YOLOv11改进 | 添加注意力机制 | 轻量化iRMB倒置残差块注意力机制（含二次创新C3k2、C2PSA）

1 iRMB注意力机制介绍

论文地址：https://arxiv.org/pdf/2301.01146

1.1 摘要

本文重点研究在参数规模、浮点运算量（FLOPs）和模型性能之间进行权衡，开发面向密集预测任务的现代化高效轻量级模型。倒残差块（IRB）作为轻量级CNN的基础架构，但在基于注意力机制的模型中尚未得到充分认可。本研究从统一视角重新思考高效IRB与Transformer的有效组件，将基于CNN的IRB扩展至注意力模型，并抽象出适用于轻量级模型设计的单残差元移动块（MMB）。遵循简洁高效的设计准则，推导出现代化倒残差移动块（iRMB），构建了仅采用iRMB模块、类ResNet结构的高效模型（EMO）用于下游任务。在ImageNet-1K、COCO2017和ADE20K基准测试中的大量实验表明，EMO模型性能优于现有最优方法：EMO-1M/2M/5M分别达到71.5%、75.1%和78.4%的Top-1准确率，超越同量级的CNN/注意力模型，同时在参数规模、运行效率和准确率之间实现良好平衡——在iPhone14上的运行速度比EdgeNeXt快2.8-4.0倍。

代码地址：https://github.com/zhangzjn/EMO

1.2 iRMB注意力机制介绍

iRMB是一种面向轻量化视觉模型设计的混合架构，旨在通过统一CNN的局部归纳偏置与Transformer的全局动态建模能力，实现参数效率与计算效率的平衡。其核心在于将传统CNN中的倒置残差块（Inverted Residual Block）与注意力机制的关键组件进行结构解耦与功能重组，形成既能保留轻量化优势、又能捕捉长程依赖关系的模块化单元。这种设计尤其适配移动端设备对模型轻量性、推理速度和任务性能的联合需求。

---

​iRMB的创新性技术贡献

1. ​跨架构的功能融合​
   ​将CNN的倒置残差机制与Transformer的注意力动态权重分配相结合，提出“残差移动”范式：

   • ​局部特征提取：沿用CNN的深度可分离卷积（Depthwise Conv）作为基础操作，保障轻量化与局部特征建模能力。
   • ​全局动态增强：引入隐式空间注意力（如Squeeze-and-Excitation机制）或轻量化自注意力变体，通过通道/空间维度的动态权重调整，增强对全局上下文信息的敏感度。

2. ​结构扩展与参数复用​

   • ​跨架构泛化：突破传统IRB仅服务于CNN的局限，通过可扩展的残差连接与多分支特征交互设计，将其扩展到基于注意力的模型中，实现跨架构组件（如MobileNet中的IRB与Vision Transformer中的MHSA）的兼容性适配。
   • ​元移动块抽象：提出参数化的扩展比率（Expansion Ratio）与操作符选择机制，允许同一模块在不同计算预算下动态调整卷积核尺寸、通道扩展倍数及注意力分支的激活阈值，实现“一模块多形态”的灵活部署。

3. ​端到端效率优化​

   • ​硬件感知设计：针对移动端芯片（如ARM CPU/NPU）优化内存访问模式，通过跨层权重共享与计算图重参数化技术，减少访存开销与分支计算冗余。
   • ​模块级效率验证：在iPhone等终端设备上实测推理延迟，结合FLOPs/参数量的理论分析，确保模块设计同时满足理论效率与硬件执行效率的最优解。

---

​技术优势验证

通过ImageNet分类、COCO检测、ADE20K分割等任务实验，iRMB展现出以下优势：

• ​性能提升：EMO系列模型（基于iRMB构建）在同等参数量下，Top-1准确率显著优于MobileNet、EdgeNeXt等轻量模型。
• ​速度优势：在iPhone14上，iRMB的iPhone14实测速度比EdgeNeXt快2.8-4.0倍，证明其硬件友好性。
• ​任务泛化性：单一模块设计可无缝迁移至检测、分割等密集预测任务，避免传统轻量模型在多任务适配时的性能衰减问题。

1.3 结构

2 核心代码

import math
import torch
import torch.nn as nn
import torch.nn.functional as F
from functools import partial
from einops import rearrange
from timm.models._efficientnet_blocks import SqueezeExcite
from timm.models.layers import DropPath
 
