Class ConvInUpsampleNetwork

modules/parallel_wavegan/layers/upsample.py:125–183

Convolution + upsampling network module.

class ConvInUpsampleNetwork(torch.nn.Module):
    """Convolution + upsampling network module."""

    def __init__(self,
                 upsample_scales,
                 nonlinear_activation=None,
                 nonlinear_activation_params={},
                 interpolate_mode="nearest",
                 freq_axis_kernel_size=1,
                 aux_channels=80,
                 aux_context_window=0,
                 use_causal_conv=False
                 ):
        """Initialize convolution + upsampling network module.

        Args:
            upsample_scales (list): List of upsampling scales.
            nonlinear_activation (str): Activation function name.
            nonlinear_activation_params (dict): Arguments for specified activation function.
            mode (str): Interpolation mode.
            freq_axis_kernel_size (int): Kernel size in the direction of frequency axis.
            aux_channels (int): Number of channels of pre-convolutional layer.
            aux_context_window (int): Context window size of the pre-convolutional layer.
            use_causal_conv (bool): Whether to use causal structure.

        """
        super(ConvInUpsampleNetwork, self).__init__()
        self.aux_context_window = aux_context_window
        self.use_causal_conv = use_causal_conv and aux_context_window > 0
        # To capture wide-context information in conditional features
        kernel_size = aux_context_window + 1 if use_causal_conv else 2 * aux_context_window + 1
        # NOTE(kan-bayashi): Here do not use padding because the input is already padded
        self.conv_in = Conv1d(aux_channels, aux_channels, kernel_size=kernel_size, bias=False)
        self.upsample = UpsampleNetwork(
            upsample_scales=upsample_scales,
            nonlinear_activation=nonlinear_activation,
            nonlinear_activation_params=nonlinear_activation_params,
            interpolate_mode=interpolate_mode,
            freq_axis_kernel_size=freq_axis_kernel_size,
            use_causal_conv=use_causal_conv,
        )

    def forward(self, c):
        """Calculate forward propagation.

        Args:
            c : Input tensor (B, C, T').

        Returns:
            Tensor: Upsampled tensor (B, C, T),
                where T = (T' - aux_context_window * 2) * prod(upsample_scales).

        Note:
            The length of inputs considers the context window size.

        """
        c_ = self.conv_in(c)
        c = c_[:, :, :-self.aux_context_window] if self.use_causal_conv else c_