treeflow.bijectors.fixed_topology_bijector module

class treeflow.bijectors.fixed_topology_bijector.FixedTopologyRootedTreeBijector(topology: TensorflowTreeTopology, height_bijector: Bijector, sampling_times: Tensor | None = None, name='FixedTopologyRootedTreeBijector', validate_args=False)

Bases: Bijector

inverse_event_ndims(event_ndims, **kwargs)

Returns the number of event dimensions produced by inverse.

Parameters:

  • event_ndims – Structure of Python and/or Tensor int`s, and/or `None values. The structure should match that of self.inverse_min_event_ndims, and all non-None values must be greater than or equal to the corresponding value in self.inverse_min_event_ndims.

  • **kwargs – Optional keyword arguments forwarded to nested bijectors.

Returns:

Structure of integers and/or None values matching

self.forward_min_event_ndims. These are computed using ‘prefer static’ semantics: if any inputs are None, some or all of the outputs may be None, indicating that the output dimension could not be inferred (conversely, if all inputs are non-None, all outputs will be non-None). If all input event_ndims are Python int`s, all of the (non-`None) outputs will be Python int`s; otherwise, some or all of the outputs may be `Tensor `int`s.

Return type:

inverse_event_ndims

copy(**override_parameters_kwargs)

Creates a copy of the bijector.

Note: the copy bijector may continue to depend on the original initialization arguments.

Parameters:

**override_parameters_kwargs – String/value dictionary of initialization arguments to override with new values.

Returns:

A new instance of type(self) initialized from the union

of self.parameters and override_parameters_kwargs, i.e., dict(self.parameters, **override_parameters_kwargs).

Return type:

bijector

property dtype
experimental_batch_shape(x_event_ndims=None, y_event_ndims=None)

Returns the batch shape of this bijector for inputs of the given rank.

The batch shape of a bijector decribes the set of distinct transformations it represents on events of a given size. For example: the bijector tfb.Scale([1., 2.]) has batch shape [2] for scalar events (event_ndims = 0), because applying it to a scalar event produces two scalar outputs, the result of two different scaling transformations. The same bijector has batch shape [] for vector events, because applying it to a vector produces (via elementwise multiplication) a single vector output.

Bijectors that operate independently on multiple state parts, such as tfb.JointMap, must broadcast to a coherent batch shape. Some events may not be valid: for example, the bijector tfd.JointMap([tfb.Scale([1., 2.]), tfb.Scale([1., 2., 3.])]) does not produce a valid batch shape when event_ndims = [0, 0], since the batch shapes of the two parts are inconsistent. The same bijector does define valid batch shapes of [], [2], and [3] if event_ndims is [1, 1], [0, 1], or [1, 0], respectively.

Since transforming a single event produces a scalar log-det-Jacobian, the batch shape of a bijector with non-constant Jacobian is expected to equal the shape of forward_log_det_jacobian(x, event_ndims=x_event_ndims) or inverse_log_det_jacobian(y, event_ndims=y_event_ndims), for x or y of the specified ndims.

Parameters:

  • x_event_ndims – Optional Python int (structure) number of dimensions in a probabilistic event passed to forward; this must be greater than or equal to self.forward_min_event_ndims. If None, defaults to self.forward_min_event_ndims. Mutually exclusive with y_event_ndims. Default value: None.

  • y_event_ndims – Optional Python int (structure) number of dimensions in a probabilistic event passed to inverse; this must be greater than or equal to self.inverse_min_event_ndims. Mutually exclusive with x_event_ndims. Default value: None.

Returns:

TensorShape batch shape of this bijector for a

value with the given event rank. May be unknown or partially defined.

Return type:

batch_shape

experimental_batch_shape_tensor(x_event_ndims=None, y_event_ndims=None)

Returns the batch shape of this bijector for inputs of the given rank.

