YOLOv11改进 | 卷积模块 | 分布移位卷积DSConv替换Conv

news/2024/10/5 14:25:41 标签: YOLO, 人工智能, 深度学习, 面试, 目标检测, YOLO11, python

秋招面试专栏推荐 ：深度学习算法工程师面试问题总结【百面算法工程师】——点击即可跳转 

💡💡💡本专栏所有程序均经过测试，可成功执行💡💡💡

本文介绍DSConv， DSConv 将传统的卷积核分解为两个组件：可变量化核 (VQK) 和分布偏移。通过在 VQK 中仅存储整数值来实现更低的内存使用和更高的速度，同时通过应用基于内核和通道的分布偏移来保留与原始卷积相同的输出。通过将浮点运算替换为整数运算，将卷积核中的内存使用量减少了 14 倍，并将运算速度提高了 10 倍。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

目录

 1. 论文

2. 代码实现

YOLOv8%E4%BB%A3%E7%A0%81%E4%B8%AD-toc" style="margin-left:40px;">2.1 添加DSConv到YOLOv11代码中

2.2 更改init.py文件

2.3 新增yaml文件

2.4 在task.py中进行注册

2.5 执行程序

3.修改后的网络结构图

4. 完整代码分享

5. GFLOPs

6. 进阶

7.总结

 1. 论文

论文地址：DSConv: Efficient Convolution Operator——点击即可跳转

官方代码：官方代码仓库——点击即可跳转

2. 代码实现

YOLOv8%E4%BB%A3%E7%A0%81%E4%B8%AD">2.1 添加DSConv到YOLOv11代码中

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

python">from torch.nn.modules.conv import _ConvNd
from torch.nn.modules.utils import _pair

class DSConv(_ConvNd):
    def __init__(self, in_channels, out_channels, kernel_size, stride=1,
                 padding=None, dilation=1, groups=1, padding_mode='zeros', bias=False, block_size=32, KDSBias=False,
                 CDS=False):
        padding = _pair(autopad(kernel_size, padding, dilation))
        kernel_size = _pair(kernel_size)
        stride = _pair(stride)
        dilation = _pair(dilation)

        blck_numb = math.ceil((in_channels / (block_size * groups)))
        super(DSConv, self).__init__(
            in_channels, out_channels, kernel_size, stride, padding, dilation,
            False, _pair(0), groups, bias, padding_mode)

        # KDS weight From Paper
        self.intweight = torch.Tensor(out_channels, in_channels, *kernel_size)
        self.alpha = torch.Tensor(out_channels, blck_numb, *kernel_size)

        # KDS bias From Paper
        self.KDSBias = KDSBias
        self.CDS = CDS

        if KDSBias:
            self.KDSb = torch.Tensor(out_channels, blck_numb, *kernel_size)
        if CDS:
            self.CDSw = torch.Tensor(out_channels)
            self.CDSb = torch.Tensor(out_channels)

        self.reset_parameters()

    def get_weight_res(self):
        # Include expansion of alpha and multiplication with weights to include in the convolution layer here
        alpha_res = torch.zeros(self.weight.shape).to(self.alpha.device)

        # Include KDSBias
        if self.KDSBias:
            KDSBias_res = torch.zeros(self.weight.shape).to(self.alpha.device)

        # Handy definitions:
        nmb_blocks = self.alpha.shape[1]
        total_depth = self.weight.shape[1]
        bs = total_depth // nmb_blocks

        llb = total_depth - (nmb_blocks - 1) * bs

        # Casting the Alpha values as same tensor shape as weight
        for i in range(nmb_blocks):
            length_blk = llb if i == nmb_blocks - 1 else bs

            shp = self.alpha.shape  # Notice this is the same shape for the bias as well
            to_repeat = self.alpha[:, i, ...].view(shp[0], 1, shp[2], shp[3]).clone()
            repeated = to_repeat.expand(shp[0], length_blk, shp[2], shp[3]).clone()
            alpha_res[:, i * bs:(i * bs + length_blk), ...] = repeated.clone()

            if self.KDSBias:
                to_repeat = self.KDSb[:, i, ...].view(shp[0], 1, shp[2], shp[3]).clone()
                repeated = to_repeat.expand(shp[0], length_blk, shp[2], shp[3]).clone()
                KDSBias_res[:, i * bs:(i * bs + length_blk), ...] = repeated.clone()

        if self.CDS:
            to_repeat = self.CDSw.view(-1, 1, 1, 1)
            repeated = to_repeat.expand_as(self.weight)
            print(repeated.shape)

