VisDrone 2 voc
1.
坐标不变 将txt转 xml
import os #指导入os模块到当前程序
from os import getcwd #需要导入模块
from PIL import Image #Python图像库PIL(Python Image Library)是python的第三方图像处理库PIL包括了基础的图像处理函数
import xml.etree.ElementTree as ET #Python中有多种xml处理API
import random
#root_dir = "train/"
root_dir = "F:\FQQDUIBI/visdrone\data\VisDrone2019-DET-val/"
annotations_dir = root_dir+"annotations/"
image_dir = root_dir + "images/"
label_dir = root_dir + "labels/"
# label_dir = root_dir + "images/" # yolo里面要和图片放到一起
xml_dir = root_dir+"annotations_voc/" #注意新建文件夹。后续改一下名字，运行完成之后annotations这个文件夹就不需要了。把annotations_voc命名为annotations
data_split_dir = root_dir + "train_namelist/"
sets = ['train', 'test','val']
class_name = ['ignored regions','pedestrian','people','bicycle','car', 'van', 'truck', 'tricycle','awning-tricycle', 'bus','motor','others']
def visdrone2voc(annotations_dir, image_dir, xml_dir):
for filename in os.listdir(annotations_dir): #返回指定的文件夹包含的文件或文件夹的名字的列表
fin = open(annotations_dir + filename, 'r')
image_name = filename.split('.')[0] #得到的是第一个.之前的内容 str.split(“o”)[0]得到的是第一个o之前的内容str.split(“o”)[1]得到的是第一个o和第二个o之间的内容
img = Image.open(image_dir + image_name + ".jpg")
xml_name = xml_dir + image_name + '.xml'
with open(xml_name, 'w') as fout:
fout.write('<annotation>' + '\n')
fout.write('\t' + '<folder>VOC2007</folder>' + '\n')
fout.write('\t' + '<filename>' + image_name + '.jpg' + '</filename>' + '\n')
fout.write('\t' + '<source>' + '\n')
fout.write('\t\t' + '<database>' + 'VisDrone2018 Database' + '</database>' + '\n')
fout.write('\t\t' + '<annotation>' + 'VisDrone2018' + '</annotation>' + '\n')
fout.write('\t\t' + '<image>' + 'flickr' + '</image>' + '\n')
fout.write('\t\t' + '<flickrid>' + 'Unspecified' + '</flickrid>' + '\n')
fout.write('\t' + '</source>' + '\n')
fout.write('\t' + '<owner>' + '\n')
fout.write('\t\t' + '<flickrid>' + 'qiangqiang Fan' + '</flickrid>' + '\n')
fout.write('\t\t' + '<name>' + 'qiangqiang Fan' + '</name>' + '\n')
fout.write('\t' + '</owner>' + '\n')
fout.write('\t' + '<size>' + '\n')
fout.write('\t\t' + '<width>' + str(img.size[0]) + '</width>' + '\n')
fout.write('\t\t' + '<height>' + str(img.size[1]) + '</height>' + '\n')
fout.write('\t\t' + '<depth>' + '3' + '</depth>' + '\n')
fout.write('\t' + '</size>' + '\n')
fout.write('\t' + '<segmented>' + '0' + '</segmented>' + '\n')
for line in fin.readlines():
line = line.split(',') #表示把line字符串按照逗号切分成多个字符串存在一个列表中
fout.write('\t' + '<object>' + '\n')
fout.write('\t\t' + '<name>' + class_name[int(line[5])] + '</name>' + '\n')
fout.write('\t\t' + '<pose>' + 'Unspecified' + '</pose>' + '\n')
fout.write('\t\t' + '<truncated>' + line[6] + '</truncated>' + '\n')
fout.write('\t\t' + '<difficult>' + str(int(line[7])) + '</difficult>' + '\n')
fout.write('\t\t' + '<bndbox>' + '\n')
fout.write('\t\t\t' + '<xmin>' + line[0] + '</xmin>' + '\n')
fout.write('\t\t\t' + '<ymin>' + line[1] + '</ymin>' + '\n')
# pay attention to this point!(0-based)
fout.write('\t\t\t' + '<xmax>' + line[2] + '</xmax>' + '\n') ##################################### 坐标不变
