gpflow¶

gpflow.Module¶

class gpflow.Module(name=None)[source]¶

Bases: tensorflow.python.module.module.Module

Attributes

name: Returns the name of this module as passed or determined in the ctor.
name_scope: Returns a tf.name_scope instance for this class.
non_trainable_variables: Sequence of non-trainable variables owned by this module and its submodules.
parameters
submodules: Sequence of all sub-modules.
trainable_parameters
trainable_variables: Sequence of trainable variables owned by this module and its submodules.
variables: Sequence of variables owned by this module and its submodules.

Methods

with_name_scope(method)

Decorator to automatically enter the module name scope.

gpflow.Parameter¶

class gpflow.Parameter(value, *, transform=None, prior=None, prior_on=None, trainable=None, dtype=None, name=None, unconstrained_shape=None, constrained_shape=None, shape=None)[source]¶

Bases: tensorflow_probability.python.util.deferred_tensor.TransformedVariable

Attributes

also_track: Additional variables tracked by tf.Module in self.trainable_variables.
bijector
dtype: Represents the type of the elements in a Tensor.
initializer: The initializer operation for the underlying variable.
name: The string name of this object.
name_scope: Returns a tf.name_scope instance for this class.
non_trainable_variables: Sequence of non-trainable variables owned by this module and its submodules.
pretransformed_input: Input to transform_fn.
prior_on
shape: Represents the shape of a Tensor.
submodules: Sequence of all sub-modules.
trainable: True if this instance is trainable, else False.
trainable_variables: Sequence of trainable variables owned by this module and its submodules.
transform
transform_fn: Function which characterizes the `Tensor`ization of this object.
unconstrained_variable
variables: Sequence of variables owned by this module and its submodules.

Methods

`assign`(value[, use_locking, name, read_value])	Assigns constrained value to the unconstrained parameter's variable.
`assign_add`(delta[, use_locking, name, ...])	Adds a value to this variable.
`assign_sub`(delta[, use_locking, name, ...])	Subtracts a value from this variable.
`get_shape`()	Legacy means of getting Tensor shape, for compat with 2.0.0 LinOp.
`log_prior_density`()	Log of the prior probability density of the constrained variable.
`numpy`()	Returns (copy of) deferred values as a NumPy array or scalar.
`set_shape`(shape)	Updates the shape of this pretransformed_input.
`with_name_scope`(method)	Decorator to automatically enter the module name scope.

Parameters

value (Union[int, float, Sequence[Any], ndarray, Tensor, Variable, Parameter]) –
transform (Optional[Bijector]) –
prior (Optional[Distribution]) –
prior_on (Union[str, PriorOn, None]) –
trainable (Optional[bool]) –
dtype (Union[dtype, DType, None]) –
name (Optional[str]) –
unconstrained_shape (Optional[Sequence[Optional[int]]]) –
constrained_shape (Optional[Sequence[Optional[int]]]) –
shape (Optional[Sequence[Optional[int]]]) –

assign(value, use_locking=False, name=None, read_value=True)[source]¶

Assigns constrained value to the unconstrained parameter’s variable. It passes constrained value through parameter’s transform first.

Example:

``` a = Parameter(2.0, transform=tfp.bijectors.Softplus()) b = Parameter(3.0)

a.assign(4.0) # a parameter to 2.0 value. a.assign(tf.constant(5.0)) # a parameter to 5.0 value. a.assign(b) # a parameter to constrained value of b. ```

Parameters

value (Union[int, float, Sequence[Any], ndarray, Tensor, Variable, Parameter]) – Constrained tensor-like value.
use_locking (bool) – If True, use locking during the assignment.
name (Optional[str]) – The name of the operation to be created.
read_value (bool) – if True, will return something which evaluates to the new value of the variable; if False will return the assign op.

Return type: Tensor

log_prior_density()[source]¶

Log of the prior probability density of the constrained variable.

Return type: Tensor

property trainable: bool¶

True if this instance is trainable, else False.

This attribute cannot be set directly. Use gpflow.set_trainable().

Return type: bool

gpflow.default_float¶

gpflow.default_float()[source]¶

Returns default float type

Return type: type

gpflow.default_int¶

gpflow.default_int()[source]¶

Returns default integer type

Return type: type

gpflow.default_jitter¶

gpflow.default_jitter()[source]¶

The jitter is a constant that GPflow adds to the diagonal of matrices to achieve numerical stability of the system when the condition number of the associated matrices is large, and therefore the matrices nearly singular.