tfp.edward2.RandomVariable

Class RandomVariable

Class for random variables.

RandomVariable encapsulates properties of a random variable, namely, its distribution, sample shape, and (optionally overridden) value. Its value property is a tf.Tensor, which embeds the RandomVariable object into the TensorFlow graph. RandomVariable also features operator overloading and registration to TensorFlow sessions, enabling idiomatic usage as if one were operating on tf.Tensors.

The random variable's shape is given by

sample_shape + distribution.batch_shape + distribution.event_shape,

where sample_shape is an optional argument describing the shape of independent, identical draws from the distribution (default is (), meaning a single draw); distribution.batch_shape describes the shape of independent-but-not-identical draws (determined by the shape of the distribution's parameters); and distribution.event_shape describes the shape of dependent dimensions (e.g., Normal has scalar event_shape; Dirichlet has vector event_shape).

Examples

import tensorflow_probability as tfp
from tensorflow_probability import edward2 as ed
tfd = tfp.distributions

z1 = tf.constant([[1.0, -0.8], [0.3, -1.0]])
z2 = tf.constant([[0.9, 0.2], [2.0, -0.1]])
x = ed.RandomVariable(tfd.Bernoulli(logits=tf.matmul(z1, z2)))

loc = ed.RandomVariable(tfd.Normal(0., 1.))
x = ed.RandomVariable(tfd.Normal(loc, 1.), sample_shape=50)
assert x.shape.as_list() == [50]
assert x.sample_shape.as_list() == [50]
assert x.distribution.batch_shape.as_list() == []
assert x.distribution.event_shape.as_list() == []

__init__

__init__(
    distribution,
    sample_shape=(),
    value=None
)

Create a new random variable.

Args:

  • distribution: tfd.Distribution governing the distribution of the random variable, such as sampling and log-probabilities.
  • sample_shape: tf.TensorShape of samples to draw from the random variable. Default is () corresponding to a single sample.
  • value: Fixed tf.Tensor to associate with random variable. Must have shape sample_shape + distribution.batch_shape + distribution.event_shape. Default is to sample from random variable according to sample_shape.

Raises:

  • ValueError: value has incompatible shape with sample_shape + distribution.batch_shape + distribution.event_shape.

Properties

distribution

Distribution of random variable.

dtype

Dtype of elements in this random variable.

sample_shape

Sample shape of random variable as a TensorShape.

shape

Shape of random variable.

value

Get tensor that the random variable corresponds to.

Methods

__abs__

__abs__(
    x,
    name=None
)

Computes the absolute value of a tensor.

Given a tensor x of complex numbers, this operation returns a tensor of type float32 or float64 that is the absolute value of each element in x. All elements in x must be complex numbers of the form \(a + bj\). The absolute value is computed as \( \sqrt{a^2 + b^2}\). For example:

x = tf.constant([[-2.25 + 4.75j], [-3.25 + 5.75j]])
tf.abs(x)  # [5.25594902, 6.60492229]

Args:

  • x: A Tensor or SparseTensor of type float16, float32, float64, int32, int64, complex64 or complex128.
  • name: A name for the operation (optional).

Returns:

A Tensor or SparseTensor the same size and type as x with absolute values. Note, for complex64 or complex128 input, the returned Tensor will be of type float32 or float64, respectively.

If x is a SparseTensor, returns SparseTensor(x.indices, tf.math.abs(x.values, ...), x.dense_shape)

__add__

__add__(
    a,
    *args
)

Returns x + y element-wise.

NOTE: math.add supports broadcasting. AddN does not. More about broadcasting here

Args:

  • x: A Tensor. Must be one of the following types: bfloat16, half, float32, float64, uint8, int8, int16, int32, int64, complex64, complex128, string.
  • y: A Tensor. Must have the same type as x.
  • name: A name for the operation (optional).

Returns:

A Tensor. Has the same type as x.

__and__

__and__(
    a,
    *args
)

Returns the truth value of x AND y element-wise.

NOTE: math.logical_and supports broadcasting. More about broadcasting here

Args:

  • x: A Tensor of type bool.
  • y: A Tensor of type bool.
  • name: A name for the operation (optional).

Returns:

A Tensor of type bool.

