经典网络模型---MobileNet三代模型架构之V3

MobileNet V3

1）引入Squeeze- Excitation结构

2）非线性变换改变， h-swish替换swish

SE-net

SE-net整体的结构，它可以融入到任何网络模型中

S：操作

对特征图采取全局平均池化，得到1*1*C的结果

特征图中每个通道都相当于描述了一部分特征，操作后相当于是全局的

E：Excitation操作

想得到每个特征图的重要程度评分，还需要再来两个全连接层，最终整个结果也是1*1*C，相当于attnetion

class hsigmoid(nn.Module):
    def forward(self, x):
        out = F.relu6(x + 3, inplace=True) / 6
        return out

class SeModule(nn.Module):
    def __init__(self, in_size, reduction=4):
        super(SeModule, self).__init__()
        self.se = nn.Sequential(
            nn.AdaptiveAvgPool2d(1),
            nn.Conv2d(in_size, in_size // reduction, kernel_size=1, stride=1, padding=0, bias=False),
            nn.BatchNorm2d(in_size // reduction),
            nn.ReLU(inplace=True),
            nn.Conv2d(in_size // reduction, in_size, kernel_size=1, stride=1, padding=0, bias=False),
            nn.BatchNorm2d(in_size),
            hsigmoid()
        )

    def forward(self, x):
        return x * self.se(x)

MobileNet V2和V3对比

import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.nn import init
from base import BaseModel


class hswish(nn.Module):
    def forward(self, x):
        out = x * F.relu6(x + 3, inplace=True) / 6
        return out

class Block(nn.Module):
    '''expand + depthwise + pointwise'''
    def __init__(self, kernel_size, in_size, expand_size, out_size, nolinear, semodule, stride):
        super(Block, self).__init__()
        self.stride = stride
        self.se = semodule

        self.conv1 = nn.Conv2d(in_size, expand_size, kernel_size=1, stride=1, padding=0, bias=False)
        self.bn1 = nn.BatchNorm2d(expand_size)
        self.nolinear1 = nolinear
        self.conv2 = nn.Conv2d(expand_size, expand_size, kernel_size=kernel_size, stride=stride, padding=kernel_size//2, groups=expand_size, bias=False)
        self.bn2 = nn.BatchNorm2d(expand_size)
        self.nolinear2 = nolinear
        self.conv3 = nn.Conv2d(expand_size, out_size, kernel_size=1, stride=1, padding=0, bias=False)
        self.bn3 = nn.BatchNorm2d(out_size)

        self.shortcut = nn.Sequential()
        if stride == 1 and in_size != out_size:
            self.shortcut = nn.Sequential(
                nn.Conv2d(in_size, out_size, kernel_size=1, stride=1, padding=0, bias=False),
                nn.BatchNorm2d(out_size),
            )

    def forward(self, x):
        out = self.nolinear1(self.bn1(self.conv1(x)))
        out = self.nolinear2(self.bn2(self.conv2(out)))
        out = self.bn3(self.conv3(out))
        if self.se != None:
            out = self.se(out)
        out = out + self.shortcut(x) if self.stride==1 else out
        return out


class MobileNetV3_Large(BaseModel):
    def __init__(self, num_classes=1000):
        super(MobileNetV3_Large, self).__init__()
        self.conv1 = nn.Conv2d(1, 16, kernel_size=3, stride=2, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(16)
        self.hs1 = hswish()

        self.bneck = nn.Sequential(
            Block(3, 16, 16, 16, nn.ReLU(inplace=True), None, 1),
            Block(3, 16, 64, 24, nn.ReLU(inplace=True), None, 2),
            Block(3, 24, 72, 24, nn.ReLU(inplace=True), None, 1),
            Block(5, 24, 72, 40, nn.ReLU(inplace=True), SeModule(40), 2),
            Block(5, 40, 120, 40, nn.ReLU(inplace=True), SeModule(40), 1),
            Block(5, 40, 120, 40, nn.ReLU(inplace=True), SeModule(40), 1),
            Block(3, 40, 240, 80, hswish(), None, 2),
            Block(3, 80, 200, 80, hswish(), None, 1),
            Block(3, 80, 184, 80, hswish(), None, 1),
            Block(3, 80, 184, 80, hswish(), None, 1),
            Block(3, 80, 480, 112, hswish(), SeModule(112), 1),
            Block(3, 112, 672, 112, hswish(), SeModule(112), 1),
            Block(5, 112, 672, 160, hswish(), SeModule(160), 1),
            Block(5, 160, 672, 160, hswish(), SeModule(160), 2),
            Block(5, 160, 960, 160, hswish(), SeModule(160), 1),
        )


        self.conv2 = nn.Conv2d(160, 960, kernel_size=1, stride=1, padding=0, bias=False)
        self.bn2 = nn.BatchNorm2d(960)
        self.hs2 = hswish()
        self.linear3 = nn.Linear(960, 1280)
        self.bn3 = nn.BatchNorm1d(1280)
        self.hs3 = hswish()
        self.linear4 = nn.Linear(1280, num_classes)
        self.init_params()

    def init_params(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):
        x = 1
        out = self.hs1(self.bn1(self.conv1(x)))
        out = self.bneck(out)
        out = self.hs2(self.bn2(self.conv2(out)))
        out = F.avg_pool2d(out, 7)
        out = out.view(out.size(0), -1)
        out = self.hs3(self.bn3(self.linear3(out)))
        out = self.linear4(out)
        return out

 效果对比