MobileNetV2.py

import torch.nn as nn
import math
import numpy as np
import torch
from torchsummary import summary

def conv_bn(inp,oup,stride):
    return nn.Sequential(
        nn.Conv2d(inp,oup,3,stride,1,bias=False),
        nn.BatchNorm2d(oup),
        nn.ReLU6(inplace=True)
    )

def conv_1x1_bn(inp,oup):
    return nn.Sequential(
        nn.Conv2d(inp,oup,1,1,0,bias=False),
        nn.BatchNorm2d(oup),
        nn.ReLU6(inplace=True)
    )

def make_divisible(x,divisible_by=8):
    return int(np.ceil(x * 1./divisible_by) * divisible_by)

class InvertedResidual(nn.Module):
    def __init__(self,inp,oup,stride,expand_ratio):
        super(InvertedResidual,self).__init__()
        self.stride = stride
        assert stride in [1,2]

        hidden_dim = int(inp * expand_ratio)
        # 如果stide == 1 并且 输入 等于 输出 则使用残差连接
        self.use_res_connect = self.stride == 1 and inp == oup
        # 这里为什么 扩大比例为1时 不需要pw
        if expand_ratio == 1:
            self.conv = nn.Sequential(
                # dw  groups作用是控制分组卷积，默认不分组，为1组
                nn.Conv2d(hidden_dim,hidden_dim,3,stride,1,groups=hidden_dim,bias=False),
                nn.BatchNorm2d(hidden_dim),
                nn.ReLU6(inplace=True),
                # pw-linear
                nn.Conv2d(hidden_dim,oup,1,1,0,bias=False),
                nn.BatchNorm2d(oup)
            )
        else:
            self.conv = nn.Sequential(
                # pw
                nn.Conv2d(inp,hidden_dim,1,1,0,bias=False),
                nn.BatchNorm2d(oup),
                nn.ReLU6(inplace=True),
                # dw
                nn.Conv2d(hidden_dim, hidden_dim, 3, stride, 1, groups=hidden_dim, bias=False),
                nn.BatchNorm2d(hidden_dim),
                nn.ReLU6(inplace=True),
                # pw-linear
                nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
                nn.BatchNorm2d(oup),
            )

    def forward(self,x):
        if self.use_res_connect:
            return x + self.conv(x)
        else:
            return self.conv(x)

class MobileNetV2(nn.Module):
    def __init__(self,n_class=1000,input_size=224,width_mult=1):
        super(MobileNetV2, self).__init__()
        block = InvertedResidual
        input_channel = 32
        last_channel = 1280
        interverted_residual_setting = [
            # t:扩展系数,c:输出通道数,n:该模块重复次数,s：第一次出现时的步长（后面重复该模块步长都是1）
            # 注意： 扩展系数即invertedResidual Block中第一个1x1卷积核的个数是输入的通道数的多少倍，也就是中间部分的通道数是输入的通道数的多少倍
            [1,16,1,1],
            [6,24,2,2],
            [6,32,3,2],
            [6,64,4,2],
            [6,96,3,1],
            [6,160,3,2],
            [6,320,1,1],
        ]
        # building first layer 第一层是正常的卷积层 224x224x3  输入为3通道的图片
        assert input_size%32 == 0
        # input_channel = make_divisible(input_channel * width_mult)  # first channel is always 32!
        self.last_channel = make_divisible(last_channel * width_mult) if width_mult > 1.0 else last_channel
        self.features = [conv_bn(1,input_channel,2)]
        # building inverted residual blocks
        for t,c,n,s in interverted_residual_setting:
            # 乘放大系数
            output_channel = make_divisible(c * width_mult) if t > 1 else c
            for i in range(n):
                if i == 0:
                    self.features.append(block(input_channel,output_channel,s,expand_ratio=1))
                else:
                    self.features.append(block(input_channel, output_channel, 1, expand_ratio=1))
                input_channel = output_channel

        # building last several layers
        self.features.append(conv_1x1_bn(input_channel, self.last_channel))
        # make it nn.Sequential
        self.features = nn.Sequential(*self.features)

        # building classifier
        self.classifier = nn.Linear(self.last_channel,n_class)
        self._initialize_weights()

    def forward(self,x):
        x = self.features(x)
        x = x.mean(3).mean(2)
        x = self.classifier(x)
        return x

    def _initialize_weights(self):
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
                m.weight.data.normal_(0, math.sqrt(2. / n))
                if m.bias is not None:
                    m.bias.data.zero_()
            elif isinstance(m, nn.BatchNorm2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_()
            elif isinstance(m, nn.Linear):
                n = m.weight.size(1)
                m.weight.data.normal_(0, 0.01)
                m.bias.data.zero_()


def mobilenet_v2(pretrained = True):
    model = MobileNetV2(width_mult=1)
    # 根据实际需求调整最后一层全连接层 model.classifier = nn.Linear(1280,1000)
    if pretrained:
        try:
            from torch.hub import load_state_dict_from_url
        except ImportError:
            from torch.utils.model_zoo import load_url as load_state_dict_from_url
        model.load_state_dict(torch.load('./mobienetv2.pth'),strict=False)
    return model

if __name__ == "__main__":
    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
    net = mobilenet_v2(True).to(device)
    # summary params:模型、输入尺寸、批数量、设备
    print(summary(net,(3,224,224)))