一、本文介绍
本文给大家带来的改进机制是SENet(Squeeze-and-Excitation Networks)其是一种通过调整卷积网络中的通道关系来提升 性能 的网络结构。SENet并不是一个独立的 网络模型 ,而是一个可以和现有的任何一个模型相结合的模块 ( 可以看作是一种通道型的注意力机制 ) 。在SENet中,所谓的 挤压和激励 (Squeeze-and-Excitation)操作是作为一个单元添加到传统的卷积网络结构中,如残差单元中 ( 后面我会把修改好的残差单元给大家大家直接复制粘贴即可使用 ) 。这样可以增强 模型 对通道间关系的捕获,提升整体的特征表达能力,而不需要从头开始设计一个全新的网络架构。因此,SENet可以看作是对现有网络模型的一种改进和增强 ( 亲测大中小三中目标检测上都有一定程度的涨点效果 ) ,附二次创新C2PSASENet。
二、SENetV1框架原理
论文地址: 官方论文地址
代码地址: 官方代码地址
SENet(Squeeze-and-Excitation Networks)的主要思想 在于通过挤压-激励(SE)块强化了网络对通道间依赖性的建模。这一创新的核心在于自适应地重新校准每个通道的特征响应,显著提升了网络对特征的表示能力。SE块的叠加构成了 SENet架构 ,有效提高了模型在不同数据集上的泛化性。SENet的创新点包括其独特的结构设计,它在增加极少计算成本的情况下,为现有CNN模型带来了显著的性能提升,并在国际 图像识别 竞赛ILSVRC 2017中取得了突破性的成果
上图展示了一个挤压-激励(Squeeze-and-Excitation, SE)块的结构。输入特征图
经过一个变换
后产生特征图
。然后,特征图
被压缩成一个全局描述子,这是通过全局平均池化
实现的,产生一个通道描述子。这个描述子经过两个全连接层
,第一个是
降维
,第二个是升维,并通过激活函数如ReLU和Sigmoid激活。最后,原始特征图
与学习到的通道权重
相乘,得到重新校准的特征图
。这种结构有助于网络通过学习通道间的依赖性,自适应地强化或抑制某些特征通道。
上面的图片展示了两种 神经网络 模块的结构图:Inception模块和残差(ResNet)模块。每个模块都有其标准形式和一个修改形式,对比图融入了Squeeze-and-Excitation (SE)块来提升性能。
左面的部分是原始Inception模块(左)和SE-Inception模块(右)。SE-Inception模块通过全局平均池化和两个全连接层(第一个使用ReLU激活函数,第二个使用Sigmoid函数)来生成通道级权重,然后对输入特征图进行缩放。
右面的部分展示了原始残差模块(左)和SE-ResNet模块(右)。SE-ResNet模块在传统的残差连接之后添加了SE块,同样使用全局平均池化和全连接层来获得通道级权重,并对残差模块的输出进行缩放。
这两个修改版模块都旨在增强网络对特征的重要性评估能力,从而提升整体模型的性能。
三、SENetV1核心代码
使用方式看章节四。
- import torch
- import torch.nn as nn
- __all__ = ['SELayerV1', 'C2PSA_SENetV1']
- class SELayerV1(nn.Module):
- def __init__(self, channel, reduction=16):
- super(SELayerV1, 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)
- 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):
- """Initialize Conv layer with given arguments including activation."""
- 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):
- """Apply convolution, batch normalization and activation to input tensor."""
- return self.act(self.bn(self.conv(x)))
- def forward_fuse(self, x):
- """Perform transposed convolution of 2D data."""
- return self.act(self.conv(x))
- class PSABlock(nn.Module):
- """
- PSABlock class implementing a Position-Sensitive Attention block for neural networks.
- This class encapsulates the functionality for applying multi-head attention and feed-forward neural network layers
- with optional shortcut connections.
- Attributes:
- attn (Attention): Multi-head attention module.
- ffn (nn.Sequential): Feed-forward neural network module.
- add (bool): Flag indicating whether to add shortcut connections.
- Methods:
- forward: Performs a forward pass through the PSABlock, applying attention and feed-forward layers.
