import os

import glob

import pandas as pd

import xml.etree.ElementTree as ET

DIR_NAME = 'out_xml'

def xml_to_csv(path):

    xml_list = []

    for xml_file in glob.glob(path + '/*.xml'):#glob.glob会返回制定路径下所有符合格式的文件列表，我们这里对列表遍历

        tree = ET.parse(xml_file)#创建解析树

        root = tree.getroot()#得到解析树的根元素

        for member in root.findall('object'):#对xml里面的object遍历

            value = (root.find('filename').text,

                     int(root.find('size')[0].text),

                     int(root.find('size')[1].text),

                     member[0].text,

                     int(member[4][0].text),

                     int(member[4][1].text),

                     int(member[4][2].text),

                     int(member[4][3].text)

                     )

            xml_list.append(value)#拿到数据

    column_name = ['filename', 'width', 'height', 'class', 'xmin', 'ymin', 'xmax', 'ymax']#列名

    xml_df = pd.DataFrame(xml_list, columns=column_name)#生成csv

    return xml_df

def main():

    image_path = os.path.join(os.getcwd(), DIR_NAME)#将DIR_NAME里的xml文件全部读入

    xml_df = xml_to_csv(image_path)#得到csv

    xml_df.to_csv('raccoon_labels.csv', index=None)#写入文件

    print('执行完毕')

main()

"""

用法:

  # 在 tensorflow/models目录下，打开命令行

  # 生成训练集的tfrecord文件，执行以下命令:

  python generate_tfrecord.py --csv_input=train_labels.csv  --output_path=train.record

  # 生成测试集的tfrecord文件，执行以下命令:

  python generate_tfrecord.py --csv_input=test_labels.csv  --output_path=test.record

  #记得把里面文件名改为对应的文件名，

"""

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', '', 'Path to the CSV input')

flags.DEFINE_string('output_path', '', 'Path to output TFRecord')

FLAGS = flags.FLAGS

# labelmap，一个labelname对应一个value

def class_text_to_int(row_label):

    if row_label == 'red':

        return 1

    elif row_label == 'blue':

        return 2

    else:

        None

def split(df, group):

    data = namedtuple('data', ['filename', 'object'])#命名元组，元素分别为filename和object

    gb = df.groupby(group)#得到group划分后的list

    return [data(filename, gb.get_group(x)) for filename, x in zip(gb.groups.keys(), gb.groups)]#zip生成一一对应关系，对每个group对应的块生成data格式的元组，并最终组合成list返回

def create_tf_example(group, path):

    with tf.gfile.GFile(os.path.join(path, '{}'.format(group.filename)), 'rb') as fid:#以二进制读的方式打开file

        encoded_jpg = fid.read()#读入filename对应的图片数据

    encoded_jpg_io = io.BytesIO(encoded_jpg)#转化为二进制数据

    image = Image.open(encoded_jpg_io)

    width, height = image.size

    filename = group.filename.encode('utf8')#utf-8编码存储

    image_format = b'jpg'

    xmins = []

    xmaxs = []

    ymins = []

    ymaxs = []

    classes_text = []

    classes = []

    for index, row in group.object.iterrows():#对每个Object操作

        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),

    }))#生成example协议块

    return tf_example

def main():

    writer = tf.python_io.TFRecordWriter(FLAGS.output_path)#创建tfrecord存储器

    path = os.path.join(os.getcwd(), 'images')#配置文件所在的路径

    examples = pd.read_csv(FLAGS.csv_input)#输入的csv文件所在路径读入

    grouped = split(examples, 'filename')#根据filename进行划分，得到list

    for group in grouped:

        tf_example = create_tf_example(group, path)

        writer.write(tf_example.SerializeToString())#压缩example中的map为二进制并写入tfrecord

    writer.close()

    output_path = os.path.join(os.getcwd(), FLAGS.output_path)

    print('Successfully created the TFRecords: {}'.format(output_path))

main()

touch car_label_map.pbtxt

gedit car_label_map.pbtxt

item {

  id: 1

  name: 'red'

}

item {

  id: 2

  name: 'blue'

}