braindecode.augmentation.Mixup¶

class braindecode.augmentation.Mixup(alpha, beta_per_sample=False, random_state=None)¶

Implements Iterator for Mixup for EEG data. See [1]. Implementation based on [2].

Parameters

alpha: float: Mixup hyperparameter.
beta_per_sample: bool (default=False): By default, one mixing coefficient per batch is drawn from a beta distribution. If True, one mixing coefficient per sample is drawn.
random_state: int | numpy.random.Generator, optional: Seed to be used to instantiate numpy random number generator instance. Defaults to None.

References

1: Hongyi Zhang, Moustapha Cisse, Yann N. Dauphin, David Lopez-Paz (2018). mixup: Beyond Empirical Risk Minimization. In 2018 International Conference on Learning Representations (ICLR) Online: https://arxiv.org/abs/1710.09412
2: https://github.com/facebookresearch/mixup-cifar10/blob/master/train.py

Methods

get_params(*batch)¶

Return transform parameters.

Parameters

Returns

params: dict: Contains the values sampled uniformly between 0 and 1 setting the linear interpolation between examples (lam) and the shuffled indices of examples that are mixed into original examples (idx_perm).

static operation(X, y, lam, idx_perm)¶

Mixes two channels of EEG data.

See [1] for details. Implementation based on [2].

Parameters

Xtorch.Tensor: EEG data in form batch_size, n_channels, n_times
ytorch.Tensor: Target of length batch_size
lamtorch.Tensor: Values between 0 and 1 setting the linear interpolation between examples.
idx_perm: torch.Tensor: Permuted indices of example that are mixed into original examples.

Returns

tuple: X, y. Where X is augmented and y is a tuple of length 3 containing the labels of the two mixed channels and the mixing coefficient.

References

1: Hongyi Zhang, Moustapha Cisse, Yann N. Dauphin, David Lopez-Paz (2018). mixup: Beyond Empirical Risk Minimization. In 2018 International Conference on Learning Representations (ICLR) Online: https://arxiv.org/abs/1710.09412
2: https://github.com/facebookresearch/mixup-cifar10/blob/master/train.py