braindecode.augmentation.Transform¶
- class braindecode.augmentation.Transform(probability=1.0, random_state=None)¶
Basic transform class used for implementing data augmentation operations.
- Parameters
- operationcallable
A function taking arrays X, y (inputs and targets resp.) and other required arguments, and returning the transformed X and y.
- probabilityfloat, optional
Float between 0 and 1 defining the uniform probability of applying the operation. Set to 1.0 by default (e.g always apply the operation).
- random_state: int, optional
Seed to be used to instatiate numpy random number generator instance. Used to decide whether or not to transform given the probability argument. Defaults to None.
Methods
- forward(X: torch.Tensor, y: Optional[torch.Tensor] = None) Tuple[torch.Tensor, torch.Tensor]¶
General forward pass for an augmentation transform.
- Parameters
- Xtorch.Tensor
EEG input example or batch.
- ytorch.Tensor | None
EEG labels for the example or batch. Defaults to None.
- Returns
- torch.Tensor
Transformed inputs.
- torch.Tensor, optional
Transformed labels. Only returned when y is not None.
- get_params(*batch)¶
