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 = reduction
self.cardinality=4
self.avg_pool = nn.AdaptiveAvgPool2d(1)
#cardinality 1
self.fc1 = nn.Sequential(
nn.Linear(in_channel,in_channel//self.reduction, bias=False),
nn.ReLU(inplace=True)
)
# cardinality 2
self.fc2 = nn.Sequential(
nn.Linear(in_channel, in_channel // self.reduction, bias=False),
nn.ReLU(inplace=True)
)
# cardinality 3
self.fc3 = nn.Sequential(
nn.Linear(in_channel, in_channel // self.reduction, bias=False),
nn.ReLU(inplace=True)
)
# cardinality 4
self.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, and
expansion.
"""
super().__init__()
c_ = int(c2 * e) # hidden channels
self.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 == c2
def 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 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(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 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 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 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 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)
不知不觉已经看完了哦,动动小手留个点赞吧--_--