of successes `s` that occur until we observe `f` failures.

The probability mass function (pmf) is,

```none pmf(s; f, p) = p**s (1 - p)**f / Z Z = s! (f - 1)! / (s + f - 1)! ```

where: * `total_count = f`, * `probs = p`, * `Z` is the normalizaing constant, and, * `n!` is the factorial of `n`.

Properties

Public properties

object allow_nan_stats get;

object allow_nan_stats_dyn get;

TensorShape batch_shape get;

object batch_shape_dyn get;

object dtype get;

object dtype_dyn get;

TensorShape event_shape get;

object event_shape_dyn get;

object logits get;

Log-odds of a `1` outcome (vs `0`).

object logits_dyn get;

Log-odds of a `1` outcome (vs `0`).

string name get;

object name_dyn get;

IDictionary<object, object> parameters get;

object parameters_dyn get;

Tensor probs get;

Probability of a `1` outcome (vs `0`).

object probs_dyn get;

Probability of a `1` outcome (vs `0`).

object PythonObject get;

object reparameterization_type get;

object reparameterization_type_dyn get;

object total_count get;

Number of negative trials.

object total_count_dyn get;

Number of negative trials.

object validate_args get;

object validate_args_dyn get;