__all__ = ['iRMB', 'C2PSA_iRMB', 'C3k2_iRMB']
 
inplace = True  # 全局变量
 
class LayerNorm2d(nn.Module):
 
    def __init__(self, normalized_shape, eps=1e-6, elementwise_affine=True):
        super().__init__()
        self.norm = nn.LayerNorm(normalized_shape, eps, elementwise_affine)
 
    def forward(self, x):
        x = rearrange(x, 'b c h w -> b h w c').contiguous()
        x = self.norm(x)
        x = rearrange(x, 'b h w c -> b c h w').contiguous()
        return x
 
 
def get_norm(norm_layer='in_1d'):
    eps = 1e-6
    norm_dict = {
        'none': nn.Identity,
        'in_1d': partial(nn.InstanceNorm1d, eps=eps),
        'in_2d': partial(nn.InstanceNorm2d, eps=eps),
        'in_3d': partial(nn.InstanceNorm3d, eps=eps),
        'bn_1d': partial(nn.BatchNorm1d, eps=eps),
        'bn_2d': partial(nn.BatchNorm2d, eps=eps),
        # 'bn_2d': partial(nn.SyncBatchNorm, eps=eps),
        'bn_3d': partial(nn.BatchNorm3d, eps=eps),
        'gn': partial(nn.GroupNorm, eps=eps),
        'ln_1d': partial(nn.LayerNorm, eps=eps),
        'ln_2d': partial(LayerNorm2d, eps=eps),
    }
    return norm_dict[norm_layer]
 
 
def get_act(act_layer='relu'):
    act_dict = {
        'none': nn.Identity,
        'relu': nn.ReLU,
        'relu6': nn.ReLU6,
        'silu': nn.SiLU
    }
    return act_dict[act_layer]
 
 
class ConvNormAct(nn.Module):
 
    def __init__(self, dim_in, dim_out, kernel_size, stride=1, dilation=1, groups=1, bias=False,
                 skip=False, norm_layer='bn_2d', act_layer='relu', inplace=True, drop_path_rate=0.):
        super(ConvNormAct, self).__init__()
        self.has_skip = skip and dim_in == dim_out
        padding = math.ceil((kernel_size - stride) / 2)
        self.conv = nn.Conv2d(dim_in, dim_out, kernel_size, stride, padding, dilation, groups, bias)
        self.norm = get_norm(norm_layer)(dim_out)
        self.act = get_act(act_layer)(inplace=inplace)
        self.drop_path = DropPath(drop_path_rate) if drop_path_rate else nn.Identity()
 
    def forward(self, x):
        shortcut = x
        x = self.conv(x)
        x = self.norm(x)
        x = self.act(x)
        if self.has_skip:
            x = self.drop_path(x) + shortcut
        return x
 
 
 
class iRMB(nn.Module):
 
    def __init__(self, dim_in,  norm_in=True, has_skip=True, exp_ratio=1.0, norm_layer='bn_2d',
                 act_layer='relu', v_proj=True, dw_ks=3, stride=1, dilation=1, se_ratio=0.0, dim_head=8, window_size=7,
                 attn_s=True, qkv_bias=False, attn_drop=0., drop=0., drop_path=0., v_group=False, attn_pre=False):
        super().__init__()
        dim_out = dim_in
        self.norm = get_norm(norm_layer)(dim_in) if norm_in else nn.Identity()
        dim_mid = int(dim_in * exp_ratio)
        self.has_skip = (dim_in == dim_out and stride == 1) and has_skip
        self.attn_s = attn_s
        if self.attn_s:
            assert dim_in % dim_head == 0, 'dim should be divisible by num_heads'
            self.dim_head = dim_head
            self.window_size = window_size
            self.num_head = dim_in // dim_head
            self.scale = self.dim_head ** -0.5
            self.attn_pre = attn_pre
            self.qk = ConvNormAct(dim_in, int(dim_in * 2), kernel_size=1, bias=qkv_bias, norm_layer='none',
                                  act_layer='none')
            self.v = ConvNormAct(dim_in, dim_mid, kernel_size=1, groups=self.num_head if v_group else 1, bias=qkv_bias,
                                 norm_layer='none', act_layer=act_layer, inplace=inplace)
            self.attn_drop = nn.Dropout(attn_drop)
        else:
            if v_proj:
                self.v = ConvNormAct(dim_in, dim_mid, kernel_size=1, bias=qkv_bias, norm_layer='none',
                                     act_layer=act_layer, inplace=inplace)
            else:
                self.v = nn.Identity()
        self.conv_local = ConvNormAct(dim_mid, dim_mid, kernel_size=dw_ks, stride=stride, dilation=dilation,
                                      groups=dim_mid, norm_layer='bn_2d', act_layer='silu', inplace=inplace)
        self.se = SqueezeExcite(dim_mid, rd_ratio=se_ratio, act_layer=get_act(act_layer)) if se_ratio > 0.0 else nn.Identity()
 
