instantiators

instantiate_callbacks(callbacks_cfg: DictConfig) → List[Callback][source]

Instantiates callbacks from config.

Parameters:

callbacks_cfg – A DictConfig object containing callback configurations.

Returns:

A list of instantiated callbacks.

instantiate_datamodule(cfg: DictConfig, limit_scf_iterations: int | list[int] | None = -1) → OFDataModule[source]

Instantiates datamodule from config.

Instantiates a datamodule from the provided configuration. Adds additional keys and the transformation matrix.

Parameters:

  • cfg – A DictConfig object containing the train configuration.

  • limit_scf_iterations – Which SCF iterations to use (see mldft.ml.data.components.dataset.OFDataset). By default, only the ground state is loaded.

Returns:

An instantiated datamodule.

instantiate_loggers(logger_cfg: DictConfig) → List[Logger][source]

Instantiates loggers from config.

Parameters:

logger_cfg – A DictConfig object containing logger configurations.

Returns:

A list of instantiated loggers.

instantiate_model(checkpoint_path, device: str | device, model_dtype: dtype = torch.float64) → MLDFTLitModule[source]

Instantiate a model from a checkpoint.

Parameters:

  • checkpoint_path – The path to the checkpoint.

  • device – The device to load the model on.

  • model_dtype – The dtype of the model.

  • deterministic – Whether the model should be deterministic.

Returns:

The instantiated model.