yolov8添加注意力机制

最新推荐文章于 2024-09-11 14:38:02 发布

d boss

最新推荐文章于 2024-09-11 14:38:02 发布

阅读量850

点赞数

分类专栏： yolov8相关文章标签： YOLO 深度学习人工智能

本文链接：https://blog.csdn.net/weixin_51230935/article/details/133861287

版权

yolov8相关专栏收录该内容

5 篇文章 2 订阅

订阅专栏

前提

参考这篇文章改进YOLO系列：改进YOLOv8，教你YOLOv8如何添加20多种注意力机制，并实验不同位置。_yolo注意力机制_一休哥※的博客-CSDN博客

我使用的是yolov8最新的项目文件，参考上面这篇文章的第二种添加方法

一、添加代码

打开yolov8项目文件，找到文件conv.py，正常在该路径下： ultralytics/nn/modules/conv.py

在最后面添加注意力机制的代码，我是从上面文章中复制过来的

打开ultralytics/nn/modules/__init__.py，修改 from .conv import 和 __all__ 括号中添加 GAM_Attention

from .conv import (CBAM, ChannelAttention, Concat, Conv, Conv2, ConvTranspose, DWConv, DWConvTranspose2d, Focus,
                   GhostConv, LightConv, RepConv, SpatialAttention, GAM_Attention)
__all__ = ('Conv', 'Conv2', 'LightConv', 'RepConv', 'DWConv', 'DWConvTranspose2d', 'ConvTranspose', 'Focus',
           'GhostConv', 'ChannelAttention', 'SpatialAttention', 'CBAM', 'Concat', 'TransformerLayer',
           'TransformerBlock', 'MLPBlock', 'LayerNorm2d', 'DFL', 'HGBlock', 'HGStem', 'SPP', 'SPPF', 'C1', 'C2', 'C3',
           'C2f', 'C3x', 'C3TR', 'C3Ghost', 'GhostBottleneck', 'Bottleneck', 'BottleneckCSP', 'Proto', 'Detect',
           'Segment', 'Pose', 'Classify', 'TransformerEncoderLayer', 'RepC3', 'RTDETRDecoder', 'AIFI',
           'DeformableTransformerDecoder', 'DeformableTransformerDecoderLayer', 'MSDeformAttn', 'MLP', 'GAM_Attention')

打开ultralytics/nn/tasks.py，在from ultralytics.nn.modules import括号后添加GAM_Attention

from ultralytics.nn.modules import (AIFI, C1, C2, C3, C3TR, SPP, SPPF, Bottleneck, BottleneckCSP, C2f, C3Ghost, C3x,
                                    Classify, Concat, Conv, Conv2, ConvTranspose, Detect, DWConv, DWConvTranspose2d,
                                    Focus, GhostBottleneck, GhostConv, HGBlock, HGStem, Pose, RepC3, RepConv,
                                    RTDETRDecoder, Segment, GAM_Attention)

继续在其中添加代码，如图是我添加代码的位置，我不懂为什么要加在这里，先试试

二、新建yaml文件

复制他的yaml代码并重命名为 yolov8m-Backbone-ATT.yaml，路径为ultralytics/cfg/models/v8/yolov8m-Backbone-ATT.yaml ，修改nc

# Ultralytics YOLO 🚀, GPL-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. 'model=yolov8n.yaml' will call yolov8-SPPCSPC.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 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, 3, GAM_Attention, [1024]]
  - [-1, 1, SPPF, [1024, 5]]  # 10

# YOLOv8.0n head
head:
  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
  - [[-1, 6], 1, Concat, [1]]  # cat backbone P4
  - [-1, 3, C2f, [512]]  # 13

  - [-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, Conv, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]]  # cat head P4
  - [-1, 3, C2f, [512]]  # 19 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 10], 1, Concat, [1]]  # cat head P5
  - [-1, 3, C2f, [1024]]  # 22 (P5/32-large)

  - [[16, 19, 22], 1, Detect, [nc]]  # Detect(P3, P4, P5)