当前位置：网站首页>voc数据格式转为coco数据格式

voc数据格式转为coco数据格式

2022-06-11 23:51:00 【weixin_44323744】

把voc数据格式转为coco数据格式，想把在yolo里使用的数据转为在mmdet中应用数据格式，首先，在yolo里的labels时txt类型如下图1，而在voc转为coco数据格式时，需要先将txt类型转为xml类型，xml类型如下图2所示。

图1 txt类型

下面将txt类型转为xml：

from xml.dom.minidom import Document
import os
import cv2

def makexml(txtPath,xmlPath,picPath): #读取txt路径，xml保存路径，数据集图片所在路径
        dict = {'0':'identity', '1':'action', '2':'abnormal entity'}
        files = os.listdir(txtPath)
        for i, name in enumerate(files):
          print(name)
          xmlBuilder = Document()
          annotation = xmlBuilder.createElement("annotation")  # 创建annotation标签
          xmlBuilder.appendChild(annotation)
          txtFile=open(txtPath+name)
          txtList = txtFile.readlines()
          img = cv2.imread(picPath+name[0:-4]+".jpg")
          Pheight,Pwidth,Pdepth=img.shape
          for i in txtList:
             oneline = i.strip().split(" ")
             if len(xmlBuilder.getElementsByTagName("folder")) == 0:  # 只让folder size标签记录一次
                folder = xmlBuilder.createElement("folder")#folder标签
                folderContent = xmlBuilder.createTextNode("VOC2007")
                folder.appendChild(folderContent)
                annotation.appendChild(folder)

                filename = xmlBuilder.createElement("filename")#filename标签
                filenameContent = xmlBuilder.createTextNode(name[0:-4]+".jpg")
                filename.appendChild(filenameContent)
                annotation.appendChild(filename)

                size = xmlBuilder.createElement("size")  # size标签
                width = xmlBuilder.createElement("width")  # size子标签width
                widthContent = xmlBuilder.createTextNode(str(Pwidth))
                width.appendChild(widthContent)
                size.appendChild(width)
                height = xmlBuilder.createElement("height")  # size子标签height
                heightContent = xmlBuilder.createTextNode(str(Pheight))
                height.appendChild(heightContent)
                size.appendChild(height)
                depth = xmlBuilder.createElement("depth")  # size子标签depth
                depthContent = xmlBuilder.createTextNode(str(Pdepth))
                depth.appendChild(depthContent)
                size.appendChild(depth)
                annotation.appendChild(size)
 
             object = xmlBuilder.createElement("object")
             picname = xmlBuilder.createElement("name")
             nameContent = xmlBuilder.createTextNode(dict[oneline[0]])
             picname.appendChild(nameContent)
             object.appendChild(picname)
             pose = xmlBuilder.createElement("pose")
             poseContent = xmlBuilder.createTextNode("Unspecified")
             pose.appendChild(poseContent)
             object.appendChild(pose)
             truncated = xmlBuilder.createElement("truncated")
             truncatedContent = xmlBuilder.createTextNode("0")
             truncated.appendChild(truncatedContent)
             object.appendChild(truncated)
             difficult = xmlBuilder.createElement("difficult")
             difficultContent = xmlBuilder.createTextNode("0")
             difficult.appendChild(difficultContent)
             object.appendChild(difficult)
             bndbox = xmlBuilder.createElement("bndbox")
             xmin = xmlBuilder.createElement("xmin")
             mathData=int(((float(oneline[1]))*Pwidth+1)-(float(oneline[3]))*0.5*Pwidth)
             xminContent = xmlBuilder.createTextNode(str(mathData))
             xmin.appendChild(xminContent)
             bndbox.appendChild(xmin)
             ymin = xmlBuilder.createElement("ymin")
             mathData = int(((float(oneline[2]))*Pheight+1)-(float(oneline[4]))*0.5*Pheight)
             yminContent = xmlBuilder.createTextNode(str(mathData))
             ymin.appendChild(yminContent)
             bndbox.appendChild(ymin)
             xmax = xmlBuilder.createElement("xmax")
             mathData = int(((float(oneline[1]))*Pwidth+1)+(float(oneline[3]))*0.5*Pwidth)
             xmaxContent = xmlBuilder.createTextNode(str(mathData))
             xmax.appendChild(xmaxContent)
             bndbox.appendChild(xmax)
             ymax = xmlBuilder.createElement("ymax")
             mathData = int(((float(oneline[2]))*Pheight+1)+(float(oneline[4]))*0.5*Pheight)
             ymaxContent = xmlBuilder.createTextNode(str(mathData))
             ymax.appendChild(ymaxContent)
             bndbox.appendChild(ymax)
             object.appendChild(bndbox)
 
             annotation.appendChild(object)
 
          f = open(xmlPath+name[0:-4]+".xml", 'w')
          xmlBuilder.writexml(f, indent='\t', newl='\n', addindent='\t', encoding='utf-8')
          f.close()

# txt所在文件夹路径，xml文件保存路径，图片所在文件夹路径 
makexml("data/splited1/labels/train/","data/splited1/xml/val/","data/splited1/images/train/")

