输出能将voc格式数据集转换为coco格式数据集的脚本

下面是一个将VOC格式数据集转换为COCO格式数据集的Python脚本，需要安装COCO API：

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

def xml_to_json(xml_file, root_path, image_id):
    with open(xml_file, 'r') as f:
        tree = ET.parse(f)
        root = tree.getroot()
        size = root.find('size')
        width = int(size.find('width').text)
        height = int(size.find('height').text)
        image = {
            'id': image_id,
            'width': width,
            'height': height,
            'file_name': os.path.join(root_path, root.find('filename').text),
            'annotations': []
        }
        for obj in root.findall('object'):
            name = obj.find('name').text
            bbox = obj.find('bndbox')
            xmin = int(bbox.find('xmin').text)
            ymin = int(bbox.find('ymin').text)
            xmax = int(bbox.find('xmax').text)
            ymax = int(bbox.find('ymax').text)
            image['annotations'].append({
                'id': len(image['annotations'])+1,
                'image_id': image_id,
                'category_id': name,
                'bbox': [xmin, ymin, xmax-xmin, ymax-ymin],
                'area': (xmax-xmin)*(ymax-ymin),
                'iscrowd': 0
            })
        return image

def voc_to_coco(voc_path, save_path):
    categories = []
    annotations = []
    images = []
    category_id = {}
    image_id = 1
    annotation_id = 1
    for idx, class_name in enumerate(os.listdir(os.path.join(voc_path, 'Annotations'))):
        categories.append({'id': idx+1, 'name': class_name})
        category_id[class_name] = idx+1
        xml_files = os.listdir(os.path.join(voc_path, 'Annotations', class_name))
        for xml_file in xml_files:
            image = xml_to_json(os.path.join(voc_path, 'Annotations', class_name, xml_file), os.path.join(voc_path, 'JPEGImages'), image_id)
            images.append(image)
            for annotation in image['annotations']:
                annotation['id'] = annotation_id
                annotation['category_id'] = category_id[annotation['category_id']]
                annotations.append(annotation)
                annotation_id += 1
            image_id += 1
    data = {
        'categories': categories,
        'annotations': annotations,
        'images': images
    }
    with open(save_path, 'w') as f:
        json.dump(data, f, indent=2)

voc_path = 'path/to/VOC_dataset'
save_path = 'path/to/save/COCO_dataset.json'
voc_to_coco(voc_path, save_path)

其中，`voc_path`为VOC格式数据集的路径，`save_path`为转换后COCO格式数据集的保存路径。注意，该脚本仅适用于单标签分类任务，如果需要进行多标签分类、检测或分割任务，请根据需要进行修改。