gpflux.layers.likelihood_layer

A Keras Layer that wraps a likelihood, while containing the necessary operations for training.

Module Contents

class TrackableLayer

Bases: gpflow.keras.tf_keras.layers.Layer

With the release of TensorFlow 2.5, our TrackableLayer workaround is no longer needed. See Prowler-io/gpflux#189. Will be removed in GPflux version 1.0.0

unwrap_dist(dist: tfp.distributions.Distribution) → tfp.distributions.Distribution

Unwrap the given distribution, if it is wrapped in a _TensorCoercible.

class LikelihoodLayer(likelihood: gpflow.likelihoods.Likelihood)

Bases: gpflux.layers.trackable_layer.TrackableLayer

A Keras layer that wraps a GPflow Likelihood. This layer expects a tfp.distributions.MultivariateNormalDiag as its input, describing q(f). When training, calling this class computes the negative variational expectation \(-\mathbb{E}_{q(f)}[\log p(y|f)]\) and adds it as a layer loss. When not training, it computes the mean and variance of y under q(f) using predict_mean_and_var().

Note

Use either this LikelihoodLayer (together with gpflux.models.DeepGP) or LikelihoodLoss (e.g. together with a tf.keras.Sequential model). Do not use both at once because this would add the loss twice.

call(inputs: tfp.distributions.MultivariateNormalDiag, targets: gpflow.base.TensorType | None = None, training: bool = None) → LikelihoodOutputs

When training (training=True), this method computes variational expectations (data-fit loss) and adds this information as a layer loss. When testing (the default), it computes the posterior mean and variance of y.

Parameters:

inputs – The output distribution of the previous layer. This is currently expected to be a MultivariateNormalDiag; that is, the preceding GPLayer should have full_cov=full_output_cov=False.

Returns:

a LikelihoodOutputs tuple with the mean and variance of f and, if not training, the mean and variance of y.

Todo

Turn this layer into a DistributionLambda as well and return the correct Distribution instead of a tuple containing mean and variance only.

class LikelihoodOutputs(f_mean: gpflow.base.TensorType, f_var: gpflow.base.TensorType, y_mean: gpflow.base.TensorType | None, y_var: gpflow.base.TensorType | None)

Bases: tf.Module

This class encapsulates the outputs of a LikelihoodLayer.

It contains the mean and variance of the marginal distribution of the final latent GPLayer, as well as the mean and variance of the likelihood.

This class includes the TensorMetaClass to make objects behave as a tf.Tensor. This is necessary so that it can be returned from the tfp.layers.DistributionLambda Keras layer.