braindecode.augmentation.functional.mixup¶
- braindecode.augmentation.functional.mixup(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. WhereXis augmented andyis 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