        self.proj_drop = nn.Dropout(drop)
        self.proj = ConvNormAct(dim_mid, dim_out, kernel_size=1, norm_layer='none', act_layer='none', inplace=inplace)
        self.drop_path = DropPath(drop_path) if drop_path else nn.Identity()
 
    def forward(self, x):
        shortcut = x
        x = self.norm(x)
        B, C, H, W = x.shape
        if self.attn_s:
            # padding
            if self.window_size <= 0:
                window_size_W, window_size_H = W, H
            else:
                window_size_W, window_size_H = self.window_size, self.window_size
            pad_l, pad_t = 0, 0
            pad_r = (window_size_W - W % window_size_W) % window_size_W
            pad_b = (window_size_H - H % window_size_H) % window_size_H
            x = F.pad(x, (pad_l, pad_r, pad_t, pad_b, 0, 0,))
            n1, n2 = (H + pad_b) // window_size_H, (W + pad_r) // window_size_W
            x = rearrange(x, 'b c (h1 n1) (w1 n2) -> (b n1 n2) c h1 w1', n1=n1, n2=n2).contiguous()
            # attention
            b, c, h, w = x.shape
            qk = self.qk(x)
            qk = rearrange(qk, 'b (qk heads dim_head) h w -> qk b heads (h w) dim_head', qk=2, heads=self.num_head,
                           dim_head=self.dim_head).contiguous()
            q, k = qk[0], qk[1]
            attn_spa = (q @ k.transpose(-2, -1)) * self.scale
            attn_spa = attn_spa.softmax(dim=-1)
            attn_spa = self.attn_drop(attn_spa)
            if self.attn_pre:
                x = rearrange(x, 'b (heads dim_head) h w -> b heads (h w) dim_head', heads=self.num_head).contiguous()
                x_spa = attn_spa @ x
                x_spa = rearrange(x_spa, 'b heads (h w) dim_head -> b (heads dim_head) h w', heads=self.num_head, h=h,
                                  w=w).contiguous()
                x_spa = self.v(x_spa)
            else:
                v = self.v(x)
                v = rearrange(v, 'b (heads dim_head) h w -> b heads (h w) dim_head', heads=self.num_head).contiguous()
                x_spa = attn_spa @ v
                x_spa = rearrange(x_spa, 'b heads (h w) dim_head -> b (heads dim_head) h w', heads=self.num_head, h=h,
                                  w=w).contiguous()
            # unpadding
            x = rearrange(x_spa, '(b n1 n2) c h1 w1 -> b c (h1 n1) (w1 n2)', n1=n1, n2=n2).contiguous()
            if pad_r > 0 or pad_b > 0:
                x = x[:, :, :H, :W].contiguous()
        else:
            x = self.v(x)
 
        x = x + self.se(self.conv_local(x)) if self.has_skip else self.se(self.conv_local(x))
 
        x = self.proj_drop(x)
        x = self.proj(x)
 
        x = (shortcut + self.drop_path(x)) if self.has_skip else x
        return x
 
 
 
def autopad(k, p=None, d=1):  # kernel, padding, dilation
    """Pad to 'same' shape outputs."""
    if d > 1:
        k = d * (k - 1) + 1 if isinstance(k, int) else [d * (x - 1) + 1 for x in k]  # actual kernel-size
    if p is None:
        p = k // 2 if isinstance(k, int) else [x // 2 for x in k]  # auto-pad
    return p
 
 
class Conv(nn.Module):
    """Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation)."""
 
