braindecode.modules.SEANetConv1d

class braindecode.modules.SEANetConv1d(in_channels, out_channels, kernel_size, stride=1, dilation=1, causal=False)

Weight-normed Conv1d with EnCodec’s reflect padding.

The output keeps ceil(n_times / stride) samples: the padding is split around the signal (causal=False) or put on the left (causal=True).

Methods

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

Return type:

Tensor