下面将xml类型转为json格式:

在转换之前，先将xml文件名放在一个txt文件里

# create_xml_list.py
import os
xml_list = os.listdir('data/splited1/xml/train')
with open('data/splited1/xml_list.txt','a') as f:
    for i in xml_list:
        if i[-3:]=='xml':
            f.write(str(i)+'\n')

下面就可以将xml转为json

# voc2coco.py

# pip install lxml

import sys
import os
import json
import xml.etree.ElementTree as ET

START_BOUNDING_BOX_ID = 1
PRE_DEFINE_CATEGORIES = {}
# If necessary, pre-define category and its id
#  PRE_DEFINE_CATEGORIES = {"aeroplane": 1, "bicycle": 2, "bird": 3, "boat": 4,
                         #  "bottle":5, "bus": 6, "car": 7, "cat": 8, "chair": 9,
                         #  "cow": 10, "diningtable": 11, "dog": 12, "horse": 13,
                         #  "motorbike": 14, "person": 15, "pottedplant": 16,
                         #  "sheep": 17, "sofa": 18, "train": 19, "tvmonitor": 20}
PRE_DEFINE_CATEGORIES = {'identity':0, 'action':1, 'abnormal entity':2}

def get(root, name):
    vars = root.findall(name)
    return vars


def get_and_check(root, name, length):
    vars = root.findall(name)
    if len(vars) == 0:
        raise NotImplementedError('Can not find %s in %s.'%(name, root.tag))
    if length > 0 and len(vars) != length:
        raise NotImplementedError('The size of %s is supposed to be %d, but is %d.'%(name, length, len(vars)))
    if length == 1:
        vars = vars[0]
    return vars


def get_filename_as_int(filename):
    try:
        filename = os.path.splitext(filename)[0]
        return int(filename)
    except:
        raise NotImplementedError('Filename %s is supposed to be an integer.'%(filename))


def convert(xml_list, xml_dir, json_file):
    list_fp = open(xml_list, 'r')
    json_dict = {"images":[], "type": "instances", "annotations": [],
                 "categories": []}
    categories = PRE_DEFINE_CATEGORIES
    bnd_id = START_BOUNDING_BOX_ID
    for line in list_fp:
        line = line.strip()
        print("Processing %s"%(line))
        xml_f = os.path.join(xml_dir, line)
        tree = ET.parse(xml_f)
        root = tree.getroot()
        path = get(root, 'path')
        if len(path) == 1:
            filename = os.path.basename(path[0].text)
        elif len(path) == 0:
            print(root)
            filename = get_and_check(root, 'filename', 1).text
        else:
            raise NotImplementedError('%d paths found in %s'%(len(path), line))
        ## The filename must be a number
        image_id = get_filename_as_int(filename)
        size = get_and_check(root, 'size', 1)
        width = int(get_and_check(size, 'width', 1).text)
        height = int(get_and_check(size, 'height', 1).text)
        image = {'file_name': filename, 'height': height, 'width': width,
                 'id':image_id}
        json_dict['images'].append(image)
        ## Cruuently we do not support segmentation
        #  segmented = get_and_check(root, 'segmented', 1).text
        #  assert segmented == '0'
        for obj in get(root, 'object'):
            category = get_and_check(obj, 'name', 1).text
            if category not in categories:
                new_id = len(categories)
                categories[category] = new_id
            category_id = categories[category]
            bndbox = get_and_check(obj, 'bndbox', 1)
            xmin = int(get_and_check(bndbox, 'xmin', 1).text) - 1
            ymin = int(get_and_check(bndbox, 'ymin', 1).text) - 1
            xmax = int(get_and_check(bndbox, 'xmax', 1).text)
            ymax = int(get_and_check(bndbox, 'ymax', 1).text)
            assert(xmax > xmin)
            assert(ymax > ymin)
            o_width = abs(xmax - xmin)
            o_height = abs(ymax - ymin)
            ann = {'area': o_width*o_height, 'iscrowd': 0, 'image_id':
                   image_id, 'bbox':[xmin, ymin, o_width, o_height],
                   'category_id': category_id, 'id': bnd_id, 'ignore': 0,
                   'segmentation': []}
            json_dict['annotations'].append(ann)
            bnd_id = bnd_id + 1

    for cate, cid in categories.items():
        cat = {'supercategory': 'none', 'id': cid, 'name': cate}
        json_dict['categories'].append(cat)
    json_fp = open(json_file, 'w')
    json_str = json.dumps(json_dict)
    json_fp.write(json_str)
    json_fp.close()
    list_fp.close()


if __name__ == '__main__':
    if len(sys.argv) <= 1:
        print('3 auguments are need.')
        print('Usage: %s XML_LIST.txt XML_DIR OUTPU_JSON.json'%(sys.argv[0]))
        exit(1)

    # xml_list.txt xml_folder coco.json
    convert(sys.argv[1], sys.argv[2], sys.argv[3])

运行上面的代码 python voc2json.py 后面加上三个路径xml_list.txt ，xml_folder ，coco.json

生成的json里的内容