YOLO11改进 | 注意力机制 | 正确的 Self-Attention 与 CNN 融合范式，性能速度全面提升【独家创新】

 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💡💡💡

---

卷积和自注意力是两种强大的表征学习技术，它们通常被认为是彼此不同的两种平行方法。ACmix模型通过结合卷积和自注意力的优势，旨在解决卷积神经网络和自注意力模型在表征学习中的各自局限性，提高模型性能。通过这种方式，ACmix在图像识别和下游任务上实现了性能提升。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. ACmix代码实现

2.1 将ACmix添加到YOLO11中

2.2 更改init.py文件

2.3 添加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

论文链接：https://arxiv.org/pdf/2111.14556.pdf

代码链接：https://github.com/Panxuran/ACmix

预训练模型：models: Models of MindSpore

2. ACmix代码实现

2.1 将ACmix添加到YOLO11中

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

import torch.nn.functional as F
import timedef position(H, W, is_cuda=True):if is_cuda:loc_w = torch.linspace(-1.0, 1.0, W).cuda().unsqueeze(0).repeat(H, 1)loc_h = torch.linspace(-1.0, 1.0, H).cuda().unsqueeze(1).repeat(1, W)else:loc_w = torch.linspace(-1.0, 1.0, W).unsqueeze(0).repeat(H, 1)loc_h = torch.linspace(-1.0, 1.0, H).unsqueeze(1).repeat(1, W)loc = torch.cat([loc_w.unsqueeze(0), loc_h.unsqueeze(0)], 0).unsqueeze(0)return locdef stride(x, stride):b, c, h, w = x.shapereturn x[:, :, ::stride, ::stride]def init_rate_half(tensor):if tensor is not None:tensor.data.fill_(0.5)def init_rate_0(tensor):if tensor is not None:tensor.data.fill_(0.)class ACmix(nn.Module):def __init__(self, in_planes, kernel_att=7, head=4, kernel_conv=3, stride=1, dilation=1):super(ACmix, self).__init__()self.in_planes = in_planesself.out_planes = in_planesself.head = headself.kernel_att = kernel_attself.kernel_conv = kernel_convself.stride = strideself.dilation = dilationself.rate1 = torch.nn.Parameter(torch.Tensor(1))self.rate2 = torch.nn.Parameter(torch.Tensor(1))self.head_dim = self.out_planes // self.headself.conv1 = nn.Conv2d(in_planes, self.out_planes, kernel_size=1)self.conv2 = nn.Conv2d(in_planes, self.out_planes, kernel_size=1)self.conv3 = nn.Conv2d(in_planes, self.out_planes, kernel_size=1)self.conv_p = nn.Conv2d(2, self.head_dim, kernel_size=1)self.padding_att = (self.dilation * (self.kernel_att - 1) + 1) // 2self.pad_att = torch.nn.ReflectionPad2d(self.padding_att)self.unfold = nn.Unfold(kernel_size=self.kernel_att, padding=0, stride=self.stride)self.softmax = torch.nn.Softmax(dim=1)self.fc = nn.Conv2d(3*self.head, self.kernel_conv * self.kernel_conv, kernel_size=1, bias=False)self.dep_conv = nn.Conv2d(self.kernel_conv * self.kernel_conv * self.head_dim, self.out_planes, kernel_size=self.kernel_conv, bias=True, groups=self.head_dim, padding=1, stride=stride)self.reset_parameters()def reset_parameters(self):init_rate_half(self.rate1)init_rate_half(self.rate2)kernel = torch.zeros(self.kernel_conv * self.kernel_conv, self.kernel_conv, self.kernel_conv)for i in range(self.kernel_conv * self.kernel_conv):kernel[i, i//self.kernel_conv, i%self.kernel_conv] = 1.kernel = kernel.squeeze(0).repeat(self.out_planes, 1, 1, 1)self.dep_conv.weight = nn.Parameter(data=kernel, requires_grad=True)self.dep_conv.bias = init_rate_0(self.dep_conv.bias)def forward(self, x):q, k, v = self.conv1(x), self.conv2(x), self.conv3(x)scaling = float(self.head_dim) ** -0.5b, c, h, w = q.shapeh_out, w_out = h//self.stride, w//self.stride# ### att# ## positional encoding https://github.com/iscyy/yoloairpe = self.conv_p(position(h, w, x.is_cuda))q_att = q.view(b*self.head, self.head_dim, h, w) * scalingk_att = k.view(b*self.head, self.head_dim, h, w)v_att = v.view(b*self.head, self.head_dim, h, w)if self.stride > 1:q_att = stride(q_att, self.stride)q_pe = stride(pe, self.stride)else:q_pe = peunfold_k = self.unfold(self.pad_att(k_att)).view(b*self.head, self.head_dim, self.kernel_att*self.kernel_att, h_out, w_out) # b*head, head_dim, k_att^2, h_out, w_outunfold_rpe = self.unfold(self.pad_att(pe)).view(1, self.head_dim, self.kernel_att*self.kernel_att, h_out, w_out) # 1, head_dim, k_att^2, h_out, w_outatt = (q_att.unsqueeze(2)*(unfold_k + q_pe.unsqueeze(2) - unfold_rpe)).sum(1) # (b*head, head_dim, 1, h_out, w_out) * (b*head, head_dim, k_att^2, h_out, w_out) -> (b*head, k_att^2, h_out, w_out)att = self.softmax(att)out_att = self.unfold(self.pad_att(v_att)).view(b*self.head, self.head_dim, self.kernel_att*self.kernel_att, h_out, w_out)out_att = (att.unsqueeze(1) * out_att).sum(2).view(b, self.out_planes, h_out, w_out)## convf_all = self.fc(torch.cat([q.view(b, self.head, self.head_dim, h*w), k.view(b, self.head, self.head_dim, h*w), v.view(b, self.head, self.head_dim, h*w)], 1))f_conv = f_all.permute(0, 2, 1, 3).reshape(x.shape[0], -1, x.shape[-2], x.shape[-1])out_conv = self.dep_conv(f_conv)return self.rate1 * out_att + self.rate2 * out_conv

