由于在制作VOC数据集时,未生成标注文件(xml),直接生成了labels,格式如下:
先需将其转换为xml文件,格式如下,用于别的模型训练。
转化代码如下(C++):
# encoding: utf-8
from xml.dom.minidom import Document
import os
import os.path
from PIL import Image
ann_path = "/home/swl/darknet_smoke/scripts/VOCdevkit/VOC2019/111111/labels/" # labels .txt文件夹所在位置
img_path = "/home/swl/darknet_smoke/scripts/VOCdevkit/VOC2019/111111/JPEGImages/" # 原图文件夹所在位置
xml_path = "/home/swl/darknet_smoke/scripts/VOCdevkit/VOC2019/111111/Annotations/" # 所需生成的xml文件所在位置
#print("111")
if not os.path.exists(xml_path):
os.mkdir(xml_path)
#print("1121")
def writeXml(tmp, imgname, w, h, objbud, wxml):
doc = Document()
#owner
##print("111")
a = float (str(w))
#print(a)
#print(type(a))
b = float (str(h))
#print(b)
#print(type(b))
annotation = doc.createElement('annotation') #创建annotation一级节点
doc.appendChild(annotation)
##print(annotation)
#owner
folder = doc.createElement('folder')
annotation.appendChild(folder)
folder_txt = doc.createTextNode("VOC2005")
folder.appendChild(folder_txt)
filename = doc.createElement('filename')
annotation.appendChild(filename)
filename_txt = doc.createTextNode(imgname)
filename.appendChild(filename_txt)
#ones#
source = doc.createElement('source')
annotation.appendChild(source)
database = doc.createElement('database')
source.appendChild(database)
database_txt = doc.createTextNode("The VOC2019 Database")
database.appendChild(database_txt)
# 以下两个为VOC里没有的
annotation_new = doc.createElement('annotation')
source.appendChild(annotation_new)
annotation_new_txt = doc.createTextNode("PASCAL VOC2019")
annotation_new.appendChild(annotation_new_txt)
image = doc.createElement('image')
source.appendChild(image)
image_txt = doc.createTextNode("flickr")
image.appendChild(image_txt)
#onee#
#twos#
size = doc.createElement('size')
annotation.appendChild(size)
#width
width = doc.createElement('width')
size.appendChild(width)
width_txt = doc.createTextNode(str(w))
width.appendChild(width_txt)
#height
height = doc.createElement('height')
size.appendChild(height)
height_txt = doc.createTextNode(str(h))
height.appendChild(height_txt)
#depth
depth = doc.createElement('depth')
size.appendChild(depth)
depth_txt = doc.createTextNode("3")
depth.appendChild(depth_txt)
#twoe#
segmented = doc.createElement('segmented')
annotation.appendChild(segmented)
segmented_txt = doc.createTextNode("0")
segmented.appendChild(segmented_txt)
##print("111")
for i in range(0,len(objbud)/5):
#threes#
object_new = doc.createElement("object")
annotation.appendChild(object_new)
name = doc.createElement('name')
object_new.appendChild(name)
name_txt = doc.createTextNode("smoke")
name.appendChild(name_txt)
pose = doc.createElement('pose')
object_new.appendChild(pose)
pose_txt = doc.createTextNode("Unspecified")
pose.appendChild(pose_txt)
truncated = doc.createElement('truncated')
object_new.appendChild(truncated)
truncated_txt = doc.createTextNode("0")
truncated.appendChild(truncated_txt)
difficult = doc.createElement('difficult')
object_new.appendChild(difficult)
difficult_txt = doc.createTextNode("0")
difficult.appendChild(difficult_txt)
#threes-1#
bndbox = doc.createElement('bndbox')
object_new.appendChild(bndbox)
xmin = doc.createElement('xmin')
bndbox.appendChild(xmin)
xmin_txt = doc.createTextNode(str(int (float (objbud[i*5+1])*a-float (objbud[i*5+3])*(a/2.0))))
#xmin_txt = doc.createTextNode(str(float (objbud[i*5+1])))
xmin.appendChild(xmin_txt)
#print(float (objbud[i*5+1])*a-a/2)
#print(float (objbud[i*5+1]))
#print(type(float (objbud[i*5+1])))
ymin = doc.createElement('ymin')
bndbox.appendChild(ymin)
ymin_txt = doc.createTextNode(str(int (float (objbud[i*5+2])*b-float (objbud[i*5+4])*(b/2.0))))
ymin.appendChild(ymin_txt)
xmax = doc.createElement('xmax')
bndbox.appendChild(xmax)
xmax_txt = doc.createTextNode(str(int (float (objbud[i*5+1])*a+float (objbud[i*5+3])*(a/2.0))))
xmax.appendChild(xmax_txt)
ymax = doc.createElement('ymax')
bndbox.appendChild(ymax)
ymax_txt = doc.createTextNode(str(int (float (objbud[i*5+2])*b+float (objbud[i*5+4])*(b/2.0))))
ymax.appendChild(ymax_txt)
#threee-1#
#threee#
##print("11")
tempfile = tmp + "test.xml"
with open(tempfile, "w") as f:
f.write(doc.toprettyxml(indent = '\t', encoding='utf-8'))
rewrite = open(tempfile, "r")
lines = rewrite.read().split('\n')
newlines = lines[1:len(lines)-1]
fw = open(wxml, "w")
for i in range(0, len(newlines)):
fw.write(newlines[i] + '\n')
fw.close()
rewrite.close()
os.remove(tempfile)
return
for files in os.walk(ann_path):
temp = "/home/swl/Documents/temp/" #要改要改要改要改
if not os.path.exists(temp):
os.mkdir(temp)
for file in files[2]:
print file + "-->start!"
img_name = os.path.splitext(file)[0] + '.jpg'
fileimgpath = img_path + img_name
im=Image.open(fileimgpath)
width= int(im.size[0])
height= int(im.size[1])
filelabel = open(ann_path + file, "r")
lines = filelabel.read().split('\n')
obj = lines[:len(lines)-1]
filename = xml_path + os.path.splitext(file)[0] + '.xml'
writeXml(temp, img_name, width, height, obj, filename)
os.rmdir(temp)