XML to COCO数据

XML to COCO数据

# coding:utf-8
# pip install lxml

import os
import glob
import json
import shutil
import numpy as np
import xml.etree.ElementTree as ET

path2 = "/raid/ZXF/project_jishi/data/物料堆放/coco"  # 输出文件夹
classes = ['box', 'bag', 'basket', 'shelf']  # 类别
train_xml_dir = "/raid/ZXF/project_jishi/data/物料堆放/data"  # xml原始文件夹和图片放在一起
test_xml_dir = "/raid/ZXF/project_jishi/data/物料堆放/data"  #训练集和验证集放在一起
# xml_dir = "/raid/ZXF/project_jishi/data/物料堆放/data"  # xml原始文件夹和图片放在一起
# train_ratio = 0.9  # 训练集的比例

START_BOUNDING_BOX_ID = 1

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


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 convert(xml_list, json_file):
    json_dict = {"images": [], "type": "instances", "annotations": [], "categories": []}
    categories = pre_define_categories.copy()
    bnd_id = START_BOUNDING_BOX_ID
    all_categories = {}
    for index, line in enumerate(xml_list):
        # print("Processing %s"%(line))
        xml_f = line
        tree = ET.parse(xml_f)
        root = tree.getroot()

        filename = os.path.basename(xml_f)[:-4] + ".jpg"
        image_id = 20190000001 + index
        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 in all_categories:
                all_categories[category] += 1
            else:
                all_categories[category] = 1
            if category not in categories:
                if only_care_pre_define_categories:
                    continue
                new_id = len(categories) + 1
                print(
                    "[warning] category '{}' not in 'pre_define_categories'({}), create new id: {} automatically".format(
                        category, pre_define_categories, new_id))
                categories[category] = new_id
            category_id = categories[category]
            bndbox = get_and_check(obj, 'bndbox', 1)
            xmin = int(float(get_and_check(bndbox, 'xmin', 1).text))
            ymin = int(float(get_and_check(bndbox, 'ymin', 1).text))
            xmax = int(float(get_and_check(bndbox, 'xmax', 1).text))
            ymax = int(float(get_and_check(bndbox, 'ymax', 1).text))
            assert (xmax > xmin), "xmax <= xmin, {}".format(line)
            assert (ymax > ymin), "ymax <= ymin, {}".format(line)
            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()
    print("------------create {} done--------------".format(json_file))
    print("find {} categories: {} -->>> your pre_define_categories {}: {}".format(len(all_categories),
                                                                                  all_categories.keys(),
                                                                                  len(pre_define_categories),
                                                                                  pre_define_categories.keys()))
    print("category: id --> {}".format(categories))
    print(categories.keys())
    print(categories.values())


if __name__ == '__main__':

    pre_define_categories = {}
    for i, cls in enumerate(classes):
        pre_define_categories[cls] = i + 1
    # pre_define_categories = {'a1': 1, 'a3': 2, 'a6': 3, 'a9': 4, "a10": 5}
    only_care_pre_define_categories = True
    # only_care_pre_define_categories = False

    if os.path.exists(path2 + "/annotations"):
        shutil.rmtree(path2 + "/annotations")
    os.makedirs(path2 + "/annotations")
    if os.path.exists(path2 + "/train2017"):
        shutil.rmtree(path2 + "/train2017")
    os.makedirs(path2 + "/train2017")
    if os.path.exists(path2 + "/val2017"):
        shutil.rmtree(path2 + "/val2017")
    os.makedirs(path2 + "/val2017")

    save_json_train = path2 + '/annotations/instances_train2017.json'
    save_json_val = path2 + '/annotations/instances_val2017.json'

    #进行使用ratio获得train test 的区别
    # xml_list = glob.glob(xml_dir + "/*.xml")
    # xml_list = np.sort(xml_list)
    # np.random.seed(100)
    # np.random.shuffle(xml_list)
    #
    # train_num = int(len(xml_list) * train_ratio)
    # xml_list_train = xml_list[:train_num]
    # xml_list_val = xml_list[train_num:]


    xml_list_train = glob.glob(train_xml_dir + "/*.xml")
    xml_list_train = np.sort(xml_list_train)
    np.random.seed(100)
    np.random.shuffle(xml_list_train)

    xml_list_val = glob.glob(test_xml_dir + "/*.xml")
    xml_list_val = np.sort(xml_list_val)
    np.random.seed(100)
    np.random.shuffle(xml_list_val)

    convert(xml_list_train, save_json_train)
    convert(xml_list_val, save_json_val)

    f1 = open(path2 + "/train.txt", "w")
    for xml in xml_list_train:
        img = xml[:-4] + ".jpg"
        f1.write(os.path.basename(xml)[:-4] + "\n")
        shutil.copyfile(img, path2 + "/train2017/" + os.path.basename(img))

    f2 = open(path2 + "/test.txt", "w")
    for xml in xml_list_val:
        img = xml[:-4] + ".jpg"
        f2.write(os.path.basename(xml)[:-4] + "\n")
        shutil.copyfile(img, path2 + "/val2017/" + os.path.basename(img))

    f1.close()

    f2.close()
    print("-------------------------------")
    print("train number:", len(xml_list_train))
    print("val number:", len(xml_list_val))

XML to yolo

# coding:utf-8
# pip install lxml

import os
import glob
import json
import shutil
import numpy as np
import xml.etree.ElementTree as ET

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

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 convert(all_image_path, txt_file):
    all_label_list = list()
    image_list=os.listdir(all_image_path)
    all_xml_path=os.path.join(os.path.dirname(all_image_path),"xml")  #所有的xml label文件路径
    for index, name in enumerate(image_list):
        image_path=os.path.join(all_image_path,name)
        xml_path=os.path.join(all_xml_path,name[:-4]+".xml")

        xml_f = xml_path
        tree = ET.parse(xml_f)
        root = tree.getroot()
        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)

        for obj in get(root, 'object'):
            category = get_and_check(obj, 'name', 1).text
            bndbox = get_and_check(obj, 'bndbox', 1)
            xmin = int(float(get_and_check(bndbox, 'xmin', 1).text))
            ymin = int(float(get_and_check(bndbox, 'ymin', 1).text))
            xmax = int(float(get_and_check(bndbox, 'xmax', 1).text))
            ymax = int(float(get_and_check(bndbox, 'ymax', 1).text))

            image_path=image_path+" "+category+" "+str(xmin)+" "+str(ymin)+" "+str(xmax)+" "+str(ymax)
        all_label_list.append(image_path+"\n")
    with open(txt_file,'w') as out:
        out.writelines(all_label_list)

if __name__ == '__main__':
    image_path="/raid/ZXF/project_jishi/data/ori/test/pic"
    txt_file="/raid/ZXF/project_jishi/data/ori/test/test.txt"
    convert(image_path,txt_file)