voc格式数据集转coco格式

voc格式和coco格式在目标检测领域是用的比较多的。所以记录一下我将voc格式的数据集转coco格式的过程。
分离训练集和测试集
由于voc格式的数据集中，训练集和测试集的注释文件放在一个文件夹下，所以我需要先将其分离。

# Written by GX
# if you want to use it to copy some file from one directory to the other directory,
# you can you this file
# first, you should have a list file. eg:trainval.txt
# ---------------------------------------------------------------------------------------------------------

import os
import shutil

# the path is you original file directory
# the newpath is the new directory
class BatchCopy():
    def __init__(self):
        self.path = '/home/zhgx/WorkSpace/KITTI/VOC2007/Annotations'
        self.newpath = '/home/zhgx/WorkSpace/KITTI/VOC2007/train_annotations'

    def copy_file(self):
        filelist = os.listdir(self.path)  # file list in this directory
        # print(len(filelist))
        test_list = loadFileList()
        # print(len(test_list))
        for f in filelist:
            filedir = os.path.join(self.path, f)
            (shotname, extension) = os.path.splitext(f)
            if str(shotname) in test_list:
                # print('success')
                shutil.copyfile(str(filedir),os.path.join(self.newpath,f))
                

# load the list of train/test file list
def loadFileList():
    filelist = []
    f = open("/home/zhgx/WorkSpace/KITTI/VOC2007/ImageSets/Main/trainval.txt", "r")
    lines = f.readlines()
    for line in lines:
        line = line.strip('\r\n')  # to remove the '\n' for test.txt, '\r\n' for tainval.txt 
        line = str(line)
        filelist.append(line)
    f.close()
    # print(filelist)
    return filelist

if __name__ == '__main__':
    demo = BatchCopy()
    demo.copy_file()
    filelist = os.listdir('/home/zhgx/WorkSpace/KITTI/VOC2007/train_annotations')
    # print(len(filelist))

将训练集/测试集的注释复制到新路径下备用。（注意测试集要放另一个文件夹）
转换格式
代码出自https://github.com/withyou1771/Detectron_FocalLoss/blob/master/tools/xml_to_json.py

# if you want to use, just change the xml_path and json_file to you need.
import xml.etree.ElementTree as ET
import os
import json

coco = dict()
coco['images'] = []
coco['type'] = 'instances'
coco['annotations'] = []
coco['categories'] = []

category_set = dict()
image_set = set()

category_item_id = 0
image_id = 20180000000
annotation_id = 0


def addCatItem(name):
    global category_item_id
    category_item = dict()
    category_item['supercategory'] = 'none'
    category_item_id += 1
    category_item['id'] = category_item_id
    category_item['name'] = name
    coco['categories'].append(category_item)
    category_set[name] = category_item_id
    return category_item_id


def addImgItem(file_name, size):
    global image_id
    if file_name is None:
        raise Exception('Could not find filename tag in xml file.')
    if size['width'] is None:
        raise Exception('Could not find width tag in xml file.')
    if size['height'] is None:
        raise Exception('Could not find height tag in xml file.')
    image_id += 1
    image_item = dict()
    image_item['id'] = image_id
    image_item['file_name'] = file_name
    image_item['width'] = size['width']
    image_item['height'] = size['height']
    coco['images'].append(image_item)
    image_set.add(file_name)
    return image_id


def addAnnoItem(object_name, image_id, category_id, bbox):
    global annotation_id
    annotation_item = dict()
    annotation_item['segmentation'] = []
    seg = []
    # bbox[] is x,y,w,h
    # left_top
    seg.append(bbox[0])
    seg.append(bbox[1])
    # left_bottom
    seg.append(bbox[0])
    seg.append(bbox[1] + bbox[3])
    # right_bottom
    seg.append(bbox[0] + bbox[2])
    seg.append(bbox[1] + bbox[3])
    # right_top
    seg.append(bbox[0] + bbox[2])
    seg.append(bbox[1])

    annotation_item['segmentation'].append(seg)

    annotation_item['area'] = bbox[2] * bbox[3]
    annotation_item['iscrowd'] = 0
    annotation_item['ignore'] = 0
    annotation_item['image_id'] = image_id
    annotation_item['bbox'] = bbox
    annotation_item['category_id'] = category_id
    annotation_id += 1
    annotation_item['id'] = annotation_id
    coco['annotations'].append(annotation_item)