fout.write('\t\t\t' + '<ymax>' + line[3] + '</ymax>' + '\n') ##################################### 坐标不变
fout.write('\t\t' + '</bndbox>' + '\n')
fout.write('\t' + '</object>' + '\n')
fin.close()
fout.write('</annotation>')
def data_split(xml_dir, data_split_dir):
trainval_percent = 0.2
train_percent = 0.9
total_xml = os.listdir(xml_dir)
if not os.path.exists(data_split_dir):
os.makedirs(data_split_dir)
num = len(total_xml)
list = range(num)
tv = int(num * trainval_percent)
tr = int(tv * train_percent)
trainval = random.sample(list, tv)
train = random.sample(trainval, tr)
ftrainval = open(data_split_dir+'/trainval.txt', 'w')
ftest = open(data_split_dir+'/test.txt', 'w')
ftrain = open(data_split_dir+'/train.txt', 'w')
fval = open(data_split_dir+'/val.txt', 'w')
for i in list:
name = total_xml[i][:-4] + '\n'
if i in trainval:
ftrainval.write(name)
if i in train:
ftest.write(name)
else:
fval.write(name)
else:
ftrain.write(name)
ftrainval.close()
ftrain.close()
fval.close()
ftest.close()
def convert(size, box):
dw = 1. / size[0]
dh = 1. / size[1]
x = (box[0] + box[1]) / 2.0
y = (box[2] + box[3]) / 2.0
w = box[1] - box[0]
h = box[3] - box[2]
x = x * dw
w = w * dw
y = y * dh
h = h * dh
return (x, y, w, h)
def convert_annotation_voc(xml_dir, label_dir, image_name):
in_file = open(xml_dir + '%s.xml' % (image_name))
out_file = open(label_dir + '%s.txt' % (image_name), 'w')
tree = ET.parse(in_file)
root = tree.getroot()
size = root.find('size')
w = int(size.find('width').text)
h = int(size.find('height').text)
for obj in root.iter('object'):
difficult = obj.find('difficult').text
cls = obj.find('name').text
if cls not in class_name or int(difficult) == 1:
continue
cls_id = class_name.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)
if cls_id != 0: # 忽略掉0类
if cls_id != 11: # 忽略掉11类
out_file.write(str(cls_id - 1) + " " + " ".join([str(a) for a in bb]) + '\n') # 其他类id-1。可以根据自己需要修改代码
if __name__ == '__main__':
visdrone2voc(annotations_dir, image_dir, xml_dir) #将visdrone转化为voc的xml格式
data_split(xml_dir, data_split_dir) # 将数据集分开成train、val、test
2. label 新建 labels
xml 2 txt -0 -11
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
sets = ['train', 'test', 'val']
classes = ['ignored regions', 'pedestrian', 'people', 'bicycle', 'car', 'van', 'truck', 'tricycle', 'awning-tricycle',
'bus', 'motor', 'others'] # each category's name
'''
def convert(size, box):
dw = 1. / size[0]
dh = 1. / size[1]
x = (box[0] + box[1]) / 2.0
y = (box[2] + box[3]) / 2.0
w = box[1] - box[0]
h = box[3] - box[2]
x = x * dw
w = w * dw
y = y * dh
h = h * dh
return (x, y, w, h)
'''
def convert_annotation(image_id):
in_file = open('F:/FQQDUIBI/visdrone\data\VisDrone2019-DET-val/annotations_voc/%s.xml' % (image_id))
out_file = open('F:/FQQDUIBI/visdrone\data\VisDrone2019-DET-val\labels/%s.txt' % (image_id), 'w')
tree = ET.parse(in_file)
root = tree.getroot()
#size = root.find('size')
# w = int(size.find('width').text)
# h = int(size.find('height').text)
for obj in root.iter('object'):
difficult = obj.find('difficult').text
cls = obj.find('name').text
