YOLO11改进 | 卷积模块 | 引入多尺度分支来增强特征表征的注意力机制【CVPR2021】

kay_545

于 2024-10-10 13:26:30 发布

阅读量499

点赞数 10

分类专栏： YOLO11改进有效涨点文章标签：人工智能计算机视觉 yolo11 YOLO 深度学习目标检测 yolo11改进

本文链接：https://blog.csdn.net/m0_67647321/article/details/142783575

版权

YOLO11改进有效涨点专栏收录该内容

29 篇文章 32 订阅

订阅专栏

💡💡💡本专栏所有程序均经过测试，可成功执行💡💡💡

DBB（多样化分支块）是一种用于提高卷积神经网络性能的通用模块，能够在不增加推理时间成本的情况下增强单一卷积的表征能力。通过结合不同尺度和复杂度的多样化分支，DBB丰富了特征空间，包括卷积序列、多尺度卷积和平均池化。文章在介绍主要的原理后，将手把手教学如何进行模块的代码添加和修改，并将修改后的完整代码放在文章的最后，方便大家一键运行，小白也可轻松上手实践。以帮助您更好地学习深度学习目标检测YOLO系列的挑战。

专栏地址：YOLO11入门 + 改进涨点——点击即可跳转欢迎订阅

1. 论文

论文地址：Diverse Branch Block: Building a Convolution as an Inception-like Unit——点击即可跳转

官方仓库：官方代码仓库——点击即可跳转

2. 将DBB添加到YOLO11中

2.1 DBB代码实现

关键步骤一: 将下面代码粘贴到在/ultralytics/ultralytics/nn/modules/block.py中

import torch
import torch.nn as nn
import math
from ultralytics.utils.checks import check_version
import torch.nn.functional as F
import numpy as np

__all__ = ['Detect_DBB', 'Segment_DBB', 'Pose_DBB']

TORCH_1_10 = check_version(torch.__version__, '1.10.0')

def make_anchors(feats, strides, grid_cell_offset=0.5):
    """Generate anchors from features."""
    anchor_points, stride_tensor = [], []
    assert feats is not None
    dtype, device = feats[0].dtype, feats[0].device
    for i, stride in enumerate(strides):
        _, _, h, w = feats[i].shape
        sx = torch.arange(end=w, device=device, dtype=dtype) + grid_cell_offset  # shift x
        sy = torch.arange(end=h, device=device, dtype=dtype) + grid_cell_offset  # shift y
        sy, sx = torch.meshgrid(sy, sx, indexing='ij') if TORCH_1_10 else torch.meshgrid(sy, sx)
        anchor_points.append(torch.stack((sx, sy), -1).view(-1, 2))
        stride_tensor.append(torch.full((h * w, 1), stride, dtype=dtype, device=device))
    return torch.cat(anchor_points), torch.cat(stride_tensor)


def dist2bbox(distance, anchor_points, xywh=True, dim=-1):
    """Transform distance(ltrb) to box(xywh or xyxy)."""
    lt, rb = distance.chunk(2, dim)
    x1y1 = anchor_points - lt
    x2y2 = anchor_points + rb
    if xywh:
        c_xy = (x1y1 + x2y2) / 2
        wh = x2y2 - x1y1
        return torch.cat((c_xy, wh), dim)  # xywh bbox
    return torch.cat((x1y1, x2y2), dim)  # xyxy bbox



class DFL(nn.Module):
    """
    Integral module of Distribution Focal Loss (DFL).

    Proposed in Generalized Focal Loss https://ieeexplore.ieee.org/document/9792391
    """

    def __init__(self, c1=16):
        """Initialize a convolutional layer with a given number of input channels."""
        super().__init__()
        self.conv = nn.Conv2d(c1, 1, 1, bias=False).requires_grad_(False)
        x = torch.arange(c1, dtype=torch.float)
        self.conv.weight.data[:] = nn.Parameter(x.view(1, c1, 1, 1))
        self.c1 = c1

    def forward(self, x):
        """Applies a transformer layer on input tensor 'x' and returns a tensor."""
        b, c, a = x.shape  # batch, channels, anchors
        return self.conv(x.view(b, 4, self.c1, a).transpose(2, 1).softmax(1)).view(b, 4, a)
        # return self.conv(x.view(b, self.c1, 4, a).softmax(1)).view(b, 4, a)


class Proto(nn.Module):
    """YOLOv8 mask Proto module for segmentation models."""

    def __init__(self, c1, c_=256, c2=32):
        """
        Initializes the YOLOv8 mask Proto module with specified number of protos and masks.

