YOLOv11改进 | Conv篇 | 重参数化多元分支模块DiverseBranchBlock二次创新C3k2（有效涨点，重参数化模块高效推理）

​

​

​

​

import torch
import torch.nn as nn
import torch.nn.functional as F
import numpy as np
 
 
__all__ = ['DiverseBranchBlock', 'C3k2_DBB_backbone', 'C3k2_DBB_neck']
 
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)
 
 
 
class Bottleneck_DBB(nn.Module):
    # Standard bottleneck with DCN
    def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5):  # ch_in, ch_out, shortcut, groups, kernels, expand
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
 
        self.cv1 = Conv(c1, c_, k[0], 1)
        self.cv2 = DiverseBranchBlock(c_, c2, 3, stride=1, groups=g)
        self.add = shortcut and c1 == c2
 
    def forward(self, x):
        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
 
 
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 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 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_DBB(c_, c_, shortcut, g, k=(k, k), e=1.0) for _ in range(n)))
 
class C3k2_DBB_backbone(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_DBB(self.c, self.c, shortcut, g) for _ in range(n)
        )
 
 
class C3k2_DBB_neck(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)
        )
 
 
 
 
 
if __name__ == "__main__":
    # Generating Sample image
    image_size = (1, 64, 224, 224)
    image = torch.rand(*image_size)
 
    # Model
    model = C3k2_DBB_backbone(64, 64)
 
    out = model(image)
    print(out.size())

​

​

# 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_DBB_backbone, [256, False, 0.25]]
  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2_DBB_backbone, [512, False, 0.25]]
  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2_DBB_backbone, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
  - [-1, 2, C3k2_DBB_backbone, [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_DBB_backbone, [512, False]] # 13
 
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
  - [-1, 2, C3k2_DBB_backbone, [256, False]] # 16 (P3/8-small)
 
  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2_DBB_backbone, [512, False]] # 19 (P4/16-medium)
 
  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 10], 1, Concat, [1]] # cat head P5
  - [-1, 2, C3k2_DBB_backbone, [1024, True]] # 22 (P5/32-large)
 
  - [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)

# 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_DBB_neck, [256, False, 0.25]]
  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2_DBB_neck, [512, False, 0.25]]
  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2_DBB_neck, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
  - [-1, 2, C3k2_DBB_neck, [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_DBB_neck, [512, False]] # 13
 
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
  - [-1, 2, C3k2_DBB_neck, [256, False]] # 16 (P3/8-small)
 
  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2_DBB_neck, [512, False]] # 19 (P4/16-medium)
 
  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 10], 1, Concat, [1]] # cat head P5
  - [-1, 2, C3k2_DBB_neck, [1024, True]] # 22 (P5/32-large)
 
  - [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)

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