yolov5 CABlock

Yolov5中的CABlock是指Coordinate Attention Block，它是一种用于增强YOLOv5的backbone的注意力机制。CABlock的代码实现如下：

class CABlock(nn.Module):
    def __init__(self, inp, oup, reduction=32):
        super(CABlock, self).__init__()
        mip = max(8, inp // reduction)
        self.conv1 = nn.Conv2d(inp, mip, 1, 1, bias=False)
        self.bn1 = nn.BatchNorm2d(mip)
        self.act = h_swish()
        self.conv_h = nn.Conv2d(mip, oup, 1, 1, bias=False)
        self.conv_w = nn.Conv2d(mip, oup, 1, 1, bias=False)
    
    def forward(self, x):
        identity = x
        _, _, h, w = x.size()
        pool_h = nn.AdaptiveAvgPool2d((h, 1))
        x_h = pool_h(x)
        pool_w = nn.AdaptiveAvgPool2d((1, w))
        x_w = pool_w(x).permute(0, 1, 3, 2)
        y = torch.cat([x_h, x_w], dim=2)
        y = self.conv1(y)
        y = self.bn1(y)
        y = self.act(y)
        y_h, y_w = torch.split(y, [h, w], dim=2)
        y_w = y_w.permute(0, 1, 3, 2)
        a_h = self.conv_h(y_h).sigmoid()
        a_w = self.conv_w(y_w).sigmoid()
        return identity * a_w * a_h

CABlock包含了两个注意力模块，分别是水平方向的注意力模块和垂直方向的注意力模块。在前向传播过程中，首先对输入的特征图进行平均池化操作，得到水平方向和垂直方向上的平均特征图。然后经过一系列卷积和激活操作，得到两个注意力图像a_h和a_w。最后将输入特征图与这两个注意力图像相乘，得到最终的输出特征图。这个过程可以增强输入特征图中的重要信息，并提升模型的性能。<span class="em">1</span><span class="em">2</span>
#### 引用[.reference_title]
- *1* *2* [【YOLOv5-6.x】解决加入CA注意力机制不显示FLOPs的问题](https://blog.csdn.net/weixin_43799388/article/details/124086801)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v93^chatsearchT3_1"}}] [.reference_item style="max-width: 100%"]
[ .reference_list ]