        Input arguments are ch_in, number of protos, number of masks.
        """
        super().__init__()
        self.cv1 = Conv(c1, c_, k=3)
        self.upsample = nn.ConvTranspose2d(c_, c_, 2, 2, 0, bias=True)  # nn.Upsample(scale_factor=2, mode='nearest')
        self.cv2 = Conv(c_, c_, k=3)
        self.cv3 = Conv(c_, c2)

    def forward(self, x):
        """Performs a forward pass through layers using an upsampled input image."""
        return self.cv3(self.cv2(self.upsample(self.cv1(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))

def transI_fusebn(kernel, bn):
    gamma = bn.weight
    std = (bn.running_var + bn.eps).sqrt()
    return kernel * ((gamma / std).reshape(-1, 1, 1, 1)), bn.bias - bn.running_mean * gamma / std


def transII_addbranch(kernels, biases):
    return sum(kernels), sum(biases)


def transIII_1x1_kxk(k1, b1, k2, b2, groups):
    if groups == 1:
        k = F.conv2d(k2, k1.permute(1, 0, 2, 3))  #
        b_hat = (k2 * b1.reshape(1, -1, 1, 1)).sum((1, 2, 3))
    else:
        k_slices = []
        b_slices = []
        k1_T = k1.permute(1, 0, 2, 3)
        k1_group_width = k1.size(0) // groups
        k2_group_width = k2.size(0) // groups
        for g in range(groups):
            k1_T_slice = k1_T[:, g * k1_group_width:(g + 1) * k1_group_width, :, :]
            k2_slice = k2[g * k2_group_width:(g + 1) * k2_group_width, :, :, :]
            k_slices.append(F.conv2d(k2_slice, k1_T_slice))
            b_slices.append(
                (k2_slice * b1[g * k1_group_width:(g + 1) * k1_group_width].reshape(1, -1, 1, 1)).sum((1, 2, 3)))
        k, b_hat = transIV_depthconcat(k_slices, b_slices)
    return k, b_hat + b2


def transIV_depthconcat(kernels, biases):
    return torch.cat(kernels, dim=0), torch.cat(biases)


def transV_avg(channels, kernel_size, groups):
    input_dim = channels // groups
    k = torch.zeros((channels, input_dim, kernel_size, kernel_size))
    k[np.arange(channels), np.tile(np.arange(input_dim), groups), :, :] = 1.0 / kernel_size ** 2
    return k


#   This has not been tested with non-square kernels (kernel.size(2) != kernel.size(3)) nor even-size kernels
def transVI_multiscale(kernel, target_kernel_size):
    H_pixels_to_pad = (target_kernel_size - kernel.size(2)) // 2
    W_pixels_to_pad = (target_kernel_size - kernel.size(3)) // 2
    return F.pad(kernel, [H_pixels_to_pad, H_pixels_to_pad, W_pixels_to_pad, W_pixels_to_pad])


def conv_bn(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1,
            padding_mode='zeros'):
    conv_layer = nn.Conv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size,
                           stride=stride, padding=padding, dilation=dilation, groups=groups,
                           bias=False, padding_mode=padding_mode)
    bn_layer = nn.BatchNorm2d(num_features=out_channels, affine=True)
    se = nn.Sequential()
    se.add_module('conv', conv_layer)
    se.add_module('bn', bn_layer)
    return se


class IdentityBasedConv1x1(nn.Conv2d):
    def __init__(self, channels, groups=1):
        super(IdentityBasedConv1x1, self).__init__(in_channels=channels, out_channels=channels, kernel_size=1, stride=1,
                                                   padding=0, groups=groups, bias=False)

        assert channels % groups == 0
        input_dim = channels // groups
        id_value = np.zeros((channels, input_dim, 1, 1))
        for i in range(channels):
            id_value[i, i % input_dim, 0, 0] = 1
        self.id_tensor = torch.from_numpy(id_value).type_as(self.weight)
        nn.init.zeros_(self.weight)

