braindecode.modules.SqueezeAndExcitation#

class braindecode.modules.SqueezeAndExcitation(in_channels, reduction_rate, bias=False)[source]#

Squeeze-and-Excitation Networks from [Hu2018].

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 SqueezeAndExcitation
>>> module = SqueezeAndExcitation(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

[Hu2018]

Hu, J., Albanie, S., Sun, G., Wu, E., 2018. Squeeze-and-Excitation Networks. CVPR 2018.

Methods

forward(x)[source]#

Apply the Squeeze-and-Excitation block to the input tensor.

Parameters:

x (Pytorch.Tensor)

Returns:

scale*x

Return type:

Pytorch.Tensor