braindecode.augmentation.functional.amplitude_scale#
- braindecode.augmentation.functional.amplitude_scale(X, y, scale, random_state=None)[source]#
Rescale amplitude of each channel based on a random sampled scaling value.
Part of the augmentations proposed in [1]
- Parameters:
X (
Tensor) – EEG input example or batch.y (
Tensor) – EEG labels for the example or batch.scale (
tuple) – Interval(low, high)from which the per (sample, channel) scaling value is uniformly sampled.random_state (
int|RandomState|None) – Seed used to instantiate the numpy random number generator that draws the scaling values. Defaults to None.
- Return type:
- Returns:
torch.Tensor – Transformed inputs.
torch.Tensor – Transformed labels.
References
[1]Mohsenvand, M.N., Izadi, M.R. & Maes, P.. (2020). Contrastive Representation Learning for Electroencephalogram Classification. Proceedings of the Machine Learning for Health NeurIPS Workshop, in Proceedings of Machine Learning Research 136:238-253