    def forward(self, input):
        kernel = self.weight + self.id_tensor.to(self.weight.device).type_as(self.weight)
        result = F.conv2d(input, kernel, None, stride=1, padding=0, dilation=self.dilation, groups=self.groups)
        return result

    def get_actual_kernel(self):
        return self.weight + self.id_tensor.to(self.weight.device)


class BNAndPadLayer(nn.Module):
    def __init__(self,
                 pad_pixels,
                 num_features,
                 eps=1e-5,
                 momentum=0.1,
                 affine=True,
                 track_running_stats=True):
        super(BNAndPadLayer, self).__init__()
        self.bn = nn.BatchNorm2d(num_features, eps, momentum, affine, track_running_stats)
        self.pad_pixels = pad_pixels

    def forward(self, input):
        output = self.bn(input)
        if self.pad_pixels > 0:
            if self.bn.affine:
                pad_values = self.bn.bias.detach() - self.bn.running_mean * self.bn.weight.detach() / torch.sqrt(
                    self.bn.running_var + self.bn.eps)
            else:
                pad_values = - self.bn.running_mean / torch.sqrt(self.bn.running_var + self.bn.eps)
            output = F.pad(output, [self.pad_pixels] * 4)
            pad_values = pad_values.view(1, -1, 1, 1)
            output[:, :, 0:self.pad_pixels, :] = pad_values
            output[:, :, -self.pad_pixels:, :] = pad_values
            output[:, :, :, 0:self.pad_pixels] = pad_values
            output[:, :, :, -self.pad_pixels:] = pad_values
        return output

    @property
    def weight(self):
        return self.bn.weight

    @property
    def bias(self):
        return self.bn.bias

    @property
    def running_mean(self):
        return self.bn.running_mean

    @property
    def running_var(self):
        return self.bn.running_var

    @property
    def eps(self):
        return self.bn.eps


class DiverseBranchBlock(nn.Module):
    def __init__(self, in_channels, out_channels, kernel_size,
                 stride=1, padding=None, dilation=1, groups=1,
                 internal_channels_1x1_3x3=None,
                 deploy=False, single_init=False):
        super(DiverseBranchBlock, self).__init__()
        self.deploy = deploy

        self.nonlinear = Conv.default_act

        self.kernel_size = kernel_size
        self.out_channels = out_channels
        self.groups = groups

        if padding is None:
            padding = autopad(kernel_size, padding, dilation)
        assert padding == kernel_size // 2

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

        else:

            self.dbb_origin = conv_bn(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size,
                                      stride=stride, padding=padding, dilation=dilation, groups=groups)

            self.dbb_avg = nn.Sequential()
            if groups < out_channels:
                self.dbb_avg.add_module('conv',
                                        nn.Conv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=1,
                                                  stride=1, padding=0, groups=groups, bias=False))
                self.dbb_avg.add_module('bn', BNAndPadLayer(pad_pixels=padding, num_features=out_channels))
                self.dbb_avg.add_module('avg', nn.AvgPool2d(kernel_size=kernel_size, stride=stride, padding=0))
                self.dbb_1x1 = conv_bn(in_channels=in_channels, out_channels=out_channels, kernel_size=1, stride=stride,
                                       padding=0, groups=groups)
            else:
                self.dbb_avg.add_module('avg', nn.AvgPool2d(kernel_size=kernel_size, stride=stride, padding=padding))

            self.dbb_avg.add_module('avgbn', nn.BatchNorm2d(out_channels))

            if internal_channels_1x1_3x3 is None:
                internal_channels_1x1_3x3 = in_channels if groups < out_channels else 2 * in_channels  # For mobilenet, it is better to have 2X internal channels

            self.dbb_1x1_kxk = nn.Sequential()
            if internal_channels_1x1_3x3 == in_channels:
                self.dbb_1x1_kxk.add_module('idconv1', IdentityBasedConv1x1(channels=in_channels, groups=groups))
            else:
                self.dbb_1x1_kxk.add_module('conv1',
                                            nn.Conv2d(in_channels=in_channels, out_channels=internal_channels_1x1_3x3,
                                                      kernel_size=1, stride=1, padding=0, groups=groups, bias=False))
            self.dbb_1x1_kxk.add_module('bn1', BNAndPadLayer(pad_pixels=padding, num_features=internal_channels_1x1_3x3,
                                                             affine=True))
            self.dbb_1x1_kxk.add_module('conv2',
                                        nn.Conv2d(in_channels=internal_channels_1x1_3x3, out_channels=out_channels,
                                                  kernel_size=kernel_size, stride=stride, padding=0, groups=groups,
                                                  bias=False))
            self.dbb_1x1_kxk.add_module('bn2', nn.BatchNorm2d(out_channels))