__bool__

__bool__(
    a,
    *args
)

Dummy method to prevent a tensor from being used as a Python bool.

This overload raises a TypeError when the user inadvertently treats a Tensor as a boolean (e.g. in an if statement). For example:

if tf.constant(True):  # Will raise.
  # ...

if tf.constant(5) < tf.constant(7):  # Will raise.
  # ...

This disallows ambiguities between testing the Python value vs testing the dynamic condition of the Tensor.

Raises:

TypeError.

__div__

__div__(
    a,
    *args
)

Divide two values using Python 2 semantics. Used for Tensor.div.

Args:

  • x: Tensor numerator of real numeric type.
  • y: Tensor denominator of real numeric type.
  • name: A name for the operation (optional).

Returns:

x / y returns the quotient of x and y.

__eq__

__eq__(other)

__floordiv__

__floordiv__(
    a,
    *args
)

Divides x / y elementwise, rounding toward the most negative integer.

The same as tf.div(x,y) for integers, but uses tf.floor(tf.div(x,y)) for floating point arguments so that the result is always an integer (though possibly an integer represented as floating point). This op is generated by x // y floor division in Python 3 and in Python 2.7 with from __future__ import division.

x and y must have the same type, and the result will have the same type as well.

Args:

  • x: Tensor numerator of real numeric type.
  • y: Tensor denominator of real numeric type.
  • name: A name for the operation (optional).

Returns:

x / y rounded down.

Raises:

  • TypeError: If the inputs are complex.

__ge__

__ge__(
    a,
    *args
)

Returns the truth value of (x >= y) element-wise.

NOTE: math.greater_equal supports broadcasting. More about broadcasting here

Args:

  • x: A Tensor. Must be one of the following types: float32, float64, int32, uint8, int16, int8, int64, bfloat16, uint16, half, uint32, uint64.
  • y: A Tensor. Must have the same type as x.
  • name: A name for the operation (optional).

Returns:

A Tensor of type bool.

__getitem__

__getitem__(
    a,
    *args
)

Overload for Tensor.getitem.

This operation extracts the specified region from the tensor. The notation is similar to NumPy with the restriction that currently only support basic indexing. That means that using a non-scalar tensor as input is not currently allowed.

Some useful examples:

# strip leading and trailing 2 elements
foo = tf.constant([1,2,3,4,5,6])
print(foo[2:-2].eval())  # => [3,4]

# skip every row and reverse every column
foo = tf.constant([[1,2,3], [4,5,6], [7,8,9]])
print(foo[::2,::-1].eval())  # => [[3,2,1], [9,8,7]]

# Use scalar tensors as indices on both dimensions
print(foo[tf.constant(0), tf.constant(2)].eval())  # => 3

# Insert another dimension
foo = tf.constant([[1,2,3], [4,5,6], [7,8,9]])
print(foo[tf.newaxis, :, :].eval()) # => [[[1,2,3], [4,5,6], [7,8,9]]]
print(foo[:, tf.newaxis, :].eval()) # => [[[1,2,3]], [[4,5,6]], [[7,8,9]]]
print(foo[:, :, tf.newaxis].eval()) # => [[[1],[2],[3]], [[4],[5],[6]],
[[7],[8],[9]]]

# Ellipses (3 equivalent operations)
foo = tf.constant([[1,2,3], [4,5,6], [7,8,9]])
print(foo[tf.newaxis, :, :].eval())  # => [[[1,2,3], [4,5,6], [7,8,9]]]
print(foo[tf.newaxis, ...].eval())  # => [[[1,2,3], [4,5,6], [7,8,9]]]
print(foo[tf.newaxis].eval())  # => [[[1,2,3], [4,5,6], [7,8,9]]]

Notes: - tf.newaxis is None as in NumPy. - An implicit ellipsis is placed at the end of the slice_spec - NumPy advanced indexing is currently not supported.

Args:

  • tensor: An ops.Tensor object.
  • slice_spec: The arguments to Tensor.getitem.
  • var: In the case of variable slice assignment, the Variable object to slice (i.e. tensor is the read-only view of this variable).

Returns:

The appropriate slice of "tensor", based on "slice_spec".

