twodlearn.constrained module¶
Constrained variables
This module defines a set of constrained variables. These variables are trainable, and can only take values inside a given region. For example, PositiveVariable is only allowed to take positive values.
-
class
twodlearn.constrained.
BoundedVariable
(min, max, initializer, initial_value=None, trainable=True, collections=None, validate_shape=True, caching_device=None, name='variable', variable_def=None, dtype=None, expected_shape=None, import_scope=None, constraint=None, options=None)[source]¶ Bases:
twodlearn.constrained.TransformedVariable
Creates a variable that can only take values inside a range
-
class
twodlearn.constrained.
ConstrainedVariable
(initial_value, min=0.0, max=inf, name=None)[source]¶
-
class
twodlearn.constrained.
PositiveVariable
(initial_value, trainable=True, collections=None, validate_shape=True, caching_device=None, name=None, variable_def=None, dtype=None, expected_shape=None, import_scope=None, constraint=None, **kargs)[source]¶ Bases:
twodlearn.constrained.TransformedVariable
Creates a variable that can only take positive values.
This fuction uses tf.nn.softplus to ensure positive values.
Tdl autoinitialization with arguments:
-
tolerance
[source]¶ (
InputArgument
) tolerance for positive variables.
-
raw
[source]¶ (
SimpleParameter
) raw value before making a transformation
-
tolerance
[source] tolerance for positive variables.
-
-
class
twodlearn.constrained.
PositiveVariable2
(initial_value, trainable=True, collections=None, validate_shape=True, caching_device=None, name=None, variable_def=None, dtype=None, expected_shape=None, import_scope=None, constraint=None, **kargs)[source]¶ Bases:
twodlearn.constrained.TransformedVariable
Creates a variable that can only take positive values. This function uses pow(x,2) as a reparameterization of the variable
-
class
twodlearn.constrained.
PositiveVariableExp
(initial_value, max=None, trainable=True, collections=None, validate_shape=True, caching_device=None, name=None, tolerance=None)[source]¶ Bases:
twodlearn.constrained.TransformedVariable
Creates a variable that can only take positive values.
This function uses
exp()
as a reparameterization of the variableTdl autoinitialization with arguments:
-
raw
[source]¶ (
ParameterInit
) raw value before making a transformation
-
tolerance
[source]¶ (
InputArgument
) tolerance for positive variables.
-
max
[source]
-
raw
[source] raw value before making a transformation
-
tolerance
[source] tolerance for positive variables.
-
-
class
twodlearn.constrained.
TransformedVariable
(initial_value, trainable=True, collections=None, validate_shape=True, caching_device=None, name=None, variable_def=None, dtype=None, expected_shape=None, import_scope=None, constraint=None, **kargs)[source]¶ Bases:
twodlearn.core.common.TdlModel
Variable that uses a transformation to ensure the output is constrained.
Initialization is performed using the inverse method
raw = tf.Variable(inverse(initial_value))
The value is defined using the transform
value = transform(raw)
Tdl autoinitialization with arguments:
-
raw
[source]¶ (
SimpleParameter
) raw value before making a transformation
-
classmethod
init_wrapper
(initializer, trainable, **kargs)[source]¶ wraps the object to be used as an initializer.
-
raw
[source] raw value before making a transformation
-
value
[source]
-