一键转换labelimg格式为COCO格式

将VOC格式的数据转换为COCO格式

1.实现了将目标检测任务中使用的 Pascal VOC 格式标注数据转换为 COCO 格式标注数据，并生成两个 COCO 格式的 JSON 文件，用于训练和验证。
2.通过解析 XML 文件，提取图片信息、类别信息和目标框信息，并将这些数据添加到对应的 COCO 格式数据中。
3.使用随机数种子将数据按照 8:2 的比例划分为训练集和验证集，并将相应的图片拷贝到新的文件夹中。
4.将生成的 COCO 格式数据分别保存为两个 JSON 文件。这样转换后的数据格式更适合用于训练目标检测模型，尤其是对于使用 COCO 格式的深度学习框架。

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

# 设置随机数种子，可以是任意整数
random_seed = 42

# 设置随机数种子
random.seed(random_seed)


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

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

# category_set = dict()
image_set = set()
train_image_id = 1
val_image_id = 200000  # Assuming you have less than 200000 images
category_item_id = 1
annotation_id = 1
category_set = ['huaheng_ng', 'liuwen', 'gubao', 'huaheng_ok', 'qipi']

def split_list_by_ratio(input_list, ratio=0.8):
    # 计算切分的索引位置
    split_index = int(len(input_list) * ratio)
    # 随机打乱列表
    random.shuffle(input_list)
    # 划分为两个列表并返回
    return input_list[:split_index], input_list[split_index:]

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_train['categories'].append(category_item)
    coco_val['categories'].append(category_item)
    category_item_id += 1


def addImgItem(file_name, size, img_suffixes, is_train):
    global train_image_id  # 声明变量为全局变量
    global val_image_id  # 声明变量为全局变量
    # 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] + img_suffixes
    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)
    if is_train:
        image_item['id'] = train_image_id
        coco_train['images'].append(image_item)
        image_id = train_image_id
        train_image_id += 1
    else:
        image_item['id'] = val_image_id
        coco_val['images'].append(image_item)
        image_id = val_image_id
        val_image_id += 1
    image_set.add(jpg_name)
    image_id = image_id + 1
    return image_id


def addAnnoItem(object_name, image_id, category_id, bbox, is_train):
    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)
    if is_train:
        coco_train['annotations'].append(annotation_item)
    else:
        coco_val['annotations'].append(annotation_item)

def parseXmlFiles(xml_path, xmllist, img_suffixes, is_train):
    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 , , ,