关于coco(.json)转voc(.xml)后，object消失的问题

step1 coco转voc代码

此代码借鉴于此博客：link

需要修改的地方

savepath
填写“提取出的类别”保存的地方，会生成两个子文件夹（images、annotations）
datasets_list
修改为自己的存放coco数据集的文件夹的名称
classes_names
修改为自己需要类的名字
dataDir
原coco数据集保存的目录

代码内容

from pycocotools.coco import COCO
import os
import shutil
from tqdm import tqdm
# import skimage.io as io
import matplotlib.pyplot as plt
import cv2
from PIL import Image, ImageDraw

# 存储路径
savepath = "/home/boni/Downloads/coco_extract/"

img_dir = savepath + 'images/'
anno_dir = savepath + 'Annotations/'
# datasets_list=['train2014', 'val2014']
datasets_list = ['train2017']

# 选择自己的类
classes_names = ['person', 'bicycle', 'car', 'motorcycle', 'bus', 'train', 'traffic', 'fire hydrant', 'stop sign']

# 原数据存储
dataDir = '/home/boni/Downloads/coco_extract'

headstr = """\
<annotation>
    <folder>VOC</folder>
    <filename>%s</filename>
    <source>
        <database>My Database</database>
        <annotation>COCO</annotation>
        <image>flickr</image>
        <flickrid>NULL</flickrid>
    </source>
    <owner>
        <flickrid>NULL</flickrid>
        <name>company</name>
    </owner>
    <size>
        <width>%d</width>
        <height>%d</height>
        <depth>%d</depth>
    </size>
    <segmented>0</segmented>
"""
objstr = """\
    <object>
        <name>%s</name>
        <pose>Unspecified</pose>
        <truncated>0</truncated>
        <difficult>0</difficult>
        <bndbox>
            <xmin>%d</xmin>
            <ymin>%d</ymin>
            <xmax>%d</xmax>
            <ymax>%d</ymax>
        </bndbox>
    </object>
"""

tailstr = '''\
</annotation>
'''


# if the dir is not exists,make it,else delete it
def mkr(path):
    if os.path.exists(path):
        shutil.rmtree(path)
        os.mkdir(path)
    else:
        os.mkdir(path)


mkr(img_dir)
mkr(anno_dir)


def id2name(coco):
    classes = dict()
    for cls in coco.dataset['categories']:
        classes[cls['id']] = cls['name']
    return classes


def write_xml(anno_path, head, objs, tail):
    f = open(anno_path, "w")
    f.write(head)
    for obj in objs:
        f.write(objstr % (obj[0], obj[1], obj[2], obj[3], obj[4]))
    f.write(tail)


def save_annotations_and_imgs(coco, dataset, filename, objs):
    # eg:COCO_train2014_000000196610.jpg-->COCO_train2014_000000196610.xml
    anno_path = anno_dir + filename[:-3] + 'xml'
    # img_path = dataDir + dataset + '/' + filename
    img_path = dataDir + '/' + dataset + '/' + filename
    print(img_path)
    dst_imgpath = img_dir + filename

    img = cv2.imread(img_path)
    # if (img.shape[2] == 1):
    #    print(filename + " not a RGB image")
    #   return
    shutil.copy(img_path, dst_imgpath)

    head = headstr % (filename, img.shape[1], img.shape[0], img.shape[2])
    tail = tailstr
    write_xml(anno_path, head, objs, tail)


def showimg(coco, dataset, img, classes, cls_id, show=True):
    global dataDir
    I = Image.open('%s/%s/%s' % (dataDir, dataset, img['file_name']))
    # Íš¹ýid£¬µÃµœ×¢Ê͵ÄÐÅÏ¢
    annIds = coco.getAnnIds(imgIds=img['id'], catIds=cls_id, iscrowd=None)
    # print(annIds)
    anns = coco.loadAnns(annIds)
    # print(anns)
    # coco.showAnns(anns)
    objs = []
    for ann in anns:
        class_name = classes[ann['category_id']]
        if class_name in classes_names:
            print(class_name)
            if 'bbox' in ann:
                bbox = ann['bbox']
                xmin = int(bbox[0])
                ymin = int(bbox[1])
                xmax = int(bbox[2] + bbox[0])
                ymax = int(bbox[3] + bbox[1])
                obj = [class_name, xmin, ymin, xmax, ymax]
                objs.append(obj)
                draw = ImageDraw.Draw(I)
                draw.rectangle([xmin, ymin, xmax, ymax])
    if show:
        plt.figure()
        plt.axis('off')
        plt.imshow(I)
        plt.show()

    return objs


for dataset in datasets_list:
    # ./COCO/annotations/instances_train2014.json
    annFile = '{}/annotations/instances_{}.json'.format(dataDir, dataset)

    # COCO API for initializing annotated data
    coco = COCO(annFile)

    # show all classes in coco
    classes = id2name(coco)
    print(classes)
    # [1, 2, 3, 4, 6, 8]
    classes_ids = coco.getCatIds(catNms=classes_names)
    print(classes_ids)
    for cls in classes_names:
        # Get ID number of this class
        cls_id = coco.getCatIds(catNms=[cls])
        img_ids = coco.getImgIds(catIds=cls_id)
        print(cls, len(img_ids))
        # imgIds=img_ids[0:10]
        for imgId in tqdm(img_ids):
            img = coco.loadImgs(imgId)[0]
            filename = img['file_name']
            # print(filename)
            objs = showimg(coco, dataset, img, classes, classes_ids, show=False)
            print(objs)
            save_annotations_and_imgs(coco, dataset, filename, objs)

文档结构显示

step2：删除无object项的xml文件及对应的图片

# coding=utf-8
import xml.dom.minidom
import os

# 未连接前xml,images路径
file_path = '/home/boni/Downloads/coco_extract/Annotations/'
img_path = '/home/boni/Downloads/coco_extract/images/'
# 获取路径下所有的xml文档，并保存在列表xml_file中（xml_file是list类型)
xml_file = os.listdir(file_path)
# 获取list长度
# print(len(xml_file))

"""
获取每个元素并与之前的路径连接，对每个xml进行object标签遍历,
xml中有object标签就直接跳过，没有就直接删除对应的xml文档，
并删除JEPGImages下对应的图片
"""
for i in range(len(xml_file)):
    # 连接并保存为新的路径
    new_file_path = os.path.join(file_path, xml_file[i])
    new_img_path = os.path.join(img_path, xml_file[i][:-3]+'jpg')
    # print(new_file_path)
    # print(new_img_path)
    # 打开xml文档
    dom = xml.dom.minidom.parse(new_file_path)
    # 得到文档元素对象
    root = dom.documentElement
    bb = root.getElementsByTagName('object')
    if bb.length == 0:
        # print("no object")
        # 删除无object的xml
        os.remove(new_file_path)
        # print("has remove this xml")
        # 删除无object的xml对应的照片
        os.remove(new_img_path)
        # print("has remove this image")
    else:
        # print("have object")
        print(bb.length)

如有不清楚的地方可关注留言