改进YOLOv5系列：4.YOLOv5_最新MobileOne结构换Backbone修改，超轻量型架构，移动端仅需1ms推理！苹果最新移动端高效主干网络

YOLOv5改进，适用于 YOLOv7、YOLOv4、Scaled_YOLOv4、YOLOv3、YOLOR一系列YOLO算法的模块改进

QAQ

新的仓库即将更新ing， 不是以前那个！！！
到时候这个csdn博客通知，关注不迷路！！！

一系列YOLO算法改进Trick组合！
很多Trick排列组合
助力论文
数据集涨点
创新点改进

具体看置顶博客

以下MobileOne网络模块 的改进，最新MobileOne结构换Backbone

1.MoblieOne理论

论文参考：最新MobileOne结构: Paper

MobileOne的核心模块基于MobileNetV1而设计，同时吸收了重参数思想，得到下图所示的结构。注：这里的重参数机制还存在一个超参k用于控制重参数分支的数量

MobileOneBlock 块在训练时和测试时有两种不同的结构。左：具有可重新参数化分支的训练时间 MobileOne 块。右图：MobileOne 在重新参数化分支的推理。ReLU 或 SE-ReLU 都用作激活。过参数化因子是针对每个变体调整的超参数。

使用YOLOv5算法作为演示，模块可以无缝插入到YOLOv7、YOLOv5、YOLOv4、Scaled_YOLOv4、YOLOv3、YOLOR等一系列YOLO算法中

2.在YOLOv5中加入MoblieOne模块

新增YOLOv5的yaml配置文件

首先增加以下yolov5_MobileOne.yaml文件

代码
# YOLOv5改进   MIT license

# Parameters
nc: 80  # number of classes
depth_multiple: 0.33  # model depth multiple
width_multiple: 0.50  # layer channel multiple
anchors:
  - [10,13, 16,30, 33,23]  # P3/8
  - [30,61, 62,45, 59,119]  # P4/16
  - [116,90, 156,198, 373,326]  # P5/32

# YOLOv5改进 v1.0 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
   [-1, 6, MobileOne, [128, 4, 1, False]],
   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
   [-1, 6, MobileOne, [256, 4, 1, False]],
   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
   [-1, 6, MobileOne, [512, 4, 1, False]],
   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
   [-1, 6, MobileOne, [1024, 4, 1, False]],
   [-1, 1, SPPF, [1024, 5]],  # 9
  ]

# YOLOv5改进 v1.0 head
head:
  [[-1, 1, Conv, [512, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
   [-1, 3, C3, [512, False]],  # 13

   [-1, 1, Conv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)

   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 14], 1, Concat, [1]],  # cat head P4
   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)

   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 10], 1, Concat, [1]],  # cat head P5
   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)

   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]

注意：YOLOv5的yaml文件中的MobileOne只是n个MobileOneBlock模块, 使用者可以自行再魔改结构

当需要修改yaml配置文件，将xx模块 加到你想加入的位置（层数）；
首先基于一个可以成功运行的.yaml模型配置文件，进行新增或者减少层数 之后，那么该层网络后续的层的编号都会发生改变，对应的一些层都需要针对性的修改，以匹配通道和层数的关系

common.py配置

在./models/common.py文件中增加以下模块，直接复制即可

import torch.nn as nn
import numpy as np
import torch

def conv_bn(in_channels, out_channels, kernel_size, stride, padding, groups=1):
    result = nn.Sequential()
    result.add_module('conv', nn.Conv2d(in_channels=in_channels, out_channels=out_channels,
                                                  kernel_size=kernel_size, stride=stride, padding=padding, groups=groups, bias=False))
    result.add_module('bn', nn.BatchNorm2d(num_features=out_channels))
    return result

class DepthWiseConv(nn.Module):
    def __init__(self, inc, kernel_size, stride=1):
        super().__init__()
        padding = 1
        if kernel_size == 1:
            padding = 0
        # self.conv = nn.Sequential(
        #     nn.Conv2d(inc, inc, kernel_size, stride, padding, groups=inc, bias=False,),
        #     nn.BatchNorm2d(inc),
        # )
        self.conv = conv_bn(inc, inc,kernel_size, stride, padding, inc)

    def forward(self, x):
        return self.conv(x)
    

class PointWiseConv(nn.Module):
    def __init__(self, inc, outc):
        super().__init__()
        # self.conv = nn.Sequential(
        #     nn.Conv2d(inc, outc, 1, 1, 0, bias=False),
        #     nn.BatchNorm2d(outc),
        # )
        self.conv = conv_bn(inc, outc, 1, 1, 0)
    def forward(self, x):
        return self.conv(x)



class MobileOneBlock(nn.Module):

