LostTech.TensorFlow : API Documentation

Type Gumbel

Namespace tensorflow.contrib.distributions.bijectors

Parent Bijector

Interfaces IGumbel

Compute `Y = g(X) = exp(-exp(-(X - loc) / scale))`.

This bijector maps inputs from `[-inf, inf]` to [0, 1]`. The inverse of the bijector applied to a uniform random variable `X ~ U(0, 1) gives back a random variable with the [Gumbel distribution](https://en.wikipedia.org/wiki/Gumbel_distribution):

```none Y ~ Gumbel(loc, scale) pdf(y; loc, scale) = exp( -( (y - loc) / scale + exp(- (y - loc) / scale) ) ) / scale ```

Properties

Public properties

object dtype get;

object dtype_dyn get;

object forward_min_event_ndims get;

object forward_min_event_ndims_dyn get;

IList<object> graph_parents get;

object graph_parents_dyn get;

object inverse_min_event_ndims get;

object inverse_min_event_ndims_dyn get;

bool is_constant_jacobian get;

object is_constant_jacobian_dyn get;

Tensor loc get;

The `loc` in `Y = g(X) = exp(-exp(-(X - loc) / scale))`.

object loc_dyn get;

The `loc` in `Y = g(X) = exp(-exp(-(X - loc) / scale))`.

object name get;

object name_dyn get;

object PythonObject get;

object scale get;

This is `scale` in `Y = g(X) = exp(-exp(-(X - loc) / scale))`.

object scale_dyn get;

This is `scale` in `Y = g(X) = exp(-exp(-(X - loc) / scale))`.

bool validate_args get;

object validate_args_dyn get;