第三十一节，使用谷歌Object Detection API进行目标检测

# Copyright 2017 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================

r"""Convert raw PASCAL dataset to TFRecord for object_detection.

Example usage:
    ./create_pascal_tf_record --data_dir=/home/user/VOCdevkit         --year=VOC2012         --output_path=/home/user/pascal.record
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import hashlib
import io
import logging
import os

from lxml import etree
import PIL.Image
import tensorflow as tf

from object_detection.utils import dataset_util
from object_detection.utils import label_map_util

import sys


#配置logging
logging.basicConfig(format=‘%(asctime)s %(levelname)s %(message)s‘,
                    level=logging.INFO,
                    stream=sys.stdout)


#命令行参数  主要包括数据集根目录，数据类型，输出tf文件路径等
flags = tf.app.flags
flags.DEFINE_string(‘data_dir‘, ‘‘, ‘Root directory to raw PASCAL VOC dataset.‘)
flags.DEFINE_string(‘set‘, ‘train‘, ‘Convert training set, validation set or ‘
                    ‘merged set.‘)
flags.DEFINE_string(‘annotations_dir‘, ‘Annotations‘,
                    ‘(Relative) path to annotations directory.‘)
flags.DEFINE_string(‘year‘, ‘VOC2007‘, ‘Desired challenge year.‘)
flags.DEFINE_string(‘output_path‘, ‘‘, ‘Path to output TFRecord‘)
flags.DEFINE_string(‘label_map_path‘, ‘voc/pascal_label_map.pbtxt‘,
                    ‘Path to label map proto‘)
flags.DEFINE_boolean(‘ignore_difficult_instances‘, False, ‘Whether to ignore ‘
                     ‘difficult instances‘)
FLAGS = flags.FLAGS

SETS = [‘train‘, ‘val‘, ‘trainval‘, ‘test‘]
YEARS = [‘VOC2007‘, ‘VOC2012‘, ‘merged‘]


def dict_to_tf_example(data,
                       dataset_directory,
                       label_map_dict,
                       ignore_difficult_instances=False,
                       image_subdirectory=‘JPEGImages‘):
  """Convert XML derived dict to tf.Example proto.

  Notice that this function normalizes the bounding box coordinates provided
  by the raw data.

  Args:
    data: dict holding PASCAL XML fields for a single image (obtained by
      running dataset_util.recursive_parse_xml_to_dict)
    dataset_directory: Path to root directory holding PASCAL dataset
    label_map_dict: A map from string label names to integers ids.
    ignore_difficult_instances: Whether to skip difficult instances in the
      dataset  (default: False).
    image_subdirectory: String specifying subdirectory within the
      PASCAL dataset directory holding the actual image data.

  Returns:
    example: The converted tf.Example.

  Raises:
    ValueError: if the image pointed to by data[‘filename‘] is not a valid JPEG
  """
  #获取相对图片路径
  img_path = os.path.join(data[‘folder‘], image_subdirectory, data[‘filename‘])
  #获取图片绝对路径
  full_path = os.path.join(dataset_directory, img_path)
  #读取图片 
  with tf.gfile.GFile(full_path, ‘rb‘) as fid:
    encoded_jpg = fid.read()
  encoded_jpg_io = io.BytesIO(encoded_jpg)
  image = PIL.Image.open(encoded_jpg_io)
  if image.format != ‘JPEG‘:
    raise ValueError(‘Image format not JPEG‘)
  key = hashlib.sha256(encoded_jpg).hexdigest()

  #获取图片的宽和高
  width = int(data[‘size‘][‘width‘])
  height = int(data[‘size‘][‘height‘])

  xmin = []
  ymin = []
  xmax = []
  ymax = []
  classes = []
  classes_text = []
  truncated = []
  poses = []
  difficult_obj = []
  for obj in data[‘object‘]:
    #是否为难以辨识的物体， 主要指要结体背景才能判断出类别的物体。虽有标注， 但一般忽略这类物体 跳过难以识别的？
    difficult = bool(int(obj[‘difficult‘]))
    if ignore_difficult_instances and difficult:
      continue

    difficult_obj.append(int(difficult))

    #bounding box 计算目标边界 归一化到[0,1]之间  左上角坐标，右下角坐标
    xmin.append(float(obj[‘bndbox‘][‘xmin‘]) / width)
    ymin.append(float(obj[‘bndbox‘][‘ymin‘]) / height)
    xmax.append(float(obj[‘bndbox‘][‘xmax‘]) / width)
    ymax.append(float(obj[‘bndbox‘][‘ymax‘]) / height)
    
