YOLOv8改进 | Conv篇 | YOLOv8引入SCConv模块

1. SCConv介绍

摘要：卷积神经网络（CNN）在各种计算机视觉任务中取得了显着的性能，但这是以巨大的计算资源为代价的，部分原因是卷积层提取了冗余特征。 最近的工作要么压缩训练有素的大型模型，要么探索精心设计的轻量级模型。 在本文中，我们尝试利用特征之间的空间和通道冗余进行 CNN 压缩，并提出一种高效的卷积模块，称为 SCConv（空间和通道重建卷积），以减少冗余计算并促进代表性特征学习。 所提出的 SCConv 由两个单元组成：空间重建单元（SRU）和通道重建单元（CRU）。 SRU采用分离重建方法来抑制空间冗余，而CRU采用分割-变换-融合策略来减少通道冗余。 此外，SCConv是一个即插即用的架构单元，可以直接用来替换各种卷积神经网络中的标准卷积。 实验结果表明，SCConv嵌入模型能够通过减少冗余特征来实现更好的性能，同时显着降低复杂度和计算成本。

官方论文地址：SCConv官方论文地址

官方代码地址：SCConv官方代码地址

SCConv模块结构图:

2.核心代码

import torch
import torch.nn.functional as F
import torch.nn as nn


class GroupBatchnorm2d(nn.Module):
    def __init__(self, c_num: int,
                 group_num: int = 16,
                 eps: float = 1e-10
                 ):
        super(GroupBatchnorm2d, self).__init__()
        assert c_num >= group_num
        self.group_num = group_num
        self.weight = nn.Parameter(torch.randn(c_num, 1, 1))
        self.bias = nn.Parameter(torch.zeros(c_num, 1, 1))
        self.eps = eps

    def forward(self, x):
        N, C, H, W = x.size()
        x = x.view(N, self.group_num, -1)
        mean = x.mean(dim=2, keepdim=True)
        std = x.std(dim=2, keepdim=True)
        x = (x - mean) / (std + self.eps)
        x = x.view(N, C, H, W)
        return x * self.weight + self.bias


class SRU(nn.Module):
    def __init__(self,
                 oup_channels: int,
                 group_num: int = 16,
                 gate_treshold: float = 0.5,
                 torch_gn: bool = True
                 ):
        super().__init__()

        self.gn = nn.GroupNorm(num_channels=oup_channels, num_groups=group_num) if torch_gn else GroupBatchnorm2d(
            c_num=oup_channels, group_num=group_num)
        self.gate_treshold = gate_treshold
        self.sigomid = nn.Sigmoid()

    def forward(self, x):
        gn_x = self.gn(x)
        w_gamma = self.gn.weight / sum(self.gn.weight)
        w_gamma = w_gamma.view(1, -1, 1, 1)
        reweigts = self.sigomid(gn_x * w_gamma)
        # Gate
        w1 = torch.where(reweigts > self.gate_treshold, torch.ones_like(reweigts), reweigts)
        w2 = torch.where(reweigts > self.gate_treshold, torch.zeros_like(reweigts), reweigts)
        x_1 = w1 * x
        x_2 = w2 * x
        y = self.reconstruct(x_1, x_2)
        return y

    def reconstruct(self, x_1, x_2):
        x_11, x_12 = torch.split(x_1, x_1.size(1) // 2, dim=1)
        x_21, x_22 = torch.split(x_2, x_2.size(1) // 2, dim=1)
        return torch.cat([x_11 + x_22, x_12 + x_21], dim=1)


class CRU(nn.Module):
    def __init__(self,
                 op_channel: int,
                 alpha: float = 1 / 2,
                 squeeze_radio: int = 2,
                 group_size: int = 2,
                 group_kernel_size: int = 3,
                 ):
        super().__init__()
        self.up_channel = up_channel = int(alpha * op_channel)
        self.low_channel = low_channel = op_channel - up_channel
        self.squeeze1 = nn.Conv2d(up_channel, up_channel // squeeze_radio, kernel_size=1, bias=False)
        self.squeeze2 = nn.Conv2d(low_channel, low_channel // squeeze_radio, kernel_size=1, bias=False)
        # up
        self.GWC = nn.Conv2d(up_channel // squeeze_radio, op_channel, kernel_size=group_kernel_size, stride=1,
                             padding=group_kernel_size // 2, groups=group_size)
        self.PWC1 = nn.Conv2d(up_channel // squeeze_radio, op_channel, kernel_size=1, bias=False)
        # low
        self.PWC2 = nn.Conv2d(low_channel // squeeze_radio, op_channel - low_channel // squeeze_radio, kernel_size=1,
                              bias=False)
        self.advavg = nn.AdaptiveAvgPool2d(1)

