关于对Comformer中卷积层的理解

"""ConvolutionModule definition."""
from torch import nn
class ConvolutionModule(nn.Module):
    """ConvolutionModule in Conformer model.

    Args:
        channels (int): The number of channels of conv layers.
        kernel_size (int): Kernerl size of conv layers.

    """
    def __init__(self, channels, kernel_size, activation=nn.ReLU(), bias=True):
        """Construct an ConvolutionModule object."""
        super(ConvolutionModule, self).__init__()
        # kernerl_size should be a odd number for 'SAME' padding
        assert (kernel_size - 1) % 2 == 0

        self.pointwise_conv1 = nn.Conv1d(   
            channels,
            2 * channels,  #输出通道为输入的两倍，扩张维度
            kernel_size=1, #卷积核为1，也就是对每一列独立做卷积，token内的交互
            stride=1,
            padding=0,
            bias=bias,
        )
        self.depthwise_conv = nn.Conv1d(
            channels,
            channels,
            kernel_size, #卷积核这里设置的31
            stride=1,
            padding=(kernel_size - 1) // 2, #填充是15，随着卷积核的变化而变化，目的是使得输出形状和输入形状相同
            groups=channels,  #分了channels组，表示只对每个卷积核范围内的token建立交互，而不对dim维度进行卷积
            bias=bias,
        )
        self.norm = nn.BatchNorm1d(channels)
        self.pointwise_conv2 = nn.Conv1d(
            channels,
            channels,
            kernel_size=1,
            stride=1,
            padding=0,
            bias=bias,
        )
        self.activation = activation

    def forward(self, x):
        """Compute convolution module.

        Args:
            x (torch.Tensor): Input tensor (#batch, time, channels).

        Returns:
            torch.Tensor: Output tensor (#batch, time, channels).

        """
        # exchange the temporal dimension and the feature dimension
        x = x.transpose(1, 2)  #为了后面卷积操作，需要先转置

        # GLU mechanism
        x = self.pointwise_conv1(x)  # (batch, 2*channel, dim)
        x = nn.functional.glu(x, dim=1)  # (batch, channel, dim)

        # 1D Depthwise Conv   相当于深度可分离卷积的形式，可以降低参数量，并分别对通道维度和time维度卷积
        x = self.depthwise_conv(x)
        x = self.activation(self.norm(x))

        x = self.pointwise_conv2(x)

        return x.transpose(1, 2)