### Python 实现空间注意力机制与通道注意力机制结合的代码示例 以下是基于 CBAM (Convolutional Block Attention Module)[^1] 的 Python 代码实现，该模块同时包含了空间注意力机制和通道注意力机制： ```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_attention = ChannelAttention(in_planes, ratio) self.spatial_attention = SpatialAttention(kernel_size) def forward(self, x): out = x * self.channel_attention(x) # Apply channel attention out = out * self.spatial_attention(out) # Apply spatial attention return out # Example usage of the CBAM module if __name__ == "__main__": input_tensor = torch.randn((8, 64, 32, 32)) # Batch size: 8, Channels: 64, Height: 32, Width: 32 cbam_module = CBAM(in_planes=64) output_tensor = cbam_module(input_tensor) print(output_tensor.shape) # Output shape should match the input tensor's shape ``` #### 说明 上述代码实现了 CBAM 模块的功能[^1]。CBAM 首先通过 `ChannelAttention` 提取通道维度上的重要性权重[^2]，随后利用 `SpatialAttention` 获取空间维度上的关注区域[^3]。最终，这两个部分的结果被逐元素相乘并返回。 --- ###