if cls not in classes:
continue
cls_id = classes.index(cls)
xmlbox = obj.find('bndbox')
b = ((xmlbox.find('xmin').text), (xmlbox.find('ymin').text), (xmlbox.find('xmax').text),(xmlbox.find('ymax').text))
#bb = convert((w, h), b)
if cls_id != 0: # 忽略掉0类
if cls_id != 11: # 忽略掉11类
out_file.write(xmlbox.find('xmin').text + ',' + xmlbox.find('ymin').text + ',' + xmlbox.find('xmax').text + ',' + xmlbox.find('ymax').text + ','
+ '1' + ',' + str(cls_id - 1) + ',' + '0' + ',' + difficult + '\n') # 其他类id-1。可以根据自己需要修改代码
wd = getcwd()
print(wd)
for image_set in sets:
if not os.path.exists('F:/FQQDUIBI/visdrone\data\VisDrone2019-DET-val\labels/'):
os.makedirs('F:/FQQDUIBI/visdrone\data\VisDrone2019-DET-val\labels/')
image_ids = open(r"F:\FQQDUIBI\visdrone\data\VisDrone2019-DET-val\ImageSets\Main\%s.txt" % (image_set)).read().strip().split()
list_file = open('%s.txt' % (image_set), 'w')
for image_id in image_ids:
list_file.write('F:/FQQDUIBI/visdrone\data\VisDrone2019-DET-val\images/%s.jpg\n' % (image_id))
convert_annotation(image_id)
list_file.close()
3.
txt to xml
import os #指导入os模块到当前程序
from os import getcwd #需要导入模块
from PIL import Image #Python图像库PIL(Python Image Library)是python的第三方图像处理库PIL包括了基础的图像处理函数
import xml.etree.ElementTree as ET #Python中有多种xml处理API
import random
#root_dir = "train/"
root_dir = "F:\FQQDUIBI/visdrone\data\VisDrone2019-DET-val/"
annotations_dir = root_dir+"annotations/"
image_dir = root_dir + "images/"
label_dir = root_dir + "labels/"
# label_dir = root_dir + "images/" # yolo里面要和图片放到一起
xml_dir = root_dir+"annotations_voc/" #注意新建文件夹。后续改一下名字，运行完成之后annotations这个文件夹就不需要了。把annotations_命名为annotations
data_split_dir = root_dir + "train_namelist/"
sets = ['train', 'test','val']
class_name = ['pedestrian','people','bicycle','car', 'van', 'truck', 'tricycle','awning-tricycle', 'bus','motor']
def visdrone2voc(annotations_dir, image_dir, xml_dir):
for filename in os.listdir(annotations_dir): #返回指定的文件夹包含的文件或文件夹的名字的列表
fin = open(annotations_dir + filename, 'r')
image_name = filename.split('.')[0] #得到的是第一个.之前的内容 str.split(“o”)[0]得到的是第一个o之前的内容str.split(“o”)[1]得到的是第一个o和第二个o之间的内容
img = Image.open(image_dir + image_name + ".jpg")
xml_name = xml_dir + image_name + '.xml'
with open(xml_name, 'w') as fout:
fout.write('<annotation>' + '\n')
fout.write('\t' + '<folder>VOC2007</folder>' + '\n')
fout.write('\t' + '<filename>' + image_name + '.jpg' + '</filename>' + '\n')
fout.write('\t' + '<source>' + '\n')
fout.write('\t\t' + '<database>' + 'VisDrone2018 Database' + '</database>' + '\n')
fout.write('\t\t' + '<annotation>' + 'VisDrone2018' + '</annotation>' + '\n')
fout.write('\t\t' + '<image>' + 'flickr' + '</image>' + '\n')
fout.write('\t\t' + '<flickrid>' + 'Unspecified' + '</flickrid>' + '\n')
fout.write('\t' + '</source>' + '\n')
fout.write('\t' + '<owner>' + '\n')
fout.write('\t\t' + '<flickrid>' + 'qiangqiang Fan' + '</flickrid>' + '\n')
fout.write('\t\t' + '<name>' + 'qiangqiang Fan' + '</name>' + '\n')
fout.write('\t' + '</owner>' + '\n')
fout.write('\t' + '<size>' + '\n')