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 添加yaml文件

关键步骤三：在/ultralytics/ultralytics/cfg/models/11下面新建文件yolo11_ACmix.yaml文件，粘贴下面的内容

• 目标检测

# 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 GFLOPss: [0.50, 0.50, 1024] # summary: 319 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPsm: [0.50, 1.00, 512] # summary: 409 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPsl: [1.00, 1.00, 512] # summary: 631 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPsx: [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, 1, ACmix, [1024]] # 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, Conv, [256, 3, 2]]- [[-1, 14], 1, Concat, [1]] # cat head P4- [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)- [-1, 1, Conv, [512, 3, 2]]- [[-1, 11], 1, Concat, [1]] # cat head P5- [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)- [[17, 20, 23], 1, Detect, [nc]] # Detect(P3, P4, P5)

• 语义分割

# 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 GFLOPss: [0.50, 0.50, 1024] # summary: 319 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPsm: [0.50, 1.00, 512] # summary: 409 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPsl: [1.00, 1.00, 512] # summary: 631 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPsx: [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, 1, ACmix, [1024]] # 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, Conv, [256, 3, 2]]- [[-1, 14], 1, Concat, [1]] # cat head P4- [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)- [-1, 1, Conv, [512, 3, 2]]- [[-1, 11], 1, Concat, [1]] # cat head P5- [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)- [[17, 20, 23], 1, Segment, [nc, 32, 256]] # Segment(P3, P4, P5)

• 旋转目标检测

# 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 GFLOPss: [0.50, 0.50, 1024] # summary: 319 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPsm: [0.50, 1.00, 512] # summary: 409 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPsl: [1.00, 1.00, 512] # summary: 631 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPsx: [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, 1, ACmix, [1024]] # 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, Conv, [256, 3, 2]]- [[-1, 14], 1, Concat, [1]] # cat head P4- [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)- [-1, 1, Conv, [512, 3, 2]]- [[-1, 11], 1, Concat, [1]] # cat head P5- [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)- [[17, 20, 23], 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

