braindecode.modules.GatherExcite#

class braindecode.modules.GatherExcite(in_channels, seq_len=62, extra_params=False, use_mlp=False, reduction_rate=4)[source]#

Gather-Excite Networks from [Hu2018b].

Parameters:

  • in_channels (int) – number of input feature channels

  • seq_len (int) – sequence length along temporal dimension

  • extra_params (bool) – whether to use a convolutional layer as a gather module

  • use_mlp (bool) – whether to use an excite block with fully-connected layers

  • reduction_rate (int) – reduction ratio of the excite block (if used)

Examples

>>> import torch
>>> from braindecode.modules import GatherExcite
>>> module = GatherExcite(in_channels=16, seq_len=64, extra_params=False, use_mlp=True)
>>> inputs = torch.randn(2, 16, 1, 64)
>>> outputs = module(inputs)
>>> outputs.shape
torch.Size([2, 16, 1, 64])

References

[Hu2018b]

Hu, J., Albanie, S., Sun, G., Vedaldi, A., 2018. Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks. NeurIPS 2018.

Methods

forward(x)[source]#

Apply the Gather-Excite Networks block to the input tensor.

Parameters:

x (Pytorch.Tensor)

Return type:

Pytorch.Tensor