"""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)
