coco数据集转换为voc格式

1。coco数据集简介，共标注了90类

1:person
2:bicycle
3:car
4:motorcycle
5:airplane
6:bus
7:train
8:truck
9:boat
10:traffic light
11:fire hydrant
13:stop sign
14:parking meter
15:bench
16:bird
17:cat
18:dog
19:horse
20:sheep
21:cow
22:elephant
23:bear
24:zebra
25:giraffe
27:backpack
28:umbrella
31:handbag
32:tie
33:suitcase
34:frisbee
35:skis
36:snowboard
37:sports ball
38:kite
39:baseball bat
40:baseball glove
41:skateboard
42:surfboard
43:tennis racket
44:bottle
46:wine glass
47:cup
48:fork
49:knife
50:spoon
51:bowl
52:banana
53:apple
54:sandwich
55:orange
56:broccoli
57:carrot
58:hot dog
59:pizza
60:donut
61:cake
62:chair
63:couch
64:potted plant
65:bed
67:dining table
70:toilet
72:tv
73:laptop
74:mouse
75:remote
76:keyboard
77:cell phone
78:microwave
79:oven
80:toaster
81:sink
82:refrigerator
84:book
85:clock
86:vase
87:scissors
88:teddy bear
89:hair drier
90:toothbrush

将coco数据转换成voc格式coco_to_voc.py

'''
把coco数据集合的所有标注转换到voc格式，不改变图片命名方式，
注意，原来有一些图片是黑白照片，检测出不是 RGB 图像，这样的图像不会被放到新的文件夹中
更新日期：2019-11-19
'''
from pycocotools.coco import COCO #这个包可以从git上下载https://github.com/cocodataset/cocoapi/tree/master/PythonAPI，也可以直接用修改后的coco.py
import  os, cv2, shutil
from lxml import etree, objectify
from tqdm import tqdm
from PIL import Image

CKimg_dir ='/home/jerry/data/data/object_detect/coco2017_voc/images'
CKanno_dir = '/home/jerry/data/data/object_detect/coco2017_voc/annotations'
#若模型保存文件夹不存在，创建模型保存文件夹，若存在，删除重建
def mkr(path):
    if os.path.exists(path):
        shutil.rmtree(path)
        os.mkdir(path)
    else:
        os.mkdir(path)


def save_annotations(filename, objs,filepath):
    annopath = CKanno_dir + "/" + filename[:-3] + "xml" #生成的xml文件保存路径
    dst_path = CKimg_dir + "/" + filename
    img_path=filepath
    img = cv2.imread(img_path)
    im = Image.open(img_path)
    if im.mode != "RGB":
        print(filename + " not a RGB image")
        im.close()
        return
    im.close()
    shutil.copy(img_path, dst_path)#把原始图像复制到目标文件夹
    E = objectify.ElementMaker(annotate=False)
    anno_tree = E.annotation(
        E.folder('1'),
        E.filename(filename),
        E.source(
            E.database('CKdemo'),
            E.annotation('VOC'),
            E.image('CK')
        ),
        E.size(
            E.width(img.shape[1]),
            E.height(img.shape[0]),
            E.depth(img.shape[2])
        ),
        E.segmented(0)
    )
    for obj in objs:
        E2 = objectify.ElementMaker(annotate=False)
        anno_tree2 = E2.object(
            E.name(obj[0]),
            E.pose(),
            E.truncated("0"),
            E.difficult(0),
            E.bndbox(
                E.xmin(obj[2]),
                E.ymin(obj[3]),
                E.xmax(obj[4]),
                E.ymax(obj[5])
            )
        )
        anno_tree.append(anno_tree2)
    etree.ElementTree(anno_tree).write(annopath, pretty_print=True)


def showbycv(coco, dataType, img, classes,origin_image_dir,verbose=False):
    filename = img['file_name']
    filepath=os.path.join(origin_image_dir,dataType,filename)
    I = cv2.imread(filepath)
    annIds = coco.getAnnIds(imgIds=img['id'],  iscrowd=None)
    anns = coco.loadAnns(annIds)
    objs = []
    for ann in anns:
        name = classes[ann['category_id']]
        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 = [name, 1.0, xmin, ymin, xmax, ymax]
            objs.append(obj)
            if verbose:
                cv2.rectangle(I, (xmin, ymin), (xmax, ymax), (255, 0, 0))
                cv2.putText(I, name, (xmin, ymin), 3, 1, (0, 0, 255))
    save_annotations(filename, objs,filepath)
    if verbose:
        cv2.imshow("img", I)
        cv2.waitKey(0)


def catid2name(coco):#将名字和id号建立一个字典
    classes = dict()
    for cat in coco.dataset['categories']:
        classes[cat['id']] = cat['name']
        # print(str(cat['id'])