Raises:

  • ValueError: If a slice range is negative size.
  • TypeError: If the slice indices aren't int, slice, ellipsis, tf.newaxis or scalar int32/int64 tensors.

__gt__

__gt__(
    a,
    *args
)

Returns the truth value of (x > y) element-wise.

NOTE: math.greater supports broadcasting. More about broadcasting here

Args:

  • x: A Tensor. Must be one of the following types: float32, float64, int32, uint8, int16, int8, int64, bfloat16, uint16, half, uint32, uint64.
  • y: A Tensor. Must have the same type as x.
  • name: A name for the operation (optional).

Returns:

A Tensor of type bool.

__invert__

__invert__(
    a,
    *args
)

Returns the truth value of NOT x element-wise.

Args:

  • x: A Tensor of type bool.
  • name: A name for the operation (optional).

Returns:

A Tensor of type bool.

__iter__

__iter__(
    a,
    *args
)

__le__

__le__(
    a,
    *args
)

Returns the truth value of (x <= y) element-wise.

NOTE: math.less_equal supports broadcasting. More about broadcasting here

Args:

  • x: A Tensor. Must be one of the following types: float32, float64, int32, uint8, int16, int8, int64, bfloat16, uint16, half, uint32, uint64.
  • y: A Tensor. Must have the same type as x.
  • name: A name for the operation (optional).

Returns:

A Tensor of type bool.

__lt__

__lt__(
    a,
    *args
)

Returns the truth value of (x < y) element-wise.

NOTE: math.less supports broadcasting. More about broadcasting here

Args:

  • x: A Tensor. Must be one of the following types: float32, float64, int32, uint8, int16, int8, int64, bfloat16, uint16, half, uint32, uint64.
  • y: A Tensor. Must have the same type as x.
  • name: A name for the operation (optional).

Returns:

A Tensor of type bool.

__matmul__

__matmul__(
    a,
    *args
)

Multiplies matrix a by matrix b, producing a * b.

The inputs must, following any transpositions, be tensors of rank >= 2 where the inner 2 dimensions specify valid matrix multiplication arguments, and any further outer dimensions match.

Both matrices must be of the same type. The supported types are: float16, float32, float64, int32, complex64, complex128.

Either matrix can be transposed or adjointed (conjugated and transposed) on the fly by setting one of the corresponding flag to True. These are False by default.

If one or both of the matrices contain a lot of zeros, a more efficient multiplication algorithm can be used by setting the corresponding a_is_sparse or b_is_sparse flag to True. These are False by default. This optimization is only available for plain matrices (rank-2 tensors) with datatypes bfloat16 or float32.

For example:

# 2-D tensor `a`
# [[1, 2, 3],
#  [4, 5, 6]]
a = tf.constant([1, 2, 3, 4, 5, 6], shape=[2, 3])

# 2-D tensor `b`
# [[ 7,  8],
#  [ 9, 10],
#  [11, 12]]
b = tf.constant([7, 8, 9, 10, 11, 12], shape=[3, 2])

# `a` * `b`
# [[ 58,  64],
#  [139, 154]]
c = tf.matmul(a, b)


# 3-D tensor `a`
# [[[ 1,  2,  3],
#   [ 4,  5,  6]],
#  [[ 7,  8,  9],
#   [10, 11, 12]]]
a = tf.constant(np.arange(1, 13, dtype=np.int32),
                shape=[2, 2, 3])

# 3-D tensor `b`
# [[[13, 14],
#   [15, 16],
#   [17, 18]],
#  [[19, 20],
#   [21, 22],
#   [23, 24]]]
b = tf.constant(np.arange(13, 25, dtype=np.int32),
                shape=[2, 3, 2])

# `a` * `b`
# [[[ 94, 100],
#   [229, 244]],
#  [[508, 532],
#   [697, 730]]]
c = tf.matmul(a, b)

# Since python >= 3.5 the @ operator is supported (see PEP 465).
# In TensorFlow, it simply calls the `tf.matmul()` function, so the
# following lines are equivalent:
d = a @ b @ [[10.], [11.]]
d = tf.matmul(tf.matmul(a, b), [[10.], [11.]])

