一、注意力机制介绍:
注意力机制(Attention Mechanism)是深度学习中一种重要的技术,它可以帮助模型更好地关注输入数据中的关键信息,从而提高模型的性能。注意力机制最早在自然语言处理领域的序列到序列(seq2seq)模型中得到广泛应用,后来逐渐扩展到了计算机视觉、语音识别等多个领域。
注意力机制的基本思想是为输入数据的每个部分分配一个权重,这个权重表示该部分对于当前任务的重要程度。在自然语言处理任务中,这通常意味着对输入句子中的每个单词分配一个权重,而在计算机视觉任务中,这可能意味着为输入图像的每个像素或区域分配一个权重。
添加方法
总结:1.在conv.py加入注意力代码
2.在__init.oy__和tasks.py引用GAM
3.修改yaml文件
1.在conv.py代码中加入注意力代码
conv.py的路径:ultralytics-main\ultralytics\nn\modules\conv.py
如图下所示:
在conv.py的最下面添加注意力代码:
代码如下:
#-----------注意力机制代码-----------------
import torch.nn as nn
import torch
class GAM_Attention(nn.Module):
def __init__(self, in_channels,c2, rate=4):
super(GAM_Attention, self).__init__()
self.channel_attention = nn.Sequential(
nn.Linear(in_channels, int(in_channels / rate)),
nn.ReLU(inplace=True),
nn.Linear(int(in_channels / rate), in_channels)
)
self.spatial_attention = nn.Sequential(
nn.Conv2d(in_channels, int(in_channels / rate), kernel_size=7, padding=3),
nn.BatchNorm2d(int(in_channels / rate)),
nn.ReLU(inplace=True),
nn.Conv2d(int(in_channels / rate), in_channels, kernel_size=7, padding=3),
nn.BatchNorm2d(in_channels)
)
def forward(self, x):
b, c, h, w = x.shape
x_permute = x.permute(0, 2, 3, 1).view(b, -1, c)
x_att_permute = self.channel_attention(x_permute).view(b, h, w, c)
x_channel_att = x_att_permute.permute(0, 3, 1, 2).sigmoid()
x = x * x_channel_att
x_spatial_att = self.spatial_attention(x).sigmoid()
out = x * x_spatial_att
return out
if __name__ == '__main__':
x = torch.randn(1, 64, 20, 20)
b, c, h, w = x.shape
net = GAM_Attention(in_channels=c)
y = net(x)
print(y.size())
效果如图下所示:
2.注册及引用GAM_Attention
__init__.py文件中引用GAM_Attention
路径:ultralytics-main\ultralytics\nn\modules\__init__.py
如图下:
在__init__.py文件中,在导包里面找到from .conv import和__all__,最后面添加GAM_Attention。
如图下所示:
tasks.py 文件中引用GAM_Attention
路径:ultralytics-main\ultralytics\nn\tasks.py
如图下:
在tasks.py文件中,在导包里面找到from ultralytics.nn.modules最后面添加GAM_Attention
如图下所示:
在tasks.py里写入调用方式
打开tasks.py,Ctrl键+F查找n = 1(有空格)就可以找到添加的位置,如效果图:
# """**************add Attention***************"""
elif m in {GAM_Attention}:
c1, c2 = ch[f], args[0]
if c2 != nc: # if not output
c2 = make_divisible(min(c2, max_channels) * width, 8)
args = [c1, c2, *args[1:]]
效果如图下所示:
3.修改自己的yolov8.yaml文件:
路径如下:ultralytics-main\ultralytics\cfg\models\v8\my_yolov8.yaml
如图下所示:
修改后的代码如下(可以直接复制到自己的yaml里面):
# 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: 80 # 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)
自己修改可以根据下图(修改后的图)红色箭头是需要修改的:
完成以上就可以训练了