StagerNet

class selfeeg.models.zoo.StagerNet(nb_classes: int, Chans: int, Samples: int, dropRate: float = 0.5, kernLength: int = 64, F: int = 8, Pool: int = 16, return_logits: bool = True, seed: int = None)[source]

Pytorch implementation of the StagerNet model.

Original paper can be found here [stager] . The expected input is a 3D tensor with size (Batch x Channels x Samples).

Parameters:

  • nb_classes (int) – The number of classes. If less than 2, a binary classification problem is considered (output dimensions will be [batch, 1] in this case).

  • Chans (int) – The number of EEG channels.

  • Samples (int) – The sample length. It will be used to calculate the embedding size (for head initialization).

  • dropRate (float, optional) –

    The dropout percentage in range [0,1].

    Default = 0.5

  • kernLength (int, optional) –

    The length of the temporal convolutional layer.

    Default = 64

  • F (int, optional) –

    The number of output filters in the temporal convolution layer.

    Default = 8

  • pool (int, optional) –

    The temporal pooling kernel size.

    Default = 16

  • return_logits (bool, optional) –

    Whether to return the output as logit or probability. It is suggested to not use False as the pytorch crossentropy applies the softmax internally.

    Default = True

  • seed (int, optional) –

    A custom seed for model initialization. It must be a nonnegative number. If None is passed, no custom seed will be set

    Default = None

References

[stager]

Chambon et al., A deep learning architecture for temporal sleep stage classification using multivariate and multimodal time series, arXiv:1707.03321

Example

>>> import selfeeg.models
>>> import torch
>>> x = torch.randn(4,8,512)
>>> mdl = models.StagerNet(4,8,512)
>>> out = mdl(x)
>>> print(out.shape) # shoud return torch.Size([4, 4])
>>> print(torch.isnan(out).sum()) # shoud return 0