coco数据集转voc

一.coco数据集筛选需要的标签

根据类别生成对应的json文件

import json
className = {
    1:'person',
    3: "car",
    6: "bus",
    8: "truck"
}

classNum = [1, 3, 6, 8]
coco_json=r".\annotations\instances_train2017.json"

def writeNum(Num):
    with open("COCO_train.json", "a+") as f:
        f.write(str(Num))
        
inputfile = []
inner = {}

with open(coco_json, "r+") as f:
    allData = json.load(f)
    data =allData["annotations"]
    print(data[1])
    print("read ready")
    
for i in data:
    if (i['category_id'] in classNum):
        inner = {
            "filename":str(i["image_id"]).zfill(12),
            "name":className[i["category_id"]],
            "bndbox":i["bbox"]
        }

二.根据筛选出的图片id，选取图片

import json
import os
import cv2
from multiprocessing import Pool
import shutil

def keep_pic(path, savePath, file):
    # img = cv2.imread(os.path.join(path, file))
    # cv2.imwrite(os.path.join(savePath, file), img)
    old_path = os.path.join(path, file)
    new_path = os.path.join(savePath, file)
    shutil.copy(old_path, new_path)
    # 如果想要速度快
    # shutil.move(old_path, new_path)


# print(nameStr)
# print(len(nameStr))



if __name__ == "__main__":
    nameStr = []
    # for i in data:
    #     imgName = str(i["filename"]) + ".jpg"
    #     nameStr.append(imgName)
    
    with open("COCO_train.json", "r+") as f:
        data = json.load(f)
        print("read ready")
        
    for i in data:
        imgName = str(i["filename"]) + ".jpg"
        nameStr.append(imgName)
    
    # 去重
    nameStr = set(nameStr)
    path = 'E:/darknet/coco/train/'
    count = 0
    # keep_pic(path, "test", file)
    l = Pool(processes=8)
    l.daemon = False
    # for imageName in fileList[:3]:
    for file in nameStr:
        print("imageName: ", file)
        l.apply_async(keep_pic, args=(path, "E:/darknet/coco/VOC2017_/JPEGImages/", file, ))  # 异步执行
        
    # # 关闭进程池，停止接受其它进程
    l.close()
    # # 阻塞进程
    l.join()

三.coco数据集转VOC

import xml.dom
import xml.dom.minidom
import os
# from PIL import Image
import cv2
import json
import threading
from multiprocessing import Pool
# xml文件规范定义


_IMAGE_PATH = 'E:/darknet/coco/train/'

_INDENT = '' * 4
_NEW_LINE = '\n'
_FOLDER_NODE = 'COCO2017'
_ROOT_NODE = 'annotation'
_DATABASE_NAME = 'LOGODection'
_ANNOTATION = 'COCO2017'
_AUTHOR = 'SyGoing_CSDN'
_SEGMENTED = '0'
_DIFFICULT = '0'
_TRUNCATED = '0'
_POSE = 'Unspecified'
person_num = 0
car_num = 0
bus_num = 0
truck_num = 0
# _IMAGE_COPY_PATH= 'JPEGImages'
_ANNOTATION_SAVE_PATH = 'E:/darknet/coco/VOC2017_/Annotations'


# _IMAGE_CHANNEL= 3

# 封装创建节点的过程
def createElementNode(doc, tag, attr):  # 创建一个元素节点
    element_node = doc.createElement(tag)

    # 创建一个文本节点
    text_node = doc.createTextNode(attr)

    # 将文本节点作为元素节点的子节点
    element_node.appendChild(text_node)

    return element_node


# 封装添加一个子节点
def createChildNode(doc, tag, attr, parent_node):
    child_node = createElementNode(doc, tag, attr)

    parent_node.appendChild(child_node)


# object节点比较特殊
def createObjectNode(doc, attrs):
    object_node = doc.createElement('object')

    midname = attrs['name']
    # if midname == "person":
    #     person_num += 1
    # elif midname == "car":
    #     car_num += 1
    # elif
    # if midname != 'person':
    #     midname = 'car'

    createChildNode(doc, 'name', midname,
                    object_node)