    default_act = nn.SiLU()  # default activation
 
    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True):
        """Initialize Conv layer with given arguments including activation."""
        super().__init__()
        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p, d), groups=g, dilation=d, bias=False)
        self.bn = nn.BatchNorm2d(c2)
        self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()
 
    def forward(self, x):
        """Apply convolution, batch normalization and activation to input tensor."""
        return self.act(self.bn(self.conv(x)))
 
    def forward_fuse(self, x):
        """Perform transposed convolution of 2D data."""
        return self.act(self.conv(x))
 
class PSABlock(nn.Module):
    """
    PSABlock class implementing a Position-Sensitive Attention block for neural networks.
    This class encapsulates the functionality for applying multi-head attention and feed-forward neural network layers
    with optional shortcut connections.
    Attributes:
        attn (Attention): Multi-head attention module.
        ffn (nn.Sequential): Feed-forward neural network module.
        add (bool): Flag indicating whether to add shortcut connections.
    Methods:
        forward: Performs a forward pass through the PSABlock, applying attention and feed-forward layers.
    Examples:
        Create a PSABlock and perform a forward pass
        >>> psablock = PSABlock(c=128, attn_ratio=0.5, num_heads=4, shortcut=True)
        >>> input_tensor = torch.randn(1, 128, 32, 32)
        >>> output_tensor = psablock(input_tensor)
    """
 
    def __init__(self, c, attn_ratio=0.5, num_heads=4, shortcut=True) -> None:
        """Initializes the PSABlock with attention and feed-forward layers for enhanced feature extraction."""
        super().__init__()
 
        self.attn = iRMB(c)
        self.ffn = nn.Sequential(Conv(c, c * 2, 1), Conv(c * 2, c, 1, act=False))
        self.add = shortcut
 
    def forward(self, x):
        """Executes a forward pass through PSABlock, applying attention and feed-forward layers to the input tensor."""
        x = x + self.attn(x) if self.add else self.attn(x)
        x = x + self.ffn(x) if self.add else self.ffn(x)
        return x
 
 
class C2PSA_iRMB(nn.Module):
    """
    C2PSA module with attention mechanism for enhanced feature extraction and processing.
    This module implements a convolutional block with attention mechanisms to enhance feature extraction and processing
    capabilities. It includes a series of PSABlock modules for self-attention and feed-forward operations.
    Attributes:
        c (int): Number of hidden channels.
        cv1 (Conv): 1x1 convolution layer to reduce the number of input channels to 2*c.
        cv2 (Conv): 1x1 convolution layer to reduce the number of output channels to c.
        m (nn.Sequential): Sequential container of PSABlock modules for attention and feed-forward operations.
    Methods:
        forward: Performs a forward pass through the C2PSA module, applying attention and feed-forward operations.
    Notes:
        This module essentially is the same as PSA module, but refactored to allow stacking more PSABlock modules.
    Examples:
        >>> c2psa = C2PSA(c1=256, c2=256, n=3, e=0.5)
        >>> input_tensor = torch.randn(1, 256, 64, 64)
        >>> output_tensor = c2psa(input_tensor)
    """
 
    def __init__(self, c1, c2, n=1, e=0.5):
        """Initializes the C2PSA module with specified input/output channels, number of layers, and expansion ratio."""
        super().__init__()
        assert c1 == c2
        self.c = int(c1 * e)
        self.cv1 = Conv(c1, 2 * self.c, 1, 1)
        self.cv2 = Conv(2 * self.c, c1, 1)
 
        self.m = nn.Sequential(*(PSABlock(self.c, attn_ratio=0.5, num_heads=self.c // 64) for _ in range(n)))
 
    def forward(self, x):
        """Processes the input tensor 'x' through a series of PSA blocks and returns the transformed tensor."""
        a, b = self.cv1(x).split((self.c, self.c), dim=1)
        b = self.m(b)
        return self.cv2(torch.cat((a, b), 1))
    
class Bottleneck(nn.Module):
    """Standard bottleneck."""

    def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5):
        """Initializes a standard bottleneck module with optional shortcut connection and configurable parameters."""
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, k[0], 1)
        self.cv2 = Conv(c_, c2, k[1], 1, g=g)
        self.add = shortcut and c1 == c2

    def forward(self, x):
        """Applies the YOLO FPN to input data."""
        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))

class C3(nn.Module):
    """CSP Bottleneck with 3 convolutions."""

    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
        """Initialize the CSP Bottleneck with given channels, number, shortcut, groups, and expansion values."""
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c1, c_, 1, 1)
        self.cv3 = Conv(2 * c_, c2, 1)  # optional act=FReLU(c2)
        self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, k=((1, 1), (3, 3)), e=1.0) for _ in range(n)))

    def forward(self, x):
        """Forward pass through the CSP bottleneck with 2 convolutions."""
        return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1))

class C3k(C3):
    """C3k is a CSP bottleneck module with customizable kernel sizes for feature extraction in neural networks."""

