resnet 优化之cbam

1. cbam

https://blog.csdn.net/qq_44666320/article/details/105694019

https://blog.csdn.net/qq_38410428/article/details/103694759

2. se net

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)

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)

在ResNet网络中添加注意力机制
注意点：因为不能改变ResNet的网络结构，所以CBAM不能加在block里面（也可以加在block里面，此时网络不能加载预训练参数），因为加在block里面网络结构发生了变化，所以不能用预训练参数。

              加在最后一层卷积和第一层卷积不改变网络，可以用预训练参数。

就是你如果希望使用预训练模型。那么就加在第一层卷积和 最后一层卷积后面 

如果你从头训：随便你加在哪里