Function that executes a Vanilla Biometric evaluation pipeline. Instead working with a :py:class: `bob.bio.base.pipelines.vanilla_biometrics.abstract_class.Database`,
this function takes independent `background_model_samples`, `biometric_references` and `probes`. Thus it enables to perform cross-database experiments.
Parameters
----------
pipeline: Instance of :py:class:`bob.bio.base.pipelines.vanilla_biometrics.VanillaBiometricsPipeline`
A constructed vanilla-biometrics pipeline. The pipeline should already have been setup for writing using the
:py:function: `bob.bio.base.pipelines.vanilla_biometrics.vanilla_biometrics.setup_writing` function
background_model_samples: List of :py:class:`bob.pipelines.samples.SampleSet` used for training the model.
(Such as the output of a :py:method: `bob.bio.base.pipelines.vanilla_biometrics.abstract_class.Database.background_model_samples()`)
biometric_references: List of :py:class:`bob.pipelines.samples.SampleSet` used for enrolling the biometric references.
(Such as the output of a :py:method: `bob.bio.base.pipelines.vanilla_biometrics.abstract_class.Database.references()`)
probes: List of :py:class:`bob.pipelines.samples.SampleSet` used to probe the model.
(Such as the output of a :py:method: `bob.bio.base.pipelines.vanilla_biometrics.abstract_class.Database.probes()`)
dask_client: instance of :py:class:`dask.distributed.Client` or ``None``
A Dask client instance used to run the experiment in parallel on multiple
machines, or locally.
Basic configs can be found in ``bob.pipelines.config.distributed``.
output: str
Path where the results and checkpoints will be saved to.
score_file_name: str
Name of the ouput CSV scores file
write_metadata_scores: bool
Use the CSVScoreWriter instead of the FourColumnScoreWriter when True.
checkpoint: bool
Whether checkpoint files will be created for every step of the pipelines.