braindecode.modules.GSoP#

class braindecode.modules.GSoP(in_channels, reduction_rate, bias=True)[source]#

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.

Examples

>>> import torch
>>> from braindecode.modules import GSoP
>>> module = GSoP(in_channels=16, reduction_rate=4)
>>> inputs = torch.randn(2, 16, 1, 64)
>>> outputs = module(inputs)
>>> outputs.shape
torch.Size([2, 16, 1, 64])

References

[Gao2018]

Gao, Z., Jiangtao, X., Wang, Q., Li, P., 2018. Global Second-order Pooling Convolutional Networks. CVPR 2018.

Methods

forward(x)[source]#

Apply the Global Second-order Pooling Convolutional Networks block.

Parameters:: x (Pytorch.Tensor)
Return type:: Pytorch.Tensor