Permutes the rightmost dimension of a Tensor
.
Inherits From: Bijector
tf . contrib . distributions . bijectors . Permute (
permutation , validate_args = False , name = None
)
import tensorflow_probability as tfp
tfb = tfp . bijectors
reverse = tfb . Permute ( permutation = [ 2 , 1 , 0 ])
reverse . forward ([ - 1. , 0. , 1. ])
# ==> [1., 0., -1]
reverse . inverse ([ 1. , 0. , - 1 ])
# ==> [-1., 0., 1.]
reverse . forward_log_det_jacobian ( any_value )
# ==> 0.
reverse . inverse_log_det_jacobian ( any_value )
# ==> 0.
Warning: tf.estimator
may repeatedly build the graph thus
Permute(np.random.permutation(event_size)).astype("int32"))
is not a
reliable parameterization (nor would it be even if using tf.constant
). A
safe alternative is to use tf.compat.v1.get_variable
to achieve "init once"
behavior,
i.e.,
def init_once ( x , name ):
return tf . compat . v1 . get_variable ( name , initializer = x , trainable = False )
Permute ( permutation = init_once (
np . random . permutation ( event_size ) . astype ( "int32" ),
name = "permutation" ))
Args
permutation
An int
-like vector-shaped Tensor
representing the
permutation to apply to the rightmost dimension of the transformed
Tensor
.
validate_args
Python bool
indicating whether arguments should be
checked for correctness.
name
Python str
, name given to ops managed by this object.
Raises
TypeError
if not permutation.dtype.is_integer
.
ValueError
if permutation
does not contain exactly one of each of
{0, 1, ..., d}
.
Attributes
dtype
dtype of Tensor
s 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.
Note: Jacobian matrix is either constant for both forward and inverse or
neither.
name
Returns the string name of this Bijector
.
permutation
validate_args
Returns True if Tensor arguments will be validated.
Methods
forward
View source
forward (
x , name = 'forward'
)
Returns the forward Bijector
evaluation, i.e., X = g(Y).
Args
x
Tensor
. The input to the "forward" evaluation.
name
The name to give this op.
Raises
TypeError
if self.dtype
is specified and x.dtype
is not
self.dtype
.
NotImplementedError
if _forward
is not implemented.
forward_event_shape
View source
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.
Args
input_shape
TensorShape
indicating event-portion shape passed into
forward
function.
Returns
forward_event_shape_tensor
TensorShape
indicating event-portion shape
after applying forward
. Possibly unknown.
forward_event_shape_tensor
View source
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
.
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
Tensor
, int32
vector indicating
event-portion shape after applying forward
.
forward_log_det_jacobian
View source
forward_log_det_jacobian (
x , event_ndims , name = 'forward_log_det_jacobian'
)
Returns both 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 x.shape.ndims - event_ndims
dimensions.
name
The name to give this op.
Returns
Tensor
, if this bijector is injective.
If not injective this is not implemented.
Raises
TypeError
if self.dtype
is specified and y.dtype
is not
self.dtype
.
NotImplementedError
if neither _forward_log_det_jacobian
nor {_inverse
, _inverse_log_det_jacobian
} are implemented, or
this is a non-injective bijector.
inverse
View source
inverse (
y , name = 'inverse'
)
Returns the inverse Bijector
evaluation, i.e., X = g^{-1}(Y).
Args
y
Tensor
. The input to the "inverse" evaluation.
name
The name to give this op.
Returns
Tensor
, 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 self.dtype
is specified and y.dtype
is not
self.dtype
.
NotImplementedError
if _inverse
is not implemented.
inverse_event_shape
View source
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.
Args
output_shape
TensorShape
indicating event-portion shape passed into
inverse
function.
Returns
inverse_event_shape_tensor
TensorShape
indicating event-portion shape
after applying inverse
. Possibly unknown.
inverse_event_shape_tensor
View source
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
.
Args
output_shape
Tensor
, int32
vector indicating event-portion shape
passed into inverse
function.
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
inverse_log_det_jacobian (
y , event_ndims , name = 'inverse_log_det_jacobian'
)
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 y.shape.ndims - event_ndims
dimensions.
name
The name to give this op.
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
.
Raises
TypeError
if self.dtype
is specified and y.dtype
is not
self.dtype
.
NotImplementedError
if _inverse_log_det_jacobian
is not implemented.