EFDiscriminator

class torcheeg.models.EFDiscriminator(in_channels: int = 1, num_electrodes: int = 32, hid_channels_cnn: int = 1, chunk_size: int = 384)

EFDiscriminator: the discriminator that comes with EEGFuseNet is to distinguish whether the input EEG signals is a fake one generated by the eegfusenet or a real one collected from human brain.

• Paper: Z. Liang, R. Zhou, L. Zhang, L. Li, G. Huang, Z. Zhang, and S. Ishii, EEGFuseNet: Hybrid Unsupervised Deep Feature Characterization and Fusion for High-Dimensional EEG With an #Application to Emotion Recognition, IEEE Transactions on Neural Systems and Rehabilitation Engineering, 29, pp. 1913-1925, 2021.

• URL: https://github.com/KAZABANA/EEGfusenet

g_model=EEGfuseNet(num_electrodes=20,hid_channels_gru=16,num_layers_gru=1,hid_channels_cnn=1,chunk_size=128)
d_model = EFDiscriminator(num_electrodes=20,hid_channels_cnn=1,chunk_size=128)
X = torch.rand(128,1,20,128)
fake_X,deep_feature=g_model(X)
p_real,p_fake = d_model(X),d_model(fake_X)

Parameters:

• in_channels (int) – The number of channels of the signal corresponding to each electrode. If the original signal is used as input, in_channels is set to 1; if the original signal is split into multiple sub-bands, in_channels is set to the number of bands. (default: 1)

• num_electrodes (int) – The number of electrodes. (default: 32)

• hid_channels_cnn (int) – The number of filters in CNN based encoder. (default: 1)

• chunk_size (int) – Number of data points included in each EEG chunk. (default: 384)

forward(x)

Parameters:

x (torch.Tensor) – EEG signal representation or the fake generated EEGsignal, the size of the input EEG signal is( batch size × Channel × Time) whose ideal input shape is [n, 32, 384]. Here, n corresponds to the batch size, 32 corresponds to num_electrodes, and 384 corresponds to chunk_size.

Returns:

The possibilities that model judging the corresponding input signals is real.

Return type:

torch.Tensor[size of batch, 1]