    #类别名
    classes_text.append(obj[‘name‘].encode(‘utf8‘))
    #获取该类别对应的标签
    classes.append(label_map_dict[obj[‘name‘]])
    #物体是否被部分遮挡 
    truncated.append(int(obj[‘truncated‘]))
    #物体的姿势
    poses.append(obj[‘pose‘].encode(‘utf8‘))

  #tf文件一条记录格式
  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(
          data[‘filename‘].encode(‘utf8‘)),
      ‘image/source_id‘: dataset_util.bytes_feature(
          data[‘filename‘].encode(‘utf8‘)),
      ‘image/key/sha256‘: dataset_util.bytes_feature(key.encode(‘utf8‘)),
      ‘image/encoded‘: dataset_util.bytes_feature(encoded_jpg),
      ‘image/format‘: dataset_util.bytes_feature(‘jpeg‘.encode(‘utf8‘)),
      ‘image/object/bbox/xmin‘: dataset_util.float_list_feature(xmin),
      ‘image/object/bbox/xmax‘: dataset_util.float_list_feature(xmax),
      ‘image/object/bbox/ymin‘: dataset_util.float_list_feature(ymin),
      ‘image/object/bbox/ymax‘: dataset_util.float_list_feature(ymax),
      ‘image/object/class/text‘: dataset_util.bytes_list_feature(classes_text),
      ‘image/object/class/label‘: dataset_util.int64_list_feature(classes),
      ‘image/object/difficult‘: dataset_util.int64_list_feature(difficult_obj),
      ‘image/object/truncated‘: dataset_util.int64_list_feature(truncated),
      ‘image/object/view‘: dataset_util.bytes_list_feature(poses),
  }))
  return example


def main(_):
  ‘‘‘
  主要是通过读取VOCdevkit\VOC2012\Annotations下的xml文件
  然后获取对应的图片文件的路径，图片大小，文件名，边界框、以及图片数据等信息写入rfrecord文件
  ‘‘‘
  if FLAGS.set not in SETS:
    raise ValueError(‘set must be in : {}‘.format(SETS))
  if FLAGS.year not in YEARS:
    raise ValueError(‘year must be in : {}‘.format(YEARS))

  data_dir = FLAGS.data_dir
  years = [‘VOC2007‘, ‘VOC2012‘]
  if FLAGS.year != ‘merged‘:
    years = [FLAGS.year]
  
  #创建对象，用于向记录文件写入记录
  writer = tf.python_io.TFRecordWriter(FLAGS.output_path)

  #获取类别名->index的映射 dict类型
  label_map_dict = label_map_util.get_label_map_dict(FLAGS.label_map_path)

  for year in years:
    logging.info(‘Reading from PASCAL %s dataset.‘, year)
    #获取aeroplane_train.txt文件的全路径  改文件保存部分文件名(一共5717/5823个文件，各类图片都有)
    examples_path = os.path.join(data_dir, year, ‘ImageSets‘, ‘Main‘,
                                 ‘aeroplane_‘ + FLAGS.set + ‘.txt‘)
    #获取所有图片标注xml文件的路径
    annotations_dir = os.path.join(data_dir, year, FLAGS.annotations_dir)
    
    #list 存放文件名  
    examples_list = dataset_util.read_examples_list(examples_path)
    
    #遍历annotations_dir目录下，examples_list中指定的xml文件
    for idx, example in enumerate(examples_list):
      if idx % 100 == 0:
        logging.info(‘On image %d of %d‘, idx, len(examples_list))
      path = os.path.join(annotations_dir, example + ‘.xml‘)
      with tf.gfile.GFile(path, ‘r‘) as fid:
        xml_str = fid.read()
      xml = etree.fromstring(xml_str)
      #获取annotation节点的内容
      data = dataset_util.recursive_parse_xml_to_dict(xml)[‘annotation‘]

      #把数据整理成tfrecord需要的数据结构
      tf_example = dict_to_tf_example(data, FLAGS.data_dir, label_map_dict,
                                      FLAGS.ignore_difficult_instances)
      
      #向tf文件写入一条记录
      writer.write(tf_example.SerializeToString())

  writer.close()


if __name__ == ‘__main__‘:
  tf.app.run()