#YOLO# #目标检测# #计算机视觉#
一、本文介绍
作为入门性篇章,这里介绍了CAA注意力在YOLOv8中的使用。包含CAA原理分析,CAA的代码、CAA的使用方法、以及添加以后的yaml文件及运行记录。
二、CAA原理分析
CAA官方论文地址:文章
CAA官方代码地址:代码
CAA注意力机制:CAA旨在掌握远距离之间的上下文相互依存关系像素,同时增强中心特征。CAA模块通过池化、卷积和Sigmoid等操作,生成了一个加权注意力图,使得特征图中的不同区域能够根据其全局上下文信息进行加权,从而对不同重要性的特征进行选择性加强或抑制。
三、相关代码:
CAA注意力的代码,如下:
python
from typing import Optional
from mmcv.cnn import ConvModule
from mmengine.model import BaseModule, constant_init
class CAA(BaseModule):
"""Context Anchor Attention"""
def __init__(
self,
channels: int,
h_kernel_size: int = 11,
v_kernel_size: int = 11,
norm_cfg: Optional[dict] = dict(type='BN', momentum=0.03, eps=0.001),
act_cfg: Optional[dict] = dict(type='SiLU'),
init_cfg: Optional[dict] = None,
):
super().__init__(init_cfg)
self.avg_pool = nn.AvgPool2d(7, 1, 3)
self.conv1 = ConvModule(channels, channels, 1, 1, 0,
norm_cfg=norm_cfg, act_cfg=act_cfg)
self.h_conv = ConvModule(channels, channels, (1, h_kernel_size), 1,
(0, h_kernel_size // 2), groups=channels,
norm_cfg=None, act_cfg=None)
self.v_conv = ConvModule(channels, channels, (v_kernel_size, 1), 1,
(v_kernel_size // 2, 0), groups=channels,
norm_cfg=None, act_cfg=None)
self.conv2 = ConvModule(channels, channels, 1, 1, 0,
norm_cfg=norm_cfg, act_cfg=act_cfg)
self.act = nn.Sigmoid()
def forward(self, x):
attn_factor = self.act(self.conv2(self.v_conv(self.h_conv(self.conv1(self.avg_pool(x))))))
return attn_factor
四、YOLOv8中CAA使用方法
1.YOLOv8中添加CAA模块:
首先在ultralytics/nn/modules/conv.py最后添加模块的代码。
2.在conv.py的开头__all__ = 内添加CAA模块的类别名:
3.在同级文件夹下的__init__.py内添加CAA的相关内容:(分别是from .conv import CAA ;以及在__all__内添加CAA)
4.在ultralytics/nn/tasks.py进行CAA注意力机制的注册,以及在YOLOv8的yaml配置文件中添加CAA即可。
首先打开task.py文件,按住Ctrl+F,输入parse_model进行搜索。找到parse_model函数。在其最后一个else前面添加以下注册代码:
python
elif m in {CBAM,ECA,ShuffleAttention,CoordAtt,CAA}:#添加注意力模块,没有CBAM、eca的,M删除即可
c1, c2 = ch[f], args[0]
if c2 != nc:
c2 = make_divisible(min(c2, max_channels) * width, 8)
args = [c1, *args[1:]]
然后,就是新建一个名为YOLOv8_CAA.yaml的配置文件:(路径:ultralytics/cfg/models/v8/YOLOv8_CAA.yaml)其中参数中nc,由自己的数据集决定。本文测试,采用的coco8数据集,有80个类别。
python
# 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: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call CPAM-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 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, 1, CAA, [1024]]
- [-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, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 15 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 21 (P5/32-large)
- [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)
在根目录新建一个train.py文件,内容如下:
python
from ultralytics import YOLO
import warnings
with warnings.catch_warnings():
warnings.simplefilter("ignore")
model = YOLO('ultralytics/cfg/models/v8/YOLOv8_CAA.yaml') # 从YAML建立一个新模型
results = model.train(data='ultralytics/cfg/datasets/coco8.yaml', epochs=1,imgsz=640,optimizer="SGD")
训练输出:
五、总结
以上就是CAA的原理及使用方式,但具体CAA注意力机制的具体位置放哪里,效果更好。需要根据不同的数据集做相应的实验验证。希望本文能够帮助你入门YOLO中注意力机制的使用。