    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, k=3):
        """Initializes the C3k module with specified channels, number of layers, and configurations."""
        super().__init__(c1, c2, n, shortcut, g, e)
        c_ = int(c2 * e)  # hidden channels
        # self.m = nn.Sequential(*(RepBottleneck(c_, c_, shortcut, g, k=(k, k), e=1.0) for _ in range(n)))
        self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, k=(k, k), e=1.0) for _ in range(n)))

class C2f(nn.Module):
    """Faster Implementation of CSP Bottleneck with 2 convolutions."""

    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):
        """Initializes a CSP bottleneck with 2 convolutions and n Bottleneck blocks for faster processing."""
        super().__init__()
        self.c = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, 2 * self.c, 1, 1)
        self.cv2 = Conv((2 + n) * self.c, c2, 1)  # optional act=FReLU(c2)
        self.m = nn.ModuleList(Bottleneck(self.c, self.c, shortcut, g, k=((3, 3), (3, 3)), e=1.0) for _ in range(n))

    def forward(self, x):
        """Forward pass through C2f layer."""
        y = list(self.cv1(x).chunk(2, 1))
        y.extend(m(y[-1]) for m in self.m)
        return self.cv2(torch.cat(y, 1))

    def forward_split(self, x):
        """Forward pass using split() instead of chunk()."""
        y = list(self.cv1(x).split((self.c, self.c), 1))
        y.extend(m(y[-1]) for m in self.m)
        return self.cv2(torch.cat(y, 1))
    
class C3k2(C2f):
    """Faster Implementation of CSP Bottleneck with 2 convolutions."""

    def __init__(self, c1, c2, n=1, c3k=False, e=0.5, g=1, shortcut=True):
        """Initializes the C3k2 module, a faster CSP Bottleneck with 2 convolutions and optional C3k blocks."""
        super().__init__(c1, c2, n, shortcut, g, e)
        self.m = nn.ModuleList(
            C3k(self.c, self.c, 2, shortcut, g) if c3k else Bottleneck(self.c, self.c, shortcut, g) for _ in range(n)
        )

class C3k_iRMB(C3k):
    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5, k=3):
        super().__init__(c1, c2, n, shortcut, g, e, k)
        c_ = int(c2 * e)  # hidden channels
        self.m = nn.Sequential(*(iRMB(c_, c_) for _ in range(n)))

class C3k2_iRMB(C3k2):
    def __init__(self, c1, c2, n=1, c3k=False, e=0.5, g=1, shortcut=True):
        super().__init__(c1, c2, n, c3k, e, g, shortcut)
        self.m = nn.ModuleList(C3k_iRMB(self.c, self.c, 2, shortcut, g) if c3k else iRMB(self.c, self.c) for _ in range(n))

3 改进步骤

3.1 在ultralytics/nn下新建Addmodule文件夹，并在Addmodule里创建iRMB.py

在iRMB.py文件里添加给出的iRMB代码

添加完iRMB代码后，在ultralytics/nn/Addmodule/__init__.py文件中引用

from .iRMB import *

在ultralytics/nn/tasks.py里引用

from .Addmodule import *

3.2 在ultralytics/nn/tasks.py查找

（1）在tasks.py找到parse_model函数（ctrl+f 可以直接搜索parse_model位置），添加：

        elif m in {iRMB}:
            c2 = ch[f]
            args = [c2, *args]

到此，修改完成。

4 创建YOLO11_iRMB.yaml

（1）第一种（创新C2PSA）

# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLO11 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
 
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolo11n.yaml' will call yolo11.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.50, 0.25, 1024] # summary: 319 layers, 2624080 parameters, 2624064 gradients, 6.6 GFLOPs
  s: [0.50, 0.50, 1024] # summary: 319 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPs
  m: [0.50, 1.00, 512] # summary: 409 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPs
  l: [1.00, 1.00, 512] # summary: 631 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPs
  x: [1.00, 1.50, 512] # summary: 631 layers, 56966176 parameters, 56966160 gradients, 196.0 GFLOPs
 
