把xml文件转换成 COCO Dataset 数据特点的json文件形式

最新推荐文章于 2023-09-24 12:51:43 发布

sustyle

最新推荐文章于 2023-09-24 12:51:43 发布

阅读量929

点赞数

分类专栏：目标检测文章标签：科研文献管理 openvino blob

本文链接：https://blog.csdn.net/sunchanglan151/article/details/121378445

版权

目标检测专栏收录该内容

10 篇文章 2 订阅

订阅专栏

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

转换中这句话的逻辑一直过不去！！！报错，我找了下大概错误原因是.xml文件中的filename。

由于实验需要，现在要求必须让最后生成的json文件中的image_id=图片的id。但是我使用的代码竟然把image_id直接自增了，导致我最后使用Efficinetdet进行模型评估的时候发现image_id全是自增的数字，并不是图片的id。这给实验带来了麻烦。

解决的方法是在一开始转换成json的时候就把image_id给设置好。代码如下：

import os
import glob
import json
import shutil
import numpy as np
import xml.etree.ElementTree as ET
 
path2 = "."#当前该文件路径
 
 
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"
        a, b = os.path.splitext(filename)

        image_id = a
       
        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':int(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':
                   int(image_id), 'bbox':[xmin, ymin, o_width, o_height],
                   'category_id': category_id, 'id': bnd_id, 'ignore': 0,
                   'segmentation': []}
            json_dict['annotations'].append(ann)#将生成的json文件加入annotations文件夹
            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__':
    classes = ['fire']
    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
 
    train_ratio = 0.9#控制train和val的比例，train_ratio=1是全部生成为train数据
    save_json_train = 'instances_train2014.json'#生成训练集json文件名
    save_json_val = 'instances_val2014.json'
    xml_dir = "ass"#存放xml文件的文件夹
 
    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:]
 
    convert(xml_list_train, save_json_train)
    convert(xml_list_val, save_json_val)
 
    if os.path.exists(path2 + "/annotations"):
        shutil.rmtree(path2 + "/annotations")
    os.makedirs(path2 + "/annotations")
    if os.path.exists(path2 + "/images/train2014"):
        shutil.rmtree(path2 + "/images/train2014")
    os.makedirs(path2 + "/images/train2014")
    if os.path.exists(path2 + "/images/val2014"):
        shutil.rmtree(path2 +"/images/val2014")
    os.makedirs(path2 + "/images/val2014")
 
    f1 = open("train.txt", "w")
    for xml in xml_list_train:
        img = xml[:-4] + ".jpg"#根据xml文件路径获取图片路径，此时图片和xml文件都在annotations文件夹中
        f1.write(os.path.basename(xml)[:-4] + "\n")
        shutil.copyfile(img, path2 + "/images/train2014/" + os.path.basename(img))#将用于训练的图片存入训练集
 
    f2 = open("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 + "/images/val2014/" + os.path.basename(img))#将用于测试的图片存入测试集
    f1.close()
    f2.close()
    print("-------------------------------")
    print("train number:", len(xml_list_train))
    print("val number:", len(xml_list_val))

代码改动的地方是这个部分

 
        filename = os.path.basename(xml_f)[:-4] + ".jpg"
        a, b = os.path.splitext(filename)

        image_id = a

把当前xml文件的名字和后缀名取出来，但是直接这样赋值给image_id是以字符串的形式保存的，但是参考这个

https://blog.csdn.net/wc781708249/article/details/79603522

我们发现，image_id和id值是相同的，而且二者都是整数，所以最后再强制类型转换一下即可。

int(image_id)

另外提一下：一开始我的思路是直接更改.xml文件中的path和filename字段，但是还是没有解决问题。但是绝对有必要记录下我的测试过程。

修改path

import xml.dom.minidom
import os
 
path='/Users/sunchanglan/Desktop/dieasesDetection/Dataset/Labels' # xml文件存放路径
sv_path='/Users/sunchanglan/Desktop/dieasesDetection/Dataset/annotations' # 修改后的xml文件存放路径
files=os.listdir(path)
 
for xmlFile in files:
	dom=xml.dom.minidom.parse(os.path.join(path,xmlFile)) #打开xml文件，送到dom解析
 
	root=dom.documentElement #得到文档元素对象
 
	item=root.getElementsByTagName('path') #获取path这一node名字及相关属性值
 
	a,b=os.path.splitext(xmlFile) #分离出文件名a
 
	for i in item:
		#i.firstChild.data=a + '.jpg'
		i.firstChild.data = "/Users/sunchanglan/Desktop/dieasesDetection/Dataset/images/" + a + '.jpg'
 
	with open(os.path.join(sv_path,xmlFile),'w') as fh:
		dom.writexml(fh)

修改filename

import xml.dom.minidom
import os

path = r'/Users/sunchanglan/Desktop/dieasesDetection/Dataset/Labels'# xml文件存放路径
sv_path = r'/Users/sunchanglan/Desktop/dieasesDetection/Dataset/annotations'# 修改后的xml文件存放路径
files = os.listdir(path)
print(files)

for xmlFile in files:
    dom = xml.dom.minidom.parse(os.path.join(path, xmlFile))# 打开xml文件，送到dom解析
    root = dom.documentElement# 得到文档元素对象
    names = root.getElementsByTagName('filename')
    # item = root.getElementsByTagName('path') #获取path这一node名字及相关属性值
    a, b = os.path.splitext(xmlFile)# 分离出文件名a
# print(a,b)
for n in names:
    n.firstChild.data = a + '.jpg'

 
with open(os.path.join(sv_path, xmlFile), 'w') as fh:
    dom.writexml(fh)

二者代码相近，我尝试将二者写入同一个脚本文件中，但是报错！

另一个问题是这个改了不论是path还是filename之后再转json文件还是报错，好像是dom解析出了问题。还有一个问题是会更改版本问题！！所以大家慎重选择这两种方法解决。

以上代码都是从网上找的开源的，我已经调通，需要的按要求自行取用！

sustyle

关注

0
点赞
踩
5

收藏

觉得还不错? 一键收藏
打赏
0
评论
把xml文件转换成 COCO Dataset 数据特点的json文件形式

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 s.
复制链接

扫一扫