kaggle Airbus Ship Detection Challenge coco数据集转voc(xml)格式

本文是kaggle Airbus Ship Detection Challenge 数据集转化为coco格式的基础上将其转化为适合yolo训练的voc格式。

kaggle Airbus Ship Detection Challenge 训练集下载：https://blog.csdn.net/weixin_42880443/article/details/82015347

kaggle Airbus Ship Detection Challenge 训练集预处理(转化为coco)格式：https://github.com/pascal1129/kaggle_airbus_ship_detection/tree/master/0_rle_to_coco

coco数据集样式

处理好的coco_label大致长这样，一共是29000余张可用图片，上面是图片id，下面是图片label

运行程序

    #-*- coding:utf-8-*-
    
    import xml.dom
    import xml.dom.minidom
    import os
    # from PIL import Image
    import cv2
    import json
    
    # xml文件规范定义
    
    
    _IMAGE_PATH = 'E:/coco/COCO/train'
    
    _INDENT = '' * 4
    _NEW_LINE = '\n'
    _FOLDER_NODE = 'COCO2014'
    _ROOT_NODE = 'annotation'
    _DATABASE_NAME = 'LOGODection'
    _ANNOTATION = 'COCO2014'
    _AUTHOR = 'CSDN'
    _SEGMENTED = '0'
    _DIFFICULT = '0'
    _TRUNCATED = '0'
    _POSE = 'Unspecified'
    
    # _IMAGE_COPY_PATH= 'JPEGImages'
    _ANNOTATION_SAVE_PATH = '/home/casiie/dehaze/airbus/dataset/annon'
    
    
    # _IMAGE_CHANNEL= 3
    
    # 封装创建节点的过程
    def createElementNode(doc, tag, attr):  #创建一个元素节点
        element_node = doc.createElement(tag)
    
        # 创建一个文本节点
        text_node = doc.createTextNode(attr)
    
        # 将文本节点作为元素节点的子节点
        element_node.appendChild(text_node)
    
        return element_node
    
    
    # 封装添加一个子节点
    def createChildNode(doc, tag, attr, parent_node):
        child_node = createElementNode(doc,tag, attr)
    
        parent_node.appendChild(child_node)
    
    
    # object节点比较特殊
    def createObjectNode(doc, attrs):
    
        object_node =doc.createElement('object')
    
        midname=attrs['id']
        midname = midname-1
        print(midname)
    
        global i
    
    
        createChildNode(doc, 'name', ('ship'),
                        object_node)
    
        #createChildNode(doc, 'name',attrs['name'],
        #                object_node)
    
        createChildNode(doc, 'pose',
                        _POSE, object_node)
    
        createChildNode(doc, 'truncated',
                        _TRUNCATED,object_node)
    
        createChildNode(doc, 'difficult',
                        _DIFFICULT,object_node)
    
        bndbox_node = doc.createElement('bbox')
    
        createChildNode(doc, 'xmin',str(int(attrs['bbox'][0])),
                        bndbox_node)
    
    
        print(attrs['bbox'][0])
    
        createChildNode(doc, 'ymin',str(int(attrs['bbox'][1])),
                        bndbox_node)
    
        createChildNode(doc, 'xmax',str(int(attrs['bbox'][0] + attrs['bbox'][2])),
                        bndbox_node)
    
        createChildNode(doc, 'ymax',str(int(attrs['bbox'][1] + attrs['bbox'][3])),
                        bndbox_node)
    
        object_node.appendChild(bndbox_node)
    
        return object_node
    
    
    # 将documentElement写入XML文件
    def writeXMLFile(doc, filename):
        tmpfile = open('tmp.xml', 'w')
    
        doc.writexml(tmpfile, addindent='' *4, newl='\n', encoding='utf-8')
    
    
        tmpfile.close()
    
        # 删除第一行默认添加的标记
    
        fin = open('tmp.xml')
        # print(filename)
        fout = open(filename, 'w')
        # print(os.path.dirname(fout))
    
        lines = fin.readlines()
    
        for line in lines[1:]:
    
            if line.split():
                fout.writelines(line)
    
