• xml -> csv


    https://www.cnblogs.com/pacino12134/p/11291398.html

    1、xml

    使用labelmg工具对图片进行标注得到xml格式文件,以图片为例介绍内容信息:

    对上面的图片进行标注后,得到xml文件:

    其内容分类两部分:

    1. 第一个黑色方框,图像的整体部分,包括图像的名称、位置、长宽高等等;
    2. 第二个黑色方框,标注框信息,每个红色框就是一个object标签(表示一个标注框)的信息,包括目标类别名称、位置信息等

    xml内的信息是由一个个对象组成,标签之间存在层级关系,例如annotation为最上层的标签,就是这个xml所在的文件夹,其他标签为字标签。

    2、xml -> csv

    字符(逗号)分割值。

    每个object标签代表一个标注框,都会在csv文件中生成一条数据,每天数据的属性为:图片文件名、宽度、高度、类别、框的左上角x坐标、框的左上角y、框的右上角x、框的右上角y。

    xml转csv的代码如下:

    复制代码
    # -*- coding: utf-8 -*-
    """
    将文件夹内所有XML文件的信息记录到CSV文件中
    """
    
    import os  
    import glob  
    import pandas as pd  
    import xml.etree.ElementTree as ET  
    
      
    def xml_to_csv(path):          #path:annotations的文件夹路径
        xml_list = []  
        for xml_file in glob.glob(path + '/*.xml'):  #对path目录下的每一个xml文件
            tree = ET.parse(xml_file)  #获得xml对应的解析树
            root = tree.getroot()  #获得根标签annotations
            # print(root)  
            print(root.find('filename').text)  
            for member in root.findall('object'):  #对每一个object标签(框)
                value = (root.find('filename').text,  #在根标签下查找filename标签(图片文件名字),获得文本信息
                         int(root.find('size')[0].text),  #在根标签下找size标签,并获得第0个字标签(width)的文本信息,转化为int
                         int(root.find('size')[1].text),   #在根标签下找size标签,并获得di1个字标签(height)的文本信息,转化为int
                         member[0].text,  #获得object标签的第0个字标签name的文信息
                         int(member[4][0].text),  #获得object的第四个子标签bndbox,获得bndbox的第0个字标签(xmin)的文本信息,转化为int
                         int(float(member[4][1].text)),  #获得object的第四个子标签bndbox,获得bndbox的第1个字标签(ymin)的文本信息,转化为int
                         int(member[4][2].text),  #获得object的第四个子标签bndbox,获得bndbox的第2个字标签(xmax)的文本信息,转化为int
                         int(member[4][3].text)  #获得object的第四个子标签bndbox,获得bndbox的第3个字标签(ymax)的文本信息,转化为int
                         )  
                xml_list.append(value)  
        column_name = ['filename', 'width', 'height', 'class', 'xmin', 'ymin', 'xmax', 'ymax']  
        xml_df = pd.DataFrame(xml_list, columns=column_name)  
        return xml_df  
      
    def main():  
        for directory in ['train','test','validation']:  #对应train和test文件夹
            #对应根目录下的/images中的train和test文件夹,本脚本要放在voc文件夹下,和annotations是同级的,否则修改getcwd函数
            xml_path = os.path.join(os.getcwd(), 'annotations/{}'.format(directory))   
            xml_df = xml_to_csv(xml_path)  
            xml_df.to_csv('data/whsyxt_{}_labels.csv'.format(directory), index=None)  #xml转化为对应的csv保存
            print('Successfully converted xml to csv.')  
    
    main()
    复制代码

    对应的xml文件如下图:

    最后得到两个文件:

    文件打开类似于这样的:

    其中的filename只是图片文件的名字,不包括路径。

    3、xml转换为tfrecord

     每个图片会生成一个xml文件,批量的将xml文件转化成tfrecord格式。

    4、csv转换成tfrecord

    将多个xml文件写入到一个csv文件中去,每一行是一个xml文件的信息,接下来直接将这个csv文件转换成tfrecord格式就可以了,很方便快。

    由于图像和标签值不在一起,所以要将整张图片信息和csv文件合并起来,整合成为tfrecord格式写入到本地中,用于训练。

    代码来自tensorflow/object_dection/models-master/research/object_detection/test_generate_tfrecord.py:

    复制代码
    Usage:
      # From tensorflow/models/
      # Create train data:
      python generate_tfrecord.py --csv_input=data/train_labels.csv  --output_path=data/train.record
    
