tfp.bijectors.Split

Split a Tensor event along an axis into a list of Tensors.

Inherits From: Bijector

Example Use:

split = tfb.Split(
    num_or_size_splits=[4, 1, 3],
    axis=-1
  )
y = split.forward(tf.zeros([5, 6, 8]))
==> [<`Tensor`, shape=(5, 6, 4)>,
     <`Tensor`, shape=(5, 6, 1)>,
     <`Tensor`, shape=(5, 6, 3)>]

# The inverse of `split` concatenates a list of `Tensor`s along `axis`.
x_ = split.inverse(y_)
x_.shape
==> TensorShape([5, 6, 8])

num_or_size_splits Either a Python integer indicating the number of splits along axis or a 1-D integer Tensor or Python list containing the sizes of each output tensor along axis. If a list/Tensor, it may contain at most one value of -1, which indicates a split size that is unknown and determined from input.
axis A negative integer or scalar int32 Tensor. The dimension along which to split. Must be negative to enable the bijector to support arbitrary batch dimensions. Defaults to -1 (note that this is different from the tf.Split default of 0). Must be statically known.
validate_args Python bool indicating whether arguments should be checked for correctness.
name Python str, name given to ops managed by this object.

axis

dtype dtype of Tensors transformable by this distribution.
forward_min_event_ndims Returns the minimal number of dimensions bijector.forward operates on.
graph_parents Returns this Bijector's graph_parents as a Python list.
inverse_min_event_ndims Returns the minimal number of dimensions bijector.inverse operates on.
is_constant_jacobian Returns true iff the Jacobian matrix is not a function of x.

name Returns the string name of this Bijector.
name_scope Returns a tf.name_scope instance for this class.
num_splits

parameters Dictionary of parameters used to instantiate this Bijector.
split_sizes

submodules Sequence of all sub-modules.

Submodules are modules which are properties of this module, or found as properties of modules which are properties of this module (and so on).

a = tf.Module()
b = tf.Module()
c = tf.Module()
a.b = b
b.c = c
list(a.submodules) == [b, c]
True
list(b.submodules) == [c]
True
list(c.submodules) == []
True

trainable_variables Sequence of trainable variables owned by this module and its submodules.

validate_args Returns True if Tensor arguments will be validated.
variables Sequence of variables owned by this module and its submodules.

Methods

forward

View source

Returns the forward Bijector evaluation, i.e., X = g(Y).

Equivalent to tf.split(x).

Args
x Tensor. The input to the 'forward' evaluation.
name The name to give this op.

Returns
List of Tensors.

Raises
TypeError if self.dtype is specified and x.dtype is not self.dtype.
ValueError if the sum of split_sizes does not equal the size of the axis dimension of x.

forward_dtype

View source

Returns the dtype of the output of the forward transformation.

Args
dtype tf.dtype, or nested structure of tf.dtypes, of the input to forward.
name The name to give this op.
**kwargs Named arguments forwarded to subclass implementation.

Returns
tf.dtype or nested structure of tf.dtypes of the output of forward.

forward_event_shape

View source

Shape of a single sample from a single batch as a list of TensorShapes.

Same meaning as forward_event_shape_tensor. May be only partially defined.

Args
input_shape TensorShape indicating event-portion shape passed into forward function.

Returns
forward_event_shape A list of (possibly unknown) TensorShapes indicating event-portion shape after applying forward. The length of the list is equal to the number of splits.

forward_event_shape_tensor

View source

Shape of a sample from a single batch as a list of int32 1D Tensors.

Args
input_shape Tensor, int32 vector indicating event-portion shape passed into forward function.
name name to give to the op

Returns
forward_event_shape_tensor A list of Tensor, int32 vectors indicating event-portion shape after applying forward. The length of the list is equal to the number of splits.

forward_log_det_jacobian

View source

Returns the forward_log_det_jacobian.

Args
x Tensor. The input to the 'forward' Jacobian determinant evaluation.
event_ndims Number of dimensions in the probabilistic events being transformed. Must be greater than or equal to self.forward_min_event_ndims. The result is summed over the final dimensions to produce a scalar Jacobian determinant for each event, i.e. it has shape rank(x) - event_ndims dimensions.
name The name to give this op.

Returns
Tensor, if this bijector is injective. If not injective this is not implemented.

inverse

View source

Returns the inverse Bijector evaluation, i.e., X = g^{-1}(Y).

Args
y List of Tensors. The input to the 'inverse' evaluation.
name The name to give this op.

Returns
Tensor.