    # createChildNode(doc, 'name',attrs['name'],
    #                object_node)

    createChildNode(doc, 'pose',
                    _POSE, object_node)

    createChildNode(doc, 'truncated',
                    _TRUNCATED, object_node)

    createChildNode(doc, 'difficult',
                    _DIFFICULT, object_node)

    bndbox_node = doc.createElement('bndbox')

    createChildNode(doc, 'xmin', str(int(attrs['bndbox'][0])),
                    bndbox_node)

    createChildNode(doc, 'ymin', str(int(attrs['bndbox'][1])),
                    bndbox_node)

    createChildNode(doc, 'xmax', str(int(attrs['bndbox'][0] + attrs['bndbox'][2])),
                    bndbox_node)

    createChildNode(doc, 'ymax', str(int(attrs['bndbox'][1] + attrs['bndbox'][3])),
                    bndbox_node)

    object_node.appendChild(bndbox_node)

    return object_node


# 将documentElement写入XML文件
def writeXMLFile(doc, filename):
    tmpfile = open('tmp.xml', 'w')

    doc.writexml(tmpfile, addindent='' * 4, newl='\n', encoding='utf-8')

    tmpfile.close()

    # 删除第一行默认添加的标记

    fin = open('tmp.xml')
    # print(filename)
    fout = open(filename, 'w')
    # print(os.path.dirname(fout))

    lines = fin.readlines()

    for line in lines[1:]:
        if line.split():
            fout.writelines(line)

            # new_lines =''.join(lines[1:])

        # fout.write(new_lines)

    fin.close()

    fout.close()

def write(_ANNOTATION_SAVE_PATH, saveName):
    xml_file_name = os.path.join(_ANNOTATION_SAVE_PATH, (saveName + '.xml'))
    # withopen(xml_file_name,"w") as f:
    #     pass

    img = cv2.imread(os.path.join(img_path, imageName))
    print(os.path.join(img_path, imageName))
    # cv2.imshow(img)
    height, width, channel = img.shape
    print(height, width, channel)

    my_dom = xml.dom.getDOMImplementation()

    doc = my_dom.createDocument(None, _ROOT_NODE, None)

    # 获得根节点
    root_node = doc.documentElement

    # folder节点

    createChildNode(doc, 'folder', _FOLDER_NODE, root_node)

    # filename节点

    createChildNode(doc, 'filename', saveName + '.jpg', root_node)

    # source节点

    source_node = doc.createElement('source')

    # source的子节点

    createChildNode(doc, 'database', _DATABASE_NAME, source_node)

    createChildNode(doc, 'annotation', _ANNOTATION, source_node)

    createChildNode(doc, 'image', 'flickr', source_node)

    createChildNode(doc, 'flickrid', 'NULL', source_node)

    root_node.appendChild(source_node)

    # owner节点

    owner_node = doc.createElement('owner')

    # owner的子节点

    createChildNode(doc, 'flickrid', 'NULL', owner_node)

    createChildNode(doc, 'name', _AUTHOR, owner_node)

    root_node.appendChild(owner_node)

    # size节点

    size_node = doc.createElement('size')

    createChildNode(doc, 'width', str(width), size_node)

    createChildNode(doc, 'height', str(height), size_node)

    createChildNode(doc, 'depth', str(channel), size_node)

    root_node.appendChild(size_node)

    # segmented节点

    createChildNode(doc, 'segmented', _SEGMENTED, root_node)

    for ann in ann_data:
        imgName = "COCO_train2017_" + str(ann["filename"])
        cname = saveName;
        if (saveName == imgName):
            # object节点
            object_node = createObjectNode(doc, ann)
            root_node.appendChild(object_node)

        else:
            continue

        # 构建XML文件名称

    print(xml_file_name)

    # 创建XML文件

    # createXMLFile(attrs, width,height, xml_file_name)

    # # 写入文件
    #
    writeXMLFile(doc, xml_file_name)


if __name__ == "__main__":
    ##读取图片列表
    img_path = "E:/darknet/coco/VOC2017_/JPEGImages/"
    fileList = os.listdir(img_path)

    if fileList == 0:
        os._exit(-1)

    with open("COCO_train.json", "r") as f:
        ann_data = json.load(f)

    current_dirpath = os.path.dirname(os.path.abspath('__file__'))

    if not os.path.exists(_ANNOTATION_SAVE_PATH):
        os.mkdir(_ANNOTATION_SAVE_PATH)

    for imageName in fileList:
        print("imageName: ", imageName)
        write(_ANNOTATION_SAVE_PATH, imageName)