                # new_lines =''.join(lines[1:])
    
            # fout.write(new_lines)
    
        fin.close()
    
        fout.close()
    
    
    if __name__ == "__main__":
        ##读取图片列表
        img_path ="/home/casiie/dehaze/airbus/dataset/train/"
        fileList = os.listdir(img_path)
        if fileList == 0:
            os._exit(-1)
    
        with open("instances_ships_train2018.json", encoding='utf-8') as f:
            #line = f.read()
            ann_data = json.load(f)
    
        current_dirpath =os.path.dirname(os.path.abspath('__file__'))
    
        #if notos.path.exists(_ANNOTATION_SAVE_PATH):
        #    os.mkdir(_ANNOTATION_SAVE_PATH)
    
            # if notos.path.exists(_IMAGE_COPY_PATH):
        #    os.mkdir(_IMAGE_COPY_PATH)
    
        for imageName in fileList:
    
            saveName =imageName.strip(".jpg")
            print(saveName)
            # pos =fileList[xText].rfind(".")
            # textName =fileList[xText][:pos]
    
            # ouput_file = open(_TXT_PATH +'/' + fileList[xText])
            # ouput_file =open(_TXT_PATH)
    
            # lines = ouput_file.readlines()
    
            xml_file_name =os.path.join(_ANNOTATION_SAVE_PATH, (saveName + '.xml'))
            #print(xml_file_name)
            # withopen(xml_file_name,"w") as f:
            #     pass
    
            img =cv2.imread(os.path.join(img_path, imageName))
            print(os.path.join(img_path,imageName))
            # cv2.imshow(img)
            height, width, channel =img.shape
            print(height, width, channel)
    
            my_dom = xml.dom.getDOMImplementation()
            #print(my_dom)
    
            doc = my_dom.createDocument(None,_ROOT_NODE, None)
            #print(doc)
    
            # 获得根节点
            root_node = doc.documentElement
    
            # folder节点
    
            createChildNode(doc, 'folder',_FOLDER_NODE, root_node)
    
            # filename节点
    
            createChildNode(doc, 'filename',saveName + '.jpg', root_node)
    
            # source节点
    
            source_node =doc.createElement('source')
    
            # source的子节点
    
            createChildNode(doc, 'database',_DATABASE_NAME, source_node)
    
            createChildNode(doc, 'annotation',_ANNOTATION, source_node)
    
            createChildNode(doc, 'image','flickr', source_node)
    
            createChildNode(doc, 'flickrid','NULL', source_node)
    
           	root_node.appendChild(source_node)
    
            # owner节点
    
            owner_node = doc.createElement('owner')
    
            # owner的子节点
    
            createChildNode(doc, 'flickrid','NULL', owner_node)
    
            createChildNode(doc, 'name',_AUTHOR, owner_node)
    
            root_node.appendChild(owner_node)
    
            # size节点
    
            size_node =doc.createElement('size')
    
            createChildNode(doc, 'width',str(width), size_node)
    
            createChildNode(doc, 'height',str(height), size_node)
    
            createChildNode(doc, 'depth',str(channel), size_node)
    
            root_node.appendChild(size_node)
    
            # segmented节点
    
            createChildNode(doc, 'segmented',_SEGMENTED, root_node)
    
            for ann in ann_data["images"]:
                #print(ann)
                #print(ann["id"])
                
    			#检查image id与annotations是否相符
                if(saveName+('.jpg') == ann['file_name']):
                    print(ann['file_name'])
                    r = ann['id']
                    print(r)
                    for bnn in ann_data["annotations"]:
                        if (r == bnn['id']):
    
                        
                            cname=saveName
    
                    # object节点
                            object_node =createObjectNode(doc, bnn)
    
                            root_node.appendChild(object_node)
    
                        else:
                            continue
                else:
                    continue
    
    
                    # 构建XML文件名称
    
            print(xml_file_name)
    
            # 创建XML文件
    
            # createXMLFile(attrs, width,height, xml_file_name)
    
            # # 写入文件
            #
            writeXMLFile(doc, xml_file_name)

这里注意更改路径

我生成的xml没有缩进，不过不影响使用

报错

TypeError: string indices must be integers

json节点名字错误，有些json的节点是双引号，有些为单引号
注意多层的话为[’’][’’]
中间有空层的加[0]

参考

https://blog.csdn.net/ouyangfushu/article/details/79543575
https://blog.csdn.net/yjl9122/article/details/56842098
https://blog.csdn.net/hehangjiang/article/details/79108232
https://blog.csdn.net/qq_34493665/article/details/84988064
https://www.cnblogs.com/laoniubile/p/6036919.html