SequenceWise Operation

[igor17400]

Hi there,

Could please someone provide an explanation for the necessity of the SequenceWise operation?

Additionally, if possible, could explain how this operation is similar to TimeDistributed layer from Keras, as discussed in this thread?

class SequenceWise(nn.Module):
    def __init__(self, module):
        """
        Collapses input of dim T*N*H to (T*N)*H, and applies to a module.
        Allows handling of variable sequence lengths and minibatch sizes.
        :param module: Module to apply input to.
        """
        super(SequenceWise, self).__init__()
        self.module = module

    def forward(self, x):
        t, n = x.size(0), x.size(1)
        x = x.view(t * n, -1)
        x = self.module(x)
        x = x.view(t, n, -1)
        return x

    def __repr__(self):
        tmpstr = self.__class__.__name__ + ' (\n'
        tmpstr += self.module.__repr__()
        tmpstr += ')'
        return tmpstr

[stale]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.