VOC数据集格式（xml）转COCO数据集格式（json）问题解决

问题来源

目标检测应用过程中，原本使用的YOLOv3使用数据集格式是voc数据集格式。使用的labelImg软件标注图片，生成每张图片的xml文件包含标注信息。

最近更换在detectorn2上进行目标检测，需要使用coco数据集格式，常用labelme软件标注图片，生成每张图片的json文件包含标注信息，再集合成一个总的json文件包含所有图片的。

转换的python文件与注释

import sys
import os
import json
import xml.etree.ElementTree as ET
 
 
START_BOUNDING_BOX_ID = 1 //设置自己从哪个id开始
# If necessary, pre-define category and its id 对每一个目标物体设置id号
#  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 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(filename)://获取文件的名称 后面调用时对通过路径获得的名称进行处理
    try:
        filename = os.path.split(filename)[1] //只保留名称，不要路径
        return (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()
        #line=line+".xml"
        print("Processing %s"%(line))
        xml_f = os.path.join(xml_dir, line)
        tree = ET.parse(xml_f)
        root = tree.getroot()
        path = get(root, 'path')[0] //出错原因，未加[0]
        if len(path) == 1:
            filename = os.path.splitext(path)[1]
            #filename = (path[0].text)
        elif len(path) == 0:
            #filename = get_and_check(root, 'filename', 1).text
            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(filename) //调用上面的函数获得image_id，与文件名相同
        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__':
    xml_list='val.txt'  // xml文件生成的txt文本，内容是有那些xml文件
    xml_dir='val_label' //xml文件路径 自定义
    json_dir='10.json'  //自己生成的json文件
    convert(xml_list, xml_dir, json_dir)

写

遇到的问题

下次再写