Raises
TypeError if self.dtype is specified and y.dtype is not self.dtype.

inverse_dtype

View source

Returns the dtype of the output of the inverse transformation.

Args
dtype tf.dtype, or nested structure of tf.dtypes, of the input to inverse.
name The name to give this op.
**kwargs Named arguments forwarded to subclass implementation.

Returns
tf.dtype or nested structure of tf.dtypes of the output of inverse.

inverse_event_shape

View source

Shape of a sample from a single batch as a [nested] TensorShape.

Same meaning as inverse_event_shape_tensor. May be only partially defined.

Args
output_shapes Iterable of TensorShapes indicating the event shapes passed into inverse function. The length of the iterable must be equal to the number of splits.

Returns
inverse_event_shape_tensor TensorShape indicating event-portion shape after applying inverse. Possibly unknown.

inverse_event_shape_tensor

View source

Shape of a single sample from a single batch as an int32 1D Tensor.

Args
output_shapes An iterable of Tensor, int32 vectors indicating event-shapes passed into inverse function. The length of the iterable must be equal to the number of splits.
name Name to give to the op.

Returns
inverse_event_shape_tensor Tensor, int32 vector indicating event-portion shape after applying inverse.

inverse_log_det_jacobian

View source

Returns the (log o det o Jacobian o inverse)(y).

Mathematically, returns: log(det(dX/dY))(Y). (Recall that: X=g^{-1}(Y).)

Note that forward_log_det_jacobian is the negative of this function, evaluated at g^{-1}(y).

Args
y Tensor. The input to the 'inverse' Jacobian determinant evaluation.
event_ndims Number of dimensions in the probabilistic events being transformed. Must be greater than or equal to self.inverse_min_event_ndims. The result is summed over the final dimensions to produce a scalar Jacobian determinant for each event, i.e. it has shape rank(y) - event_ndims dimensions.
name The name to give this op.
**kwargs Named arguments forwarded to subclass implementation.

Returns
ildj Tensor, if this bijector is injective. If not injective, returns the tuple of local log det Jacobians, log(det(Dg_i^{-1}(y))), where g_i is the restriction of g to the ith partition Di.

Raises
TypeError if self.dtype is specified and y.dtype is not self.dtype.
NotImplementedError if _inverse_log_det_jacobian is not implemented.

with_name_scope

Decorator to automatically enter the module name scope.

class MyModule(tf.Module):
  @tf.Module.with_name_scope
  def __call__(self, x):
    if not hasattr(self, 'w'):
      self.w = tf.Variable(tf.random.normal([x.shape[1], 3]))
    return tf.matmul(x, self.w)

Using the above module would produce tf.Variables and tf.Tensors whose names included the module name:

mod = MyModule()
mod(tf.ones([1, 2]))
<tf.Tensor: shape=(1, 3), dtype=float32, numpy=..., dtype=float32)>
mod.w
<tf.Variable 'my_module/Variable:0' shape=(2, 3) dtype=float32,
numpy=..., dtype=float32)>

Args
method The method to wrap.

Returns
The original method wrapped such that it enters the module's name scope.

__call__

View source

Applies or composes the Bijector, depending on input type.

This is a convenience function which applies the Bijector instance in three different ways, depending on the input:

  1. If the input is a tfd.Distribution instance, return tfd.TransformedDistribution(distribution=input, bijector=self).
  2. If the input is a tfb.Bijector instance, return tfb.Chain([self, input]).
  3. Otherwise, return self.forward(input)

Args
value A tfd.Distribution, tfb.Bijector, or a Tensor.
name Python str name given to ops created by this function.
**kwargs Additional keyword arguments passed into the created tfd.TransformedDistribution, tfb.Bijector, or self.forward.

Returns
composition A tfd.TransformedDistribution if the input was a tfd.Distribution, a tfb.Chain if the input was a tfb.Bijector, or a Tensor computed by self.forward.

Examples

sigmoid = tfb.Reciprocal()(
    tfb.AffineScalar(shift=1.)(
      tfb.Exp()(
        tfb.AffineScalar(scale=-1.))))
# ==> `tfb.Chain([
#         tfb.Reciprocal(),
#         tfb.AffineScalar(shift=1.),
#         tfb.Exp(),
#         tfb.AffineScalar(scale=-1.),
#      ])`  # ie, `tfb.Sigmoid()`

log_normal = tfb.Exp()(tfd.Normal(0, 1))
# ==> `tfd.TransformedDistribution(tfd.Normal(0, 1), tfb.Exp())`

tfb.Exp()([-1., 0., 1.])
# ==> tf.exp([-1., 0., 1.])