braindecode.modules.GCT#

class braindecode.modules.GCT(in_channels: int)[source]#

Gated Channel Transformation from [Yang2020].

Parameters:

in_channels (int) – number of input feature channels

References

[Yang2020]

Yang, Z. Linchao, Z., Wu, Y., Yang, Y., 2020.

Gated Channel Transformation for Visual Recognition. CVPR 2020.

Methods

forward(x, eps: float = 1e-05)[source]#

Apply the Gated Channel Transformation block to the input tensor.

Parameters:

• x (Pytorch.Tensor)

• eps (float, default=1e-5)

Returns:

the original tensor x multiplied by the gate.

Return type:

Pytorch.Tensor