VOC数据集转化为COCO数据集

VOC数据集转化为COCO数据集

代码如下:

#!/usr/bin/python

# pip install lxml

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

from tqdm import tqdm

START_BOUNDING_BOX_ID = 1
PRE_DEFINE_CATEGORIES = {}  # 类别id对应键值, 如果有类别关, 需要填写此项, 即VOC中names对应的类别id如 1, 2, 3...
IMAGE_ID = 0  # 全局图片ID


# 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}


def create_xml_list(xml_dir, output_path):
    xml_list = os.listdir(xml_dir)
    with open(output_path, 'w') as f:
        for i in xml_list:
            if i[-3:] == 'xml':
                f.write(str(i) + '\n')


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]
        global IMAGE_ID
        IMAGE_ID = IMAGE_ID + 1
        return IMAGE_ID
        # 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 tqdm(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:
            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 = float(get_and_check(bndbox, 'xmin', 1).text)  # 使用 float 保留原精度
            ymin = float(get_and_check(bndbox, 'ymin', 1).text)
            xmax = float(get_and_check(bndbox, 'xmax', 1).text)
            ymax = float(get_and_check(bndbox, 'ymax', 1).text)
            assert (xmax > xmin)
            assert (ymax > ymin)
            o_width = float(xmax - xmin)
            o_height = float(ymax - ymin)
            ann = {'area': o_width * o_height, 'iscrowd': 0, 'image_id':
                image_id, 'bbox': [xmin, ymin, o_width, o_height],
                   'category_id': int(category), '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)
    #
    # convert(sys.argv[1], sys.argv[2], sys.argv[3])
	
    xml_path = 'D:/Users/Desktop/GradProject/datasets/test_xml2'
    xml_list = 'D:/Users/Desktop/xml_list.txt'
    json_path = 'D:/Users/Desktop/test_annotations.json'
    create_xml_list(xml_path, xml_list)
    convert(xml_list, xml_path, json_path)

转换流程:

1. 先将要转化的所有.xml文件名保存在xml_list.txt列表中。
2. 遍历 xml_list.txt 的文件进行转化

参考: VOC数据集和COCO数据集直接的相互转换