      # Create test data:
      python generate_tfrecord.py --csv_input=data/test_labels.csv  --output_path=data/test.record
    """
    from __future__ import division
    from __future__ import print_function
    from __future__ import absolute_import
    
    import os
    import io
    import pandas as pd
    import tensorflow as tf
    
    from PIL import Image
    from object_detection.utils import dataset_util
    from collections import namedtuple, OrderedDict
    
    flags = tf.app.flags
    """
        DEFINE_string定义了个命令行参数
    
        flage_name:csv_input,参数名字
        defalut_name:默认值 ,这里的默认值是data/test_labels.csv
        docstring:对该参数的说明
    
        可以使用tf.app.flags.FLAGS取出该参数的值:
        FLAGS = tf.app.flags.FLAGS
        print(FLAGS.csv_input),输出的就是data/test_labels.csv
    
    """
    flags.DEFINE_string('csv_input', 'data/test_labels.csv', 'Path to the CSV input')
    flags.DEFINE_string('output_path', 'data/test.record', 'Path to output TFRecord')
    FLAGS = flags.FLAGS
    
    
    # TO-DO replace this with label map
    # 修改成你自己的标签
    def class_text_to_int(row_label):
        if row_label == 'face':
            return 0
        elif row_label == 'cat':
            return 1
        #............
            
    
    def split(df, group):
        """namedtuple工厂函数,返回一个名为`data`的类,并赋值给名为data的变量
        定义:Point = namedtuple('Point', ['x', 'y']) 
        创建对象:p = Point(11, y=22) 
                    p[0] + p[1] 输出 33
        解包:x, y = p
             x,y 输出:(11, 22)
        访问:p.x + p.y  输出 33
            
        """
        data = namedtuple('data', ['filename', 'object'])
        gb = df.groupby(group)
        return [data(filename, gb.get_group(x)) for filename, x in zip(gb.groups.keys(), gb.groups)]
    
    #读取每张图片,得到每张图片的信息,将每张图片信息和图片里的object标注框信息(在csv里)合并在一起
    #group
    #path:iamge目录
    def create_tf_example(group, path):
        #image目录 + image的名字 = image的绝对路径路径
        with tf.gfile.GFile(os.path.join(path, '{}'.format(group.filename)), 'rb') as fid:
            encoded_jpg = fid.read()
        encoded_jpg_io = io.BytesIO(encoded_jpg)
        image = Image.open(encoded_jpg_io)
        width, height = image.size
    
        filename = group.filename.encode('utf8')
        image_format = b'jpg'
        xmins = []
        xmaxs = []
        ymins = []
        ymaxs = []
        classes_text = []
        classes = []
    
        for index, row in group.object.iterrows():
            xmins.append(row['xmin'] / width)
            xmaxs.append(row['xmax'] / width)
            ymins.append(row['ymin'] / height)
            ymaxs.append(row['ymax'] / height)
            classes_text.append(row['class'].encode('utf8'))
            classes.append(class_text_to_int(row['class']))
        #图像所有信息encoded_jpg和object信息整合一起
        tf_example = tf.train.Example(features=tf.train.Features(feature={
            'image/height': dataset_util.int64_feature(height),
            'image/width': dataset_util.int64_feature(width),
            'image/filename': dataset_util.bytes_feature(filename),
            'image/source_id': dataset_util.bytes_feature(filename),
            'image/encoded': dataset_util.bytes_feature(encoded_jpg),
            'image/format': dataset_util.bytes_feature(image_format),
            'image/object/bbox/xmin': dataset_util.float_list_feature(xmins),
            'image/object/bbox/xmax': dataset_util.float_list_feature(xmaxs),
            'image/object/bbox/ymin': dataset_util.float_list_feature(ymins),
            'image/object/bbox/ymax': dataset_util.float_list_feature(ymaxs),
            'image/object/class/text': dataset_util.bytes_list_feature(classes_text),
            'image/object/class/label': dataset_util.int64_list_feature(classes),
        }))
        return tf_example
    
    
    def main(_):
        writer = tf.python_io.TFRecordWriter(FLAGS.output_path)
        path = os.path.join(os.getcwd(), 'images/test')    #一个csv文件最后生成一个tfrecord文件
        examples = pd.read_csv(FLAGS.csv_input)//读csv文件内容,返回pandas对象矩阵
            """
                 filename  width  height   class  xmin  ymin  xmax  ymax
            0  000001.jpg    353     500     dog    43   233   205   362
            1  000001.jpg    353     500  person   117    12   296   226
            2  000002.jpg    335     500   train   122   188   220   299
            
            """
        grouped = split(examples, 'filename')
            """
            [
            data(filename='000002.jpg', object=     filename  width  height  class  xmin  ymin  xmax  ymax
                    2  000002.jpg    335     500  train   122   188   220   299), 
            #两个1.jpg是因为这张图片里面有两个object        
            data(filename='000001.jpg', object=     filename  width  height   class  xmin  ymin  xmax  ymax
                    0  000001.jpg    353     500     dog    43   233   205   362
                    1  000001.jpg    353     500  person   117    12   296   226)
            ]
            
