widerface数据集下载及转voc2007格式

参考博客：转自于该博客
自己又重新整理了一下

widerface数据集下载

数据集下载
下载这四个文件

转为voc2007格式

from skimage import io
import shutil
import random
import os
import string
 
headstr = """\

    VOC2007
    %06d.jpg
    
        My Database
        PASCAL VOC2007
        flickr
        NULL
    
    
        NULL
        company
    
    
        %d
        %d
        %d
    
    0
"""
objstr = """\
    
"""
 
tailstr = '''\

'''
 
def all_path(filename):
    return os.path.join('XXXX/XXXXX', filename)    ###注意修改文件夹地址
 
def writexml(idx, head, bbxes, tail):
    filename = all_path("Annotations/%06d.xml" % (idx))
    f = open(filename, "w")
    f.write(head)
    for bbx in bbxes:
        f.write(objstr % ('face', bbx[0], bbx[1], bbx[0] + bbx[2], bbx[1] + bbx[3]))
    f.write(tail)
    f.close()
 
 
def clear_dir():
    if shutil.os.path.exists(all_path('Annotations')):
        shutil.rmtree(all_path('Annotations'))
    if shutil.os.path.exists(all_path('ImageSets')):
        shutil.rmtree(all_path('ImageSets'))
    if shutil.os.path.exists(all_path('JPEGImages')):
        shutil.rmtree(all_path('JPEGImages'))
 
    shutil.os.mkdir(all_path('Annotations'))
    shutil.os.makedirs(all_path('ImageSets/Main'))
    shutil.os.mkdir(all_path('JPEGImages'))
 
 
def excute_datasets(idx, datatype):
    f = open(all_path('ImageSets/Main/' + datatype + '.txt'), 'a')
    f_bbx = open(all_path('wider_face_split/wider_face_' + datatype + '_bbx_gt.txt'), 'r')
 
    while True:
        filename = f_bbx.readline().strip('\n')
        if not filename:
            break
        im = io.imread(all_path('WIDER_' + datatype + '/images/'+filename))
        head = headstr % (idx, im.shape[1], im.shape[0], im.shape[2])
        nums = f_bbx.readline().strip('\n')
        bbxes = []
        for ind in range(int(nums)):
            bbx_info = f_bbx.readline().strip(' \n').split(' ')
            bbx = [int(bbx_info[i]) for i in range(len(bbx_info))]
            #x1, y1, w, h, blur, expression, illumination, invalid, occlusion, pose
            if bbx[7]==0:
                bbxes.append(bbx)
        writexml(idx, head, bbxes, tailstr)
        shutil.copyfile(all_path('WIDER_' + datatype + '/images/'+filename), all_path('JPEGImages/%06d.jpg' % (idx)))
        f.write('%06d\n' % (idx))
        idx +=1
    f.close()
    f_bbx.close()
    return idx
 
 
# 打乱样本
def shuffle_file(filename):
    f = open(filename, 'r+')
    lines = f.readlines()
    random.shuffle(lines)
    f.seek(0)
    f.truncate()
    f.writelines(lines)
    f.close()
 
 
if __name__ == '__main__':
    clear_dir()
    idx = 1
    idx = excute_datasets(idx, 'train')
    idx = excute_datasets(idx, 'val')

注意：下载的原始数据标注会有几个出现问题
如下：

所以找到 wider_face_split 文件夹中wider_face_train_bbx_gt.txt对应的错误标签即可（注释是空的）如下

下面列出来自己找的错误的标注：
10422行：0_Parade_Parade_0_452.jpg
86537行：2_Demonstration_Political_Rally_2_444.jpg
133392行：39_Ice_Skating_iceskiing_39_380.jpg
145712行：46_Jockey_Jockey_46_576.jpg

百度云下载

链接
提取码：28g6