cbam注意力机制代码
时间: 2023-06-28 13:06:49 浏览: 109
以下是使用PyTorch实现CBAM注意力机制的示例代码:
```python
import torch
import torch.nn as nn
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 // ratio, 1, bias=False)
self.relu1 = nn.ReLU()
self.fc2 = nn.Conv2d(in_planes // ratio, 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)
class CBAM(nn.Module):
def __init__(self, in_planes, ratio=16, kernel_size=7):
super(CBAM, self).__init__()
self.channel_att = ChannelAttention(in_planes, ratio)
self.spatial_att = SpatialAttention(kernel_size)
def forward(self, x):
x = x * self.channel_att(x)
x = x * self.spatial_att(x)
return x
```
这里实现了`ChannelAttention`和`SpatialAttention`两个模块,最后将它们结合起来形成CBAM注意力机制。其中`ChannelAttention`模块对输入的每个通道进行全局平均池化和全局最大池化,然后通过两个卷积层得到每个通道的注意力权重;`SpatialAttention`模块则对输入的每个空间位置进行通道维度上的最大池化和平均池化,然后将它们拼接在一起并通过卷积层得到每个空间位置的注意力权重。最后将两个注意力权重相乘,得到最终的注意力特征表示。