目录
1. 修改VOC标签的名称
该代码使用于对目标检测VOC标签中的标签名称进行修改。
<?xml version='1.0' encoding='us-ascii'?>
<annotation>
<folder>img</folder>
<filename>12.jpg</filename>
<path>E:\img\12.jpg</path>
<source>
<database>Unknown</database>
</source>
<size>
<width>640</width>
<height>640</height>
<depth>3</depth>
</size>
<segmented>0</segmented>
<object>
<name>insulator</name>
<pose>Unspecified</pose>
<truncated>1</truncated>
<difficult>0</difficult>
<bndbox>
<xmin>203</xmin>
<ymin>177</ymin>
<xmax>281</xmax>
<ymax>640</ymax>
</bndbox>
</object>
<object>
<name>insulator</name>
<pose>Unspecified</pose>
<truncated>1</truncated>
<difficult>0</difficult>
<bndbox>
<xmin>344</xmin>
<ymin>167</ymin>
<xmax>436</xmax>
<ymax>640</ymax>
</bndbox>
</object>
</annotation>比如说我们需要将上面voc标签中的“insulator”改为“insulator2”，就可以在下面代码中将“name= ['原始类别', '修改后的类别']”修改为“name= ['insulator', 'insulator2']”。程序中path表示的是存放voc标签的路径。
import os.path
import xml.dom.minidom
# 原始xml文件存放路径
path = 'D:\csv2coco\Annotations_new'
# 定义需替换的类名['原始类别名称','新名称']
name = ['原始类别', '修改后的类别']
files = os.listdir(path) # 返回文件夹中的文件名列表
for xmlFile in files:
dom = xml.dom.minidom.parse(path + '\\' + xmlFile)
root = dom.documentElement
newfilename = root.getElementsByTagName('name')
for i, t in enumerate(newfilename):
if t.firstChild.data == name[0]:
newfilename[i].firstChild.data = name[1]
with open(os.path.join(path, xmlFile), 'w') as fh:
dom.writexml(fh)
2. voc标签转换为txt标签
该代码用来从 VOC格式的annotations/*.xml 生成 YOLO格式的labels/*.txt;从xml文件中提取对应于图片的注释信息，并将其按yolo训练所需的格式存储在*.txt文件中，一个xml文件生成一个对应的txt文件。
import os.path
import xml.etree.ElementTree as ET
class_names = ['类别1', '类别2'', '类别3'' ,'类别4'' ]
xmlpath = '' # 原xml路径
txtpath = '' # 转换后txt文件存放路径
files = []
if not os.path.exists(txtpath):
os.makedirs(txtpath)
for root, dirs, files in os.walk(xmlpath):
pass
# print("current dir is {}\nhis subdirs are {}\nnumber of files in current dir is {}\n".format(root,dirs,len(files)))
number = len(files)
print(number)
# print(type(files[0]),files[0],files[0][0],files[0][1],files[0][2],files[0][3],files[0][4])#files[i] <--> *.xml
i = 0
while i < number:
name = files[i][0:-4]
print(name)
xml_name = name + ".xml"
txt_name = name + ".txt"
xml_file_name = xmlpath + '\\'+ xml_name
txt_file_name = txtpath + '\\'+txt_name
print(xml_name,txt_name,xml_file_name,txt_file_name)
xml_file = open(xml_file_name,encoding='utf-8')
print(xml_file)
tree = ET.parse(xml_file)
print(tree)
root = tree.getroot()
print(root)
image_name = root.find('filename').text
print(image_name)
w = int(root.find('size').find('width').text)
h = int(root.find('size').find('height').text)
c = int(root.find('size').find('depth').text)
print("img_width={},img_height={},img_channels={}".format(w,h,c))
#write info from xml to txt
obj=[i for i in root.iter('object') ]
print(obj)
f_txt = open(txt_file_name, 'w+')
content = ""
first = True
for obj in root.iter('object'):
name = obj.find('name').text
class_num = class_names.index(name)
# class_num = 0
xmlbox = obj.find('bndbox')
x1 = int(xmlbox.find('xmin').text)
x2 = int(xmlbox.find('xmax').text)
y1 = int(xmlbox.find('ymin').text)
y2 = int(xmlbox.find('ymax').text)
if first:
content += str(class_num) + " " + \
str((x1 + x2) / 2 / w) + " " + str((y1 + y2) / 2 / h) + " " + \
str((x2 - x1) / w) + " " + str((y2 - y1) / h)
first = False
else:
content += "\n" + \
str(class_num) + " " + \
str((x1 + x2) / 2 / w) + " " + str((y1 + y2) / 2 / h) + " " + \
str((x2 - x1) / w) + " " + str((y2 - y1) / h)
print(str(i / (number - 1) * 100) + "%\n")
# print(content)
f_txt.write(content)
f_txt.close()
xml_file.close()
i += 13. CSV标签转换为VOC标签
此代码会设计到一些环境库的安装：
1. 安装pandas库
pip install pandas2. 安装glob库（python3.7）
pip install glob33. 安装cv2库
pip install opencv-python1. 首先更改代码中以下几个配置。
csv_file = "labels.csv"
saved_path = ".VOC2007/" # path to save converted voc dataset
image_save_path = "./JPEGImages/" # converted voc images path
