MobileNetV3_YoloV3_Pytorch更改backbone与ncnn落地纪实

1. MobileNetV3网络介绍

1. mobileNetv3介绍
2. 网络结构图
   
   
3. github代码实现

2. DrakNet53网络介绍

3. 使用MobileNetV3替换DrakNet53

exp size=144所在层输出的feature map为26*26 ,所以将第一个分支接在该层后面，进行输出。conv2d,1x1、pool,7x7 、conv2d,1x1,NBN、conv2d,1x1,NBN这几个层去掉，然后将第二个分支接在最后一个bneck层

'''MobileNetV3 in PyTorch.
See the paper "Inverted Residuals and Linear Bottlenecks:
Mobile Networks for Classification, Detection and Segmentation" for more details.
'''
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.nn import init

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

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)


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_Small(nn.Module):
    def __init__(self):
        super(MobileNetV3_Small, self).__init__()
        self.conv1 = nn.Conv2d(3, 16, kernel_size=3, stride=2, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(16)
        self.hs1 = hswish()

        self.bneck_part1 = nn.Sequential(
            Block(3, 16, 16, 16, nn.ReLU(inplace=True), SeModule(16), 2),
            Block(3, 16, 72, 24, nn.ReLU(inplace=True), None, 2),
            Block(3, 24, 88, 24, nn.ReLU(inplace=True), None, 1),
            Block(5, 24, 96, 40, hswish(), SeModule(40), 2),
            Block(5, 40, 240, 40, hswish(), SeModule(40), 1),
            Block(5, 40, 240, 40, hswish(), SeModule(40), 1),
            Block(5, 40, 120, 48, hswish(), SeModule(48), 1),
            Block(5, 48, 144, 48, hswish(), SeModule(48), 1),
        )
        self.bneck_part2 = nn.Sequential(
            Block(5, 48, 288, 96, hswish(), SeModule(96), 2),
            Block(