【数据集处理】voc格式数据集转换为coco格式

一般情况下，我们VOC格式的数据集，存放在三个文件中：Annotation；ImageSets；以及JPEGImages。

• 其中Annotation存放所有的xml文件；
• ImageSets中有一个Main，Main中有train.txt；val.txt；test.txt以及trainval.txt
• JPEGImages存放所有的图片

但是如果转为coco数据集格式，需要我们首先将Annotation文件中的xml文件分为三部分，分别为train；val；test，然后分别转换为coco格式的数据集。

一.划分Annotation

1. 新建train；val；和test三个文件夹，用来存放各自的Annotation。
2. 执行代码：

#某一个txt文本中的数字存的是图片的名字，
#要把这些名字的图片保存到另一个文件夹中
#修改两处，注意自己建立文件
from PIL import Image
import os

f3 = open("/home/dlut/网络/CornerNet-Lite-master/VOCdevkit/VOC2007/ImageSets/Main/train.txt",'r') #train文件所在路径
for line2 in f3.readlines():
    line3=line2[:-1] #读取所有数字  000000
    xmldir = '/home/dlut/网络/CornerNet-Lite-master/VOCdevkit/VOC2007/Annotations/' 
     #所有的xml文件绝对路径
    savedir = '/home/dlut/网络/CornerNet-Lite-master/VOCdevkit/VOC2007/train/'
    #将用于train的xml文件提取出来的绝对路径
    xmllist = os.listdir(xmldir)
    for xml in xmllist:
        # if '.xml' in xml:
        if '.xml' in xml:
            if line3 in xml:
                fo = open(savedir + '/' + '{}'.format(xml), 'w')  
                print('{}'.format(xml))
                fi = open(xmldir + '/' + '{}'.format(xml), 'r')
                content = fi.readlines()
                for line in content:
                    fo.write(line)
                fo.close()
                print('替换成功')
f3.close()

train的提取完毕之后，再自行修改train为val，提取val，在提取test。然后就可以得到三个文件夹，train，test，val，每个文件中存放的是各自的Annotation。

二、数据集：voc格式转换为coco格式

#coding:utf-8
import sys
import os
import json
import xml.etree.ElementTree as ET
 
START_BOUNDING_BOX_ID = 1

#注意下面的dict存储的是实际检测的类别，需要根据自己的实际数据进行修改
#这里以自己的数据集person和hat两个类别为例，如果是VOC数据集那就是20个类别
#注意类别名称和xml文件中的标注名称一致

PRE_DEFINE_CATEGORIES = {"normal":0,"defect":1,"norbolt":2,"debolt":3}
#注意按照自己的数据集名称修改编号和名称

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_dir, json_file):
    xmlFiles = os.listdir(xml_dir)
    
    json_dict = {"images":[], "type": "instances", "annotations": [],
                 "categories": []}
    categories = PRE_DEFINE_CATEGORIES
    bnd_id = START_BOUNDING_BOX_ID
    num = 0
    for line in xmlFiles:
#         print("Processing %s"%(line))
        num +=1
        if num%50==0:
            print("processing ",num,"; file ",line)
            
        xml_f = os.path.join(xml_dir, line)
        tree = ET.parse(xml_f)
        root = tree.getroot()
        ## The filename must be a number
        filename = line[:-4]
        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}
        image = {'file_name': (filename+'.jpg'), '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()
 
if __name__ == '__main__':
    folder_list= ["train","val","test"]
    #注意更改base_dir为本地实际图像和标注文件路径
    base_dir = "/home/dlut/网络/CenterNet-master/VOC2018/"
    #修改为自己的路径
    
    for i in range(3):
        folderName = folder_list[i]
        xml_dir = base_dir + folderName
        json_dir = base_dir + folderName + "/instances_" + folderName + ".json"

        print("deal: ",folderName)
        print("xml dir: ",xml_dir)
        print("json file: ",json_dir)
        
        convert(xml_dir,json_dir)

最后会在各自的train，val，test文件夹中生成各自的COCO个是数据集，名称分别为：instances_train.json；instances_val.json；instances_test.json。可以自己手动修改为：train.json；val.json；test.json。

参考：

Python将voc数据格式转化为coco数据格式
Python: 文件夹下xml内容批量替换、删除