        #   The experiments reported in the paper used the default initialization of bn.weight (all as 1). But changing the initialization may be useful in some cases.
        if single_init:
            #   Initialize the bn.weight of dbb_origin as 1 and others as 0. This is not the default setting.
            self.single_init()

    def get_equivalent_kernel_bias(self):
        k_origin, b_origin = transI_fusebn(self.dbb_origin.conv.weight, self.dbb_origin.bn)

        if hasattr(self, 'dbb_1x1'):
            k_1x1, b_1x1 = transI_fusebn(self.dbb_1x1.conv.weight, self.dbb_1x1.bn)
            k_1x1 = transVI_multiscale(k_1x1, self.kernel_size)
        else:
            k_1x1, b_1x1 = 0, 0

        if hasattr(self.dbb_1x1_kxk, 'idconv1'):
            k_1x1_kxk_first = self.dbb_1x1_kxk.idconv1.get_actual_kernel()
        else:
            k_1x1_kxk_first = self.dbb_1x1_kxk.conv1.weight
        k_1x1_kxk_first, b_1x1_kxk_first = transI_fusebn(k_1x1_kxk_first, self.dbb_1x1_kxk.bn1)
        k_1x1_kxk_second, b_1x1_kxk_second = transI_fusebn(self.dbb_1x1_kxk.conv2.weight, self.dbb_1x1_kxk.bn2)
        k_1x1_kxk_merged, b_1x1_kxk_merged = transIII_1x1_kxk(k_1x1_kxk_first, b_1x1_kxk_first, k_1x1_kxk_second,
                                                              b_1x1_kxk_second, groups=self.groups)

        k_avg = transV_avg(self.out_channels, self.kernel_size, self.groups)
        k_1x1_avg_second, b_1x1_avg_second = transI_fusebn(k_avg.to(self.dbb_avg.avgbn.weight.device),
                                                           self.dbb_avg.avgbn)
        if hasattr(self.dbb_avg, 'conv'):
            k_1x1_avg_first, b_1x1_avg_first = transI_fusebn(self.dbb_avg.conv.weight, self.dbb_avg.bn)
            k_1x1_avg_merged, b_1x1_avg_merged = transIII_1x1_kxk(k_1x1_avg_first, b_1x1_avg_first, k_1x1_avg_second,
                                                                  b_1x1_avg_second, groups=self.groups)
        else:
            k_1x1_avg_merged, b_1x1_avg_merged = k_1x1_avg_second, b_1x1_avg_second

        return transII_addbranch((k_origin, k_1x1, k_1x1_kxk_merged, k_1x1_avg_merged),
                                 (b_origin, b_1x1, b_1x1_kxk_merged, b_1x1_avg_merged))

    def switch_to_deploy(self):
        if hasattr(self, 'dbb_reparam'):
            return
        kernel, bias = self.get_equivalent_kernel_bias()
        self.dbb_reparam = nn.Conv2d(in_channels=self.dbb_origin.conv.in_channels,
                                     out_channels=self.dbb_origin.conv.out_channels,
                                     kernel_size=self.dbb_origin.conv.kernel_size, stride=self.dbb_origin.conv.stride,
                                     padding=self.dbb_origin.conv.padding, dilation=self.dbb_origin.conv.dilation,
                                     groups=self.dbb_origin.conv.groups, bias=True)
        self.dbb_reparam.weight.data = kernel
        self.dbb_reparam.bias.data = bias
        for para in self.parameters():
            para.detach_()
        self.__delattr__('dbb_origin')
        self.__delattr__('dbb_avg')
        if hasattr(self, 'dbb_1x1'):
            self.__delattr__('dbb_1x1')
        self.__delattr__('dbb_1x1_kxk')

