机械网站建设案例,做调像什么网站找活,WordPress签到打卡,官网网站建设研究前言
2023 年#xff0c;Ultralytics 推出了最新版本的 YOLO 模型。注意力机制是提高模型性能最热门的方法之一。
本次介绍的是YOLOv8-AM#xff0c;它将注意力机制融入到原始的YOLOv8架构中。具体来说#xff0c;我们分别采用四个注意力模块#xff1a;卷积块注意力模块…前言
2023 年Ultralytics 推出了最新版本的 YOLO 模型。注意力机制是提高模型性能最热门的方法之一。
本次介绍的是YOLOv8-AM它将注意力机制融入到原始的YOLOv8架构中。具体来说我们分别采用四个注意力模块卷积块注意力模块CBAM、全局注意力机制GAM、高效通道注意力ECA和随机注意力SA来设计改进模型并在数据集上进行测试。实验结果表明基于ResBlock CBAMResCBAM的YOLOv8-AM模型在IoU 50mAP 50下的平均精度提到了2.2%达到了state-of-the-artSOTA表现。相反结合GAM的YOLOv8-AM模型获得了的mAP 50并不是一个令人满意的增强。因此我们将ResBlock和GAM结合起来引入ResGAM设计另一个新的YOLOv8-AM模型获得一个较为满意的结果。
目录
前言
注意力机制
Convolutional Block Attention Module
Efficient Channel Attention
Shuffle Attention
Global Attention Mechanism
实验结果供参考
可论文指导---------v jiabei-545
改进代码(失效 v ) 注意力机制 带有YOLOv8-AM的结构图 YOLOv8 架构由四个关键组件组成Backbone、Neck、Head 和 Loss Function。 Backbone 融合了 Cross Stage Partial (CSP) 概念具有减少计算负载、同时增强 CNN 学习能力的优势。如图所示YOLOv8与采用C3模块的YOLOv5不同采用C2f模块该模块集成了C3模块和YOLOv7中的扩展ELANE-ELAN概念。 YOLOv8-AM模型架构详解其中注意力模块为Shuffle AttentionSA、Efficient Channel AttentionECA、Global Attention MechanismGAM、ResBlock Convolutional Block Attention ModuleResCBAM Convolutional Block Attention Module CBAM架构 CBAM 包括通道注意力C-Attention和空间注意力S-Attention如图所示。给定一个中间特征图CBAM 通过等式依次推断出 1D 通道注意力图 和 2D 空间注意力图 。 ResBlock Convolutional Block Attention Module 原理和resnet一样
# 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: 9 # number of classes
scales: # model compound scaling constants, i.e. modelyolov8n.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 GFLOPs# 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, ResBlock_CBAM, [512]]- [-1, 1, nn.Upsample, [None, 2, nearest]]- [[-1, 4], 1, Concat, [1]] # cat backbone P3- [-1, 3, C2f, [256]] # 16 (P3/8-small)- [-1, 1, ResBlock_CBAM, [256]]- [-1, 1, Conv, [256, 3, 2]]- [[-1, 12], 1, Concat, [1]] # cat head P4- [-1, 3, C2f, [512]] # 20 (P4/16-medium)- [-1, 1, ResBlock_CBAM, [512]]- [-1, 1, Conv, [512, 3, 2]]- [[-1, 9], 1, Concat, [1]] # cat head P5- [-1, 3, C2f, [1024]] # 24 (P5/32-large)- [-1, 1, ResBlock_CBAM, [1024]]- [[17, 21, 25], 1, Detect, [nc]] # Detect(P3, P4, P5)
Efficient Channel Attention Efficient Channel Attention ECA 主要包含跨通道交互和具有自适应卷积核的一维卷积如图 所示。跨通道交互代表了一种组合特征的新方法增强了特定语义的特征表达。
# 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: 9 # number of classes
scales: # model compound scaling constants, i.e. modelyolov8n.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 GFLOPs# 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, ECAAttention, [512]]- [-1, 1, nn.Upsample, [None, 2, nearest]]- [[-1, 4], 1, Concat, [1]] # cat backbone P3- [-1, 3, C2f, [256]] # 16 (P3/8-small)- [-1, 1, ECAAttention, [256]]- [-1, 1, Conv, [256, 3, 2]]- [[-1, 12], 1, Concat, [1]] # cat head P4- [-1, 3, C2f, [512]] # 20 (P4/16-medium)- [-1, 1, ECAAttention, [512]]- [-1, 1, Conv, [512, 3, 2]]- [[-1, 9], 1, Concat, [1]] # cat head P5- [-1, 3, C2f, [1024]] # 24 (P5/32-large)- [-1, 1, ECAAttention, [1024]]- [[17, 21, 25], 1, Detect, [nc]] # Detect(P3, P4, P5)
