爆改YOLOv8|利用DCNv3改进yolov8,暴力涨点，即插即用

1，本文介绍

DCNv3（Deformable Convolutional Networks v3）是对传统卷积神经网络的扩展，旨在提高特征提取的灵活性和精度。它通过引入可变形卷积，使卷积核能够适应不同的形状和尺度，从而更好地捕捉图像中的非刚性物体和复杂结构。DCNv3 在每个卷积层中通过学习自适应的采样位置来增强卷积核的适应能力，进而提高了对物体形变的鲁棒性和网络的表达能力。这种方法在图像检测和分割任务中表现优异。

关于DCNv3的详细介绍可以看论文：http://xxx.itp.ac.cn/pdf/1904.11490v2

本文将讲解如何将DCNv3融合进yolov8

话不多说，上代码！

2， 将DCNv3融合进yolov8

2.1 步骤一

找到如下的目录'ultralytics/nn/modules'，然后在这个目录下创建一个DCNv3.py文件，文件名字可以根据你自己的习惯起，然后将DCNv3的核心代码复制进去

###################### DCNV3  ####     start#############################
 
from ultralytics.nn.ops_dcnv3.modules import DCNv3
 
class DCNV3_YoLo(nn.Module):
    def __init__(self, inc, ouc, k=1, s=1, p=None, g=1, d=1, act=True):
        super().__init__()
 
        self.conv = Conv(inc, ouc, k=1)
        self.dcnv3 = DCNv3(ouc, kernel_size=k, stride=s, group=g, dilation=d)
        self.bn = nn.BatchNorm2d(ouc)
        self.act = Conv.default_act
 
    def forward(self, x):
        x = self.conv(x)
        x = x.permute(0, 2, 3, 1)
        x = self.dcnv3(x)
        x = x.permute(0, 3, 1, 2)
        x = self.act(self.bn(x))
        return x
 
class Bottleneck_DCNV3(nn.Module):
    # Standard bottleneck
    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 = DCNV3_YoLo(c_, c2, k[1], 1, g=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 DCNV3(nn.Module):
    # CSP Bottleneck with 2 convolutions
    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
        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_DCNV3(self.c, self.c, shortcut, g, k=(3, 3), e=1.0) for _ in range(n))
 
    def forward(self, x):
        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):
        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))
 
###################### DCNV3  ####     end#############################

2.2 步骤二

在task.py导入我们的模块

2.3 步骤三

在task.py的parse_model方法里面注册我们的模块

注意，共需要在二个位置进行添加

到此注册成功,复制后面的yaml文件直接运行即可

yaml文件

# Ultralytics YOLO 🚀, GPL-3.0 license
# YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
 
# Parameters
nc: 1  # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.33, 0.25, 1024]  # YOLOv8n summary: 225 layers,  3157200 parameters,  3157184 gradients,   8.9 GFLOPs
  s: [0.33, 0.50, 1024]  # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients,  28.8 GFLOPs
  m: [0.67, 0.75, 768]   # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients,  79.3 GFLOPs
  l: [1.00, 1.00, 512]   # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
  x: [1.00, 1.25, 512]   # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs
 
# YOLOv8.0n 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, 3, C2f, [128, True]]
  - [-1, 1, Conv, [256, 3, 2]]  # 3-P3/8
  - [-1, 6, C2f, [256, True]]
  - [-1, 1, Conv, [512, 3, 2]]  # 5-P4/16
  - [-1, 6, C2f, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]]  # 7-P5/32
  - [-1, 3, C2f, [1024, True]]
  - [-1, 1, SPPF, [1024, 5]]  # 9
 
# YOLOv8.0n head
head:
  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
  - [[-1, 6], 1, Concat, [1]]  # cat backbone P4
  - [-1, 3, DCNV3, [512]]  # 12
 
  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
  - [[-1, 4], 1, Concat, [1]]  # cat backbone P3
  - [-1, 3, DCNV3, [256]]  # 15 (P3/8-small)
 
  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 12], 1, Concat, [1]]  # cat head P4
  - [-1, 3, DCNV3, [512]]  # 18 (P4/16-medium)
 
  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 9], 1, Concat, [1]]  # cat head P5
  - [-1, 3, DCNV3, [1024]]  # 21 (P5/32-large)
 
  - [[15, 18, 21], 1, Detect, [nc]]  # Detect(P3, P4, P5)

# 这篇文章的改进可以与上一篇文章BiFormer的改进进行组合

爆改YOLOv8|利用BiFormer改进yolov8,暴力涨点-CSDN博客

不知不觉已经看完了哦，动动小手留个点赞吧--_--