在mmdetection第二代中如何在FCOS中使用CBAM

在mmdetection第二代中，可以通过修改FCOS的backbone网络来使用CBAM。具体步骤如下：

1. 在mmdet/models/backbones/resnet.py中导入CBAM模块：

   from ..plugins.cbam import CBAM

2. 在ResNet的构造函数中，实例化CBAM模块，并将其添加到每个ResNet block中。例如，在ResNet50中，可以添加以下代码：

   self.cbam = CBAM(channels=256)

   for i, block in enumerate(self.layers):
       if i == 0:
           block.cbam = None
       else:
           block.cbam = copy.deepcopy(self.cbam)

3. 在FCOS的构造函数中，将修改后的ResNet作为backbone网络：

   self.backbone = ResNet(
       depth=self.backbone_depth,
       num_stages=4,
       strides=(1, 2, 2, 2),
       dilations=(1, 1, 1, 1),
       out_indices=(0, 1, 2, 3),
       frozen_stages=self.frozen_stages,
       norm_cfg=self.norm_cfg,
       norm_eval=self.train_cfg.get('norm_eval', True),
       style='pytorch',
       with_cbam=True  # 添加这行代码
   )

4. 在mmdet/models/plugins/cbam.py中实现CBAM模块：

   import torch.nn as nn
   import torch.nn.functional as F
   
   
   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, channels, reduction=16):
           super(CBAM, self).__init__()
           self.ca = ChannelAttention(channels, reduction)
           self.sa = SpatialAttention()
   
       def forward(self, x):
           out = x * self.ca(x)
           out = out * self.sa(out)
           return out

通过以上步骤，就可以在FCOS中使用CBAM了。需要注意的是，以上代码仅适用于具有ResNet backbone的FCOS模型。如果使用其他的backbone网络，需要进行相应的修改。