        # Element-wise multiplication of alpha and weight
        weight_res = torch.mul(alpha_res, self.weight)
        if self.KDSBias:
            weight_res = torch.add(weight_res, KDSBias_res)
        return weight_res

    def forward(self, input):
        # Get resulting weight
        # weight_res = self.get_weight_res()

        # Returning convolution
        return F.conv2d(input, self.weight, self.bias,
                        self.stride, self.padding, self.dilation,
                        self.groups)


class DSConv2D(Conv):
    def __init__(self, inc, ouc, k=1, s=1, p=None, g=1, d=1, act=True):
        super().__init__(inc, ouc, k, s, p, g, d, act)
        self.conv = DSConv(inc, ouc, k, s, p, g, d)

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 新增yaml文件

关键步骤三：在 \ultralytics\ultralytics\cfg\models\11下新建文件 yolo11_DSConv.yaml并将下面代码复制进去

python"># 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, DSConv2D, [64, 3, 2]] # 0-P1/2
  - [-1, 1, DSConv2D, [128, 3, 2]] # 1-P2/4
  - [-1, 2, C3k2, [256, False, 0.25]]
  - [-1, 1, DSConv2D, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2, [512, False, 0.25]]
  - [-1, 1, DSConv2D, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2, [512, True]]
  - [-1, 1, DSConv2D, [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, DSConv2D, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)

  - [-1, 1, DSConv2D, [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
python"># 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, DSConv2D, [64, 3, 2]] # 0-P1/2
  - [-1, 1, DSConv2D, [128, 3, 2]] # 1-P2/4
  - [-1, 2, C3k2, [256, False, 0.25]]
  - [-1, 1, DSConv2D, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2, [512, False, 0.25]]
  - [-1, 1, DSConv2D, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2, [512, True]]
  - [-1, 1, DSConv2D, [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, DSConv2D, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)

  - [-1, 1, DSConv2D, [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]] # Detect(P3, P4, P5)

python"># 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, DSConv2D, [64, 3, 2]] # 0-P1/2
  - [-1, 1, DSConv2D, [128, 3, 2]] # 1-P2/4
  - [-1, 2, C3k2, [256, False, 0.25]]
  - [-1, 1, DSConv2D, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2, [512, False, 0.25]]
  - [-1, 1, DSConv2D, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2, [512, True]]
  - [-1, 1, DSConv2D, [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, DSConv2D, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)

  - [-1, 1, DSConv2D, [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。 

python"># 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DSConv

2.5 执行程序

在train.py中，将model的参数路径设置为yolo11_DSConv.yaml的路径

建议大家写绝对路径，确保一定能找到

python">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🚀 

python">                   from  n    params  module                                       arguments
  0                  -1  1       464  ultralytics.nn.modules.conv.DSConv2D         [3, 16, 3, 2]
  1                  -1  1      4672  ultralytics.nn.modules.conv.DSConv2D         [16, 32, 3, 2]
  2                  -1  1      6640  ultralytics.nn.modules.block.C3k2            [32, 64, 1, False, 0.25]
  3                  -1  1     36992  ultralytics.nn.modules.conv.DSConv2D         [64, 64, 3, 2]
  4                  -1  1     26080  ultralytics.nn.modules.block.C3k2            [64, 128, 1, False, 0.25]
  5                  -1  1    147712  ultralytics.nn.modules.conv.DSConv2D         [128, 128, 3, 2]
  6                  -1  1     87040  ultralytics.nn.modules.block.C3k2            [128, 128, 1, True]
  7                  -1  1    295424  ultralytics.nn.modules.conv.DSConv2D         [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.DSConv2D         [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.DSConv2D         [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_DSConv2D summary: 319 layers, 2,624,080 parameters, 2,624,064 gradients, 4.9 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

