TabularRegressionDataModule#

class torch_uncertainty.datamodules.TabularRegressionDataModule(root, batch_size, eval_batch_size=None, val_split=0.0, test_split=0.2, num_workers=1, pin_memory=True, persistent_workers=True)[source]#

UCI regression datamodule.

Parameters:

  • root (str | Path) – Root directory of the datasets.

  • batch_size (int) – Number of samples per batch during training.

  • eval_batch_size (int | None) – Number of samples per batch during evaluation. Defaults to batch_size.

  • val_split (float) – Share of training samples used for validation. Defaults to 0.

  • test_split (float) – Share of the full dataset held out as test set. Defaults to 0.2.

  • num_workers (int) – Number of data-loading subprocesses. Defaults to 1.

  • pin_memory (bool) – Whether to pin memory. Defaults to True.

  • persistent_workers (bool) – Whether to keep workers alive between epochs. Defaults to True.

prepare_data()[source]#

Download the dataset if not already present.

Return type:

None

setup(stage=None)[source]#

Create train, val, and test splits.

Parameters:

stage (str | None) – "fit", "test", or None (both). Defaults to None.

Return type:

None