functional

get_tbigru(source_fd, target_fd, **trainer_kwargs)

Construct a TBiGRU approach for FEMTO with the original hyperparameters.

Examples:

>>> import rul_adapt
>>> dm, tbigru, trainer = rul_adapt.construct.get_tbigru(3, 1)
>>> trainer.fit(tbigru, dm)
>>> trainer.test(tbigru, dm)

Parameters:

Name	Type	Description	Default
source_fd	int	The source FD of FEMTO.	required
target_fd	int	The target FD of FEMTO.	required
trainer_kwargs	Any	Overrides for the trainer class.	{}

Returns: dm: The data module for adaption of two FEMTO sub-datasets. dann: The TBiGRU approach with feature extractor and regressor. trainer: The trainer object.

get_tbigru_config(source_fd, target_fd)

Get a configuration for the TBiGRU approach.

The configuration can be modified and fed to tbigru_from_config to create the approach.

Parameters:

Name	Type	Description	Default
source_fd	int	The source FD of FEMTO.	required
target_fd	int	The target FD of FEMTO.	required

Returns: The TBiGRU configuration.

tbigru_from_config(config, **trainer_kwargs)

Construct a TBiGRU approach from a configuration. The configuration can be created by calling get_tbigru_config.

Parameters:

Name	Type	Description	Default
config	DictConfig	The TBiGRU configuration.	required
trainer_kwargs	Any	Overrides for the trainer class.	{}

Returns: dm: The data module for adaption of two FEMTO sub-datasets. dann: The TBiGRU approach with feature extractor and regressor. trainer: The trainer object.