将WIDER FACE数据集转为VOC格式

 第一步：在Wider Face官网下载数据集，官网：Wider Face

下载下列四个压缩包

 

第二步：下载完成后进行解压，解压完成之后新建三个文件夹，如下图所示

 

在ImageSets文件夹下新建一个名为Main的文件夹，

 

 第三步：编写脚本文件，生成VOC格式。

import os, cv2, sys, shutil

from xml.dom.minidom import Document


def writexml(filename, saveimg, bboxes, xmlpath):
    doc = Document()
    annotation = doc.createElement('annotation')
    doc.appendChild(annotation)
    folder = doc.createElement('folder')
    folder_name = doc.createTextNode('widerface')
    folder.appendChild(folder_name)
    annotation.appendChild(folder)
    filenamenode = doc.createElement('filename')
    filenamr_name = doc.createTextNode(filename)
    filenamenode.appendChild(filenamr_name)
    annotation.appendChild(filenamenode)
    source = doc.createElement('source')
    annotation.appendChild(source)
    database = doc.createElement('database')
    database.appendChild(doc.createTextNode('wider face Database'))
    source.appendChild(database)
    annotation_s = doc.createElement('annotation')
    annotation_s.appendChild(doc.createTextNode('PASCAL VOC2007'))
    source.appendChild(annotation_s)
    image = doc.createElement('image')
    image.appendChild(doc.createTextNode('flickr'))
    source.appendChild(image)
    flickrid = doc.createElement('flickrid')
    flickrid.appendChild(doc.createTextNode('-1'))
    source.appendChild(flickrid)
    owner = doc.createElement('owner')
    annotation.appendChild(owner)
    flickrid_o = doc.createElement('flickrid')
    flickrid_o.appendChild(doc.createTextNode('yanyu'))
    owner.appendChild(flickrid_o)
    name_o = doc.createElement('name')
    name_o.appendChild(doc.createTextNode('yanyu'))
    owner.appendChild(name_o)
    size = doc.createElement('size')
    annotation.appendChild(size)
    width = doc.createElement('width')
    width.appendChild(doc.createTextNode(str(saveimg.shape[1])))
    height = doc.createElement('height')
    height.appendChild(doc.createTextNode(str(saveimg.shape[0])))
    depth = doc.createElement('depth')
    depth.appendChild(doc.createTextNode(str(saveimg.shape[1])))
    size.appendChild(width)
    size.appendChild(height)
    size.appendChild(depth)
    segmented = doc.createElement('segmented')
    segmented.appendChild(doc.createTextNode('0'))
    for i in range(len(bboxes)):
        bbox = bboxes[i]
        objects = doc.createElement('object')
        annotation.appendChild(objects)
        object_name = doc.createElement('name')
        object_name.appendChild(doc.createTextNode('face'))
        objects.appendChild(object_name)
        pose = doc.createElement('pose')
        pose.appendChild(doc.createTextNode('Unspecified'))
        objects.appendChild(pose)
        truncated = doc.createElement('truncated')
        truncated.appendChild(doc.createTextNode('1'))
        objects.appendChild(truncated)
        difficult = doc.createElement('difficult')
        difficult.appendChild(doc.createTextNode('0'))
        objects.appendChild(difficult)
        bndcox = doc.createElement('bndbox')
        objects.appendChild(bndcox)
        xmin = doc.createElement('xmin')
        xmin.appendChild(doc.createTextNode(str(bbox[0])))
        bndcox.appendChild(xmin)
        ymin = doc.createElement('ymin')
        ymin.appendChild(doc.createTextNode(str(bbox[1])))
        bndcox.appendChild(ymin)
        xmax = doc.createElement('xmax')
        xmax.appendChild(doc.createTextNode(str(bbox[0] + bbox[2])))
        bndcox.appendChild(xmax)
        ymax = doc.createElement('ymax')
        ymax.appendChild(doc.createTextNode(str(bbox[1] + bbox[3])))
        bndcox.appendChild(ymax)
    f = open(xmlpath, "w")
    f.write(doc.toprettyxml(indent=''))
    f.close()


rootdir = "../wider_face"     #注意，这里需要根据自己的文件位置进行修改


def convertimgset(img_set):
    imgdir = rootdir + "/WIDER_" + img_set + "/images"
    gtfilepath = rootdir + "/wider_face_split/wider_face_" + img_set + "_bbx_gt.txt"

    fwrite = open(rootdir + "/ImageSets/Main/" + img_set + ".txt", 'w')

    index = 0

    with open(gtfilepath, 'r') as gtfiles:
        while(True):
            filename = gtfiles.readline()[:-1]
            if(filename == " "):
                continue
            imgpath = imgdir + "/" + filename

            img = cv2.imread(imgpath)

            if not img.data:
                break;
            numbbox = max(1, int(gtfiles.readline()))
            bboxes = []

            for i in range(numbbox):
                line = gtfiles.readline()
                lines = line.split(" ")
                lines = lines[0:4]

                bbox = (int(lines[0]), int(lines[1]), int(lines[2]), int(lines[3]))
                bboxes.append(bbox)

            filename = filename.replace("/", "_")

            if len(bboxes) == 0:
                print("no face")

            cv2.imwrite("{}/JPEGImages/{}".format(rootdir, filename), img)

            fwrite.write(filename.split(".")[0] + "\n")

            xmlpath = "{}/Annotations/{}.xml".format(rootdir, filename.split(".")[0])

            writexml(filename, img, bboxes, xmlpath)
            print("success number is ", index)

            index += 1
    fwrite.close()

if __name__ == "__main__":
    img_sets = ["train", "val"]
    for img_set in img_sets:
        convertimgset(img_set)

    shutil.move(rootdir + "/ImageSets/Main/" + "train.txt", rootdir + "/ImageSets/Main/" + "trainval.txt")
    shutil.move(rootdir + "/ImageSets/Main/" + "val.txt", rootdir + "/ImageSets/Main/" + "test.txt")

第五步：运行一下就可以得到VOC格式的数据集了