EEGNet

class dpeeg.models.EEGNet.EEGNet(nCh: int, nTime: int, nCls: int, F1: int = 8, C1: int = 63, D: int = 2, F2: int = 16, C2: int = 15, P1: int = 8, P2: int = 16, dropout: float = 0.5)

EEGNet: A Compact Convolutional Neural Network for EEG-based Brain-Computer Interfaces (EEGNet).

EEGNet [1] is a compact convolutional neural network for EEG-based BCIs. EEGNet starts with a temporal convolution to learn frequency filters, then uses a depthwise convolution, connected to each feature map individually, to learn frequency-specific spatial filters. The separable convolution is a combination of a depthwise convolution, which learns a temporal summary for each feature map individually, followed by a pointwise convolution, which learns how to optimally mix the feature maps together.

Parameters:

• nCh (int) – Number of electrode channels.

• nTime (int) – Number of data sampling points. For example, a 4-second data input with a sampling rate of 250 Hz is 1000.

• nCls (int) – Number of classification categories.

• F1 (int) – Number of temporal filters.

• C1 (int) – Temporal convolution kernel size.

• D (int) – Depth of depthwise convolution.

• F2 (int) – Number of separable convolutions.

• C2 (int) – Separable convolution kernel size.

• P1 (int) – The first pooling kernel size.

• P2 (int) – The second pooling kernel size.

• dropout (float) – Dropout rate.

References

[1]

V. J. Lawhern, A. J. Solon, N. R. Waytowich, S. M. Gordon, C. P. Hung, and B. J. Lance, “EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces,” J. Neural Eng., vol. 15, no. 5, p. 056013, Jul. 2018, doi: 10.1088/1741-2552/aace8c.

forward(x)

Forward pass function that processes the input EEG data and produces the decoded results.

Parameters:

x (Tensor) – Input EEG data, shape (batch_size, 1, nCh, nTime).

Returns:

cls_prob – Predicted class probability, shape (batch_size, nCls).

Return type:

Tensor