DataModule.convert_to_dataloader

DataModule.convert_to_dataloader(x: ndarray | torch.Tensor | None = None, y: ndarray | torch.Tensor | None = None, z: ndarray | torch.Tensor | None = None, requires_fitted: bool = True, **kwargs) → torch.utils.data.DataLoader[source]

Converts input and output data to a dataloader.

Parameters:

  • x (Union[np.ndarray, torch.Tensor]) – The input data.

  • y (Union[np.ndarray, torch.Tensor]) – The output data.

  • z (Union[np.ndarray, torch.Tensor]) – The latent representation data. The default is None. This is used if one wants to generate data with the decoder.

  • requires_fitted (bool) – Whether the transformations must be fitted. The default is True.

  • **kwargs – Additional keyword arguments to be passed to the dataloader.

Returns:

DataLoader – The dataloader containing the input and output data.