fairseq/modules/dynamic_convolution.py [187:236]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            weight = self.weight_linear(query).view(T * B * H, -1)

        # renorm_padding is only implemented in _forward_expanded
        assert not self.renorm_padding or incremental_state is not None

        if incremental_state is not None:
            input_buffer = self._get_input_buffer(incremental_state)
            if input_buffer is None:
                input_buffer = x.new()
            x_unfold = torch.cat([input_buffer, x.unsqueeze(3)], dim=3)
            if self.kernel_size > 1:
                self._set_input_buffer(
                    incremental_state, x_unfold[:, :, :, -self.kernel_size + 1 :]
                )
            x_unfold = x_unfold.view(T * B * H, R, -1)
        else:
            padding_l = self.padding_l
            if K > T and padding_l == K - 1:
                weight = weight.narrow(1, K - T, T)
                K, padding_l = T, T - 1
            # unfold the input: T x B x C --> T' x B x C x K
            x_unfold = unfold1d(x, K, padding_l, 0)
            x_unfold = x_unfold.view(T * B * H, R, K)

        if self.weight_softmax and not self.renorm_padding:
            weight = F.softmax(weight, dim=1)
        weight = weight.narrow(1, 0, K)

        if incremental_state is not None:
            weight = weight[:, -x_unfold.size(2) :]
            K = weight.size(1)

        if self.weight_softmax and self.renorm_padding:
            weight = F.softmax(weight, dim=1)

        weight = self.weight_dropout_module(weight, inplace=False)

        output = torch.bmm(x_unfold, weight.unsqueeze(2))  # T*B*H x R x 1
        output = output.view(T, B, C)
        return output

    def _forward_expanded(self, x, incremental_stat, query):
        """Turn the convolution filters into band matrices and do matrix multiplication.
        This is faster when the sequence is short, but less memory efficient.
        This is not used in the decoder during inference.
        """
        T, B, C = x.size()
        K, H = self.kernel_size, self.num_heads
        R = C // H
        assert R * H == C == self.input_size
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



fairseq/modules/dynamicconv_layer/dynamicconv_layer.py [143:192]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        weight = self.weight_linear(query).view(T * B * H, -1)

        # renorm_padding is only implemented in _forward_expanded
        assert not self.renorm_padding or incremental_state is not None

        if incremental_state is not None:
            input_buffer = self._get_input_buffer(incremental_state)
            if input_buffer is None:
                input_buffer = x.new()
            x_unfold = torch.cat([input_buffer, x.unsqueeze(3)], dim=3)
            if self.kernel_size > 1:
                self._set_input_buffer(
                    incremental_state, x_unfold[:, :, :, -self.kernel_size + 1 :]
                )
            x_unfold = x_unfold.view(T * B * H, R, -1)
        else:
            padding_l = self.padding_l
            if K > T and padding_l == K - 1:
                weight = weight.narrow(1, K - T, T)
                K, padding_l = T, T - 1
            # unfold the input: T x B x C --> T' x B x C x K
            x_unfold = unfold1d(x, K, padding_l, 0)
            x_unfold = x_unfold.view(T * B * H, R, K)

        if self.weight_softmax and not self.renorm_padding:
            weight = F.softmax(weight, dim=1)
        weight = weight.narrow(1, 0, K)

        if incremental_state is not None:
            weight = weight[:, -x_unfold.size(2) :]
            K = weight.size(1)

        if self.weight_softmax and self.renorm_padding:
            weight = F.softmax(weight, dim=1)

        weight = self.weight_dropout_module(weight, inplace=False)

        output = torch.bmm(x_unfold, weight.unsqueeze(2))  # T*B*H x R x 1
        output = output.view(T, B, C)
        return output

    def _forward_expanded(self, x, incremental_stat, query):
        """Turn the convolution filters into band matrices and do matrix multiplication.
        This is faster when the sequence is short, but less memory efficient.
        This is not used in the decoder during inference.
        """
        T, B, C = x.size()
        K, H = self.kernel_size, self.num_heads
        R = C // H
        assert R * H == C == self.input_size
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -