ODConv详解

ODConv的代码https://github.com/OSVAI/ODConv/blob/main/modules/odconv.py

ODConv引入了一种多维注意机制，该机制采用并行策略，可以沿核空间的所有四个维度学习卷积核的不同注意。

当kernel_size（图中k）等于1并且kernel_num（图中k_num）等于1时,ODConv架构图

ODConv的代码，得先看懂Attention这个类

class ODConv2d(nn.Module):
    def __init__(self, in_planes, out_planes, kernel_size, stride=1, padding=0, dilation=1, groups=1,
                 reduction=0.0625, kernel_num=4):
        super(ODConv2d, self).__init__()
        self.in_planes = in_planes
        self.out_planes = out_planes
        self.kernel_size = kernel_size
        self.stride = stride
        self.padding = padding
        self.dilation = dilation
        self.groups = groups
        self.kernel_num = kernel_num
        self.attention = Attention(in_planes, out_planes, kernel_size, groups=groups,
                                   reduction=reduction, kernel_num=kernel_num)
        self.weight = nn.Parameter(torch.randn(kernel_num, out_planes, in_planes//groups, kernel_size, kernel_size),
                                   requires_grad=True)
        self._initialize_weights()
 
        if self.kernel_size == 1 and self.kernel_num == 1:
            self._forward_impl = self._forward_impl_pw1x
        else:
            self._forward_impl = self._forward_impl_common
 
    def _initialize_weights(self):
        for i in range(self.kernel_num):
            nn.init.kaiming_normal_(self.weight[i], mode='fan_out', nonlinearity='relu')
 
    def update_temperature(self, temperature):
        self.attention.update_temperature(temperature)
 
    def _forward_impl_common(self, x):
        # Multiplying channel attention (or filter attention) to weights and feature maps are equivalent,
        # while we observe that when using the latter method the models will run faster with less gpu memory cost.
        channel_attention, filter_attention, spatial_attention, kernel_attention = self.attention(x)
        batch_size, in_planes, height, width = x.size()
        x = x * channel_attention
        x = x.reshape(1, -1, height, width)
        aggregate_weight = spatial_attention * kernel_attention * self.weight.unsqueeze(dim=0)
        aggregate_weight = torch.sum(aggregate_weight, dim=1).view(
            [-1, self.in_planes // self.groups, self.kernel_size, self.kernel_size])
        output = F.conv2d(x, weight=aggregate_weight, bias=None, stride=self.stride, padding=self.padding,
                          dilation=self.dilation, groups=self.groups * batch_size)
        output = output.view(batch_size, self.out_planes, output.size(-2), output.size(-1))
        output = output * filter_attention
        return output
 
    def _forward_impl_pw1x(self, x):
        channel_attention, filter_attention, spatial_attention, kernel_attention = self.attention(x)
        x = x * channel_attention
        output = F.conv2d(x, weight=self.weight.squeeze(dim=0), bias=None, stride=self.stride, padding=self.padding,
                          dilation=self.dilation, groups=self.groups)
        output = output * filter_attention
        return output
 
    def forward(self, x):
        return self._forward_impl(x)

 结合Attention这个类的代码看更清楚，图中橙色的Conv2d的bias=True

class Attention(nn.Module):
    def __init__(self, in_planes, out_planes, kernel_size, groups=1, reduction=0.0625, kernel_num=4, min_channel=16):
        super(Attention, self).__init__()
        attention_channel = max(int(in_planes * reduction), min_channel)
        self.kernel_size = kernel_size
        self.kernel_num = kernel_num
        self.temperature = 1.0
 
        self.avgpool = nn.AdaptiveAvgPool2d(1)
        self.fc = nn.Conv2d(in_planes, attention_channel, 1, bias=False)
        self.bn = nn.BatchNorm2d(attention_channel)
        self.relu = nn.ReLU(inplace=True)
 
        self.channel_fc = nn.Conv2d(attention_channel, in_planes, 1, bias=True)
        self.func_channel = self.get_channel_attention
 
        if in_planes == groups and in_planes == out_planes:  # depth-wise convolution
            self.func_filter = self.skip
        else:
            self.filter_fc = nn.Conv2d(attention_channel, out_planes, 1, bias=True)
            self.func_filter = self.get_filter_attention
 
        if kernel_size == 1:  # point-wise convolution
            self.func_spatial = self.skip
        else:
            self.spatial_fc = nn.Conv2d(attention_channel, kernel_size * kernel_size, 1, bias=True)
            self.func_spatial = self.get_spatial_attention
 
        if kernel_num == 1:
            self.func_kernel = self.skip
        else:
            self.kernel_fc = nn.Conv2d(attention_channel, kernel_num, 1, bias=True)
            self.func_kernel = self.get_kernel_attention
 
        self._initialize_weights()
 
    def _initialize_weights(self):
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
                if m.bias is not None:
                    nn.init.constant_(m.bias, 0)
            if isinstance(m, nn.BatchNorm2d):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)
 
    def update_temperature(self, temperature):
        self.temperature = temperature
 
    @staticmethod
    def skip(_):
        return 1.0
 
    def get_channel_attention(self, x):
        channel_attention = torch.sigmoid(self.channel_fc(x).view(x.size(0), -1, 1, 1) / self.temperature)
        return channel_attention
 
    def get_filter_attention(self, x):
        filter_attention = torch.sigmoid(self.filter_fc(x).view(x.size(0), -1, 1, 1) / self.temperature)
        return filter_attention
 
    def get_spatial_attention(self, x):
        spatial_attention = self.spatial_fc(x).view(x.size(0), 1, 1, 1, self.kernel_size, self.kernel_size)
        spatial_attention = torch.sigmoid(spatial_attention / self.temperature)
        return spatial_attention
 
    def get_kernel_attention(self, x):
        kernel_attention = self.kernel_fc(x).view(x.size(0), -1, 1, 1, 1, 1)
        kernel_attention = F.softmax(kernel_attention / self.temperature, dim=1)
        return kernel_attention
 
    def forward(self, x):
        x = self.avgpool(x)
        x = self.fc(x)
        x = self.bn(x)
        x = self.relu(x)
        return self.func_channel(x), self.func_filter(x), self.func_spatial(x), self.func_kernel(x)

当in_planes == groups 并且 in_planes == out_planes时（即depth-wise convolution），filter_attention不起作用（即等于1）；当kernel_size=1时，spatial_attention不起作用（即等于1）；当kernel_num=1时，kernel_attention不起作用（即等于1）。