labelimg标注的VOC格式(xml文件)转COCO格式(json)

学习视频:目标检测实战教程01-使用labelimg标注目标检测数据集 | voc转COCO数据集_哔哩哔哩_bilibili

1.脚本文件

下面是脚本文件,该脚本文件可以把目录下的多个 VOC 格式的 xml 标注文件转换为一个 COCO 格式的 json 文件,需要修改的地方写在代码前面了

java 复制代码
"""
需要修改的地方
1. category_set = ['dog'],此处填写数据集的类别名称
2. 代码末尾处voc格式的xml标注文件所在的目录
3. 代码末尾处对应生成的json文件存放路径
4. 51行处,生成coco标签文件格式后缀名要与自己图片文件类型对应(此处为jpg)
注:训练集与测试集中类别的顺序必须保持一致,因此最好事先确定category的顺序,书写在category_set中
"""

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

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

# category_set = dict()
image_set = set()
image_id = 1  # train:2018xxx; val:2019xxx; test:2020xxx
category_item_id = 1
annotation_id = 1

#类别
category_set = ['person','bird','cat','cow','dog','horse','sheep','aeroplane','bicycle',
                'boat','bus','car','motorbike','train','bottle','chair','diningtable','pottedplant',
                'sofa','tvmonitor']

def addCatItem(name):
    '''
    增加json格式中的categories部分
    '''
    global category_item_id
    category_item = collections.OrderedDict()
    category_item['supercategory'] = 'none'
    category_item['id'] = category_item_id
    category_item['name'] = name
    coco['categories'].append(category_item)
    category_item_id += 1


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_item = dict()    #按照一定的顺序,这里采用collections.OrderedDict()
    image_item = collections.OrderedDict()
    jpg_name = os.path.splitext(file_name)[0] + '.jpg'
    image_item['file_name'] = jpg_name
    image_item['width'] = size['width']
    image_item['height'] = size['height']
    image_item['id'] = image_id
    coco['images'].append(image_item)
    image_set.add(jpg_name)
    image_id = image_id + 1
    return image_id


def addAnnoItem(object_name, image_id, category_id, bbox):
    global annotation_id
    # annotation_item = dict()
    annotation_item = collections.OrderedDict()
    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['image_id'] = image_id
    annotation_item['bbox'] = bbox
    annotation_item['category_id'] = category_id
    annotation_item['id'] = annotation_id
    annotation_item['ignore'] = 0
    annotation_id += 1
    coco['annotations'].append(annotation_item)


def parseXmlFiles(xml_path):
    xmllist = os.listdir(xml_path)
    xmllist.sort()
    for f in xmllist:
        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()  # 抓根结点元素

        if root.tag != 'annotation':  # 根节点标签
            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

            # elem.tag, elem.attrib,elem.text
            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)  # 图片信息
                    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]
                    current_category_id = category_set.index(object_name) + 1  # index默认从0开始,但是json文件是从1开始,所以+1
                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 - 1, current_category_id,
                                                                 bbox))
                    addAnnoItem(object_name, current_image_id - 1, current_category_id, bbox)
    # categories部分
    for categoryname in category_set:
        addCatItem(categoryname)


if __name__ == '__main__':
    xml_path = 'D:\BaiduNetdiskDownload\yolov8-ship\VOCdevkit\VOC2007\Annotations'#xml文件存放目录
    json_file = 'D:\BaiduNetdiskDownload\yolov8-ship\coco.json'#生成的json文件存放路径
    parseXmlFiles(xml_path)
json.dump(coco, open(json_file, 'w'))

2.演示

VOC 格式的 xml 标注文件存放目录:D:\BaiduNetdiskDownload\yolov8-ship\okk

将脚本末尾处的 xml_path 修改为 :D:\BaiduNetdiskDownload\yolov8-ship\okk,指定生成的 json文件存放路径为 D:\BaiduNetdiskDownload\yolov8-ship\okk\coco\train.json

执行脚本文件,生成 json 文件

相关推荐
蹦蹦跳跳真可爱58916 小时前
Python----目标检测(《用于精确目标检测和语义分割的丰富特征层次结构》和R-CNN)
人工智能·python·深度学习·神经网络·目标检测·cnn
机器学习算法1 天前
基于 OpenCV 和 DLib 实现面部特征调整(眼间距、鼻子、嘴巴)
人工智能·深度学习·神经网络·opencv·目标检测·机器学习·计算机视觉
pen-ai1 天前
【深度学习】14. DL在CV中的应用章:目标检测: R-CNN, Fast R-CNN, Faster R-CNN, MASK R-CNN
深度学习·目标检测·cnn
鸢想睡觉1 天前
Mask_RCNN 环境配置及训练
人工智能·笔记·目标检测·mask_rcnn
蹦蹦跳跳真可爱5891 天前
Python----目标检测(《基于区域提议网络的实时目标检测方法》和Faster R-CNN)
人工智能·python·深度学习·神经网络·目标检测·机器学习·cnn
清梦枕星河~1 天前
OVD开放词汇检测 Detic 训练COCO数据集实践
python·目标检测·ovd·detic
猫天意1 天前
【目标检测】检测网络中neck的核心作用
人工智能·目标检测·计算机视觉·基础·cv
猫天意1 天前
【目标检测】backbone究竟有何关键作用?
人工智能·目标检测·计算机视觉·cv
江苏泊苏系统集成有限公司2 天前
集成电路制造设备防震基座选型指南:为稳定护航-江苏泊苏系统集成有限公司
人工智能·深度学习·目标检测·机器学习·制造·材料工程·精益工程
彭祥.2 天前
安全帽目标检测
人工智能·目标检测·目标跟踪