Args:

  • a: Tensor of type float16, float32, float64, int32, complex64, complex128 and rank > 1.
  • b: Tensor with same type and rank as a.
  • transpose_a: If True, a is transposed before multiplication.
  • transpose_b: If True, b is transposed before multiplication.
  • adjoint_a: If True, a is conjugated and transposed before multiplication.
  • adjoint_b: If True, b is conjugated and transposed before multiplication.
  • a_is_sparse: If True, a is treated as a sparse matrix.
  • b_is_sparse: If True, b is treated as a sparse matrix.
  • name: Name for the operation (optional).

Returns:

A Tensor of the same type as a and b where each inner-most matrix is the product of the corresponding matrices in a and b, e.g. if all transpose or adjoint attributes are False:

output[..., i, j] = sum_k (a[..., i, k] * b[..., k, j]), for all indices i, j.

  • Note: This is matrix product, not element-wise product.

Raises:

  • ValueError: If transpose_a and adjoint_a, or transpose_b and adjoint_b are both set to True.

__mod__

__mod__(
    a,
    *args
)

Returns element-wise remainder of division. When x < 0 xor y < 0 is

true, this follows Python semantics in that the result here is consistent with a flooring divide. E.g. floor(x / y) * y + mod(x, y) = x.

NOTE: floormod supports broadcasting. More about broadcasting here

Args:

  • x: A Tensor. Must be one of the following types: int32, int64, bfloat16, half, float32, float64.
  • y: A Tensor. Must have the same type as x.
  • name: A name for the operation (optional).

Returns:

A Tensor. Has the same type as x.

__mul__

__mul__(
    a,
    *args
)

Dispatches cwise mul for "DenseDense" and "DenseSparse".

__ne__

__ne__(other)

__neg__

__neg__(
    a,
    *args
)

Computes numerical negative value element-wise.

I.e., \(y = -x\).

Args:

  • x: A Tensor. Must be one of the following types: bfloat16, half, float32, float64, int32, int64, complex64, complex128.
  • name: A name for the operation (optional).

Returns:

A Tensor. Has the same type as x.

If x is a SparseTensor, returns SparseTensor(x.indices, tf.math.negative(x.values, ...), x.dense_shape)

__nonzero__

__nonzero__(
    a,
    *args
)

Dummy method to prevent a tensor from being used as a Python bool.

This is the Python 2.x counterpart to __bool__() above.

Raises:

TypeError.

__or__

__or__(
    a,
    *args
)

Returns the truth value of x OR y element-wise.

NOTE: math.logical_or supports broadcasting. More about broadcasting here

Args:

  • x: A Tensor of type bool.
  • y: A Tensor of type bool.
  • name: A name for the operation (optional).

Returns:

A Tensor of type bool.

__pow__

__pow__(
    a,
    *args
)

Computes the power of one value to another.

Given a tensor x and a tensor y, this operation computes \(x^y\) for corresponding elements in x and y. For example:

x = tf.constant([[2, 2], [3, 3]])
y = tf.constant([[8, 16], [2, 3]])
tf.pow(x, y)  # [[256, 65536], [9, 27]]

Args:

  • x: A Tensor of type float16, float32, float64, int32, int64, complex64, or complex128.
  • y: A Tensor of type float16, float32, float64, int32, int64, complex64, or complex128.
  • name: A name for the operation (optional).

Returns:

A Tensor.

__radd__

__radd__(
    a,
    *args
)

Returns x + y element-wise.

NOTE: math.add supports broadcasting. AddN does not. More about broadcasting here

Args:

  • x: A Tensor. Must be one of the following types: bfloat16, half, float32, float64, uint8, int8, int16, int32, int64, complex64, complex128, string.
  • y: A Tensor. Must have the same type as x.
  • name: A name for the operation (optional).

Returns:

A Tensor. Has the same type as x.

__rand__

__rand__(
    a,
    *args
)

Returns the truth value of x AND y element-wise.

NOTE: math.logical_and supports broadcasting. More about broadcasting here

Args:

  • x: A Tensor of type bool.
  • y: A Tensor of type bool.
  • name: A name for the operation (optional).

Returns:

A Tensor of type bool.

