CA注意力机制代码:
import torch
import torch.nn as nn
import torch.nn.functional as F
class h_sigmoid(nn.Module):
def __init__(self, inplace=True):
super(h_sigmoid, self).__init__()
self.relu = nn.ReLU6(inplace=inplace)
def forward(self, x):
return self.relu(x + 3) / 6
class h_swish(nn.Module):
def __init__(self, inplace=True):
super(h_swish, self).__init__()
self.sigmoid = h_sigmoid(inplace=inplace)
def forward(self, x):
return x * self.sigmoid(x)
class CoordAtt(nn.Module):
def __init__(self, inp, reduction=32):
super(CoordAtt, self).__init__()
self.pool_h = nn.AdaptiveAvgPool2d((None, 1))
self.pool_w = nn.AdaptiveAvgPool2d((1, None))
mip = max(8, inp // reduction)
self.conv1 = nn.Conv2d(inp, mip, kernel_size=1, stride=1, padding=0)
self.bn1 = nn.BatchNorm2d(mip)
self.act = h_swish()
self.conv_h = nn.Conv2d(mip, inp, kernel_size=1, stride=1, padding=0)
self.conv_w = nn.Conv2d(mip, inp, kernel_size=1, stride=1, padding=0)
def forward(self, x):
identity = x
n, c, h, w = x.size()
x_h = self.pool_h(x)
x_w = self.pool_w(x).permute(0, 1, 3, 2)
y = torch.cat([x_h, x_w], dim=2)
y = self.conv1(y)
y = self.bn1(y)
y = self.act(y)
x_h, x_w = torch.split(y, [h, w], dim=2)
x_w = x_w.permute(0, 1, 3, 2)
a_h = self.conv_h(x_h).sigmoid()
a_w = self.conv_w(x_w).sigmoid()
out = identity * a_w * a_h
return out
第一步,在ultralytics\nn\modules\conv.py文件末尾添加CA代码如图:
第二步,在ultralytics\nn\modules_init_.py文件下加入CA注意力机制,主要在from .conv import和__all__ = 里面添加,
图1:
图2:
第三步,在ultralytics\nn\tasks.py首先导入CoordAtt,如图:
其次:按住Ctrl+F,输入:elif m in
,在随便一个elif m in
下面添加CA代码如下:
elif m in {CoordAtt}:
args=[ch[f],*args]
如图所示:
第四步,在\ultralytics\cfg\models\v8文件下,新建一个yolov8-CA.yaml文件,代码如下:
# 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: 3 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.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 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, CoordAtt, [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, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 19 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 22 (P5/32-large)
- [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)
在主目录下新建一个train.py文件代码如下:
from ultralytics import YOLO
#import os
#os.environ['CUDA_VISIBLE_DEVICES']='1'
if __name__ == '__main__':
# Load a model
model = YOLO(r'E:\yolov8_car_deepsort\yolov8_car\ultralytics\cfg\models\v8\yolov8-CA.yaml') # 不使用预训练权重训练
# model = YOLO(r'yolov8p.yaml').load("yolov8n.pt") # 使用预训练权重训练
# Trainparameters ----------------------------------------------------------------------------------------------
model.train(
data=r'E:\yolov8_car_deepsort\yolov8_car\ultralytics\cfg\datasets\mycar.yaml',
epochs= 300 , # (int) number of epochs to train for
batch= 16 , # (int) number of images per batch (-1 for AutoBatch)
imgsz= 640 , # (int) size of input images as integer or w,h
save= True , # (bool) save train checkpoints and predict results
save_period= -1, # (int) Save checkpoint every x epochs (disabled if < 1)
project= 'result', # (str, optional) project name
name= 'yolov8-CA' ,# (str, optional) experiment name, results saved to 'project/name' directory
resume=True
)
记得把路径换成自己的路径。
运行结果如下;
添加成功。