---

# 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parse_model函数中进行注册，添加ACmix,

 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ACmix

elif m in [ACmix,]:c1, c2 = ch[f], args[0]if c2 != nc:  # if not outputc2 = make_divisible(c2 * width, 8)args = [c1, *args[1:]]

2.5 执行程序

关键步骤五: 在ultralytics文件中新建train.py，将model的参数路径设置为yolo11_ACmix.yaml的路径即可

from ultralytics import YOLO
import warnings
warnings.filterwarnings('ignore')
from pathlib import Pathif __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 modelresults = 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🚀 

  from  n    params  module                                       arguments0                  -1  1       464  ultralytics.nn.modules.conv.Conv             [3, 16, 3, 2]1                  -1  1      4672  ultralytics.nn.modules.conv.Conv             [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.Conv             [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.Conv             [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.Conv             [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    218414  ultralytics.nn.modules.block.ACmix           [256]11                  -1  1    249728  ultralytics.nn.modules.block.C2PSA           [256, 256, 1]12                  -1  1         0  torch.nn.modules.upsampling.Upsample         [None, 2, 'nearest']13             [-1, 6]  1         0  ultralytics.nn.modules.conv.Concat           [1]14                  -1  1    111296  ultralytics.nn.modules.block.C3k2            [384, 128, 1, False]15                  -1  1         0  torch.nn.modules.upsampling.Upsample         [None, 2, 'nearest']16             [-1, 4]  1         0  ultralytics.nn.modules.conv.Concat           [1]17                  -1  1     32096  ultralytics.nn.modules.block.C3k2            [256, 64, 1, False]18                  -1  1     36992  ultralytics.nn.modules.conv.Conv             [64, 64, 3, 2]19            [-1, 14]  1         0  ultralytics.nn.modules.conv.Concat           [1]20                  -1  1     86720  ultralytics.nn.modules.block.C3k2            [192, 128, 1, False]21                  -1  1    147712  ultralytics.nn.modules.conv.Conv             [128, 128, 3, 2]22            [-1, 11]  1         0  ultralytics.nn.modules.conv.Concat           [1]23                  -1  1    378880  ultralytics.nn.modules.block.C3k2            [384, 256, 1, True]24        [17, 20, 23]  1    464912  ultralytics.nn.modules.head.Detect           [80, [64, 128, 256]]
YOLO11_ACmix summary: 329 layers, 2,842,494 parameters, 2,842,478 gradients, 6.8 GFLOPs

报错解决指南： 

RuntimeError: Input type (float) and bias type (c10::Half) should be the same

 在/ultralytics/ultralytics/engine/validator.py中的116行处添加下面代码即可  

self.args.half = False

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

通过以上的改进方法，我们成功提升了模型的表现。这只是一个开始，未来还有更多优化和技术深挖的空间。在这里，我想隆重向大家推荐我的专栏——《YOLO11改进有效涨点》。这个专栏专注于前沿的深度学习技术，特别是目标检测领域的最新进展，不仅包含对YOLO11的深入解析和改进策略，还会定期更新来自各大顶会（如CVPR、NeurIPS等）的论文复现和实战分享。

为什么订阅我的专栏？ ——《YOLO11改进有效涨点》

1. 前沿技术解读：专栏不仅限于YOLO系列的改进，还会涵盖各类主流与新兴网络的最新研究成果，帮助你紧跟技术潮流。

2. 详尽的实践分享：所有内容实践性也极强。每次更新都会附带代码和具体的改进步骤，保证每位读者都能迅速上手。

3. 问题互动与答疑：订阅我的专栏后，你将可以随时向我提问，获取及时的答疑。

4. 实时更新，紧跟行业动态：不定期发布来自全球顶会的最新研究方向和复现实验报告，让你时刻走在技术前沿。

专栏适合人群：

• 对目标检测、YOLO系列网络有深厚兴趣的同学

• 希望在用YOLO算法写论文的同学

• 对YOLO算法感兴趣的同学等