privpack.model_selection.experiment module¶
Some introduction on how to define experiments.
API Documentation¶
This module defines how experiments are conducted. What is expected from your network and how many train/validation splits should be trained and tested.
-
class
privpack.model_selection.experiment.Expectations¶ Bases:
object-
class
Expectation(metric: privpack.utils.metrics.Metric, value: float, relation: Callable[[float, float], bool] = <function Expectations.Expectation.<lambda>>)¶ Bases:
object
-
add_expectation(metric: privpack.utils.metrics.Metric, value: float, relation: Callable[[float, float], bool] = <function Expectations.<lambda>>)¶
-
class
-
class
privpack.model_selection.experiment.Experiment(network: privpack.core.architectures.GenerativeAdversarialNetwork, expectations: privpack.model_selection.experiment.Expectations)¶ Bases:
object-
run(data, n_splits, epochs, batch_size, verbose=False, **kwargs)¶
-