import torch import torch.nn as nn import torch.nn.init as init class channelAttention(nn.Module): def __init__(self, channel, reduction=16): super(channelAttention, self).__init__() self.Maxpooling = nn.AdaptiveMaxPool2d(1) self.Avepooling = nn.AdaptiveAvgPool2d(1) self.ca = nn.Sequential() self.ca.add_module('conv1',nn.Conv2d(channel, channel//reduction, 1, bias=False)) self.ca.add_module('Relu', nn.ReLU()) self.ca.add_module('conv2',nn.Conv2d(channel//reduction, channel, 1, bias=False)) self.sigmod = nn.Sigmoid() def forward(self, x): M_out = self.Maxpooling(x) A_out = self.Avepooling(x) M_out = self.ca(M_out) A_out = self.ca(A_out) out = self.sigmod(M_out+A_out) return out class SpatialAttention(nn.Module): def __init__(self, kernel_size=7): super().__init__() self.conv = nn.Conv2d(in_channels=2, out_channels=1, kernel_size=kernel_size, padding=kernel_size // 2) self.sigmoid = nn.Sigmoid() def forward(self, x): max_result, _ = torch.max(x, dim=1, keepdim=True) avg_result = torch.mean(x, dim=1, keepdim=True) result = torch.cat([max_result, avg_result], dim=1) output = self.conv(result) output = self.sigmoid(output) return output class CBAM(nn.Module): def __init__(self, channel, reduction=16, kernel_size=7): super().__init__() self.ca = channelAttention(channel, reduction) self.sa = SpatialAttention(kernel_size) def init_weights(self): for m in self.modules():#权重初始化 if isinstance(m, nn.Conv2d): init.kaiming_normal_(m.weight, mode='fan_out') if m.bias is not None: init.constant_(m.bias, 0) elif isinstance(m, nn.BatchNorm2d): init.constant_(m.weight, 1) init.constant_(m.bias, 0) elif isinstance(m, nn.Linear): init.normal_(m.weight, std=0.001) if m.bias is not None: init.constant_(m.bias, 0) def forward(self, x): # b,c_,_ = x.size() # residual = x out = x*self.ca(x) out = out*self.sa(out) return out if __name__ == '__main__': input=torch.randn(50,512,7,7) kernel_size=input.shape[2] cbam = CBAM(channel=512,reduction=16,kernel_size=kernel_size) output=cbam(input) print(output.shape)