参考博客:Yolov8改进---注意力机制:ShuffleAttention、ECA、EffectiveSE、SE_shuffle attention-CSDN博客
在ultralytics/cfg/datasets/ 下新建data.yaml
path: D:/Desktop/fire_smoke_dataset(1)
train: D:/Desktop/fire_smoke_dataset(1)/images/train
val: D:/Desktop/fire_smoke_dataset(1)/images/val
nc : 2
names:
0: fire
1: smoke
main.py训练:
#coding:utf-8
from ultralytics import YOLO
model = YOLO("ultralytics/cfg/models/v8/yolov8_ShuffleAttention.yaml").load('yolov8n.pt')
# Use the model
if __name__ == '__main__':
# Use the model
results = model.train(data='ultralytics/cfg/datasets/data.yaml', epochs=100, batch=4,device='0',workers=1,amp=False) # 训练模型
# 将模型转为onnx格式
# success = model.export(format='onnx')
训练结果:
与没有改进的结果相比:
由以上两图可以看出 P值整体有所上升。
刚开始只添加了一个模块,感觉效果不是特别好。我想着多添加几个会不会好一点,我就添加了三个模块。
yolov8_ShuffleAttention.yaml:
# 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: 4 # 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, 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, 3, ShuffleAttention, [256]]
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 18 (P4/16-medium)
- [-1, 3, ShuffleAttention, [512]]
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 21 (P5/32-large)
- [-1, 3, ShuffleAttention, [1024]]
- [[15, 18, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)
训练结果如下:
效果和添加一个模块的结果差不多。