pytorch代码实现注意力机制之BAM_Attention

BAM注意力机制

瓶颈注意模块(BAM)：关注深度神经网络中注意力机制的影响，提出了一个简单而有效的注意力模块，即瓶颈注意模块(BAM)，可以与任何前馈卷积神经网络集成，沿着两个不同的路径（通道和空间）推断注意力映射。 将模块放在模型的每个瓶颈处（特征映射产生降采样），构建一个具有多个参数的分层注意，可以与任何前馈模型以端到端方式进行训练。

论文地址：https://arxiv.org/pdf/1807.06514.pdf

代码如下：

import numpy as np
import torch
from torch import nn
from torch.nn import init


class Flatten(nn.Module):
    def forward(self, x):
        return x.view(x.shape[0], -1)


class ChannelAttention(nn.Module):
    def __init__(self, channel, reduction=16, num_layers=3):
        super().__init__()
        self.avgpool = nn.AdaptiveAvgPool2d(1)
        gate_channels = [channel]
        gate_channels += [channel // reduction] * num_layers
        gate_channels += [channel]

        self.ca = nn.Sequential()
        self.ca.add_module('flatten', Flatten())
        for i in range(len(gate_channels) - 2):
            self.ca.add_module('fc%d' % i, nn.Linear(gate_channels[i], gate_channels[i + 1]))
            self.ca.add_module('bn%d' % i, nn.BatchNorm1d(gate_channels[i + 1]))
            self.ca.add_module('relu%d' % i, nn.ReLU())
        self.ca.add_module('last_fc', nn.Linear(gate_channels[-2], gate_channels[-1]))

    def forward(self, x):
        res = self.avgpool(x)
        res = self.ca(res)
        res = res.unsqueeze(-1).unsqueeze(-1).expand_as(x)
        return res


class SpatialAttention(nn.Module):
    def __init__(self, channel, reduction=16, num_layers=3, dia_val=2):
        super().__init__()
        self.sa = nn.Sequential()
        self.sa.add_module('conv_reduce1',
                           nn.Conv2d(kernel_size=1, in_channels=channel, out_channels=channel // reduction))
        self.sa.add_module('bn_reduce1', nn.BatchNorm2d(channel // reduction))
        self.sa.add_module('relu_reduce1', nn.ReLU())
        for i in range(num_layers):
            self.sa.add_module('conv_%d' % i, nn.Conv2d(kernel_size=3, in_channels=channel // reduction,
                                                        out_channels=channel // reduction, padding=1, dilation=dia_val))
            self.sa.add_module('bn_%d' % i, nn.BatchNorm2d(channel // reduction))
            self.sa.add_module('relu_%d' % i, nn.ReLU())
        self.sa.add_module('last_conv', nn.Conv2d(channel // reduction, 1, kernel_size=1))

    def forward(self, x):
        res = self.sa(x)
        res = res.expand_as(x)
        return res


class BAMBlock(nn.Module):
    def __init__(self, channel=512, reduction=16, dia_val=2):
        super().__init__()
        self.ca = ChannelAttention(channel=channel, reduction=reduction)
        self.sa = SpatialAttention(channel=channel, reduction=reduction, dia_val=dia_val)
        self.sigmoid = nn.Sigmoid()

    def init_weights(self):
        for m in self.modules():
            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()
        sa_out = self.sa(x)
        ca_out = self.ca(x)
        weight = self.sigmoid(sa_out + ca_out)
        out = (1 + weight) * x
        return out

if __name__ == '__main__':
    input = torch.randn(50, 512, 7, 7)
    bam = BAMBlock(channel=512, reduction=16, dia_val=2)
    output = bam(input)
    print(output.shape)