    def forward(self, inputs):
        if hasattr(self, 'dbb_reparam'):
            return self.nonlinear(self.dbb_reparam(inputs))

        out = self.dbb_origin(inputs)
        if hasattr(self, 'dbb_1x1'):
            out += self.dbb_1x1(inputs)
        out += self.dbb_avg(inputs)
        out += self.dbb_1x1_kxk(inputs)
        return self.nonlinear(out)

    def init_gamma(self, gamma_value):
        if hasattr(self, "dbb_origin"):
            torch.nn.init.constant_(self.dbb_origin.bn.weight, gamma_value)
        if hasattr(self, "dbb_1x1"):
            torch.nn.init.constant_(self.dbb_1x1.bn.weight, gamma_value)
        if hasattr(self, "dbb_avg"):
            torch.nn.init.constant_(self.dbb_avg.avgbn.weight, gamma_value)
        if hasattr(self, "dbb_1x1_kxk"):
            torch.nn.init.constant_(self.dbb_1x1_kxk.bn2.weight, gamma_value)

    def single_init(self):
        self.init_gamma(0.0)
        if hasattr(self, "dbb_origin"):
            torch.nn.init.constant_(self.dbb_origin.bn.weight, 1.0)

2.2 更改init.py文件

关键步骤二：修改modules文件夹下的__init__.py文件，先导入函数

然后在下面的__all__中声明函数

2.3 添加yaml文件

关键步骤三：在/ultralytics/ultralytics/cfg/m

odels/11下面新建文件yolo11_DBB.yaml文件，粘贴下面的内容

目标检测

# 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, DiverseBranchBlock, [128, 3, 2]] # 1-P2/4
  - [-1, 2, C3k2, [256, False, 0.25]]
  - [-1, 1, DiverseBranchBlock, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2, [512, False, 0.25]]
  - [-1, 1, DiverseBranchBlock, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2, [512, True]]
  - [-1, 1, DiverseBranchBlock, [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 (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)

语义分割

# 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, DiverseBranchBlock, [128, 3, 2]] # 1-P2/4
  - [-1, 2, C3k2, [256, False, 0.25]]
  - [-1, 1, DiverseBranchBlock, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2, [512, False, 0.25]]
  - [-1, 1, DiverseBranchBlock, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2, [512, True]]
  - [-1, 1, DiverseBranchBlock, [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 (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, Segment, [nc, 32, 256]] # Segment(P3, P4, P5)

旋转目标检测

# 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, DiverseBranchBlock, [128, 3, 2]] # 1-P2/4
  - [-1, 2, C3k2, [256, False, 0.25]]
  - [-1, 1, DiverseBranchBlock, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2, [512, False, 0.25]]
  - [-1, 1, DiverseBranchBlock, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2, [512, True]]
  - [-1, 1, DiverseBranchBlock, [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 (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, OBB, [nc, 1]] # Detect(P3, P4, P5)

温馨提示：本文只是对yolo11基础上添加模块，如果要对yolo11n/l/m/x进行添加则只需要指定对应的depth_multiple 和 width_multiple。

# YOLO11n
depth_multiple: 0.50  # model depth multiple
width_multiple: 0.25  # layer channel multiple
max_channel：1024
 
# YOLO11s
depth_multiple: 0.50  # model depth multiple
width_multiple: 0.50  # layer channel multiple
max_channel：1024
 
# YOLO11m
depth_multiple: 0.50  # model depth multiple
width_multiple: 1.00  # layer channel multiple
max_channel：512
 
# YOLO11l 
depth_multiple: 1.00  # model depth multiple
width_multiple: 1.00  # layer channel multiple
max_channel：512 
 
# YOLO11x
depth_multiple: 1.00  # model depth multiple
width_multiple: 1.50 # layer channel multiple
max_channel：512

2.4 在task.py中进行注册

关键步骤四：在task.py的parse_model函数中进行注册，

先在task.py导入函数

然后在task.py文件下找到parse_model这个函数，如下图，添加DBB

2.5 执行程序

关键步骤五：在ultralytics文件中新建train.py，将model的参数路径设置为yolo11_DBB.yaml的路径即可

from ultralytics import YOLO
import warnings
warnings.filterwarnings('ignore')
from pathlib import Path
 
if __name__ == '__main__':
 