    def forward(self, x):
        # Split
        up, low = torch.split(x, [self.up_channel, self.low_channel], dim=1)
        up, low = self.squeeze1(up), self.squeeze2(low)
        # Transform
        Y1 = self.GWC(up) + self.PWC1(up)
        Y2 = torch.cat([self.PWC2(low), low], dim=1)
        # Fuse
        out = torch.cat([Y1, Y2], dim=1)
        out = F.softmax(self.advavg(out), dim=1) * out
        out1, out2 = torch.split(out, out.size(1) // 2, dim=1)
        return out1 + out2


def autopad(k, p=None, d=1):
    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):
    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 Bottleneck_SCConv(nn.Module):

    def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5):
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, k[0], 1)
        self.cv2 = SCConv(c_)
        self.add = shortcut and c1 == c2

    def forward(self, x):
        """'forward()' 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_SCConv(nn.Module):
    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):
        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_SCConv(self.c, self.c, shortcut, g, k=((3, 3), (3, 3)), e=1.0) for _ in range(n))

    def forward(self, x):
        x = self.cv1(x)
        x = x.chunk(2, 1)
        y = list(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))


class SCConv(nn.Module):
    def __init__(self,
                 op_channel: int,
                 group_num: int = 4,
                 gate_treshold: float = 0.5,
                 alpha: float = 1 / 2,
                 squeeze_radio: int = 2,
                 group_size: int = 2,
                 group_kernel_size: int = 3,
                 ):
        super().__init__()
        self.SRU = SRU(op_channel,
                       group_num=group_num,
                       gate_treshold=gate_treshold)
        self.CRU = CRU(op_channel,
                       alpha=alpha,
                       squeeze_radio=squeeze_radio,
                       group_size=group_size,
                       group_kernel_size=group_kernel_size)

    def forward(self, x):
        x = self.SRU(x)
        x = self.CRU(x)
        return x


if __name__ == '__main__':
    x = torch.randn(1, 32, 16, 16)
    model = SCConv(32)
    print(model(x).shape)

3.YOLOv8中添加SCConv方式  

3.1 在ultralytics/nn下新建Extramodule

3.2 在Extramodule里创建SCConv

在SCConv.py文件里添加给出的SCConv代码

添加完SCConv代码后，在ultralytics/nn/Extramodule/__init__.py文件中引用

3.3 在task.py里引用

在ultralytics/nn/tasks.py文件里引用Extramodule

在task.py找到parse_model（ctrl+f可以直接搜索parse_model位置）

添加如下代码：

4.新建一个yolov8SCConv.yaml文件

# 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: 2 # 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_SCConv, [128, True]]
  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
  - [-1, 6, C2f_SCConv, [256, True]]
  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
  - [-1, 6, C2f_SCConv, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
  - [-1, 3, C2f_SCConv, [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, 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)

大家根据自己的数据集实际情况，修改nc大小。

5.模型训练

import warnings
warnings.filterwarnings('ignore')
from ultralytics import YOLO

if __name__ == '__main__':
    model = YOLO(r'E:\csdn\ultralytics-main\datasets\yolov8SCConv.yaml')
    model.train(data=r'E:\csdn\ultralytics-main\datasets\data.yaml',
                cache=False,
                imgsz=640,
                epochs=100,
                single_cls=False,  # 是否是单类别检测
                batch=16,
                close_mosaic=10,
                workers=0,
                device='0',
                optimizer='SGD',
                amp=True,
                project='runs/train',
                name='exp',
                )

模型结构打印，成功运行 ：

6.本文总结

到此本文的正式分享内容就结束了，在这里给大家推荐我的YOLOv8改进有效涨点专栏，后期我会根据各种最新的前沿顶会进行论文复现，也会对一些老的改进机制进行补充，如果大家觉得本文帮助到你了，订阅本专栏，关注后续更多的更新~

YOLOv8有效涨点专栏