The batch shape of a bijector decribes the set of distinct transformations it represents on events of a given size. For example: the bijector tfb.Scale([1., 2.]) has batch shape [2] for scalar events (event_ndims = 0), because applying it to a scalar event produces two scalar outputs, the result of two different scaling transformations. The same bijector has batch shape [] for vector events, because applying it to a vector produces (via elementwise multiplication) a single vector output.

Bijectors that operate independently on multiple state parts, such as tfb.JointMap, must broadcast to a coherent batch shape. Some events may not be valid: for example, the bijector tfd.JointMap([tfb.Scale([1., 2.]), tfb.Scale([1., 2., 3.])]) does not produce a valid batch shape when event_ndims = [0, 0], since the batch shapes of the two parts are inconsistent. The same bijector does define valid batch shapes of [], [2], and [3] if event_ndims is [1, 1], [0, 1], or [1, 0], respectively.

Since transforming a single event produces a scalar log-det-Jacobian, the batch shape of a bijector with non-constant Jacobian is expected to equal the shape of forward_log_det_jacobian(x, event_ndims=x_event_ndims) or inverse_log_det_jacobian(y, event_ndims=y_event_ndims), for x or y of the specified ndims.

Parameters:

  • x_event_ndims – Optional Python int (structure) number of dimensions in a probabilistic event passed to forward; this must be greater than or equal to self.forward_min_event_ndims. If None, defaults to self.forward_min_event_ndims. Mutually exclusive with y_event_ndims. Default value: None.

  • y_event_ndims – Optional Python int (structure) number of dimensions in a probabilistic event passed to inverse; this must be greater than or equal to self.inverse_min_event_ndims. Mutually exclusive with x_event_ndims. Default value: None.

Returns:

integer Tensor batch shape of this bijector for a

value with the given event rank.

Return type:

batch_shape_tensor

experimental_compute_density_correction(x, tangent_space, backward_compat=False, **kwargs)

Density correction for this transformation wrt the tangent space, at x.

Subclasses of Bijector may call the most specific applicable method of TangentSpace, based on whether the transformation is dimension-preserving, coordinate-wise, a projection, or something more general. The backward-compatible assumption is that the transformation is dimension-preserving (goes from R^n to R^n).

Parameters:

  • x – Tensor (structure). The point at which to calculate the density.

  • tangent_space – TangentSpace or one of its subclasses. The tangent to the support manifold at x.

  • backward_compat – bool specifying whether to assume that the Bijector is dimension-preserving.

  • **kwargs – Optional keyword arguments forwarded to tangent space methods.

Returns:

Tensor representing the density correction—in log

space—under the transformation that this Bijector denotes.

Return type:

density_correction

Raises:

TypeError if backward_compat is False but no method of – TangentSpace has been called explicitly.

forward(x, name='forward', **kwargs)

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

Parameters:

  • x – Tensor (structure). The input to the ‘forward’ evaluation.

  • name – The name to give this op.

  • **kwargs – Named arguments forwarded to subclass implementation.

Returns:

Tensor (structure).

Raises:

  • TypeError – if self.dtype is specified and x.dtype is not self.dtype.

  • NotImplementedError – if _forward is not implemented.

forward_dtype(dtype=<object object>, name='forward_dtype', **kwargs)

Returns the dtype returned by forward for the provided input.

forward_event_ndims(event_ndims, **kwargs)

Returns the number of event dimensions produced by forward.

Parameters:

  • event_ndims – Structure of Python and/or Tensor int`s, and/or `None values. The structure should match that of self.forward_min_event_ndims, and all non-None values must be greater than or equal to the corresponding value in self.forward_min_event_ndims.

  • **kwargs – Optional keyword arguments forwarded to nested bijectors.

Returns:

Structure of integers and/or None values matching

self.inverse_min_event_ndims. These are computed using ‘prefer static’ semantics: if any inputs are None, some or all of the outputs may be None, indicating that the output dimension could not be inferred (conversely, if all inputs are non-None, all outputs will be non-None). If all input event_ndims are Python int`s, all of the (non-`None) outputs will be Python int`s; otherwise, some or all of the outputs may be `Tensor `int`s.

