braindecode.modules.GSoP

class braindecode.modules.GSoP(in_channels, reduction_rate, bias=True)

Global Second-order Pooling Convolutional Networks from [Gao2018].

Parameters:

• in_channels (int,) – number of input feature channels

• reduction_rate (int,) – reduction ratio of the fully-connected layers

• bias (bool, default=False) – if True, adds a learnable bias will be used in the convolution.

References

[Gao2018]

Gao, Z., Jiangtao, X., Wang, Q., Li, P., 2018.

Global Second-order Pooling Convolutional Networks. CVPR 2018.

Methods

forward(x)

Apply the Global Second-order Pooling Convolutional Networks block.

Parameters:

x (Pytorch.Tensor)

Return type:

Pytorch.Tensor