resnet18+交叉注意力机制代码
时间: 2023-07-08 13:53:18 浏览: 48
以下是ResNet18网络结构加上交叉注意力机制的代码实现:
```python
import torch
import torch.nn as nn
class BasicBlock(nn.Module):
expansion = 1
def __init__(self, in_planes, planes, stride=1):
super(BasicBlock, self).__init__()
self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, padding=1, bias=False)
self.bn2 = nn.BatchNorm2d(planes)
self.ca = nn.Sequential(
nn.AdaptiveAvgPool2d(1),
nn.Conv2d(planes, planes // 8, 1, bias=False),
nn.ReLU(inplace=True),
nn.Conv2d(planes // 8, planes, 1, bias=False),
nn.Sigmoid()
)
self.sa = nn.Sequential(
nn.Conv2d(planes, planes // 8, kernel_size=1, stride=1, padding=0, bias=False),
nn.ReLU(inplace=True),
nn.Conv2d(planes // 8, planes // 8, kernel_size=3, stride=stride, padding=1, bias=False),
nn.ReLU(inplace=True),
nn.Conv2d(planes // 8, planes, kernel_size=1, stride=1, padding=0, bias=False),
nn.Sigmoid()
)
self.shortcut = nn.Sequential()
if stride != 1 or in_planes != self.expansion * planes:
self.shortcut = nn.Sequential(
nn.Conv2d(in_planes, self.expansion * planes, kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(self.expansion * planes)
)
def forward(self, x):
out = self.conv1(x)
out = self.bn1(out)
out = nn.ReLU(inplace=True)(out)
out = self.conv2(out)
out = self.bn2(out)
ca = self.ca(out)
sa = self.sa(out)
out = out * ca + out * sa
out += self.shortcut(x)
out = nn.ReLU(inplace=True)(out)
return out
class ResNet(nn.Module):
def __init__(self, block, num_blocks, num_classes=10):
super(ResNet, self).__init__()
self.in_planes = 64
self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.layer1 = self._make_layer(block, 64, num_blocks[0], stride=1)
self.layer2 = self._make_layer(block, 128, num_blocks[1], stride=2)
self.layer3 = self._make_layer(block, 256, num_blocks[2], stride=2)
self.layer4 = self._make_layer(block, 512, num_blocks[3], stride=2)
self.linear = nn.Linear(512 * block.expansion, num_classes)
def _make_layer(self, block, planes, num_blocks, stride):
strides = [stride] + [1] * (num_blocks - 1)
layers = []
for stride in strides:
layers.append(block(self.in_planes, planes, stride))
self.in_planes = planes * block.expansion
return nn.Sequential(*layers)
def forward(self, x):
out = self.conv1(x)
out = self.bn1(out)
out = nn.ReLU(inplace=True)(out)
out = self.layer1(out)
out = self.layer2(out)
out = self.layer3(out)
out = self.layer4(out)
out = nn.AdaptiveAvgPool2d(1)(out)
out = out.view(out.size(0), -1)
out = self.linear(out)
return out
def ResNet18(num_classes=10):
return ResNet(BasicBlock, [2, 2, 2, 2], num_classes=num_classes)
```
其中,交叉注意力模块的实现在`BasicBlock`中的`forward`函数中。`ca`表示通道注意力模块,`sa`表示空间注意力模块。`out = out * ca + out * sa`表示将通道注意力和空间注意力结合起来。
相关推荐
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)