DeepConvNetEncoder

class selfeeg.models.encoders.DeepConvNetEncoder(Chans: int, kernLength: int = 10, F: int = 25, Pool: int = 3, stride: int = 3, max_norm: float = None, batch_momentum: float = 0.1, ELUalpha: int = 1, dropRate: float = 0.5, seed: int = None)[source]

Pytorch Implementation of the DeepConvNet Encoder.

See DeepConvNet 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.

  • kernlength (int, optional) –

    The length of the temporal convolutional layer.

    Default = 10

  • F (int, optional) –

    The number of filters in the first layer. Next layers will continue to double the previous output feature size.

    Default = 25

  • Pool (int, optional) –

    The temporal pooling kernel size.

    Default = 3

  • stride (int, optional) –

    The stride to apply to the convolutional layers.

    Default = 3

  • max_norm (int, optional) –

    A max norm constraint to apply to each filter of the convolutional layer. See ConstrainedConv2d for more info.

    Default = None

  • batch_momentum (float, optional) –

    The batch normalization momentum.

    Default = 0.1

  • ELUalpha (float, optional) –

    The alpha value of the ELU activation function.

    Default = 1

  • dropRate (float, optional) –

    The dropout percentage in range [0,1].

    Default = 0.5

  • 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(4,8,512)
>>> mdl = models.DeepConvNetEncoder(8)
>>> out = mdl(x)
>>> print(out.shape) # shoud return torch.Size([4, 200])
>>> print(torch.isnan(out).sum()) # shoud return 0