通过上面的方法，改进就完成且成功了。在这里给大家推荐我的专栏YOLO11改进有效涨点专栏，本专栏目前是新建的，后期我会持续对各种前沿顶会进行论文复现，如果本文对你有帮助，欢迎订阅本专栏，关注后续更多的更新~如果有问题，可以随时问我


http://www.niftyadmin.cn/n/5690998.html

相关文章

过滤器Filter【详解】

过滤器Filter【详解】

过滤器Filter 1、 现有问题 在以往的Servlet中，有冗余的代码，多个Servlet都有重复的代码 比如编码格式设置 登录信息认证 2、 概念 过滤器（Filter）是处于客户端与服务器目标资源之间的一道过滤技术。 过滤器 3、 过滤器作用 执…
阅读更多...
自然常数e的定义

自然常数e的定义

参考： 自然常数e到底自然在哪？What is the Number e? 自然常数e的公式定义如下： e lim ⁡ n → ∞ ( 1 1 n ) n e \lim_{n \to \infty} \left(1 \frac{1}{n}\right)^n en→∞lim​(1n1​)n 可以用银行利息的复利来理解这个公式。举个例…
阅读更多...
SVG 简介

SVG 简介

SVG 简介 SVG（可缩放矢量图形）是一种基于XML的图像格式，用于在网页上创建二维图形。与传统的位图图像（如JPG或PNG）不同，SVG图像由直线、曲线、点和多边形等几何形状组成，这些形状可以通过数学方程来描述，因此可以无限放大而不失真。SVG格式由万维网联盟（W3C）制定，并…
阅读更多...
解决Python使用Selenium 时遇到网页 ＜body＞ 划不动的问题

解决Python使用Selenium 时遇到网页 ＜body＞ 划不动的问题

如果在使用 Selenium 时遇到网页的 <body> 划不动的问题&#xff0c;这通常是因为页面的滚动机制&#xff08;例如&#xff0c;可能使用了一个具有固定高度的容器或自定义的滚动条&#xff09;导致无法通过简单的 JavaScript 实现滚动。可以通过以下方法来解决该问题。 …
阅读更多...
大学生就业与招聘：Spring Boot系统设计

大学生就业与招聘：Spring Boot系统设计

1系统概述 1.1 研究背景 如今互联网高速发展&#xff0c;网络遍布全球&#xff0c;通过互联网发布的消息能快而方便的传播到世界每个角落&#xff0c;并且互联网上能传播的信息也很广&#xff0c;比如文字、图片、声音、视频等。从而&#xff0c;这种种好处使得互联网成了信息传…
阅读更多...
Qt系统学习篇（6）-QMainWindow

Qt系统学习篇（6）-QMainWindow

QMainWindow是一个为用户提供主窗口程序的类&#xff0c;包含一个菜单栏(menu bar)、多个工具栏(tool bars)、多个锚接部件(dock widgets)、一个状态栏(status bar)及一个中心部件(central widget)&#xff0c;是许多应用程序的基础&#xff0c;如文本编辑器&#xff0c;图片编…
阅读更多...
JAVA实现大写金额转小写金额

JAVA实现大写金额转小写金额

在金融行业中经常需要把大写金额转成小写金额&#xff0c;之前在一次开发中有个类似的需求&#xff0c;翻阅了好多博文&#xff0c;都没找到合适的&#xff0c;故没办法&#xff0c;就花了点时间研究并实现! 实现代码如下: private static final Character ZERO 零;private s…
阅读更多...
LabVIEW裂纹深度在线监测系统

LabVIEW裂纹深度在线监测系统

随着铁路运输技术的快速发展&#xff0c;火车安全问题成为重中之重&#xff0c;尤其是轮面裂纹的检测和管理。裂纹的出现可能导致严重的列车事故&#xff0c;因此&#xff0c;建立可靠的在线监测系统&#xff0c;实时掌握裂纹情况&#xff0c;对保障铁路运输安全至关重要。 La…
阅读更多...
最新文章

Copyright @ 2022~2023