Return type:

forward_event_ndims

forward_event_shape(input_shape)

Shape of a single sample from a single batch as a TensorShape.

Same meaning as forward_event_shape_tensor. May be only partially defined.

Parameters:

input_shape – TensorShape (structure) indicating event-portion shape passed into forward function.

Returns:

TensorShape (structure) indicating

event-portion shape after applying forward. Possibly unknown.

Return type:

forward_event_shape_tensor

forward_event_shape_tensor(input_shape, name='forward_event_shape_tensor')

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

Parameters:

  • input_shape – Tensor, int32 vector (structure) indicating event-portion shape passed into forward function.

  • name – name to give to the op

Returns:

Tensor, int32 vector (structure)

indicating event-portion shape after applying forward.

Return type:

forward_event_shape_tensor

forward_log_det_jacobian(x, event_ndims=None, name='forward_log_det_jacobian', **kwargs)

Returns both the forward_log_det_jacobian.

Parameters:

  • x – Tensor (structure). The input to the ‘forward’ Jacobian determinant evaluation.

  • event_ndims – Optional number of dimensions in the probabilistic events being transformed; this must be greater than or equal to self.forward_min_event_ndims. If event_ndims is specified, the log Jacobian determinant is summed to produce a scalar log-determinant for each event. Otherwise (if event_ndims is None), no reduction is performed. Multipart bijectors require structured event_ndims, such that the batch rank rank(y[i]) - event_ndims[i] is the same for all elements i of the structured input. In most cases (with the exception of tfb.JointMap) they further require that event_ndims[i] - self.inverse_min_event_ndims[i] is the same for all elements i of the structured input. Default value: None (equivalent to self.forward_min_event_ndims).

  • name – The name to give this op.

  • **kwargs – Named arguments forwarded to subclass implementation.

Returns:

Tensor (structure), if this bijector is injective.

If not injective this is not implemented.

Raises:

  • TypeError – if y’s dtype is incompatible with the expected output dtype.

  • NotImplementedError – if neither _forward_log_det_jacobian nor {_inverse, _inverse_log_det_jacobian} are implemented, or this is a non-injective bijector.

  • ValueError – if the value of event_ndims is not valid for this bijector.

property forward_min_event_ndims

Returns the minimal number of dimensions bijector.forward operates on.

Multipart bijectors return structured ndims, which indicates the expected structure of their inputs. Some multipart bijectors, notably Composites, may return structures of None.

property graph_parents

Returns this Bijector’s graph_parents as a Python list.

inverse(y, name='inverse', **kwargs)

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

Parameters:

  • y – Tensor (structure). The input to the ‘inverse’ evaluation.

  • name – The name to give this op.

  • **kwargs – Named arguments forwarded to subclass implementation.

Returns:

Tensor (structure), if this bijector is injective.

If not injective, returns the k-tuple containing the unique k points (x1, …, xk) such that g(xi) = y.

Raises:

  • TypeError – if y’s structured dtype is incompatible with the expected output dtype.

  • NotImplementedError – if _inverse is not implemented.

inverse_dtype(dtype=<object object>, name='inverse_dtype', **kwargs)

Returns the dtype returned by inverse for the provided input.

inverse_event_shape(output_shape)

Shape of a single sample from a single batch as a TensorShape.

Same meaning as inverse_event_shape_tensor. May be only partially defined.

Parameters:

output_shape – TensorShape (structure) indicating event-portion shape passed into inverse function.

Returns:

TensorShape (structure) indicating

event-portion shape after applying inverse. Possibly unknown.

Return type:

inverse_event_shape_tensor

inverse_event_shape_tensor(output_shape, name='inverse_event_shape_tensor')

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

Parameters:

  • output_shape – Tensor, int32 vector (structure) indicating event-portion shape passed into inverse function.