Shuffle Attention Shuffle Attention SA将输入特征图分为不同的组利用Shuffle Unit将通道注意力和空间注意力整合到每个组的一个块中如图所示。随后子特征被聚合并且“ ShuffleNetV2 中使用的“Channel Shuffle”算子用于促进各种子特征之间的信息通信。对于通道注意力SA 采用 GAP 来捕获和嵌入子特征。此外使用带有 sigmoid 函数的简单门控机制来创建紧凑的函数以促进精确和自适应的选择。
# SA.yaml
# 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: 9 # number of classes
scales: # model compound scaling constants, i.e. modelyolov8n.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 GFLOPs# 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, ShuffleAttention, [512]]- [-1, 1, nn.Upsample, [None, 2, nearest]]- [[-1, 4], 1, Concat, [1]] # cat backbone P3- [-1, 3, C2f, [256]] # 16 (P3/8-small)- [-1, 1, ShuffleAttention, [256]]- [-1, 1, Conv, [256, 3, 2]]- [[-1, 12], 1, Concat, [1]] # cat head P4- [-1, 3, C2f, [512]] # 20 (P4/16-medium)- [-1, 1, ShuffleAttention, [512]]- [-1, 1, Conv, [512, 3, 2]]- [[-1, 9], 1, Concat, [1]] # cat head P5- [-1, 3, C2f, [1024]] # 24 (P5/32-large)- [-1, 1, ShuffleAttention, [1024]]- [[17, 21, 25], 1, Detect, [nc]] # Detect(P3, P4, P5)
Global Attention Mechanism Global Attention Mechanism GAM采用了CBAM提出的由通道注意力和空间注意力组成的主要架构并重新设计了子模块如图所示。此外我在GAM内的各层之间添加了快捷连接这使得输入能够更快地向前传播。
# GAM.yaml
# 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: 9 # number of classes
scales: # model compound scaling constants, i.e. modelyolov8n.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 GFLOPs# 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, GAM_Attention, [512,512]]- [-1, 1, nn.Upsample, [None, 2, nearest]]- [[-1, 4], 1, Concat, [1]] # cat backbone P3- [-1, 3, C2f, [256]] # 16 (P3/8-small)- [-1, 1, GAM_Attention, [256,256]]- [-1, 1, Conv, [256, 3, 2]]- [[-1, 12], 1, Concat, [1]] # cat head P4- [-1, 3, C2f, [512]] # 20 (P4/16-medium)- [-1, 1, GAM_Attention, [512,512]]- [-1, 1, Conv, [512, 3, 2]]- [[-1, 9], 1, Concat, [1]] # cat head P5- [-1, 3, C2f, [1024]] # 24 (P5/32-large)- [-1, 1, GAM_Attention, [1024,1024]]- [[17, 21, 25], 1, Detect, [nc]] # Detect(P3, P4, P5) ResBlock Global Attention Mechanism 原理和resnet一样
实验结果供参考 ResBlock Convolutional Block Attention Module Shuffle Attention Efficient Channel Attention Global Attention Mechanism ResBlock Global Attention Mechanism 定量比较Precision/Recall/F1/mAP 可论文指导---------v jiabei-545
改进代码(失效 v )
链接: https://pan.baidu.com/s/1Fi7ghwJ6XiXrDDnoCvlvrQ?pwdzk88 提取码: zk88
欢迎大家在评论区进行讨论