__rdiv__

__rdiv__(
    a,
    *args
)

Divide two values using Python 2 semantics. Used for Tensor.div.

Args:

  • x: Tensor numerator of real numeric type.
  • y: Tensor denominator of real numeric type.
  • name: A name for the operation (optional).

Returns:

x / y returns the quotient of x and y.

__rfloordiv__

__rfloordiv__(
    a,
    *args
)

Divides x / y elementwise, rounding toward the most negative integer.

The same as tf.div(x,y) for integers, but uses tf.floor(tf.div(x,y)) for floating point arguments so that the result is always an integer (though possibly an integer represented as floating point). This op is generated by x // y floor division in Python 3 and in Python 2.7 with from __future__ import division.

x and y must have the same type, and the result will have the same type as well.

Args:

  • x: Tensor numerator of real numeric type.
  • y: Tensor denominator of real numeric type.
  • name: A name for the operation (optional).

Returns:

x / y rounded down.

Raises:

  • TypeError: If the inputs are complex.

__rmatmul__

__rmatmul__(
    a,
    *args
)

Multiplies matrix a by matrix b, producing a * b.

The inputs must, following any transpositions, be tensors of rank >= 2 where the inner 2 dimensions specify valid matrix multiplication arguments, and any further outer dimensions match.

Both matrices must be of the same type. The supported types are: float16, float32, float64, int32, complex64, complex128.

Either matrix can be transposed or adjointed (conjugated and transposed) on the fly by setting one of the corresponding flag to True. These are False by default.

If one or both of the matrices contain a lot of zeros, a more efficient multiplication algorithm can be used by setting the corresponding a_is_sparse or b_is_sparse flag to True. These are False by default. This optimization is only available for plain matrices (rank-2 tensors) with datatypes bfloat16 or float32.

For example:

# 2-D tensor `a`
# [[1, 2, 3],
#  [4, 5, 6]]
a = tf.constant([1, 2, 3, 4, 5, 6], shape=[2, 3])

# 2-D tensor `b`
# [[ 7,  8],
#  [ 9, 10],
#  [11, 12]]
b = tf.constant([7, 8, 9, 10, 11, 12], shape=[3, 2])

# `a` * `b`
# [[ 58,  64],
#  [139, 154]]
c = tf.matmul(a, b)


# 3-D tensor `a`
# [[[ 1,  2,  3],
#   [ 4,  5,  6]],
#  [[ 7,  8,  9],
#   [10, 11, 12]]]
a = tf.constant(np.arange(1, 13, dtype=np.int32),
                shape=[2, 2, 3])

# 3-D tensor `b`
# [[[13, 14],
#   [15, 16],
#   [17, 18]],
#  [[19, 20],
#   [21, 22],
#   [23, 24]]]
b = tf.constant(np.arange(13, 25, dtype=np.int32),
                shape=[2, 3, 2])

# `a` * `b`
# [[[ 94, 100],
#   [229, 244]],
#  [[508, 532],
#   [697, 730]]]
c = tf.matmul(a, b)

# Since python >= 3.5 the @ operator is supported (see PEP 465).
# In TensorFlow, it simply calls the `tf.matmul()` function, so the
# following lines are equivalent:
d = a @ b @ [[10.], [11.]]
d = tf.matmul(tf.matmul(a, b), [[10.], [11.]])

Args:

  • a: Tensor of type float16, float32, float64, int32, complex64, complex128 and rank > 1.
  • b: Tensor with same type and rank as a.
  • transpose_a: If True, a is transposed before multiplication.
  • transpose_b: If True, b is transposed before multiplication.
  • adjoint_a: If True, a is conjugated and transposed before multiplication.
  • adjoint_b: If True, b is conjugated and transposed before multiplication.
  • a_is_sparse: If True, a is treated as a sparse matrix.
  • b_is_sparse: If True, b is treated as a sparse matrix.
  • name: Name for the operation (optional).

Returns:

A Tensor of the same type as a and b where each inner-most matrix is the product of the corresponding matrices in a and b, e.g. if all transpose or adjoint attributes are False:

output[..., i, j] = sum_k (a[..., i, k] * b[..., k, j]), for all indices i, j.

  • Note: This is matrix product, not element-wise product.

