trieste.models.keras.utils#

Module Contents#

get_tensor_spec_from_data(dataset: trieste.data.Dataset) → tuple[tensorflow.TensorSpec, tensorflow.TensorSpec][source]#

Extract tensor specifications for inputs and outputs of neural network models, based on the dataset. This utility faciliates constructing neural networks, providing the required dimensions for the input and the output of the network. For example

>>> data = Dataset(
...     tf.constant([[0.1, 0.2], [0.3, 0.4]]),
...     tf.constant([[0.5], [0.7]])
... )
>>> input_spec, output_spec = get_tensor_spec_from_data(data)
>>> input_spec
TensorSpec(shape=(2,), dtype=tf.float32, name='query_points')
>>> output_spec
TensorSpec(shape=(1,), dtype=tf.float32, name='observations')
Parameters:

dataset – A dataset with query_points and observations tensors.

Returns:

Tensor specification objects for the query_points and observations tensors.

Raises:

ValueError – If the dataset is not an instance of Dataset.

sample_with_replacement(dataset: trieste.data.Dataset) → trieste.data.Dataset[source]#

Create a new dataset with data sampled with replacement. This function is useful for creating bootstrap samples of data for training ensembles.

Parameters:

dataset – The data that should be sampled.

Returns:

A (new) dataset with sampled data.

Raises:

ValueError (or InvalidArgumentError) – If the dataset is not an instance of Dataset or it is empty.

sample_model_index(size: trieste.types.TensorType, num_samples: trieste.types.TensorType, seed: int | None = None) → trieste.types.TensorType[source]#

Returns samples of indices of individual models in the ensemble.

If num_samples is smaller or equal to size (i.e. the ensemble size) indices are sampled without replacement. When num_samples is larger than size then until size is reached we sample without replacement, while after that we sample with replacement. The rationale of this mixed scheme is that typically one wants to exhaust all networks and then resample them only if required.

Parameters:

  • size – The maximum index, effectively the number of models in the ensemble.

  • num_samples – The number of samples to take.

  • seed – Optional RNG seed.

Returns:

A tensor with indices.

negative_log_likelihood(y_true: trieste.types.TensorType, y_pred: tensorflow_probability.distributions.Distribution) → trieste.types.TensorType[source]#

Maximum likelihood objective function for training neural networks.

Parameters:

  • y_true – The output variable values.

  • y_pred – The output layer of the model. It has to be a probabilistic neural network with a distribution as a final layer.

Returns:

Negative log likelihood values.