image_raw_parh = "images/" # original image path2. 然后运行程序。
3. 同样会自动创建文件夹并复制图片到相应位置。
import os
import numpy as np
import codecs
import pandas as pd
import json
from glob import glob
import cv2
import shutil
from sklearn.model_selection import train_test_split
from IPython import embed
#1.标签路径
csv_file = "../csv/train_labels.csv"
saved_path = "./VOCdevkit/VOC2007/" #保存路径
image_save_path = "./JPEGImages/"
image_raw_parh = "../csv/images/"
#2.创建要求文件夹
if not os.path.exists(saved_path + "Annotations"):
os.makedirs(saved_path + "Annotations")
if not os.path.exists(saved_path + "JPEGImages/"):
os.makedirs(saved_path + "JPEGImages/")
if not os.path.exists(saved_path + "ImageSets/Main/"):
os.makedirs(saved_path + "ImageSets/Main/")
#3.获取待处理文件
total_csv_annotations = {}
annotations = pd.read_csv(csv_file,header=None).values
for annotation in annotations:
key = annotation[0].split(os.sep)[-1]
value = np.array([annotation[1:]])
if key in total_csv_annotations.keys():
total_csv_annotations[key] = np.concatenate((total_csv_annotations[key],value),axis=0)
else:
total_csv_annotations[key] = value
#4.读取标注信息并写入 xml
for filename,label in total_csv_annotations.items():
#embed()
height, width, channels = cv2.imread(image_raw_parh + filename).shape
#embed()
with codecs.open(saved_path + "Annotations/"+filename.replace(".jpg",".xml"),"w","utf-8") as xml:
xml.write('<annotation>\n')
xml.write('\t<folder>' + 'UAV_data' + '</folder>\n')
xml.write('\t<filename>' + filename + '</filename>\n')
xml.write('\t<source>\n')
xml.write('\t\t<database>The UAV autolanding</database>\n')
xml.write('\t\t<annotation>UAV AutoLanding</annotation>\n')
xml.write('\t\t<image>flickr</image>\n')
xml.write('\t\t<flickrid>NULL</flickrid>\n')
xml.write('\t</source>\n')
xml.write('\t<owner>\n')
xml.write('\t\t<flickrid>NULL</flickrid>\n')
xml.write('\t\t<name>ChaojieZhu</name>\n')
xml.write('\t</owner>\n')
xml.write('\t<size>\n')
xml.write('\t\t<width>'+ str(width) + '</width>\n')
xml.write('\t\t<height>'+ str(height) + '</height>\n')
xml.write('\t\t<depth>' + str(channels) + '</depth>\n')
xml.write('\t</size>\n')
xml.write('\t\t<segmented>0</segmented>\n')
if isinstance(label,float):
## 空白
xml.write('</annotation>')
continue
for label_detail in label:
labels = label_detail
#embed()
xmin = int(labels[0])
ymin = int(labels[1])
xmax = int(labels[2])
ymax = int(labels[3])
label_ = labels[-1]
if xmax <= xmin:
pass
elif ymax <= ymin:
pass
else:
xml.write('\t<object>\n')
xml.write('\t\t<name>'+label_+'</name>\n')
xml.write('\t\t<pose>Unspecified</pose>\n')
xml.write('\t\t<truncated>1</truncated>\n')
xml.write('\t\t<difficult>0</difficult>\n')
xml.write('\t\t<bndbox>\n')
xml.write('\t\t\t<xmin>' + str(xmin) + '</xmin>\n')
xml.write('\t\t\t<ymin>' + str(ymin) + '</ymin>\n')
xml.write('\t\t\t<xmax>' + str(xmax) + '</xmax>\n')
xml.write('\t\t\t<ymax>' + str(ymax) + '</ymax>\n')
xml.write('\t\t</bndbox>\n')
xml.write('\t</object>\n')
print(filename,xmin,ymin,xmax,ymax,labels)
xml.write('</annotation>')
#6.split files for txt
txtsavepath = saved_path + "ImageSets/Main/"
ftrainval = open(txtsavepath+'/trainval.txt', 'w')
ftest = open(txtsavepath+'/test.txt', 'w')
ftrain = open(txtsavepath+'/train.txt', 'w')
fval = open(txtsavepath+'/val.txt', 'w')
total_files = glob(saved_path+"./Annotations/*.xml")
total_files = [i.split("/")[-1].split(".xml")[0] for i in total_files]
#test_filepath = ""
for file in total_files:
ftrainval.write(file + "\n")
# move images to voc JPEGImages folder
for image in glob(image_raw_parh+"/*.jpg"):
shutil.copy(image,saved_path+image_save_path)
train_files,val_files = train_test_split(total_files,test_size=0.15,random_state=42)
for file in train_files:
ftrain.write(file + "\n")
#val
for file in val_files:
fval.write(file + "\n")
ftrainval.close()
ftrain.close()
fval.close()
#ftest.close()
扫一扫
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