Raises:

  • ValueError: If transpose_a and adjoint_a, or transpose_b and adjoint_b are both set to True.

__rmod__

__rmod__(
    a,
    *args
)

Returns element-wise remainder of division. When x < 0 xor y < 0 is

true, this follows Python semantics in that the result here is consistent with a flooring divide. E.g. floor(x / y) * y + mod(x, y) = x.

NOTE: floormod supports broadcasting. More about broadcasting here

Args:

  • x: A Tensor. Must be one of the following types: int32, int64, bfloat16, half, float32, float64.
  • y: A Tensor. Must have the same type as x.
  • name: A name for the operation (optional).

Returns:

A Tensor. Has the same type as x.

__rmul__

__rmul__(
    a,
    *args
)

Dispatches cwise mul for "DenseDense" and "DenseSparse".

__ror__

__ror__(
    a,
    *args
)

Returns the truth value of x OR y element-wise.

NOTE: math.logical_or supports broadcasting. More about broadcasting here

Args:

  • x: A Tensor of type bool.
  • y: A Tensor of type bool.
  • name: A name for the operation (optional).

Returns:

A Tensor of type bool.

__rpow__

__rpow__(
    a,
    *args
)

Computes the power of one value to another.

Given a tensor x and a tensor y, this operation computes \(x^y\) for corresponding elements in x and y. For example:

x = tf.constant([[2, 2], [3, 3]])
y = tf.constant([[8, 16], [2, 3]])
tf.pow(x, y)  # [[256, 65536], [9, 27]]

Args:

  • x: A Tensor of type float16, float32, float64, int32, int64, complex64, or complex128.
  • y: A Tensor of type float16, float32, float64, int32, int64, complex64, or complex128.
  • name: A name for the operation (optional).

Returns:

A Tensor.

__rsub__

__rsub__(
    a,
    *args
)

Returns x - y element-wise.

NOTE: Subtract supports broadcasting. More about broadcasting here

Args:

  • x: A Tensor. Must be one of the following types: bfloat16, half, float32, float64, uint8, int8, uint16, int16, int32, int64, complex64, complex128.
  • y: A Tensor. Must have the same type as x.
  • name: A name for the operation (optional).

Returns:

A Tensor. Has the same type as x.

__rtruediv__

__rtruediv__(
    a,
    *args
)

__rxor__

__rxor__(
    a,
    *args
)

x ^ y = (x | y) & ~(x & y).

__sub__

__sub__(
    a,
    *args
)

Returns x - y element-wise.

NOTE: Subtract supports broadcasting. More about broadcasting here

Args:

  • x: A Tensor. Must be one of the following types: bfloat16, half, float32, float64, uint8, int8, uint16, int16, int32, int64, complex64, complex128.
  • y: A Tensor. Must have the same type as x.
  • name: A name for the operation (optional).

Returns:

A Tensor. Has the same type as x.

__truediv__

__truediv__(
    a,
    *args
)

__xor__

__xor__(
    a,
    *args
)

x ^ y = (x | y) & ~(x & y).

eval

eval(
    session=None,
    feed_dict=None
)

In a session, computes and returns the value of this random variable.

This is not a graph construction method, it does not add ops to the graph.

This convenience method requires a session where the graph containing this variable has been launched. If no session is passed, the default session is used.

Args:

  • session: tf.BaseSession. The tf.Session to use to evaluate this random variable. If none, the default session is used.
  • feed_dict: dict. A dictionary that maps tf.Tensor objects to feed values. See tf.Session.run() for a description of the valid feed values.

Returns:

Value of the random variable.

Examples

x = Normal(0.0, 1.0)
with tf.Session() as sess:
  # Usage passing the session explicitly.
  print(x.eval(sess))
  # Usage with the default session.  The 'with' block
  # above makes 'sess' the default session.
  print(x.eval())

get_shape

get_shape()

Get shape of random variable.

numpy

numpy()

Value as NumPy array, only available for TF Eager.

sample_shape_tensor

sample_shape_tensor(name='sample_shape_tensor')

Sample shape of random variable as a 1-D Tensor.

Args:

  • name: name to give to the op

Returns:

  • sample_shape: Tensor.

Class Members

__array_priority__