fout.write('\t\t' + '<width>' + str(img.size[0]) + '</width>' + '\n')
fout.write('\t\t' + '<height>' + str(img.size[1]) + '</height>' + '\n')
fout.write('\t\t' + '<depth>' + '3' + '</depth>' + '\n')
fout.write('\t' + '</size>' + '\n')
fout.write('\t' + '<segmented>' + '0' + '</segmented>' + '\n')
for line in fin.readlines():
line = line.split(',') #表示把line字符串按照逗号切分成多个字符串存在一个列表中
fout.write('\t' + '<object>' + '\n')
fout.write('\t\t' + '<name>' + class_name[int(line[5])] + '</name>' + '\n')
fout.write('\t\t' + '<pose>' + 'Unspecified' + '</pose>' + '\n')
fout.write('\t\t' + '<truncated>' + line[6] + '</truncated>' + '\n')
fout.write('\t\t' + '<difficult>' + str(int(line[7])) + '</difficult>' + '\n')
fout.write('\t\t' + '<bndbox>' + '\n')
fout.write('\t\t\t' + '<xmin>' + line[0] + '</xmin>' + '\n')
fout.write('\t\t\t' + '<ymin>' + line[1] + '</ymin>' + '\n')
# pay attention to this point!(0-based)
fout.write('\t\t\t' + '<xmax>' + str(int(line[0]) + int(line[2]) - 1) + '</xmax>' + '\n')
fout.write('\t\t\t' + '<ymax>' + str(int(line[1]) + int(line[3]) - 1) + '</ymax>' + '\n')
fout.write('\t\t' + '</bndbox>' + '\n')
fout.write('\t' + '</object>' + '\n')
fin.close()
fout.write('</annotation>')
def data_split(xml_dir, data_split_dir):
trainval_percent = 0.2
train_percent = 0.9
total_xml = os.listdir(xml_dir)
if not os.path.exists(data_split_dir):
os.makedirs(data_split_dir)
num = len(total_xml)
list = range(num)
tv = int(num * trainval_percent)
tr = int(tv * train_percent)
trainval = random.sample(list, tv)
train = random.sample(trainval, tr)
ftrainval = open(data_split_dir+'/trainval.txt', 'w')
ftest = open(data_split_dir+'/test.txt', 'w')
ftrain = open(data_split_dir+'/train.txt', 'w')
fval = open(data_split_dir+'/val.txt', 'w')
for i in list:
name = total_xml[i][:-4] + '\n'
if i in trainval:
ftrainval.write(name)
if i in train:
ftest.write(name)
else:
fval.write(name)
else:
ftrain.write(name)
ftrainval.close()
ftrain.close()
fval.close()
ftest.close()
def convert(size, box):
dw = 1. / size[0]
dh = 1. / size[1]
x = (box[0] + box[1]) / 2.0
y = (box[2] + box[3]) / 2.0
w = box[1] - box[0]
h = box[3] - box[2]
x = x * dw
w = w * dw
y = y * dh
h = h * dh
return (x, y, w, h)
def convert_annotation_voc(xml_dir, label_dir, image_name):
in_file = open(xml_dir + '%s.xml' % (image_name))
out_file = open(label_dir + '%s.txt' % (image_name), 'w')
tree = ET.parse(in_file)
root = tree.getroot()
size = root.find('size')
w = int(size.find('width').text)
h = int(size.find('height').text)
for obj in root.iter('object'):
difficult = obj.find('difficult').text
cls = obj.find('name').text
if cls not in class_name or int(difficult) == 1:
continue
cls_id = class_name.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)
if cls_id != 0: # 忽略掉0类
if cls_id != 11: # 忽略掉11类
out_file.write(str(cls_id - 1) + " " + " ".join([str(a) for a in bb]) + '\n') # 其他类id-1。可以根据自己需要修改代码
if __name__ == '__main__':
visdrone2voc(annotations_dir, image_dir, xml_dir) #将visdrone转化为voc的xml格式
data_split(xml_dir, data_split_dir) # 将数据集分开成train、val、test
浙公网安备 33010602011771号