D:\yolov5-master\models目录下新建mobilevit.py文件夹

代码内容：

import torch
import torch.nn as nn
from einops import rearrange
def conv_1x1_bn(inp, oup):
    return nn.Sequential(
        nn.Conv2d(inp, oup, 1, 1, 0, bias=False),
        nn.BatchNorm2d(oup),
        nn.SiLU()
    )
def conv_nxn_bn(inp, oup, kernal_size=3, stride=1):
    return nn.Sequential(
        nn.Conv2d(inp, oup, kernal_size, stride, 1, bias=False),
        nn.BatchNorm2d(oup),
        nn.SiLU()
    )
class PreNorm(nn.Module):
    def __init__(self, dim, fn):
        super().__init__()
        self.norm = nn.LayerNorm(dim)
        self.fn = fn # mg
    
    def forward(self, x, **kwargs):
        return self.fn(self.norm(x), **kwargs)
class Attention(nn.Module):
    def __init__(self, dim, heads=8, dim_head=64, dropout=0.):
        super().__init__()
        inner_dim = dim_head *  heads
        project_out = not (heads == 1 and dim_head == dim)
        self.heads = heads
        self.scale = dim_head ** -0.5
        self.attend = nn.Softmax(dim = -1)
        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
        self.to_out = nn.Sequential(
            nn.Linear(inner_dim, dim),
            nn.Dropout(dropout)# mg
        ) if project_out else nn.Identity()
    def forward(self, x):
        qkv = self.to_qkv(x).chunk(3, dim=-1)
        q, k, v = map(lambda t: rearrange(t, 'b p n (h d) -> b p h n d', h = self.heads), qkv)
        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
        attn = self.attend(dots)
        out = torch.matmul(attn, v)
        out = rearrange(out, 'b p h n d -> b p n (h d)')
        return self.to_out(out)
class FeedForward(nn.Module):
    def __init__(self, dim, hidden_dim, dropout=0.):
        super().__init__()
        self.net = nn.Sequential(
            nn.Linear(dim, hidden_dim),
            nn.SiLU(),
            nn.Dropout(dropout),
            nn.Linear(hidden_dim, dim),
            nn.Dropout(dropout)
        )
    
    def forward(self, x):
        return self.net(x)
class UserDefined(nn.Module):
    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout=0.):
        super().__init__()
        self.layers = nn.ModuleList([])
        for _ in range(depth):
            self.layers.append(nn.ModuleList([
                PreNorm(dim, Attention(dim, heads, dim_head, dropout)),
                PreNorm(dim, FeedForward(dim, mlp_dim, dropout))
            ]))
    
    def forward(self, x):
        for attn, ff in self.layers:
            x = attn(x) + x
            x = ff(x) + x
        return x
class MobileViT(nn.Module):
    def __init__(self, channel, dim, depth=2, kernel_size=3, patch_size=(2, 2), mlp_dim=int(64*2), dropout=0.):
        super().__init__()
        self.ph, self.pw = patch_size
        self.mv01 = IRBlock(channel, channel) 
        self.conv1 = conv_nxn_bn(channel, channel, kernel_size)
        self.conv3 = conv_1x1_bn(dim, channel)
        self.conv2 = conv_1x1_bn(channel, dim)
        self.transformer = UserDefined(dim, depth, 4, 8, mlp_dim, dropout)
        self.conv4 = conv_nxn_bn(2 * channel, channel, kernel_size)
    def forward(self, x):
        y = x.clone()
        x = self.conv1(x)
        x = self.conv2(x)
        z = x.clone()
        _, _, h, w = x.shape
        x = rearrange(x, 'b d (h ph) (w pw) -> b (ph pw) (h w) d', ph=self.ph, pw=self.pw)
        x = self.transformer(x)
        x = rearrange(x, 'b (ph pw) (h w) d -> b d (h ph) (w pw)', h=h//self.ph, w=w//self.pw, ph=self.ph, pw=self.pw)
        x = self.conv3(x)
        x = torch.cat((x, z), 1)
        x = self.conv4(x)
        x = x + y
        x = self.mv01(x)
        return x
class IRBlock(nn.Module):
    def __init__(self, inp, oup, stride=1, expansion=4):
        super().__init__()
        self.stride = stride
        assert stride in [1, 2]
        hidden_dim = int(inp * expansion)
        self.use_res_connect = self.stride == 1 and inp == oup
        if expansion == 1: # 构建没有扩展层的卷积块
            self.conv = nn.Sequential(
                # 深度可分离卷积（Depthwise Convolution）
                nn.Conv2d(hidden_dim, hidden_dim, 3, stride, 1, groups=hidden_dim, bias=False),
                nn.BatchNorm2d(hidden_dim),
                nn.SiLU(),
                # “线性”逐点卷积 (Pointwise-Linear Convolution)
                nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
                nn.BatchNorm2d(oup),
            )
        else:  # 构建包含扩展层的卷积块
            self.conv = nn.Sequential(
                # 逐点卷积 (Pointwise Convolution)
                nn.Conv2d(inp, hidden_dim, 1, 1, 0, bias=False),
                nn.BatchNorm2d(hidden_dim),
                nn.SiLU(),
                # 深度可分离卷积 (Depthwise Convolution)
                nn.Conv2d(hidden_dim, hidden_dim, 3, stride, 1, groups=hidden_dim, bias=False),
                nn.BatchNorm2d(hidden_dim),
                nn.SiLU(),
                # “线性”逐点卷积 (Pointwise-Linear Convolution)
                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)

代码解析见：

【DeepLearning-1】 注意力机制（Attention Mechanism）-CSDN博客 

【DeepLearning-2】预归一化（Pre-Normalization）策略_prenorm 代码-CSDN博客

【DeepLearning-3】前馈(feed-forward)神经网络层-CSDN博客

【DeepLearning-5】基于Transformer架构的自定义神经网络类-CSDN博客

【DeepLearning-6】实现倒置残差块（Inverted Residual Block）-CSDN博客

【DeepLearning-7】 CNN 和Transformer的混合神经网络结构-CSDN博客

D:\yolov5-master\models\yolo.py文件中加入MobileViT模型

【DeepLearning-10】yolo.py文件关键代码parse_model(d, ch)函数-CSDN博客

YOLOv5模型网络结构中加入MobileViT模块

 【DeepLearning-9】YOLOv5模型网络结构中加入MobileViT模块-CSDN博客

命令窗代码训练网络 

python train.py --cfg D:\yolov5-master\models\yolov5l.yaml