  • name – name to give to the op

Returns:

Tensor, int32 vector (structure)

indicating event-portion shape after applying inverse.

Return type:

inverse_event_shape_tensor

inverse_log_det_jacobian(y, event_ndims=None, name='inverse_log_det_jacobian', **kwargs)

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).

Parameters:

  • y – Tensor (structure). The input to the ‘inverse’ Jacobian determinant evaluation.

  • event_ndims – Optional number of dimensions in the probabilistic events being transformed; this must be greater than or equal to self.inverse_min_event_ndims. If event_ndims is specified, the log Jacobian determinant is summed to produce a scalar log-determinant for each event. Otherwise (if event_ndims is None), no reduction is performed. Multipart bijectors require structured event_ndims, such that the batch rank rank(y[i]) - event_ndims[i] is the same for all elements i of the structured input. In most cases (with the exception of tfb.JointMap) they further require that event_ndims[i] - self.inverse_min_event_ndims[i] is the same for all elements i of the structured input. Default value: None (equivalent to self.inverse_min_event_ndims).

  • name – The name to give this op.

  • **kwargs – Named arguments forwarded to subclass implementation.

Returns:

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.

Return type:

ildj

Raises:

  • TypeError – if x’s dtype is incompatible with the expected inverse-dtype.

  • NotImplementedError – if _inverse_log_det_jacobian is not implemented.

  • ValueError – if the value of event_ndims is not valid for this bijector.

property inverse_min_event_ndims

Returns the minimal number of dimensions bijector.inverse operates on.

Multipart bijectors return structured event_ndims, which indicates the expected structure of their outputs. Some multipart bijectors, notably Composites, may return structures of None.

property is_constant_jacobian

Returns true iff the Jacobian matrix is not a function of x.

Note: Jacobian matrix is either constant for both forward and inverse or neither.

Returns:

Python bool.

Return type:

is_constant_jacobian

property name

Returns the string name of this Bijector.

property name_scope

Returns a tf.name_scope instance for this class.

property non_trainable_variables

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

Note: this method uses reflection to find variables on the current instance and submodules. For performance reasons you may wish to cache the result of calling this method if you don’t expect the return value to change.

Returns:

A sequence of variables for the current module (sorted by attribute name) followed by variables from all submodules recursively (breadth first).

classmethod parameter_properties(dtype=tf.float32)

Returns a dict mapping constructor arg names to property annotations.

This dict should include an entry for each of the bijector’s Tensor-valued constructor arguments.

Parameters:

dtype – Optional float dtype to assume for continuous-valued parameters. Some constraining bijectors require advance knowledge of the dtype because certain constants (e.g., tfb.Softplus.low) must be instantiated with the same dtype as the values to be transformed.

Returns:

A

str -> `tfp.python.internal.parameter_properties.ParameterProperties dict mapping constructor argument names to ParameterProperties instances.

Return type:

parameter_properties

property parameters

Dictionary of parameters used to instantiate this Bijector.

property 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
Returns:

A sequence of all submodules.

property trainable_variables

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

Note: this method uses reflection to find variables on the current instance and submodules. For performance reasons you may wish to cache the result of calling this method if you don’t expect the return value to change.

Returns:

A sequence of variables for the current module (sorted by attribute name) followed by variables from all submodules recursively (breadth first).

property validate_args

Returns True if Tensor arguments will be validated.

property variables

Sequence of variables owned by this module and its submodules.

Note: this method uses reflection to find variables on the current instance and submodules. For performance reasons you may wish to cache the result of calling this method if you don’t expect the return value to change.

Returns:

A sequence of variables for the current module (sorted by attribute name) followed by variables from all submodules recursively (breadth first).

classmethod with_name_scope(method)

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.Variable`s and `tf.Tensor`s 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)>
Parameters:

method – The method to wrap.

Returns:

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