yolov4在WIDERFACE中训练进行人脸检测、修改WIDERFACE标注格式
1、简介
WIDERFACE是香港中文大学资讯工程学系 多媒体实验室 发布的人脸数据集
下载连接
2、标注格式
其有两种标注格式.mat与.txt。由于我只能打开.txt文件。其内容如下
0--Parade/0_Parade_marchingband_1_849.jpg
1
449 330 122 149 0 0 0 0 0 0
0--Parade/0_Parade_Parade_0_904.jpg
1
361 98 263 339 0 0 0 0 0 0
0--Parade/0_Parade_marchingband_1_799.jpg
21
78 221 7 8 2 0 0 0 0 0
78 238 14 17 2 0 0 0 0 0
113 212 11 15 2 0 0 0 0 0
134 260 15 15 2 0 0 0 0 0
163 250 14 17 2 0 0 0 0 0
201 218 10 12 2 0 0 0 0 0
182 266 15 17 2 0 0 0 0 0
245 279 18 15 2 0 0 0 0 0
304 265 16 17 2 0 0 0 2 1
328 295 16 20 2 0 0 0 0 0
389 281 17 19 2 0 0 0 2 0
406 293 21 21 2 0 1 0 0 0
436 290 22 17 2 0 0 0 0 0
522 328 21 18 2 0 1 0 0 0
643 320 23 22 2 0 0 0 0 0
653 224 17 25 2 0 0 0 0 0
793 337 23 30 2 0 0 0 0 0
535 311 16 17 2 0 0 0 1 0
29 220 11 15 2 0 0 0 0 0
3 232 11 15 2 0 0 0 2 0
20 215 12 16 2 0 0 0 2 0
分别代表
File name
Number of bounding box
x1, y1, w, h, blur, expression, illumination, invalid, occlusion, pose
3、 格式改变
在yolov4训练人头检测器 中表述了如何把xml数据格式改为yolov4使用的voc格式。因此这里我们只要把.txt文件改为单个的xml文件。然后利用yolov4训练人头检测器 中的方法进行转换就好。
.txt转xml脚本如下
3.1 生成xml脚本
def make_xml(figname, width, height, boxlist):
node_root = Element('annotation')
node_folder = SubElement(node_root, 'folder')
node_folder.text = 'VOC'
node_filename = SubElement(node_root, 'filename')
node_filename.text = figname
node_object_num = SubElement(node_root, 'object_num')
node_object_num.text = str(len(boxlist))
node_size = SubElement(node_root, 'size')
node_width = SubElement(node_size, 'width')
node_width.text = str(width)
node_height = SubElement(node_size, 'height')
node_height.text = str(height)
node_depth = SubElement(node_size, 'depth')
node_depth.text = '3'
for box in boxlist:
node_object = SubElement(node_root, 'object')
node_name = SubElement(node_object, 'name')
node_name.text = 'face'
node_difficult = SubElement(node_object, 'difficult')
node_difficult.text = '0'
node_bndbox = SubElement(node_object, 'bndbox')
node_xmin = SubElement(node_bndbox, 'xmin')
node_xmin.text = str(box['xmin'])
node_ymin = SubElement(node_bndbox, 'ymin')
node_ymin.text = str(box['ymin'])
node_xmax = SubElement(node_bndbox, 'xmax')
node_xmax.text = str(box['xmax'])
node_ymax = SubElement(node_bndbox, 'ymax')
node_ymax.text = str(box['ymax'])
#print xml 打印查看结果
tree = etree.ElementTree(node_root)
tree.write("./"+figname.split(".")[0]+'.xml', pretty_print=True, xml_declaration=False, encoding='utf-8')
return
3.2 读取txt文件分离图片信息
def readTxt(path):
f = open(path,"r")
lines = f.readlines()
dadeList=[]
data={}
boxlist=[]
flg = False
numflg = False
num=0
flgnum=0
for line in lines:
# print("line:",line)
if '.jpg' in line:
tem1 = line.split("/")
# imagrnamepath = "./images/"+tem1[1]
imagrname = line.split("/")[1]
# print("imagrname:",imagrname)
path = "./images/"+imagrname.split(".")[0]+".jpg"
# print("path:",path)
img = cv2.imread(path)
HW = img.shape
print("HW:",HW)
flg=True
flgnum=0
# print("imagrnamepath:",imagrnamepath)
# HW = getHW(imagrnamepath)
data['imagename'] = imagrname.split(".")[0]+".jpg"
data['height'] = HW[0]
data['width'] = HW[1]
elif flg:
num = int(line)
numflg=True
flgnum=0
flg=False
elif numflg:
flg = False
labes = line.split()
# print("labes:",labes)
if int(labes[8])==2:
print("abbeng")
flgnum =flgnum+1
if flgnum == num:
data['boxlist'] = boxlist
dadeList.append(data)
boxlist=[]
data={}
flg=False
numflg = False
continue
temdata={}
temdata['xmin'] = int(labes[0])
temdata['xmax'] = int(labes[0]) + (int(labes[2]))
temdata['ymin'] = int(labes[1])
temdata['ymax'] = int(labes[1]) + (int(labes[3]))
boxlist.append(temdata)
flgnum =flgnum+1
if flgnum == num:
data['boxlist'] = boxlist
dadeList.append(data)
boxlist=[]
data={}
flg=False
numflg = False
return dadeList
3.3移动图像
import os
import shutil
path='./images/'
dirs = os.listdir(path)
for dir in dirs:
if os.path.isdir(path+dir):
images = os.listdir(path+dir)
for image in images:
shutil.move(path+dir+"/"+image,path)
完整脚本