邢台装修网站建设,公司就两个开发,wordpress 免费外贸,南部县房产网秋招面试专栏推荐 #xff1a;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 #x1f4a1;#x1f4a1;#x1f4a1;本专栏所有程序均经过测试#xff0c;可成功执行#x1f4a1;#x1f4a1;#x1f4a1; 在本文中#xff0c;给大家带来的教程是… 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 在本文中给大家带来的教程是在原来的网络的基础上添加DoubleAttention。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. DoubleAttention代码实现
2.1 将DoubleAttention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 官方论文A2 -Nets: Double Attention Networks——点击即可跳转
官方代码A2 -Nets: Double Attention Networks官方代码仓库——点击即可跳转
2. DoubleAttention代码实现
2.1 将DoubleAttention添加到YOLO11中 关键步骤一将下面代码粘贴到在/ultralytics/ultralytics/nn/modules/block.py中 from torch import nn
import torch
from torch.autograd import Variable
import torch.nn.functional as Fclass DoubleAttentionLayer(nn.Module):Implementation of Double Attention Network. NIPS 2018def __init__(self, in_channels: int, c_m: int, c_n: int, reconstructFalse):Parameters----------in_channelsc_mc_nreconstruct: bool whether to re-construct output to have shape (B, in_channels, L, R)super(DoubleAttentionLayer, self).__init__()self.c_m c_mself.c_n c_nself.in_channels in_channelsself.reconstruct reconstructself.convA nn.Conv2d(in_channels, c_m, kernel_size1)self.convB nn.Conv2d(in_channels, c_n, kernel_size1)self.convV nn.Conv2d(in_channels, c_n, kernel_size1)if self.reconstruct:self.conv_reconstruct nn.Conv2d(c_m, in_channels, kernel_size1)def forward(self, x: torch.Tensor):Parameters----------x: torch.Tensor of shape (B, C, H, W)Returns-------batch_size, c, h, w x.size()assert c self.in_channels, input channel not equal!A self.convA(x) # (B, c_m, h, w) because kernel size is 1B self.convB(x) # (B, c_n, h, w)V self.convV(x) # (B, c_n, h, w)tmpA A.view(batch_size, self.c_m, h * w)attention_maps B.view(batch_size, self.c_n, h * w)attention_vectors V.view(batch_size, self.c_n, h * w)# softmax on the last dimension to create attention mapsattention_maps F.softmax(attention_maps, dim-1) # 对hxw维度进行softmax# step 1: feature gatheringglobal_descriptors torch.bmm( # attention map(V)和tmpA进行tmpA, attention_maps.permute(0, 2, 1)) # (B, c_m, c_n)# step 2: feature distribution# (B, c_n, h * w) attention on c_n dimension - channel wiseattention_vectors F.softmax(attention_vectors, dim1)tmpZ global_descriptors.matmul(attention_vectors) # B, self.c_m, h * wtmpZ tmpZ.view(batch_size, self.c_m, h, w)if self.reconstruct:tmpZ self.conv_reconstruct(tmpZ)return tmpZ
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_DoubleAttention.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. modelyolo11n.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, DoubleAttentionLayer, [1024, 1]]- [-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, 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. modelyolo11n.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, DoubleAttentionLayer, [1024, 1]]- [-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, 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. modelyolo11n.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, DoubleAttentionLayer, [1024, 1]]- [-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, 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_channel1024# YOLO11s
depth_multiple: 0.50 # model depth multiple
width_multiple: 0.50 # layer channel multiple
max_channel1024# YOLO11m
depth_multiple: 0.50 # model depth multiple
width_multiple: 1.00 # layer channel multiple
max_channel512# YOLO11l
depth_multiple: 1.00 # model depth multiple
width_multiple: 1.00 # layer channel multiple
max_channel512 # YOLO11x
depth_multiple: 1.00 # model depth multiple
width_multiple: 1.50 # layer channel multiple
max_channel512
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DoubleAttention 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DoubleAttention 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_DoubleAttention.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(datar你的数据集的yaml文件地址,epochs100, batch16, imgsz640, workers4, namePath(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 66306 ultralytics.nn.modules.block.DoubleAttentionLayer[256, 256, 1]10 -1 1 164608 ultralytics.nn.modules.block.SPPF [256, 256, 5]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_DoubleAttention summary: 323 layers, 2,690,386 parameters, 2,690,370 gradients, 6.7 GFLOPs
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——专栏地址YOLO11入门 改进涨点——点击即可跳转 欢迎订阅。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 ——专栏地址YOLO11入门 改进涨点——点击即可跳转 欢迎订阅 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。 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。 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。 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
