Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
30 commits
Select commit Hold shift + click to select a range
08a7a5f
为语句引入变量名
aasdar Sep 13, 2025
819ebfd
Merge branch 'OpenHUTB:main' into main
aasdar Sep 13, 2025
f99ab3c
自动驾驶汽车车道与路径检测系统
aasdar Sep 16, 2025
6d4a2c4
Merge branch 'OpenHUTB:main' into main
aasdar Sep 16, 2025
1552d74
Merge branch 'OpenHUTB:main' into main
aasdar Sep 22, 2025
64b17c0
Merge branch 'OpenHUTB:main' into main
aasdar Sep 23, 2025
971af7f
车辆检测系统
aasdar Sep 24, 2025
f3cef2f
Merge branch 'OpenHUTB:main' into main
aasdar Sep 29, 2025
edc891f
车辆检测
aasdar Oct 26, 2025
7250150
Merge branch 'main' of https://github.com/aasdar/nn
aasdar Oct 26, 2025
da4ab23
车辆检测
aasdar Oct 26, 2025
8a09efe
Merge branch 'OpenHUTB:main' into main
aasdar Oct 27, 2025
1855e6b
车辆检测
aasdar Oct 27, 2025
8c3888e
Merge branch 'main' of https://github.com/aasdar/nn
aasdar Oct 27, 2025
c771bdc
Merge branch 'OpenHUTB:main' into main
aasdar Dec 1, 2025
ab3be99
车辆检测
aasdar Dec 1, 2025
df04de4
Merge branch 'main' of https://github.com/aasdar/nn
aasdar Dec 1, 2025
e58c1c1
Merge branch 'OpenHUTB:main' into main
aasdar Dec 16, 2025
be544fd
车辆检测系统
aasdar Dec 16, 2025
24900a5
Merge branch 'main' of https://github.com/aasdar/nn
aasdar Dec 16, 2025
d0555db
Merge branch 'OpenHUTB:main' into main
aasdar Dec 16, 2025
0412632
车辆检测
aasdar Dec 16, 2025
69f8932
Merge branch 'main' of https://github.com/aasdar/nn
aasdar Dec 16, 2025
6a01be7
车辆检测
aasdar Dec 17, 2025
bdb6561
Merge branch 'OpenHUTB:main' into main
aasdar Dec 17, 2025
64bfcb3
车辆检测(添加模型训练代码)
aasdar Dec 17, 2025
7d6811c
车辆检测
aasdar Dec 17, 2025
282ee5c
Merge branch 'OpenHUTB:main' into 111
aasdar Dec 17, 2025
a9b81cf
车辆检测
aasdar Dec 17, 2025
0e3dd61
Merge branch 'OpenHUTB:main' into 111
aasdar Dec 17, 2025
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
113 changes: 113 additions & 0 deletions src/Yolov4_Vehicle_inspection/kmeans_for_anchors.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,113 @@
#-------------------------------------------------------------------------------------------------#
# kmeans虽然会对数据集中的框进行聚类,但是很多数据集由于框的大小相近,聚类出来的9个框相差不大,
# 这样的框反而不利于模型的训练。因为不同的特征层适合不同大小的先验框,越浅的特征层适合越大的先验框
# 原始网络的先验框已经按大中小比例分配好了,不进行聚类也会有非常好的效果。
#-------------------------------------------------------------------------------------------------#
import glob
import xml.etree.ElementTree as ET

import numpy as np

def cas_iou(box,cluster):
x = np.minimum(cluster[:,0],box[0])
y = np.minimum(cluster[:,1],box[1])

intersection = x * y
area1 = box[0] * box[1]

area2 = cluster[:,0] * cluster[:,1]
iou = intersection / (area1 + area2 -intersection)

return iou

def avg_iou(box,cluster):
return np.mean([np.max(cas_iou(box[i],cluster)) for i in range(box.shape[0])])

def kmeans(box,k):
# 取出一共有多少框
row = box.shape[0]

# 每个框各个点的位置
distance = np.empty((row,k))

# 最后的聚类位置
last_clu = np.zeros((row,))

np.random.seed()