    def __init__(self, in_channels, out_channels, k,
                 stride=1, dilation=1, padding_mode='zeros', deploy=False, use_se=False):
        super(MobileOneBlock, self).__init__()
        self.deploy = deploy
        self.in_channels = in_channels
        self.out_channels = out_channels
        self.deploy = deploy
        kernel_size = 3
        padding = 1
        assert kernel_size == 3
        assert padding == 1
        self.k = k
        padding_11 = padding - kernel_size // 2

        self.nonlinearity = nn.ReLU()

        if use_se:
            # self.se = SEBlock(out_channels, internal_neurons=out_channels // 16)
            ...
        else:
            self.se = nn.Identity()

        if deploy:
            self.dw_reparam = nn.Conv2d(in_channels=in_channels, out_channels=in_channels, kernel_size=kernel_size, stride=stride,
                                      padding=padding, dilation=dilation, groups=in_channels, bias=True, padding_mode=padding_mode)
            self.pw_reparam = nn.Conv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=1, stride=1, bias=True)

        else:
            # self.rbr_identity = nn.BatchNorm2d(num_features=in_channels) if out_channels == in_channels and stride == 1 else None
            # self.rbr_dense = conv_bn(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size, stride=stride, padding=padding, groups=groups)
            # self.rbr_1x1 = conv_bn(in_channels=in_channels, out_channels=out_channels, kernel_size=1, stride=stride, padding=padding_11, groups=groups)
            # print('RepVGG Block, identity = ', self.rbr_identity)
            self.dw_bn_layer = nn.BatchNorm2d(in_channels) if out_channels == in_channels and stride == 1 else None
            for k_idx in range(k):
                setattr(self, f'dw_3x3_{k_idx}', 
                    DepthWiseConv(in_channels, 3, stride=stride)
                )
            self.dw_1x1 = DepthWiseConv(in_channels, 1, stride=stride)

            self.pw_bn_layer = nn.BatchNorm2d(in_channels) if out_channels == in_channels and stride == 1 else None
            for k_idx in range(k):
                setattr(self, f'pw_1x1_{k_idx}', 
                    PointWiseConv(in_channels, out_channels)
                )

    def forward(self, inputs):
        if self.deploy:
            x = self.dw_reparam(inputs)
            x = self.nonlinearity(x)
            x = self.pw_reparam(x)
            x = self.nonlinearity(x)
            return x

        if self.dw_bn_layer is None:
            id_out = 0
        else:
            id_out = self.dw_bn_layer(inputs)
        
        x_conv_3x3 = []
        for k_idx in range(self.k):
            x = getattr(self, f'dw_3x3_{k_idx}')(inputs)
            x_conv_3x3.append(x)
        x_conv_1x1 = self.dw_1x1(inputs)
        # print(x_conv_1x1.shape, x_conv_3x3[0].shape)
        # print(x_conv_1x1.shape)
        # print(id_out)
        x = id_out + x_conv_1x1 + sum(x_conv_3x3)
        x = self.nonlinearity(self.se(x))

         # 1x1 conv
        if self.pw_bn_layer is None:
            id_out = 0
        else:
            id_out = self.pw_bn_layer(x)
        x_conv_1x1 = []
        for k_idx in range(self.k):
            x_conv_1x1.append(getattr(self, f'pw_1x1_{k_idx}')(x))
        x = id_out + sum(x_conv_1x1)
        x = self.nonlinearity(x)
        return x
        
class MobileOne(nn.Module):
    def __init__(self, in_channels, out_channels, n, k,
                 stride=1, dilation=1, padding_mode='zeros', deploy=False, use_se=False):
        super().__init__()
        self.m = nn.Sequential(*[MobileOneBlock(in_channels, out_channels, k, stride, deploy) for _ in range(n)])

    def forward(self, x):
        x = self.m(x)
        return x

yolo.py配置

然后找到./models/yolo.py文件下里的parse_model函数，将类名加入进去
在 models/yolo.py文件夹下

• parse_model函数中
• for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):内部
• 对应位置 下方只需要增加 MobileOne模块

参考代码

      elif m is MobileOne:
            c1, c2 = ch[f], args[0]
            c2 = make_divisible(c2 * gw, 8)
            args = [c1, c2, n, *args[1:]]

参考示意图

训练yolov5_MobileOneBlock模型

python train.py --cfg yolov5_MobileOneBlock.yaml

针对以上yaml文件继续修改

关于yolov5_MobileOneBlockyaml文件配置中的MobileOneBlock模块，可以针对不同数据集自行再进行魔改，原理一致

未经允许，禁止转载

注: MobileOne模块复现代码引用链接:https://github.com/shoutOutYangJie/MobileOne