gpflux.layers.basis_functions.fourier_features.base#

Shared functionality for stationary kernel basis functions.

Module Contents#

ShapeType[source]#: Union of valid types for describing the shape of a tf.Tensor(-like) object

class FourierFeaturesBase(kernel: gpflow.kernels.Kernel, n_components: int, **kwargs: Mapping)[source]#

Bases: abc.ABC, gpflow.keras.tf_keras.layers.Layer

The base class for all Fourier feature layers, used for both random Fourier feature layers and quadrature layers. We subclass tf.keras.layers.Layer, so we must provide :method:`build` and :method:`call` methods.

Parameters:

kernel – kernel to approximate using a set of Fourier bases.
n_components – number of components (e.g. Monte Carlo samples, quadrature nodes, etc.) used to numerically approximate the kernel.

call(inputs: gpflow.base.TensorType) → tf.Tensor[source]#

Evaluate the basis functions at inputs.

Parameters:: inputs – The evaluation points, a tensor with the shape [N, D].
Returns:: A tensor with the shape [N, M], or shape ``[P, N, M]’’ in the multioutput case.

compute_output_shape(input_shape: gpflux.types.ShapeType) → tf.TensorShape[source]#: Computes the output shape of the layer. See tf.keras.layers.Layer.compute_output_shape().

get_config() → Mapping[source]#: Returns the config of the layer. See tf.keras.layers.Layer.get_config().

abstract _compute_constant() → tf.Tensor[source]#: Compute normalizing constant for basis functions.

abstract _compute_bases(inputs: gpflow.base.TensorType) → tf.Tensor[source]#: Compute basis functions.