TinySleepNetEncoder

class selfeeg.models.encoders.TinySleepNetEncoder(Chans: int, Fs: int, F: int = 128, kernlength: int = 8, pool: int = 8, dropRate: float = 0.5, batch_momentum: float = 0.1, hidden_lstm: int = 128, seed: int = None)[source]

Pytorch Implementation of the TinySleepNet Encoder.

TinySleepNet is a minimal but better performing architecture derived from DeepSleepNet (proposed by the same authors). See TinySleepNet for some references. The expected input is a 3D tensor with size (Batch x Channels x Samples).

Parameters:

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

  • Fs (float) – The EEG sampling frequency in Hz.

  • F1 (int, optional) –

    The number of output filters in the representation learning part.

    Default = 128

  • kernlength (int, optional) –

    The length of the temporal convolutional layer.

    Default = 8

  • pool (int, optional) –

    The temporal pooling kernel size.

    Default = 8

  • dropRate (float, optional) –

    The dropout percentage in range [0,1].

    Default = 0.5

  • hidden_lstm (int, optional) –

    Hidden size of the lstm block.

    Default = 128

  • 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

Example

>>> import selfeeg.models
>>> import torch
>>> x = torch.randn(4,8,1024)
>>> mdl = models.TinySleepNetEncoder(8,32)
>>> out = mdl(x)
>>> print(out.shape) # shoud return torch.Size([4, 128])
>>> print(torch.isnan(out).sum()) # shoud return 0