VOC数据集转换为CoCo数据集（亲测有效）

 #VOC数据集格式

VOC格式的数据集分为3部分，Annotations、ImageSets、JPEGImages。

（一） Annotations：存放数据标注的xml文件，格式如下：

<?xml version="1.0" ?>
<annotation>
<folder>CUMID_train</folder>
<filename>0001.png</filename>
<path>C:\Users\86182\Desktop\CUMID_train\0001.png</path>
<source>
    <database>Unknown</database>
</source>
<size>
    <width>2040</width>
    <height>1368</height>
    <depth>3</depth>
</size>

<segmented>0</segmented>
    <object>
    <name>Machine</name>
    <pose>Unspecified</pose>
    <truncated>0</truncated>
    <difficult>0</difficult>
    <bndbox>
        <xmin>1193</xmin>
        <ymin>349</ymin>
        <xmax>1451</xmax>
        <ymax>767</ymax>
    </bndbox>
</annotation>

（二）ImageSets：存放数据分配的txt文件，文件中存放的是图像文件名称；

（三）JPEGImages：存放图像数据文件；

#CoCo数据集格式

        不同于VOC格式一个xml文件对应一张图像，CoCo格式数据集的标签文件是集中在一个json文件中的，json文件内部包含3部分：images、annotations、categeories。

CoCo #根目录

        annotations

                instances_train2017.json：训练集标注

                instances_val2017.json：验证集标注

        train2017:训练集图像

        val2017：验证集图像

json文件内部具体如下：

（一）images：存放图像名称以及大小

{
      "file_name": "img-1.png",
      "height": 720,
      "width": 720,
      "id": 0
    },

（二）annotations：存放边框位置坐标、类别、图像id等信息

{
      "area": 43507,
      "iscrowd": 0,
      "image_id": 0,
      "bbox": [
        212,
        239,
        313,
        139
      ],
      "category_id": 1,
      "id": 1,
      "ignore": 0,
      "segmentation": [
        []
      ]
    },

（三）categeories：存放数据集类别

{
      "supercategory": "none",
      "id": 1,
      "name": "pothole"
    }

#vocTococo

#!/usr/bin/python

# pip install lxml

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


START_BOUNDING_BOX_ID = 1
PRE_DEFINE_CATEGORIES = {}
# 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}
PRE_DEFINE_CATEGORIES = {"pothole": 1}

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_list, xml_dir, json_file):
    list_fp = open(xml_list, 'r')
    json_dict = {"images": [], "annotations": [],
                 "categories": []}
    categories = PRE_DEFINE_CATEGORIES
    bnd_id = START_BOUNDING_BOX_ID
    image_counter = 0  # 添加一个计数器变量

    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')
        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)
        image_id = image_counter  # 使用计数器作为image的id
        image_counter += 1  # 递增计数器
        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 = r'E:\code\python\2\VOCdevkit\VOC2007\ImageSets\Main\val.txt'
    # xml_list = './data/VOCdevkit/ImageSets/Main/val.txt'
    xml_dir = r'E:\code\python\2\VOCdevkit\VOC2007\Annotations\val'
    # json_dir = './data/COCO/annotations/test.json'  # 注意！！！这里test.json先要自己创建，不然
    json_dir = r'E:\code\python\2\VOCdevkit\instances_val2017.json'
    convert(xml_list, xml_dir, json_dir)

修改步骤：

1、PRE_DEFINE_CATEGORIES：换成自己的类别

2、xml_list：内容替换为自己的.txt文件，文件中存放的是图像名称

3、xml_dir：内容替换为自己的.xml文件夹，存放的是xml文件

4、json_dir：自定义生成的json文件位置

5、把train和val分开运行2次即可