- Examples:
- Create a PSABlock and perform a forward pass
- >>> psablock = PSABlock(c=128, attn_ratio=0.5, num_heads=4, shortcut=True)
- >>> input_tensor = torch.randn(1, 128, 32, 32)
- >>> output_tensor = psablock(input_tensor)
- """
- def __init__(self, c, attn_ratio=0.5, num_heads=4, shortcut=True) -> None:
- """Initializes the PSABlock with attention and feed-forward layers for enhanced feature extraction."""
- super().__init__()
- self.attn = SELayerV1(c)
- self.ffn = nn.Sequential(Conv(c, c * 2, 1), Conv(c * 2, c, 1, act=False))
- self.add = shortcut
- def forward(self, x):
- """Executes a forward pass through PSABlock, applying attention and feed-forward layers to the input tensor."""
- x = x + self.attn(x) if self.add else self.attn(x)
- x = x + self.ffn(x) if self.add else self.ffn(x)
- return x
- class C2PSA_SENetV1(nn.Module):
- """
- C2PSA module with attention mechanism for enhanced feature extraction and processing.
- This module implements a convolutional block with attention mechanisms to enhance feature extraction and processing
- capabilities. It includes a series of PSABlock modules for self-attention and feed-forward operations.
- Attributes:
- c (int): Number of hidden channels.
- cv1 (Conv): 1x1 convolution layer to reduce the number of input channels to 2*c.
- cv2 (Conv): 1x1 convolution layer to reduce the number of output channels to c.
- m (nn.Sequential): Sequential container of PSABlock modules for attention and feed-forward operations.
- Methods:
- forward: Performs a forward pass through the C2PSA module, applying attention and feed-forward operations.
- Notes:
- This module essentially is the same as PSA module, but refactored to allow stacking more PSABlock modules.
- Examples:
- >>> c2psa = C2PSA(c1=256, c2=256, n=3, e=0.5)
- >>> input_tensor = torch.randn(1, 256, 64, 64)
- >>> output_tensor = c2psa(input_tensor)
- """
- def __init__(self, c1, c2, n=1, e=0.5):
- """Initializes the C2PSA module with specified input/output channels, number of layers, and expansion ratio."""
- super().__init__()
- assert c1 == c2
- self.c = int(c1 * e)
- self.cv1 = Conv(c1, 2 * self.c, 1, 1)
- self.cv2 = Conv(2 * self.c, c1, 1)
- self.m = nn.Sequential(*(PSABlock(self.c, attn_ratio=0.5, num_heads=self.c // 64) for _ in range(n)))
- def forward(self, x):
- """Processes the input tensor 'x' through a series of PSA blocks and returns the transformed tensor."""
- a, b = self.cv1(x).split((self.c, self.c), dim=1)
- b = self.m(b)
- return self.cv2(torch.cat((a, b), 1))
- if __name__ == "__main__":
- # Generating Sample image
- image_size = (1, 64, 240, 240)
- image = torch.rand(*image_size)
- # Model
- mobilenet_v1 = C2PSA_SENetV1(64, 64)
- out = mobilenet_v1(image)
- print(out.size())
四、手把手教你添加SENetV1模块
4.1 修改一
第一还是建立文件,我们找到如下 ultralytics /nn文件夹下建立一个目录名字呢就是'Addmodules'文件夹( 用群内的文件的话已经有了无需新建) !然后在其内部建立一个新的py文件将核心代码复制粘贴进去即可。
4.2 修改二
第二步我们在该目录下创建一个新的py文件名字为'__init__.py'( 用群内的文件的话已经有了无需新建) ,然后在其内部导入我们的检测头如下图所示。
4.3 修改三
第三步我门中到如下文件'ultralytics/nn/tasks.py'进行导入和注册我们的模块( 用群内的文件的话已经有了无需重新导入直接开始第四步即可) !
从今天开始以后的教程就都统一成这个样子了,因为我默认大家用了我群内的文件来进行修改!!
4.4 修改四
按照我的添加在parse_model里添加即可,两个图片都是本文的机制大家按照图片进行添加即可!
