resnet50代码_【代码复现】CBAM:Convolutional Block Attention Module

本次复现是将CBAM模块，放到ResNet50 Faster R-CNN里面，Faster R-CNN的源代码来自：

jwyang/faster-rcnn.pytorch​github.com

因为这个注意力模块可以即插即用，不需要修改原来的网络结构，所以只需要稍微小改一下，在lib/model/faster_rcnn/resnet.py中修改：

首先我们先把两个注意力模块写出来：

Channel Attention module:

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)

Spatial Attention module:

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, kern