LostTech.TensorFlow : API Documentation

Type HalfNormal

Namespace tensorflow.contrib.distributions

Parent Distribution

Interfaces IHalfNormal

The Half Normal distribution with scale `scale`.

#### Mathematical details

The half normal is a transformation of a centered normal distribution. If some random variable `X` has normal distribution, ```none X ~ Normal(0.0, scale) Y = |X| ``` Then `Y` will have half normal distribution. The probability density function (pdf) is:

```none pdf(x; scale, x > 0) = sqrt(2) / (scale * sqrt(pi)) * exp(- 1/2 * (x / scale) ** 2) ) ``` Where `scale = sigma` is the standard deviation of the underlying normal distribution.

#### Examples

Examples of initialization of one or a batch of distributions.
Show Example
import tensorflow_probability as tfp
            tfd = tfp.distributions 

# Define a single scalar HalfNormal distribution. dist = tfd.HalfNormal(scale=3.0)

# Evaluate the cdf at 1, returning a scalar. dist.cdf(1.)

# Define a batch of two scalar valued HalfNormals. # The first has scale 11.0, the second 22.0 dist = tfd.HalfNormal(scale=[11.0, 22.0])

# Evaluate the pdf of the first distribution on 1.0, and the second on 1.5, # returning a length two tensor. dist.prob([1.0, 1.5])

# Get 3 samples, returning a 3 x 2 tensor. dist.sample([3])


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;

string name get;

object name_dyn get;

IDictionary<object, object> parameters get;

object parameters_dyn get;

object PythonObject get;

object reparameterization_type get;

object reparameterization_type_dyn get;

object scale get;

Distribution parameter for the scale.

object scale_dyn get;

Distribution parameter for the scale.

object validate_args get;

object validate_args_dyn get;