使用深度可分离卷积替换代码中的卷积操作

下面是深度可分离卷积的实现代码：

def conv3x3_dw(in_planes, out_planes, stride=1):
    '''3x3 depthwise convolution with padding'''
    return nn.Conv2d(in_planes, in_planes, kernel_size=3,
                     stride=stride, padding=1, groups=in_planes, bias=False), \
           nn.Conv2d(in_planes, out_planes, kernel_size=1,
                     stride=1, padding=0, bias=False)

使用方法：

将代码中的conv3x3函数替换为conv3x3_dw函数。例如，在BasicBlock类中，将self.conv1和self.conv2替换为conv3x3_dw函数的返回值。

示例：

class BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(BasicBlock, self).__init__()
        self.conv1, self.conv1_pointwise = conv3x3_dw(inplanes, planes, stride)
        self.bn1 = BatchNorm2d(planes, momentum=BN_MOMENTUM)
        self.relu = nn.ReLU(inplace=True)
        self.conv2, self.conv2_pointwise = conv3x3_dw(planes, planes)
        self.bn2 = BatchNorm2d(planes, momentum=BN_MOMENTUM)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        residual = x

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)

        if self.downsample is not None:
            residual = self.downsample(x)

        out += residual
        out = self.relu(out)

        return out

注意：

深度可分离卷积可以显著减少参数数量和计算量，但可能会导致模型性能略微下降。建议在训练模型后，根据实际情况进行调整。