def parseXmlFiles(xml_path):
    for f in os.listdir(xml_path):
        if not f.endswith('.xml'):
            continue

        bndbox = dict()
        size = dict()
        current_image_id = None
        current_category_id = None
        file_name = None
        size['width'] = None
        size['height'] = None
        size['depth'] = None

        xml_file = os.path.join(xml_path, f)
        print(xml_file)

        tree = ET.parse(xml_file)
        root = tree.getroot() 

        if root.tag != 'annotation': 
            raise Exception('pascal voc xml root element should be annotation, rather than {}'.format(root.tag))

        # elem is <folder>, <filename>, <size>, <object>
        for elem in root:
            current_parent = elem.tag
            current_sub = None
            object_name = None

            if elem.tag == 'folder':
                continue

            if elem.tag == 'filename':
                file_name = elem.text
                if file_name in category_set:
                    raise Exception('file_name duplicated')

            # add img item only after parse <size> tag
            elif current_image_id is None and file_name is not None and size['width'] is not None:
                if file_name not in image_set:
                    current_image_id = addImgItem(file_name, size)
                    print('add image with {} and {}'.format(file_name, size))
                else:
                    raise Exception('duplicated image: {}'.format(file_name))
                    # subelem is <width>, <height>, <depth>, <name>, <bndbox>
            for subelem in elem:
                bndbox['xmin'] = None
                bndbox['xmax'] = None
                bndbox['ymin'] = None
                bndbox['ymax'] = None

                current_sub = subelem.tag
                if current_parent == 'object' and subelem.tag == 'name':
                    object_name = subelem.text
                    if object_name not in category_set:
                        current_category_id = addCatItem(object_name)
                    else:
                        current_category_id = category_set[object_name]

                elif current_parent == 'size':
                    if size[subelem.tag] is not None:
                        raise Exception('xml structure broken at size tag.')
                    size[subelem.tag] = int(subelem.text)

                # option is <xmin>, <ymin>, <xmax>, <ymax>, when subelem is <bndbox>
                for option in subelem:
                    if current_sub == 'bndbox':
                        if bndbox[option.tag] is not None:
                            raise Exception('xml structure corrupted at bndbox tag.')
                        bndbox[option.tag] = int(option.text)

                # only after parse the <object> tag
                if bndbox['xmin'] is not None:
                    if object_name is None:
                        raise Exception('xml structure broken at bndbox tag')
                    if current_image_id is None:
                        raise Exception('xml structure broken at bndbox tag')
                    if current_category_id is None:
                        raise Exception('xml structure broken at bndbox tag')
                    bbox = []
                    # x
                    bbox.append(bndbox['xmin'])
                    # y
                    bbox.append(bndbox['ymin'])
                    # w
                    bbox.append(bndbox['xmax'] - bndbox['xmin'])
                    # h
                    bbox.append(bndbox['ymax'] - bndbox['ymin'])
                    print(
                    'add annotation with {},{},{},{}'.format(object_name, current_image_id, current_category_id, bbox))
                    addAnnoItem(object_name, current_image_id, current_category_id, bbox)


if __name__ == '__main__':
    xml_path = '/home/zhgx/WorkSpace/KITTI/VOC2007/test_annotations'
    json_file = '/home/zhgx/WorkSpace/KITTI/VOC2007/json/voc_2007_test.json'
    parseXmlFiles(xml_path)
    json.dump(coco, open(json_file, 'w'))

通过上述代码生成json格式的注释，然后将图片和注释按coco的要求放置即可。
一般数据集存放结构

VOC<year>
|_ JPEGImages
|  |_ <im-1-name>.jpg
|  |_ ...
|  |_ <im-N-name>.jpg
|_ annotations
|  |_ voc_<year>_train.json
|  |_ voc_<year>_val.json
|  |_ ...
|_ VOCdevkit<year>

实现数据集转换过程中忘了可以通过读取文件列表直接生成，而采用了最垃圾的分离训练测试集的方法，可以在转换代码中加一个读取文件列表的函数实现上述过程。