到此就修改完成了,大家可以复制下面的yaml文件运行。
4.2 SENetV1的yaml文件和训练截图
4.2.1 SENetV1的yaml版本一(推荐)
此版本训练信息:YOLO11-C2PSA-SENetV1 summary: 314 layers, 2,545,435 parameters, 2,545,419 gradients, 6.4 GFLOPs
版本说明:优化C2PSA注意力机制
- # 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, Conv, [64, 3, 2]] # 0-P1/2
- - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- - [-1, 2, C3k2, [256, False, 0.25]]
- - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- - [-1, 2, C3k2, [512, False, 0.25]]
- - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- - [-1, 2, C3k2, [512, True]]
- - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- - [-1, 2, C3k2, [1024, True]]
- - [-1, 1, SPPF, [1024, 5]] # 9
- - [-1, 2, C2PSA_MSDA, [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, Conv, [256, 3, 2]]
- - [[-1, 13], 1, Concat, [1]] # cat head P4
- - [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)
- - [-1, 1, Conv, [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)
4.2.2 SENetV1的yaml版本二
添加的版本二具体那种适合你需要大家自己多做实验来尝试。
此版本训练信息:YOLO11-SENetV1 summary: 340 layers, 2,605,467 parameters, 2,605,451 gradients, 6.5 GFLOPs
- # 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, Conv, [64, 3, 2]] # 0-P1/2
- - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- - [-1, 2, C3k2, [256, False, 0.25]]
- - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- - [-1, 2, C3k2, [512, False, 0.25]]
- - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- - [-1, 2, C3k2, [512, True]]
- - [-1, 1, Conv, [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, SELayerV1, []] # 17 (P3/8-small) 小目标检测层输出位置增加注意力机制
- - [-1, 1, Conv, [256, 3, 2]]
- - [[-1, 13], 1, Concat, [1]] # cat head P4
- - [-1, 2, C3k2, [512, False]] # 20 (P4/16-medium)
- - [-1, 1, SELayerV1, []] # 21 (P4/16-medium) 中目标检测层输出位置增加注意力机制
- - [-1, 1, Conv, [512, 3, 2]]
- - [[-1, 10], 1, Concat, [1]] # cat head P5
- - [-1, 2, C3k2, [1024, True]] # 24 (P5/32-large)
- - [-1, 1, SELayerV1, []] # 25 (P5/32-large) 大目标检测层输出位置增加注意力机制
- # 具体在那一层用注意力机制可以根据自己的数据集场景进行选择。
- # 如果你自己配置注意力位置注意from[17, 21, 25]位置要对应上对应的检测层!
- - [[17, 21, 25], 1, Detect, [nc]] # Detect(P3, P4, P5)
4.4 SENetV1的训练过程截图
4.5 训练代码
- import warnings
- warnings.filterwarnings('ignore')
- from ultralytics import YOLO
- if __name__ == '__main__':
- model = YOLO('模型yaml文件地址')
- # 如何切换模型版本, 上面的ymal文件可以改为 yolov8s.yaml就是使用的v8s,
- # 类似某个改进的yaml文件名称为yolov8-XXX.yaml那么如果想使用其它版本就把上面的名称改为yolov8l-XXX.yaml即可(改的是上面YOLO中间的名字不是配置文件的)!
- # model.load('yolov8n.pt') # 是否加载预训练权重,科研不建议大家加载否则很难提升精度
- model.train(data=r"填写你数据集yaml文件地址",
- # 如果大家任务是其它的'ultralytics/cfg/default.yaml'找到这里修改task可以改成detect, segment, classify, pose
- cache=False,
- imgsz=640,
- epochs=150,
- single_cls=False, # 是否是单类别检测
- batch=4,
- close_mosaic=0,
- workers=0,
- device='0',
- optimizer='SGD', # using SGD
- # resume=True, # 这里是填写True
- amp=False, # 如果出现训练损失为Nan可以关闭amp
- project='runs/train',
- name='exp',
- )
五、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YOLOv11改进有效涨点专栏,本专栏目前为新开的平均质量分98分,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, 目前本专栏免费阅读(暂时,大家尽早关注不迷路~) ,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~