【YOLOv8改进 - 卷积Conv】DCNv2：可变形卷积，显式和隐式特征交互学习

YOLO大师

已于 2024-07-24 23:46:42 修改

阅读量361

点赞数 7

文章标签： YOLO 学习 yolov8

于 2024-07-24 23:46:29 首次发布

原创文章，禁止任何形式转载！

本文链接：https://blog.csdn.net/shangyanaf/article/details/140676011

版权

YOLOv8目标检测创新改进与实战案例专栏

专栏目录： YOLOv8有效改进系列及项目实战目录包含卷积，主干注意力，检测头等创新机制以及各种目标检测分割项目实战案例

专栏链接: YOLOv8基础解析+创新改进+实战案例

介绍

摘要

学习有效的特征交叉是构建推荐系统的关键。然而，稀疏且庞大的特征空间需要进行穷举搜索以识别有效的交叉。深度与交叉网络（DCN）被提出以自动且高效地学习有界度的预测性特征交互。不幸的是，在处理数十亿训练示例的大规模网络流量的模型中，DCN 在交叉网络方面表现出有限的表达能力，无法学习更多预测性的特征交互。尽管在这方面取得了显著的研究进展，许多生产中的深度学习模型仍然依赖传统的前馈神经网络来低效地学习特征交叉。

鉴于 DCN 和现有特征交互学习方法的优缺点，我们提出了改进框架 DCN-V2，以使 DCN 在大规模工业环境中更加实用。在进行广泛的超参数搜索和模型调优的综合实验研究中，我们观察到 DCN-V2 方法在流行的基准数据集上表现优于所有最先进的算法。改进后的 DCN-V2 更具表达力，但在特征交互学习方面仍然保持成本效益，特别是在与低秩架构混合使用时。DCN-V2 简单易用，可以轻松作为构建模块，并且在 Google 的许多大规模网页排序系统中显著提高了离线准确性和在线业务指标。

文章链接

论文地址：论文地址

**代码地址：**代码地址

基本原理

核心代码

下载YoloV8代码

直接下载

GitHub地址

Git Clone

git clone https://github.com/ultralytics/ultralytics

安装环境

进入代码根目录并安装依赖。

pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple

在最新版本中，官方已经废弃了requirements.txt文件，转而将所有必要的代码和依赖整合进了ultralytics包中。因此，用户只需安装这个单一的ultralytics库，就能获得所需的全部功能和环境依赖。

pip install ultralytics

引入代码

在根目录下的ultralytics/nn/目录，新建一个 conv目录，然后新建一个以 DCNv2为文件名的py文件，把代码拷贝进去。

import torch
import torch.nn.functional as F
import torch.nn as nn
import math
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):
        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):
        return self.act(self.bn(self.conv(x)))
 
    def forward_fuse(self, x):
        return self.act(self.conv(x))
 
 

class DCNv2(nn.Module):
    def __init__(self, in_channels, out_channels, kernel_size, stride=1,
                 padding=1, dilation=1, groups=1, deformable_groups=1):
        super(DCNv2, self).__init__()

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

        self.weight = nn.Parameter(
            torch.empty(out_channels, in_channels, *self.kernel_size)
        )
        self.bias = nn.Parameter(torch.empty(out_channels))

        out_channels_offset_mask = (self.deformable_groups * 3 *
                                    self.kernel_size[0] * self.kernel_size[1])
        self.conv_offset_mask = nn.Conv2d(
            self.in_channels,
            out_channels_offset_mask,
            kernel_size=self.kernel_size,
            stride=self.stride,
            padding=self.padding,
            bias=True,
        )
        self.bn = nn.BatchNorm2d(out_channels)
        self.act = Conv.default_act
        self.reset_parameters()

    def forward(self, x):
        offset_mask = self.conv_offset_mask(x)
        o1, o2, mask = torch.chunk(offset_mask, 3, dim=1)
        offset = torch.cat((o1, o2), dim=1)
        mask = torch.sigmoid(mask)
        x = torch.ops.torchvision.deform_conv2d(
            x,
            self.weight,
            offset,
            mask,
            self.bias,
            self.stride[0], self.stride[1],
            self.padding[0], self.padding[1],
            self.dilation[0], self.dilation[1],
            self.groups,
            self.deformable_groups,
            True
        )
        x = self.bn(x)
        x = self.act(x)
        return x

    def reset_parameters(self):
        n = self.in_channels
        for k in self.kernel_size:
            n *= k
        std = 1. / math.sqrt(n)
        self.weight.data.uniform_(-std, std)
        self.bias.data.zero_()
        self.conv_offset_mask.weight.data.zero_()
        self.conv_offset_mask.bias.data.zero_()

class Bottleneck_DCNv2(nn.Module):
 
    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
        if k[0] == 3:
            self.cv1 = DCNv2(c1, c_, k[0], 1)
        else:
            self.cv1 = Conv(c1, c_, k[0], 1)
        if k[1] == 3:
            self.cv2 = DCNv2(c_, c2, k[1], 1, groups=g)
        else:
            self.cv2 = Conv(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 C2f_DCNv2(nn.Module):
 
    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_DCNv2(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).split((self.c, self.c), 1))
        y.extend(m(y[-1]) for m in self.m)
        return self.cv2(torch.cat(y, 1))

注册

在ultralytics/nn/tasks.py中进行如下操作：

步骤1:

from ultralytics.nn.conv.DCNv2  import C2f_DCNv2

步骤2

修改def parse_model(d, ch, verbose=True):

C2f_DCNv2

配置yolov8_DCNv2.yaml

ultralytics/ultralytics/cfg/models/v8/yolov8_DCNv2.yaml

# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8 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=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


# YOLOv8.0s 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_DCNv2, [256, True]]
  - [-1, 1, Conv, [512, 3, 2]]  # 5-P4/16
  - [-1, 6, C2f_DCNv2, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]]  # 7-P5/32
  - [-1, 3, C2f_DCNv2, [1024, True]]
  - [-1, 1, SPPF, [1024, 5]]  # 9

# YOLOv8.0s head
head:
  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
  - [[-1, 6], 1, Concat, [1]]  # cat backbone P4
  - [-1, 3, C2f, [512]]  # 12

  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
  - [[-1, 4], 1, Concat, [1]]  # cat backbone P3
  - [-1, 3, C2f, [256]]  # 15 (P3/8-small)

  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 12], 1, Concat, [1]]  # cat head P4
  - [-1, 3, C2f, [512]]  # 18 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 9], 1, Concat, [1]]  # cat head P5
  - [-1, 3, C2f, [1024]]  # 21 (P5/32-large)

  - [[15, 18, 21], 1, Detect, [nc]]  # Detect(P3, P4, P5)

实验

脚本


import os
from ultralytics import YOLO
 
yaml = 'ultralytics/cfg/models/v8/yolov8_DCNv2.yaml'

 
model = YOLO(yaml) 
 
model.info()
if __name__ == "__main__":
   
    results = model.train(data='coco128.yaml',
                          name='yolov8_DCNv2',
                          epochs=10, 
                          workers=8, 
                          batch=1)