DiscretizedLogistic¶

class tfsnippet.DiscretizedLogistic(mean, log_scale, bin_size, min_val=None, max_val=None, dtype=tf.float32, biased_edges=True, discretize_given=True, discretize_sample=True, epsilon=1e-07)¶

Bases: tfsnippet.distributions.base.Distribution

Discretized logistic distribution (Kingma et. al, 2016).

For discrete value x with equal intervals:

p(x) = sigmoid((x - mean + bin_size * 0.5) / scale) -
    sigmoid((x - mean - bin_size * 0.5) / scale)

where delta is the interval between two possible values of x.

The min_val and max_val specifies the minimum and maximum possible value of x. It should constraint the generated samples, and if biased_edges is True, then:

p(x_min) = sigmoid((x_min - mean + bin_size * 0.5) / scale)
p(x_max) = 1 - sigmoid((x_max - mean - bin_size * 0.5) / scale)

Attributes Summary

`base_distribution`	Get the base distribution of this distribution.
`batch_shape`	Get the batch shape of the samples.
`biased_edges`	Whether or not to use biased density for edge values?
`bin_size`	Get the bin size.
`discretize_given`	Whether or not to discretize given in `log_prob()` and `prob()`?
`discretize_sample`	Whether or not to discretize the generated samples in `sample()`?
`dtype`	Get the data type of samples.
`is_continuous`	Whether or not the distribution is continuous?
`is_reparameterized`	Whether or not the distribution is re-parameterized?
`log_scale`	Get the log-scale.
`max_val`	Get the maximum value.
`mean`	Get the mean.
`min_val`	Get the minimum value.
`value_ndims`	Get the number of value dimensions in samples.

Methods Summary

`batch_ndims_to_value`(ndims)	Convert the last few batch_ndims into value_ndims.
`expand_value_ndims`(ndims)	Convert the last few batch_ndims into value_ndims.
`get_batch_shape`()	Get the static batch shape of the samples.
`log_prob`(given[, group_ndims, name])	Compute the log-densities of x against the distribution.
`prob`(given[, group_ndims, name])	Compute the densities of x against the distribution.
`sample`([n_samples, group_ndims, …])	Generate samples from the distribution.

Attributes Documentation

base_distribution¶

Get the base distribution of this distribution.

For distribution other than tfsnippet.BatchToValueDistribution, this property should return this distribution itself.

Returns:	The base distribution.
Return type:	Distribution

batch_shape¶

Get the batch shape of the samples.

Returns:	The batch shape as tensor.
Return type:	tf.Tensor

biased_edges¶: Whether or not to use biased density for edge values?

bin_size¶: Get the bin size.

discretize_given¶: Whether or not to discretize given in log_prob() and prob()?

discretize_sample¶: Whether or not to discretize the generated samples in sample()?

dtype¶

Get the data type of samples.

Returns:	Data type of the samples.
Return type:	tf.DType

is_continuous¶

Whether or not the distribution is continuous?

Returns:	A boolean indicating whether it is continuous.
Return type:	bool

is_reparameterized¶

Whether or not the distribution is re-parameterized?

The re-parameterization trick is proposed in “Auto-Encoding Variational Bayes” (Kingma, D.P. and Welling), allowing the gradients to be propagated back along the samples. Note that the re-parameterization can be disabled by specifying is_reparameterized = False as an argument of sample().

Returns:	A boolean indicating whether it is re-parameterized.
Return type:	bool

log_scale¶: Get the log-scale.

max_val¶: Get the maximum value.

mean¶: Get the mean.

min_val¶: Get the minimum value.

value_ndims¶

Get the number of value dimensions in samples.

Returns:	The number of value dimensions in samples.
Return type:	int

Methods Documentation

batch_ndims_to_value(ndims)¶

Convert the last few batch_ndims into value_ndims.

For a particular Distribution, the number of dimensions between the samples and the log-probability of the samples should satisfy:

samples.ndims - distribution.value_ndims == log_det.ndims

We denote samples.ndims - distribution.value_ndims by batch_ndims. This method thus wraps the current distribution, converts the last few batch_ndims into value_ndims.

Parameters:	ndims (int) – The last few batch_ndims to be converted into value_ndims. Must be non-negative.
Returns:	The converted distribution.
Return type:	Distribution

expand_value_ndims(ndims)¶

Convert the last few batch_ndims into value_ndims.

For a particular Distribution, the number of dimensions between the samples and the log-probability of the samples should satisfy:

samples.ndims - distribution.value_ndims == log_det.ndims

We denote samples.ndims - distribution.value_ndims by batch_ndims. This method thus wraps the current distribution, converts the last few batch_ndims into value_ndims.

Parameters:	ndims (int) – The last few batch_ndims to be converted into value_ndims. Must be non-negative.
Returns:	The converted distribution.
Return type:	Distribution

get_batch_shape()¶

Get the static batch shape of the samples.

Returns:	The batch shape.
Return type:	tf.TensorShape

log_prob(given, group_ndims=0, name=None)¶

Compute the log-densities of x against the distribution.

Parameters:	given (Tensor) – The samples to be tested. group_ndims (int or tf.Tensor) – If specified, the last group_ndims dimensions of the log-densities will be summed up. (default 0) name – TensorFlow name scope of the graph nodes. (default “log_prob”).
Returns:	The log-densities of given.
Return type:	tf.Tensor

prob(given, group_ndims=0, name=None)¶

Compute the densities of x against the distribution.

Parameters:	given (Tensor) – The samples to be tested. group_ndims (int or tf.Tensor) – If specified, the last group_ndims dimensions of the log-densities will be summed up. (default 0) name – TensorFlow name scope of the graph nodes. (default “prob”).
Returns:	The densities of given.
Return type:	tf.Tensor

sample(n_samples=None, group_ndims=0, is_reparameterized=None, compute_density=None, name=None)¶

Generate samples from the distribution.

Parameters:

n_samples (int or tf.Tensor or None) – A 0-D int32 Tensor or None. How many independent samples to draw from the distribution. The samples will have shape [n_samples] + batch_shape + value_shape, or batch_shape + value_shape if n_samples is None.
group_ndims (int or tf.Tensor) – Number of dimensions at the end of [n_samples] + batch_shape to be considered as events group. This will effect the behavior of log_prob() and prob(). (default 0)
is_reparameterized (bool) – If True, raises RuntimeError if the distribution is not re-parameterized. If False, disable re-parameterization even if the distribution is re-parameterized. (default None, following the setting of distribution)
compute_density (bool) – Whether or not to immediately compute the log-density for the samples? (default None, determine by the distribution class itself)
name – TensorFlow name scope of the graph nodes. (default “sample”).

Returns:

The samples as: StochasticTensor.

Return type:

tfsnippet.stochastic.StochasticTensor