#主要原理
提出CBAM的作者主要对分类网络和目标检测网络进行了实验,证明了CBAM模块确实是有效的。
以ResNet为例,论文中提供了改造的示意图,如下图所示:
#CMAB模块实现,依据上面原理
#在ResNet中的每个block中添加了CBAM模块,训练数据来自benchmark ImageNet-1K。检测使用的是Faster R-CNN, Backbone选择的ResNet34,ResNet50, WideResNet18, ResNeXt50等,还跟SE等进行了对比。
#CBAM 结构代码
#通道注意力模块
class ChannelAttention(nn.Module):
def __init__(self, in_planes, ratio=16):
super(ChannelAttention, self).__init__()
self.avg_pool = nn.AdaptiveAvgPool2d(1)
self.max_pool = nn.AdaptiveMaxPool2d(1)
self.fc1 = nn.Conv2d(in_planes, in_planes // 16, 1, bias=False)
self.relu1 = nn.ReLU()
self.fc2 = nn.Conv2d(in_planes // 16, in_planes, 1, bias=False)
self.sigmoid = nn.Sigmoid()
def forward(self, x):
avg_out = self.fc2(self.relu1(self.fc1(self.avg_pool(x))))
max_out = self.fc2(self.relu1(self.fc1(self.max_pool(x))))
out = avg_out + max_out
return self.sigmoid(out)
#空间注意力模块
class SpatialAttention(nn.Module):
def __init__(self, kernel_size=7):
super(SpatialAttention, self).__init__()
assert kernel_size in (3, 7), 'kernel size must be 3 or 7'
padding = 3 if kernel_size == 7 else 1
self.conv1 = nn.Conv2d(2, 1, kernel_size, padding=padding, bias=False)
self.sigmoid = nn.Sigmoid()
def forward(self, x):
avg_out = torch.mean(x, dim=1, keepdim=True)
max_out, _ = torch.max(x, dim=1, keepdim=True)
x = torch.cat([avg_out, max_out], dim=1)
x = self.conv1(x)
return self.sigmoid(x)
#调用方法:其他模块中调用,注意oup是模块输入通道数,严格和你输入到 ChannelAttention模块中的前一个模块或者操作的输出通道数一致,SpatialAttention 没有限制
self.ca = ChannelAttention(oup)
self.sa = SpatialAttention()
#具体实现 ,x表示数据,来自当前层或者某一层数据
x = self.ca(x) * x
x = self.sa(x) * x