            """
        for group in grouped:
            tf_example = create_tf_example(group, path)//将每个图片的标注信息和图像信息结合在一起
            writer.write(tf_example.SerializeToString())
    
        writer.close()
        output_path = os.path.join(os.getcwd(), FLAGS.output_path)
        print('Successfully created the TFRecords: {}'.format(output_path))
    
    
    if __name__ == '__main__':
        tf.app.run()
    复制代码

    同理还有train_generate_tfrecord.py:

    复制代码
    """
    Usage:
      # From tensorflow/models/
      # Create train data:
      python generate_tfrecord.py --csv_input=data/train_labels.csv  --output_path=data/train.record
    
      # Create test data:
      python generate_tfrecord.py --csv_input=data/test_labels.csv  --output_path=data/test.record
    """
    from __future__ import division
    from __future__ import print_function
    from __future__ import absolute_import
    
    import os
    import io
    import pandas as pd
    import tensorflow as tf
    
    from PIL import Image
    from object_detection.utils import dataset_util
    from collections import namedtuple, OrderedDict
    
    flags = tf.app.flags
    flags.DEFINE_string('csv_input', 'data/train_labels.csv', 'Path to the CSV input')
    flags.DEFINE_string('output_path', 'data/train.record', 'Path to output TFRecord')
    FLAGS = flags.FLAGS
    
    
    # TO-DO replace this with label map
    def class_text_to_int(row_label):
        if row_label == 'face':
            return 1
        else:
            0
            
    
    def split(df, group):
        data = namedtuple('data', ['filename', 'object'])
        gb = df.groupby(group)
        return [data(filename, gb.get_group(x)) for filename, x in zip(gb.groups.keys(), gb.groups)]
    
    
    def create_tf_example(group, path):
        with tf.gfile.GFile(os.path.join(path, '{}'.format(group.filename)), 'rb') as fid:
            encoded_jpg = fid.read()
        encoded_jpg_io = io.BytesIO(encoded_jpg)
        image = Image.open(encoded_jpg_io)
        width, height = image.size
    
        filename = group.filename.encode('utf8')
        image_format = b'jpg'
        xmins = []
        xmaxs = []
        ymins = []
        ymaxs = []
        classes_text = []
        classes = []
    
        for index, row in group.object.iterrows():
            xmins.append(row['xmin'] / width)
            xmaxs.append(row['xmax'] / width)
            ymins.append(row['ymin'] / height)
            ymaxs.append(row['ymax'] / height)
            classes_text.append(row['class'].encode('utf8'))
            classes.append(class_text_to_int(row['class']))
    
        tf_example = tf.train.Example(features=tf.train.Features(feature={
            'image/height': dataset_util.int64_feature(height),
            'image/width': dataset_util.int64_feature(width),
            'image/filename': dataset_util.bytes_feature(filename),
            'image/source_id': dataset_util.bytes_feature(filename),
            'image/encoded': dataset_util.bytes_feature(encoded_jpg),
            'image/format': dataset_util.bytes_feature(image_format),
            'image/object/bbox/xmin': dataset_util.float_list_feature(xmins),
            'image/object/bbox/xmax': dataset_util.float_list_feature(xmaxs),
            'image/object/bbox/ymin': dataset_util.float_list_feature(ymins),
            'image/object/bbox/ymax': dataset_util.float_list_feature(ymaxs),
            'image/object/class/text': dataset_util.bytes_list_feature(classes_text),
            'image/object/class/label': dataset_util.int64_list_feature(classes),
        }))
        return tf_example
    
    
    def main(_):
        writer = tf.python_io.TFRecordWriter(FLAGS.output_path)
        path = os.path.join(os.getcwd(), 'images/train')
        examples = pd.read_csv(FLAGS.csv_input)
        grouped = split(examples, 'filename')
        for group in grouped:
            tf_example = create_tf_example(group, path)
            writer.write(tf_example.SerializeToString())
    
        writer.close()
        output_path = os.path.join(os.getcwd(), FLAGS.output_path)
        print('Successfully created the TFRecords: {}'.format(output_path))
    
    
    if __name__ == '__main__':
        tf.app.run()
    复制代码
  • 相关阅读:
    开源数学库
    ZendFramework综述
    MySQL临时表
    GMP for PHP
    ubuntu的LAMP环境搭建
    linux与windows区别
    js对象与打印对象
    MySQL 多库操作
    ubuntu文件系统综述
    波形声音整理资料(for Project1)
  • 原文地址:https://www.cnblogs.com/shuimuqingyang/p/14211176.html
Copyright © 2020-2023  润新知