最近使用魔导的思路对YOLOv8的损失函数进行更改:
原文链接如下:
YOLOV8改进-添加EIoU,SIoU,AlphaIoU,FocalEIoU,Wise-IoU_魔鬼面具的博客-CSDN博客
按照这个思路改进之后会出现bug:
会出现
AttributeError: 'tuple' object has no attribute 'squeeze'的报错
改进方法如下:
在ultralytics/util/metrics/bbox_iou文件中,魔导改进原文如下:
def bbox_iou(box1, box2, xywh=True, GIoU=False, DIoU=False, CIoU=False, SIoU=False, EIoU=False, Focal=False, alpha=1, gamma=0.5, eps=1e-7):
# Returns Intersection over Union (IoU) of box1(1,4) to box2(n,4)
# Get the coordinates of bounding boxes
if xywh: # transform from xywh to xyxy
(x1, y1, w1, h1), (x2, y2, w2, h2) = box1.chunk(4, -1), box2.chunk(4, -1)
w1_, h1_, w2_, h2_ = w1 / 2, h1 / 2, w2 / 2, h2 / 2
b1_x1, b1_x2, b1_y1, b1_y2 = x1 - w1_, x1 + w1_, y1 - h1_, y1 + h1_
b2_x1, b2_x2, b2_y1, b2_y2 = x2 - w2_, x2 + w2_, y2 - h2_, y2 + h2_
else: # x1, y1, x2, y2 = box1
b1_x1, b1_y1, b1_x2, b1_y2 = box1.chunk(4, -1)
b2_x1, b2_y1, b2_x2, b2_y2 = box2.chunk(4, -1)
w1, h1 = b1_x2 - b1_x1, (b1_y2 - b1_y1).clamp(eps)
w2, h2 = b2_x2 - b2_x1, (b2_y2 - b2_y1).clamp(eps)
# Intersection area
inter = (b1_x2.minimum(b2_x2) - b1_x1.maximum(b2_x1)).clamp(0) * \
(b1_y2.minimum(b2_y2) - b1_y1.maximum(b2_y1)).clamp(0)
# Union Area
union = w1 * h1 + w2 * h2 - inter + eps
# IoU
# iou = inter / union # ori iou
iou = torch.pow(inter/(union + eps), alpha) # alpha iou
if CIoU or DIoU or GIoU or EIoU or SIoU:
cw = b1_x2.maximum(b2_x2) - b1_x1.minimum(b2_x1) # convex (smallest enclosing box) width
ch = b1_y2.maximum(b2_y2) - b1_y1.minimum(b2_y1) # convex height
if CIoU or DIoU or EIoU or SIoU: # Distance or Complete IoU https://arxiv.org/abs/1911.08287v1
c2 = (cw ** 2 + ch ** 2) ** alpha + eps # convex diagonal squared
rho2 = (((b2_x1 + b2_x2 - b1_x1 - b1_x2) ** 2 + (b2_y1 + b2_y2 - b1_y1 - b1_y2) ** 2) / 4) ** alpha # center dist ** 2
if CIoU: # https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/master/utils/box/box_utils.py#L47
v = (4 / math.pi ** 2) * (torch.atan(w2 / h2) - torch.atan(w1 / h1)).pow(2)
with torch.no_grad():
alpha_ciou = v / (v - iou + (1 + eps))
if Focal:
return iou - (rho2 / c2 + torch.pow(v * alpha_ciou + eps, alpha)), torch.pow(inter/(union + eps), gamma) # Focal_CIoU
else:
return iou - (rho2 / c2 + torch.pow(v * alpha_ciou + eps, alpha)) # CIoU
elif EIoU:
rho_w2 = ((b2_x2 - b2_x1) - (b1_x2 - b1_x1)) ** 2
rho_h2 = ((b2_y2 - b2_y1) - (b1_y2 - b1_y1)) ** 2
cw2 = torch.pow(cw ** 2 + eps, alpha)
ch2 = torch.pow(ch ** 2 + eps, alpha)
if Focal:
return iou - (rho2 / c2 + rho_w2 / cw2 + rho_h2 / ch2), torch.pow(inter/(union + eps), gamma) # Focal_EIou
else:
return iou - (rho2 / c2 + rho_w2 / cw2 + rho_h2 / ch2) # EIou
elif SIoU:
# SIoU Loss https://arxiv.org/pdf/2205.12740.pdf
s_cw = (b2_x1 + b2_x2 - b1_x1 - b1_x2) * 0.5 + eps
s_ch = (b2_y1 + b2_y2 - b1_y1 - b1_y2) * 0.5 + eps
sigma = torch.pow(s_cw ** 2 + s_ch ** 2, 0.5)
sin_alpha_1 = torch.abs(s_cw) / sigma
sin_alpha_2 = torch.abs(s_ch) / sigma
threshold = pow(2, 0.5) / 2
sin_alpha = torch.where(sin_alpha_1 > threshold, sin_alpha_2, sin_alpha_1)
angle_cost = torch.cos(torch.arcsin(sin_alpha) * 2 - math.pi / 2)
rho_x = (s_cw / cw) ** 2
rho_y = (s_ch / ch) ** 2
gamma = angle_cost - 2
distance_cost = 2 - torch.exp(gamma * rho_x) - torch.exp(gamma * rho_y)
omiga_w = torch.abs(w1 - w2) / torch.max(w1, w2)
omiga_h = torch.abs(h1 - h2) / torch.max(h1, h2)
shape_cost = torch.pow(1 - torch.exp(-1 * omiga_w), 4) + torch.pow(1 - torch.exp(-1 * omiga_h), 4)
if Focal:
return iou - torch.pow(0.5 * (distance_cost + shape_cost) + eps, alpha), torch.pow(inter/(union + eps), gamma) # Focal_SIou
else:
return iou - torch.pow(0.5 * (distance_cost + shape_cost) + eps, alpha) # SIou
if Focal:
return iou - rho2 / c2, torch.pow(inter/(union + eps), gamma) # Focal_DIoU
else:
return iou - rho2 / c2 # DIoU
c_area = cw * ch + eps # convex area
if Focal:
return iou - torch.pow((c_area - union) / c_area + eps, alpha), torch.pow(inter/(union + eps), gamma) # Focal_GIoU https://arxiv.org/pdf/1902.09630.pdf
else:
return iou - torch.pow((c_area - union) / c_area + eps, alpha) # GIoU https://arxiv.org/pdf/1902.09630.pdf
if Focal:
return iou, torch.pow(inter/(union + eps), gamma) # Focal_IoU
else:
return iou # IoU
解决方法:
对每一个if后面的focal进行修改:
以CIOU为例:
if Focal:
return iou - (rho2 / c2 + torch.pow(v * alpha_ciou + eps, alpha)), torch.pow(inter/(union + eps), gamma) # Focal_CIoU
if Focal:
return iou - ((rho2 / c2 + torch.pow(v * alpha_ciou + eps, alpha)), torch.pow(inter/(union + eps), gamma))[0] # Focal_CIoU即可成功运行
同理要实现 FocalEIOU、SIOU或者其他IOU都需要进行更改
【代码】AttributeError: ‘tuple‘ object has no attribute ‘squeeze‘根据魔导YOLov8改进Focal IOU时出现问题解决。
target = target.cuda()
时,出现错误AttributeError: 'tuple' object has no attribute 'cuda'
tuple转成tensor
target是tuple类型,但.conda()需要是tensor类型
tuple——np.array——tensor(中间需要np.array中转;且np.array的元素需要是int或float(原本是str),使用.astype(in
这往往发生在我们对一个tuple类型数据,调用成员变量shape所致(a.shape 或 a.shape[])。
所以要查看调用发生处,看看自己的数据类型是不是有错。我们看代码
import numpy as np
a = np.zeros([5,5])
#正确使用方式:
print(a)
print(type(a))
print(ty...
今天来给大家介绍几种在Python编程中,所常见的几种错误类型。1.在用加号进行拼接时,必须用字符串。name='小明'
age=18
print('我的名字是'+name+',我今年'+age+'岁了')点击运行输出时会报错,错误提示为 :TypeError: must be str, not int,翻译为类型错误,必须为字符串str,不能是数字int。解决方案为:name='小明'
age=...
Pycharm关于AttributeError: ‘DataFrame’ object has no attribute ‘score’的错误
import pandas
data = pandas.read_excel(
r"C:\Users\ASUS\Desktop\0012\data7.1.2.xlsx",
data.score.describe()
# 逐项分析各统计量
data.score.size
data.score.max()
data.score.min()
data.score.sum()
data.score.mea
numpy.array可使用 shape。list不能使用shape。
可以使用np.array(list A)进行转换。
(array转list:array B B.tolist()即可)
补充知识:Pandas使用DataFrame出现错误:AttributeError: ‘list’ object has no attribute ‘astype’
在使用Pandas的DataFrame时出现了错误:AttributeError: ‘list’ object has no attribute ‘astype’
代码入下:
import pandas as pd
pop = {'Neva
import pymysql
#创建连接
con = pymysql.connect(host='localhost',user='root',password='123456',port=3306,database='zhy')
#创建游标对象
cur = con.curson()
#编写查询的sql语句
sql = 'select * from t_student'
cur.execute(sql)
print(查询成功)
students = cur.fetchall()
print(students)
except Exception as
多线程爬虫出现报错AttributeError: ‘NoneType’ object has no attribute ‘xpath’一、前言二、问题三、思考和解决问题四、运行效果
mark一下,本技术小白的第一篇CSDN博客!
最近在捣鼓爬虫,看的是机械工业出版社的《从零开始学Python网络爬虫》。这书吧,一言难尽,优点是案例比较多,说的也还算清楚,但是槽点更多:1、较多低级笔误;2、基础知识一笔带过,简单得不能再简单,对Python基础不好的人不友好;3、代码分析部分,相同的代码反复啰嗦解释多次,而一些该解释的新代码却只字不提;4、这是最重要的一点,但也不全是本书的锅。就是书中
Traceback (most recent call last):
File "D:\anaconda\lib\site-packages\django\core\handlers\exception.py", line 34, in inner
response = get_response(request)
File "D:\anaconda\lib\site-packages\django\core\handlers\base.py", line 115, in _ge
RuntimeError: Given groups=1, weight of size [6, 3, 3, 3], expected input[64, 14, 22, 3] to have 3 channels, but got 14 channels instead
卷积权重为输入3通道, 输出6通道, 卷积核大小为3*3
但是认为输入数据为14通道,是不是应该把数据通道值放到shape[1]
现在输入张量维度为torch.Size([64, 3, 22, 14]),依旧报错
RuntimeError