 
    # 加载模型
    model = YOLO("ultralytics/cfg/11/yolo11.yaml")  # 你要选择的模型yaml文件地址
    # Use the model
    results = model.train(data=r"你的数据集的yaml文件地址",
                          epochs=100, batch=16, imgsz=640, workers=4, name=Path(model.cfg).stem)  # 训练模型

🚀运行程序，如果出现下面的内容则说明添加成功🚀

                   from  n    params  module                                       arguments
  0                  -1  1       464  ultralytics.nn.modules.conv.Conv             [3, 16, 3, 2]
  1                  -1  1     10848  ultralytics.nn.modules.block.DiverseBranchBlock[16, 32, 3, 2]
  2                  -1  1      6640  ultralytics.nn.modules.block.C3k2            [32, 64, 1, False, 0.25]      
  3                  -1  1     86784  ultralytics.nn.modules.block.DiverseBranchBlock[64, 64, 3, 2]
  4                  -1  1     26080  ultralytics.nn.modules.block.C3k2            [64, 128, 1, False, 0.25]     
  5                  -1  1    345600  ultralytics.nn.modules.block.DiverseBranchBlock[128, 128, 3, 2]
  6                  -1  1     87040  ultralytics.nn.modules.block.C3k2            [128, 128, 1, True]
  7                  -1  1    674560  ultralytics.nn.modules.block.DiverseBranchBlock[128, 256, 3, 2]
  8                  -1  1    346112  ultralytics.nn.modules.block.C3k2            [256, 256, 1, True]
  9                  -1  1    164608  ultralytics.nn.modules.block.SPPF            [256, 256, 5]
 10                  -1  1    249728  ultralytics.nn.modules.block.C2PSA           [256, 256, 1]
 11                  -1  1         0  torch.nn.modules.upsampling.Upsample         [None, 2, 'nearest']
 12             [-1, 6]  1         0  ultralytics.nn.modules.conv.Concat           [1]
 13                  -1  1    111296  ultralytics.nn.modules.block.C3k2            [384, 128, 1, False]
 14                  -1  1         0  torch.nn.modules.upsampling.Upsample         [None, 2, 'nearest']
 15             [-1, 4]  1         0  ultralytics.nn.modules.conv.Concat           [1]
 16                  -1  1     32096  ultralytics.nn.modules.block.C3k2            [256, 64, 1, False]
 17                  -1  1     36992  ultralytics.nn.modules.conv.Conv             [64, 64, 3, 2]
 18            [-1, 13]  1         0  ultralytics.nn.modules.conv.Concat           [1]
 19                  -1  1     86720  ultralytics.nn.modules.block.C3k2            [192, 128, 1, False]
 20                  -1  1    147712  ultralytics.nn.modules.conv.Conv             [128, 128, 3, 2]
 21            [-1, 10]  1         0  ultralytics.nn.modules.conv.Concat           [1]
 22                  -1  1    378880  ultralytics.nn.modules.block.C3k2            [384, 256, 1, True]
 23        [16, 19, 22]  1    464912  ultralytics.nn.modules.head.Detect           [80, [64, 128, 256]]
YOLO11_DBB summary: 384 layers, 3,257,072 parameters, 3,257,056 gradients, 8.9 GFLOPs

3.修改后的网络结构图

4. 完整代码分享

这个后期补充吧~，先按照步骤来即可

5. GFLOPs

关于GFLOPs的计算方式可以查看：百面算法工程师 | 卷积基础知识——Convolution

未改进的YOLO11n GFLOPs

改进后的GFLOPs

6. 进阶

可以与其他的注意力机制或者损失函数等结合，进一步提升检测效果

7.总结

通过以上的改进方法，我们成功提升了模型的表现。这只是一个开始，未来还有更多优化和技术深挖的空间。在这里，我想隆重向大家推荐我的专栏——《YOLO11改进有效涨点》。这个专栏专注于前沿的深度学习技术，特别是目标检测领域的最新进展，不仅包含对YOLO11的深入解析和改进策略，还会定期更新来自各大顶会（如CVPR、NeurIPS等）的论文复现和实战分享。