BEncoder

class torcheeg.models.BEncoder(in_channels: int = 4, grid_size: Tuple[int, int] = (9, 9), hid_channels: int = 64)

The variational autoencoder consists of two parts, an encoder, and a decoder. The encoder compresses the input into the latent space. The decoder receives as input the information sampled from the latent space and produces it as similar as possible to ground truth. The latent vector should approach the gaussian distribution supervised by KL divergence based on the variation trick. This class implement the encoder part.

import torch

from torcheeg.models import BEncoder

encoder = BEncoder(in_channels=4)
mock_eeg = torch.randn(1, 4, 9, 9)
mu, logvar = encoder(mock_eeg)

Parameters:

• in_channels (int) – The feature dimension of each electrode. (default: 4)

• grid_size (tuple) – Spatial dimensions of grid-like EEG representation. (default: (9, 9))

• hid_channels (int) – The number of hidden nodes in the first convolutional layer, which is also used as the dimension of output mu and var. (default: 32)

forward(x: Tensor)

Parameters:

x (torch.Tensor) – EEG signal representation, the ideal input shape is [n, 4, 9, 9]. Here, n corresponds to the batch size, 4 corresponds to in_channels, and (9, 9) corresponds to grid_size.

Returns:

The mean and standard deviation vectors obtained by encoder. The shapes of the feature vectors are all [n, 64]. Here, n corresponds to the batch size, and 64 corresponds to hid_channels.

Return type:

tuple[2,]