目标检测各类数据集格式互转以及处理方法（VOC, COCO, txt）

在做目标检测时，我个人比较喜欢VOC格式的数据集，所以遇到COCO格式的数据集习惯转为VOC的，再进行处理。

代码地址

coco转voc格式

需要修改的只有路径以及jsonFileName 这个列表，都已经标明了比较清晰的注释。

'''
Author: TuZhou
Version: 1.0
Date: 2021-08-29 16:32:52
LastEditTime: 2021-08-29 17:44:57
LastEditors: TuZhou
Description: 
FilePath: \My_Yolo\datasets\coco_to_voc.py
'''

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

#要生成的voc格式图片路径
image_dir = './datasets/RoadSignsPascalVOC_Voc/images'
#要生成的voc格式xml标注路径
anno_dir = './datasets/RoadSignsPascalVOC_Voc/annotations'
#---------------------------------------------#
#你的coco格式的json类型和文件名，前者表示是train类型的json，后者表示该json文件的名字，类型名最好是与你的对应类型图片保存文件夹名一致
#我的json目录只有一个train类型，如果你有测试集的json文件，则可写成[['train', 'instance_train'], ['test', 'instance_test']]
jsonFileName = [['train', 'instance_train']]
#----------------------------------------------#


'''
Author: TuZhou
Description: 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
param {*} path 文件夹路径
return {*}
'''
def mkr(path):
    if os.path.exists(path):
        shutil.rmtree(path)
        os.mkdir(path)
    else:
        os.mkdir(path) 


'''
Author: TuZhou
Description: 保存xml文件
param {*} filename
param {*} objs
param {*} filepath
return {*}
'''
def save_annotations(filename, objs, filepath):
    annopath = anno_dir + "/" + filename[:-3] + "xml"  # 生成的xml文件保存路径
    #print("filename", filename)
    dst_path = image_dir + "/" + filename
    img_path = filepath
    img = cv2.imread(img_path)
    #此处时对非RGB图像筛选，可注释
    # 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']
    #NOTE:dataType表示coco格式中训练集或者测试集的图片文件夹名，但是我所有图片都放在JPEGImages文件夹中，所以此处为空，有需要的可以修改
    #dataType就是jsonFileName中的json类型，如果你的类型名和你的图片文件夹名一致，则可注释下行
    dataType = ''
    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'])+":"+cat['name'])
    return classes
 
 
'''
Author: TuZhou
Description: 
param {*} origin_anno_dir 原始coco的json文件目录
param {*} origin_image_dir 原始coco的图片保寸目录
param {*} verbose
return {*}
'''
def get_CK5(origin_anno_dir, origin_image_dir, verbose=False):
    for dataType, annoName in jsonFileName:
        #annFile = 'instances_{}.json'.format(dataType)
        annFile = annoName + '.json'
        annpath = os.path.join(origin_anno_dir, annFile)
        coco = COCO(annpath)
        classes = catid2name(coco)
        imgIds = coco.getImgIds()
        # imgIds=imgIds[0:1000]#测试用，抽取10张图片，看下存储效果
        for imgId in tqdm(imgIds):
            img = coco.loadImgs(imgId)[0]
            showbycv(coco, dataType,