1 The birth of attention mechanism

1. Attention mechanism , It was first known as a work in natural language processing , article Attention is all you need In detail “ What is attention mechanism ”, Interested partners can download the original text to see .
   
2. SeNet-Squeeze-and-Excitation Networks It is one of the early works of the application of attention mechanism in computer vision , And got it. 2017 Year of imagenet, The last one imagenet The champion of the competition .
   

2 Introduce SeNet Models and Pytorch Code implementation

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


class SEAttention(nn.Module):

    def __init__(self, channel=512, reduction=16):
        super().__init__()
        self.avg_pool = nn.AdaptiveAvgPool2d(1)  #  Global mean pooling   The output is c×1×1
        self.fc = nn.Sequential(
            nn.Linear(channel, channel // reduction, bias=False),  # channel // reduction Represents channel compression 
            nn.ReLU(inplace=True),
            nn.Linear(channel // reduction, channel, bias=False),  #  Restore 
            nn.Sigmoid()
        )

    def init_weights(self):
        for m in self.modules():
            print(m)  #  Not running here 
            if isinstance(m, nn.Conv2d):  #  Judge type function ——：m yes nn.Conv2d Class? ？
                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()  # 50×512×7×7
        y = self.avg_pool(x).view(b, c)  # ① maxpool After that ：50×512×1×1 ② view Shape get 50×512
        y = self.fc(y).view(b, c, 1, 1)  # 50×512×1×1
        return x * y.expand_as(x)  #  according to x.size To expand y


if __name__ == '__main__':
    input = torch.randn(50, 512, 7, 7)
    se = SEAttention(channel=512, reduction=8)  #  Instantiation model se
    output = se(input)
    print(output.shape)

• Also have say SeNet This is the model of ：（ I think it's too simple ）

class SELayer(nn.Module):
    def __init__(self, channel, reduction=16):
        super(SELayer, self).__init__()
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.fc = nn.Sequential(
            nn.Linear(channel, channel // reduction, bias=False),
            nn.ReLU(inplace=True),
            nn.Linear(channel // reduction, channel, bias=False),
            nn.Sigmoid()
        )

    def forward(self, x):
        b, c, _, _ = x.size()
        y = self.avg_pool(x).view(b, c)
        y = self.fc(y).view(b, c, 1, 1)
        return x * y.expand_as(x)