braindecode.models.TimeDistributed¶
- class braindecode.models.TimeDistributed(module)¶
Apply module on multiple windows.
Apply the provided module on a sequence of windows and return their concatenation. Useful with sequence-to-prediction models (e.g. sleep stager which must map a sequence of consecutive windows to the label of the middle window in the sequence).
- Parameters
- modulenn.Module
Module to be applied to the input windows. Must accept an input of shape (batch_size, n_channels, n_times).
Methods
- forward(x)¶
- Parameters
- xtorch.Tensor
Sequence of windows, of shape (batch_size, seq_len, n_channels, n_times).
- Returns
- torch.Tensor
Shape (batch_size, seq_len, output_size).
