【图像标注篇】格式转换详解,labelimg标注生成的xml文件转成yolov5使用的txt格式,并进行格式划分。
xml转换成txt格式代码如下
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
# 数据标签
classes = ['insulator','negative_feeder_shoulder','hat','flat_wrist','support_windbreak_cable','position_windbreak_cable']
def convert(size, box):
dw = 1./(size[0])
dh = 1./(size[1])
x = (box[0] + box[1])/2.0 - 1
y = (box[2] + box[3])/2.0 - 1
w = box[1] - box[0]
h = box[3] - box[2]
x = x*dw
w = w*dw
y = y*dh
h = h*dh
if w>=1:
w=0.99
if h>=1:
h=0.99
return (x,y,w,h)
def convert_annotation(rootpath,xmlname):
xmlpath = rootpath + '/xml'
xmlfile = os.path.join(xmlpath,xmlname)
with open(xmlfile, "r", encoding='UTF-8') as in_file:
txtname = xmlname[:-4]+'.txt'
print(txtname)
txtpath = rootpath + '/worktxt'
if not os.path.exists(txtpath):
os.makedirs(txtpath)
txtfile = os.path.join(txtpath,txtname)
with open(txtfile, "w+" ,encoding='UTF-8') as out_file:
tree=ET.parse(in_file)
root = tree.getroot()
size = root.find('size')
w = int(size.find('width').text)
h = int(size.find('height').text)
out_file.truncate()
for obj in root.iter('object'):
difficult = obj.find('Difficult').text
cls = obj.find('name').text
if cls not in classes or int(difficult)==1:
continue
cls_id = classes.index(cls)
xmlbox = obj.find('bndbox')
b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text), float(xmlbox.find('ymax').text))
bb = convert((w,h), b)
out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
if __name__ == "__main__":
rootpath='C:/Users/Dell/Desktop/merge'
xmlpath=rootpath+'/xml'
list=os.listdir(xmlpath)
for i in range(0,len(list)) :
path = os.path.join(xmlpath,list[i])
if ('.xml' in path)or('.XML' in path):
convert_annotation(rootpath,list[i])
print('done', i)
else:
print('not xml file',i)
只需修改路径即可。
格式划分8:1:1
import os
import shutil
root_path = "C:/Users/Dell/Desktop/merge/dataset/"
img_path = "C:/Users/Dell/Desktop/merge/insulator/images/"
txt_path = "C:/Users/Dell/Desktop/merge/worktxt/"
def train_test_move(txt_path,root_path,img_path):
files = os.listdir(txt_path)
l = len(files)
sets = ['train', 'valid', 'test']
k = 0
p = 0.8
for i in sets:
if not os.path.exists(root_path+i):
print(root_path+i)
os.mkdir(root_path+i)
os.mkdir(root_path+i+"/images")
os.mkdir(root_path+i+"/labels")
for file in files[round(l*k):round(l*p)]:
shutil.copy(txt_path+file,root_path+i+"/labels")
shutil.copy(img_path+file[:-3]+"jpg",root_path+i+"/images")
k = p
p += 0.1
train_test_move(txt_path,root_path,img_path)
txt格式转成xml格式
import os
import xml.etree.ElementTree as ET
from PIL import Image
import numpy as np
# 图片文件夹,后面的/不能省
img_path = 'C:/Users/Dell/Desktop/merge/insulator/images/'
# txt文件夹,后面的/不能省
labels_path = 'C:/Users/Dell/Desktop/merge/insulator/labels/'
# xml存放的文件夹,后面的/不能省
annotations_path = 'C:/Users/Dell/Desktop/merge/insulator/xml/'
labels = os.listdir(labels_path)
# 类别
classes = ["insulator"]
# 图片的高度、宽度、深度
sh = sw = sd = 0
def write_xml(imgname, sw, sh, filepath, labeldicts):
'''
imgname: 没有扩展名的图片名称
'''
# 创建Annotation根节点
root = ET.Element('xml')
# 创建filename子节点,无扩展名
ET.SubElement(root, 'filename').text = str(imgname)
# 创建size子节点
sizes = ET.SubElement(root,'size')
ET.SubElement(sizes, 'width').text = str(sw)
ET.SubElement(sizes, 'height').text = str(sh)
#ET.SubElement(sizes, 'depth').text = str(sd)
for labeldict in labeldicts:
objects = ET.SubElement(root, 'object')
ET.SubElement(objects, 'name').text = labeldict['name']
ET.SubElement(objects, 'pose').text = 'Unspecified'
ET.SubElement(objects, 'truncated').text = '0'
ET.SubElement(objects, 'Difficult').text = '0'
bndbox = ET.SubElement(objects,'bndbox')
ET.SubElement(bndbox, 'xmin').text = str(int(labeldict['xmin']))
ET.SubElement(bndbox, 'ymin').text = str(int(labeldict['ymin']))
ET.SubElement(bndbox, 'xmax').text = str(int(labeldict['xmax']))
ET.SubElement(bndbox, 'ymax').text = str(int(labeldict['ymax']))
tree = ET.ElementTree(root)
tree.write(filepath, encoding='utf-8')
for label in labels:
with open(labels_path + label, 'r') as f:
img_id = os.path.splitext(label)[0]
contents = f.readlines()
labeldicts = []
for content in contents:
# 这里要看你的图片格式了,我这里是jpg,注意修改
img = np.array(Image.open(img_path + label.strip('.txt') + '.jpg'))
# 图片的高度和宽度
#sh, sw, sd = img.shape[0], img.shape[1], img.shape[2]
sh, sw = img.shape[0], img.shape[1]
content = content.strip('\n').split()
x = float(content[1])*sw
y = float(content[2])*sh
w = float(content[3])*sw
h = float(content[4])*sh
# 坐标的转换,x_center y_center width height -> xmin ymin xmax ymax
new_dict = {'name': classes[int(content[0])],
'difficult': '0',
'xmin': x+1-w/2,
'ymin': y+1-h/2,
'xmax': x+1+w/2,
'ymax': y+1+h/2
}
labeldicts.append(new_dict)
#write_xml(img_id, sw, sh, sd, annotations_path + label.strip('.txt') + '.xml', labeldicts)
write_xml(img_id, sw, sh, annotations_path + label.strip('.txt') + '.xml', labeldicts)