Python-修改xml标注文件内容，再将VOC格式转化成COCO格式数据

在跑一个目标检测模型时，要求使用coco格式的json标注文件，而我只有voc格式的xml标注文件，因此需要将voc格式转化成coco格式。

在转化前，发现了我原来的xml标注文件中有个问题：第三行filename中的内容应该和对应的图片名保持一致，即图片000000.jpg、标注000000.xml中的filename也应为000000.jpg。但实际存在filename内容错误的xml，因此需要判定每个xml中filename是否正确，若不正确，则进行修改再保存，代码如下。

train.txt是训练图片的名字，如下所示。

train_annotation文件夹存放着训练图片的标注文件。

判断filename是否和图片名称一致，若不一致则修改。
程序一：

import xml.etree.ElementTree as ET

# 查找filename节点并更新
def Update_xml(xml_path,name):
    root = ET.parse(xml_path)
    for node in root.findall('filename'):
        if node.text != name:
            node.text = name

    root.write(xml_path)


def main():
    file_object = open('/home/jiao/HatProject/train.txt', 'rU')
    try:
        for line in file_object:
            path = '/home/jiao/HatProject/train_annotation/' + line.rstrip('\n') + '.xml'
            true_name = line.rstrip('\n') + '.jpg'
            Update_xml(path, true_name)
    finally:
        file_object.close()

if __name__ == '__main__':
    main()

程序二：

import xml.etree.ElementTree as ET
import os

# 查找filename节点并更新
def Update_xml(xml_path,name):
    root = ET.parse(xml_path)
    for node in root.findall('filename'):
        if node.text != name:
            node.text = name

    root.write(xml_path)

def main():
    xml_path = '/home/jiao/HatProject/train_annotation/'  # xml文件地址
    for xml in os.listdir(xml_path):
        xml_name = os.path.splitext(xml)
        xml_destfile = xml_path + xml_name[0] + xml_name[1]
        Update_xml(xml_destfile, xml_name[0] + '.jpg')

if __name__ == '__main__':
    main()

voc的xml格式转化coco的json格式的代码：

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 = -1
image_id = 0
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/jiao/HatProject/train_annotation'
    json_file = '/home/jiao/HatProject/instances_train.json'
    parseXmlFiles(xml_path)
    json.dump(coco, open(json_file, 'w'))