# YOLO11n backbone
backbone:
  # [from, repeats, module, args]
  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
  - [-1, 2, C3k2, [256, False, 0.25]]
  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2, [512, False, 0.25]]
  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
  - [-1, 2, C3k2, [1024, True]]
  - [-1, 1, SPPF, [1024, 5]] # 9
  - [-1, 2, C2PSA_iRMB, [1024]] # 10
 
# YOLO11n head
head:
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
  - [-1, 2, C3k2, [512, False]] # 13
 
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
  - [-1, 2, C3k2, [256, False]] # 16 (P3/8-small)
 
  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)
 
  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 10], 1, Concat, [1]] # cat head P5
  - [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)
 
  - [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)

（2）第二种

# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLO11 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
 
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolo11n.yaml' will call yolo11.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.50, 0.25, 1024] # summary: 319 layers, 2624080 parameters, 2624064 gradients, 6.6 GFLOPs
  s: [0.50, 0.50, 1024] # summary: 319 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPs
  m: [0.50, 1.00, 512] # summary: 409 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPs
  l: [1.00, 1.00, 512] # summary: 631 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPs
  x: [1.00, 1.50, 512] # summary: 631 layers, 56966176 parameters, 56966160 gradients, 196.0 GFLOPs
 
# YOLO11n backbone
backbone:
  # [from, repeats, module, args]
  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
  - [-1, 2, C3k2, [256, False, 0.25]]
  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2, [512, False, 0.25]]
  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
  - [-1, 2, C3k2, [1024, True]]
  - [-1, 1, SPPF, [1024, 5]] # 9
  - [-1, 2, C2PSA, [1024]] # 10
 
# YOLO11n head
head:
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
  - [-1, 2, C3k2, [512, False]] # 13
 
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
  - [-1, 2, C3k2, [256, False]] # 16 
  - [-1, 1, iRMB, []] # 17     小目标检测层增加注意力机制
 
  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2, [512, False]] # 20 (P4/16-medium)
  - [-1, 1, iRMB, []] # 21     中目标检测层增加注意力机制
 
  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 10], 1, Concat, [1]] # cat head P5
  - [-1, 2, C3k2, [1024, True]] # 24 
  - [-1, 1, iRMB, []] # 25     大目标检测层增加注意力机制
 

  - [[17, 21, 25], 1, Detect, [nc]] # Detect(P3, P4, P5)

(3) 第三种(创新C3k2)

# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLO11 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect

# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolo11n.yaml' will call yolo11.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.50, 0.25, 1024] # summary: 319 layers, 2624080 parameters, 2624064 gradients, 6.6 GFLOPs
  s: [0.50, 0.50, 1024] # summary: 319 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPs
  m: [0.50, 1.00, 512] # summary: 409 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPs
  l: [1.00, 1.00, 512] # summary: 631 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPs
  x: [1.00, 1.50, 512] # summary: 631 layers, 56966176 parameters, 56966160 gradients, 196.0 GFLOPs

# YOLO11n backbone
backbone:
  # [from, repeats, module, args]
  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
  - [-1, 2, C3k2_iRMB, [256, False, 0.25]]
  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2_iRMB, [512, False, 0.25]]
  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2_iRMB, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
  - [-1, 2, C3k2_iRMB, [1024, True]]
  - [-1, 1, SPPF, [1024, 5]] # 9
  - [-1, 2, C2PSA, [1024]] # 10

# YOLO11n head
head:
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
  - [-1, 2, C3k2, [512, False]] # 13

  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
  - [-1, 2, C3k2, [256, False]] # 16 (P3/8-small)

  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 10], 1, Concat, [1]] # cat head P5
  - [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)

  - [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)

5 训练模型

import warnings
warnings.filterwarnings('ignore')
from ultralytics import YOLO
 
 
if __name__ == '__main__':
    model = YOLO('YOLO11_iRMB.yaml')
    # model.load('yolo11n.pt') # loading pretrain weights
    model.train(data='dataset/data.yaml',
                cache=False,
                imgsz=640,
                epochs=300,
                batch=32,
                close_mosaic=0,
                workers=4, # Windows下出现莫名其妙卡主的情况可以尝试把workers设置为0
                # device='0',
                optimizer='SGD', # using SGD
                # patience=0, # set 0 to close earlystop.
                # resume=True, # 断点续训,YOLO初始化时选择last.pt
                # amp=False, # close amp
                # fraction=0.2,
                project='runs/train',
                name='exp',
                )