# 随机选5个当聚类中心
cluster = box[np.random.choice(row,k,replace = False)]
# cluster = random.sample(row, k)
while True:
# 计算每一行距离五个点的iou情况。
for i in range(row):
distance[i] = 1 - cas_iou(box[i],cluster)

# 取出最小点
near = np.argmin(distance,axis=1)

if (last_clu == near).all():
break

# 求每一个类的中位点
for j in range(k):
cluster[j] = np.median(
box[near == j],axis=0)

last_clu = near

return cluster

def load_data(path):
data = []
# 对于每一个xml都寻找box
for xml_file in glob.glob('{}/*xml'.format(path)):
tree = ET.parse(xml_file)
height = int(tree.findtext('./size/height'))
width = int(tree.findtext('./size/width'))
if height<=0 or width<=0:
continue

# 对于每一个目标都获得它的宽高
for obj in tree.iter('object'):
xmin = int(float(obj.findtext('bndbox/xmin'))) / width
ymin = int(float(obj.findtext('bndbox/ymin'))) / height
xmax = int(float(obj.findtext('bndbox/xmax'))) / width
ymax = int(float(obj.findtext('bndbox/ymax'))) / height

xmin = np.float64(xmin)
ymin = np.float64(ymin)
xmax = np.float64(xmax)
ymax = np.float64(ymax)
# 得到宽高
data.append([xmax-xmin,ymax-ymin])
return np.array(data)


if __name__ == '__main__':
# 运行该程序会计算'./VOCdevkit/VOC2007/Annotations'的xml
# 会生成yolo_anchors.txt
SIZE = 416
anchors_num = 9
# 载入数据集,可以使用VOC的xml
path = r'./VOCdevkit/VOC2007/Annotations'

# 载入所有的xml
# 存储格式为转化为比例后的width,height
data = load_data(path)

# 使用k聚类算法
out = kmeans(data,anchors_num)
out = out[np.argsort(out[:,0])]
print('acc:{:.2f}%'.format(avg_iou(data,out) * 100))
print(out*SIZE)
data = out*SIZE
f = open("yolo_anchors.txt", 'w')
row = np.shape(data)[0]
for i in range(row):
if i == 0:
x_y = "%d,%d" % (data[i][0], data[i][1])
else:
x_y = ", %d,%d" % (data[i][0], data[i][1])
f.write(x_y)
f.close()
31 changes: 31 additions & 0 deletions src/Yolov4_Vehicle_inspection/move_pic.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,31 @@
import os
import random
import shutil

# xml路径的地址
XmlPath = r'xml_train'
# 原图片的地址
pictureBasePath = r"E:\Insight-MVT_Annotation_Train"

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

不能用绝对路径,其他地方也是

# 保存图片的地址
saveBasePath = r"E:\picture_train"

total_xml = os.listdir(XmlPath)
num = len(total_xml)
list = range(num)
if os.path.exists(saveBasePath) == False: # 判断文件夹是否存在
os.makedirs(saveBasePath)
from tqdm import tqdm
for xml in tqdm(total_xml):
xml_temp = xml.split("__")
folder = xml_temp[0]
filename = xml_temp[1].split(".")[0] + ".jpg"
# print(folder)
# print(filename)
temp_pictureBasePath = os.path.join(pictureBasePath, folder)
filePath = os.path.join(temp_pictureBasePath, filename)
# print(filePath)
newfile = xml.split(".")[0] + ".jpg"
newfile_path = os.path.join(saveBasePath, newfile)
# print(newfile_path)
shutil.copyfile(filePath, newfile_path)
print("xml file total number", num)
15 changes: 15 additions & 0 deletions src/Yolov4_Vehicle_inspection/test.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,15 @@
#--------------------------------------------#
# 该部分代码只用于看网络结构,并非测试代码
# map测试请看get_dr_txt.py、get_gt_txt.py
# 和get_map.py
#--------------------------------------------#
import torch
from torchsummary import summary

from nets.yolo4 import YoloBody

if __name__ == "__main__":
# 需要使用device来指定网络在GPU还是CPU运行
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = YoloBody(3,20).to(device)
summary(model, input_size=(3, 416, 416))
Loading