爆改YOLOv8|利用SENetV2改进yolov8,暴力涨点

1，本文介绍

本文探讨了将 SENetV2 的稠密聚合层与 SE 模块结合，应用于 YOLOv8，以提升特征表达能力和目标检测性能。SENetV2 通过 Squeeze-and-Excitation（SE）模块优化通道和全局特征，从而提高分类准确率。文章详细介绍了 SENetV2 的结构和核心代码，并阐述了如何将其集成到 YOLOv8 中以及进行配置。

关于SENetV2的详细介绍可以看论文：https://arxiv.org/pdf/2311.10807.pdf

本文将讲解如何将SENetV2融合进yolov8

话不多说，上代码！

2，将SENetV2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SENetV2.py文件，文件名字可以根据你自己的习惯起，然后将SENetV2的核心代码复制进去

import torch
import torch.nn as nn
from .conv import Conv
# 定义SE模块
class SELayer(nn.Module):def __init__(self, channel, reduction=16):super(SELayer, self).__init__()self.avg_pool = nn.AdaptiveAvgPool2d(1)self.fc = nn.Sequential(nn.Linear(channel, channel // reduction, bias=False),nn.ReLU(inplace=True),nn.Linear(channel // reduction, channel, bias=False),nn.Sigmoid())def forward(self, x):b, c, _, _ = x.size()y = self.avg_pool(x).view(b, c)y = self.fc(y).view(b, c, 1, 1)return x * y.expand_as(x)# 定义SaE模块
class SELayerV2(nn.Module):def __init__(self, in_channel, reduction=32):super(SELayerV2, self).__init__()assert in_channel>=reduction and in_channel%reduction==0,'invalid in_channel in SaElayer'self.reduction = reductionself.cardinality=4self.avg_pool = nn.AdaptiveAvgPool2d(1)#cardinality 1self.fc1 = nn.Sequential(nn.Linear(in_channel,in_channel//self.reduction, bias=False),nn.ReLU(inplace=True))# cardinality 2self.fc2 = nn.Sequential(nn.Linear(in_channel, in_channel // self.reduction, bias=False),nn.ReLU(inplace=True))# cardinality 3self.fc3 = nn.Sequential(nn.Linear(in_channel, in_channel // self.reduction, bias=False),nn.ReLU(inplace=True))# cardinality 4self.fc4 = nn.Sequential(nn.Linear(in_channel, in_channel // self.reduction, bias=False),nn.ReLU(inplace=True))self.fc = nn.Sequential(nn.Linear(in_channel//self.reduction*self.cardinality, in_channel, bias=False),nn.Sigmoid())def forward(self, x):b, c, _, _ = x.size()y = self.avg_pool(x).view(b, c)y1 = self.fc1(y)y2 = self.fc2(y)y3 = self.fc3(y)y4 = self.fc4(y)y_concate = torch.cat([y1,y2,y3,y4],dim=1)y_ex_dim = self.fc(y_concate).view(b,c,1,1)return x * y_ex_dim.expand_as(x)class Bottleneck(nn.Module):"""Standard bottleneck."""def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5):"""Initializes a bottleneck module with given input/output channels, shortcut option, group, kernels, andexpansion."""super().__init__()c_ = int(c2 * e)  # hidden channelsself.cv1 = Conv(c1, c_, k[0], 1)self.cv2 = Conv(c_, c2, k[1], 1, g=g)self.SEV2 = SELayerV2(c2)self.add = shortcut and c1 == c2def forward(self, x):"""'forward()' applies the YOLO FPN to input data."""return x + self.SEV2(self.cv2(self.cv1(x))) if self.add else self.SEV2(self.cv2(self.cv1(x)))class C2f_SENetV2(nn.Module):"""Faster Implementation of CSP Bottleneck with 2 convolutions."""def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):"""Initialize CSP bottleneck layer with two convolutions with arguments ch_in, ch_out, number, shortcut, groups,expansion."""super().__init__()self.c = int(c2 * e)  # hidden channelsself.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))# import ipdb
#
# se_v2 = SaELayer(64)
# # 示例输入
# input = torch.randn(3, 64, 224, 224)
# output = se_v2(input)
#
# print(output.shape)#torch.Size([3, 64, 224, 224])

2.2 步骤二

在task.py导入我们的模块

from .modules.SENetV2 import SELayerV2, C2f_SENetV2

2.3 步骤三

在task.py的parse_model注册我们的模块

注意，共需要在三个位置进行添加

到此注册成功,复制后面的yaml文件直接运行即可

此处我有两种添加方式，大家可以参考，具体关于每个数据集位置不同，效果不同，大家可以自行调试

yaml文件一

# 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 GFLOPss: [0.33, 0.50, 1024]  # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients,  28.8 GFLOPsm: [0.67, 0.75, 768]   # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients,  79.3 GFLOPsl: [1.00, 1.00, 512]   # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPsx: [1.00, 1.25, 512]   # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOP# 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, C2f, [512]]  # 12- [-1, 1, nn.Upsample, [None, 2, 'nearest']]- [[-1, 4], 1, Concat, [1]]  # cat backbone P3- [-1, 3, C2f_SENetV2, [256]]  # 15 (P3/8-small)- [-1, 1, Conv, [256, 3, 2]]- [[-1, 12], 1, Concat, [1]]  # cat head P4- [-1, 3, C2f_SENetV2, [512]]  # 18 (P4/16-medium)- [-1, 1, Conv, [512, 3, 2]]- [[-1, 9], 1, Concat, [1]]  # cat head P5- [-1, 3, C2f_SENetV2, [1024]]  # 21 (P5/32-large)- [[15, 18, 21], 1, Detect, [nc]]  # Detect(P3, P4, P5)

yaml文件二

# 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 GFLOPss: [0.33, 0.50, 1024]  # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients,  28.8 GFLOPsm: [0.67, 0.75, 768]   # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients,  79.3 GFLOPsl: [1.00, 1.00, 512]   # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPsx: [1.00, 1.25, 512]   # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOP# 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, 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, SELayerV2, []]  # 16- [-1, 1, Conv, [256, 3, 2]]- [[-1, 12], 1, Concat, [1]]  # cat head P4- [-1, 3, C2f, [512]]  # 19 (P4/16-medium)- [-1, 1, SELayerV2, []]  # 20- [-1, 1, Conv, [512, 3, 2]]- [[-1, 9], 1, Concat, [1]]  # cat head P5- [-1, 3, C2f, [1024]]  # 23 (P5/32-large)- [-1, 1, SELayerV2, []]  # 24- [[16, 20, 24], 1, Detect, [nc]]  # Detect(P3, P4, P5)