为对象检测任务创建tfrecord

我正在使用tensorflow对象检测api创建用于微调任务的数据集 .

我的目录结构是：

培养/

• imgs /

---- img1.jpg

• 安/

---- img1.csv

csv，每个图像一个， label, x, y, w, h

我用这个脚本来保存tfrecord：

import tensorflow as tf
    from os import listdir
    import os
    from os.path import isfile, join
    import csv
    import json

    from object_detection.utils import dataset_util


    flags = tf.app.flags
    flags.DEFINE_string('output_path', '', 'Path to output TFRecord')
    FLAGS = flags.FLAGS

    LABEL_DICT = {}
    counter = 0

    def create_tf_example(example):
      # TODO(user): Populate the following variables from your example.
      height = 404 # Image height
      width = 720 # Image width
      filename = example['path'].encode('utf-8').strip() # Filename of the image. Empty if image is not from file

      with tf.gfile.GFile(example['path'], 'rb') as fid:
        encoded_image_data = fid.read()

      image_format = 'jpeg'.encode('utf-8').strip() # b'jpeg' or b'png'

      xmins = [] # List of normalized left x coordinates in bounding box (1 per box)
      xmaxs = [] # List of normalized right x coordinates in bounding box
                 # (1 per box)
      ymins = [] # List of normalized top y coordinates in bounding box (1 per box)
      ymaxs = [] # List of normalized bottom y coordinates in bounding box
                 # (1 per box)
      classes_text = [] # List of string class name of bounding box (1 per box)
      classes = [] # List of integer class id of bounding box (1 per box)

      for box in example['boxes']:
        #if box['occluded'] is False:
        #print("adding box")
        xmins.append(float(int(box['x']) / width))
        xmaxs.append(float(int(box['w']) + int(box['x']) / width))
        ymins.append(float(int(box['y']) / height))
        ymaxs.append(float(int(box['h']) + int(box['y']) / height))
        classes_text.append(box['label'].encode('utf-8'))
        classes.append(int(LABEL_DICT[box['label']]))


      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_image_data),
          '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 ex_info(img_path, ann_path):
      boxes = []
      head = ['label','x','y','w','h']
      with open(ann_path, 'r') as csvfile:
        annreader = csv.DictReader(csvfile, fieldnames=head)
        for box in annreader:
          boxes.append(box)
          LABEL_DICT[box['label']] = LABEL_DICT.get(box['label'], len(LABEL_DICT) + 1)

      ex = {
        "path" : img_path,
        "boxes" : boxes
      }

      return ex

    def main(_):
      writer = tf.python_io.TFRecordWriter(FLAGS.output_path)

      # TODO(user): Write code to read in your dataset to examples variable
      dataset_dir = "train"
      ann_dir = join(dataset_dir, "ann")
      imgs_dir = join(dataset_dir, "imgs")
      labelDest = "tfTrain/data/labels_map.pbtxt"

      imgs = [join(imgs_dir, f) for f in listdir(imgs_dir) if isfile(join(imgs_dir, f))]
      anns = [join(ann_dir, os.path.basename(im).replace("jpg","csv")) for im in imgs]

      for img,ann in zip(imgs,anns):
        example = ex_info(img,ann)
        #tf_example = create_tf_example(example)
        #writer.write(tf_example.SerializeToString())


      with open(labelDest, 'w', encoding='utf-8') as outL:
        for name,key in LABEL_DICT.items():
          outL.write("item { \n  id: " + str(key) + "\n  name: '" + name + "'\n}\n")


      writer.close()


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

但是当我运行火车脚本时，我收到了这个错误

python train.py --logtostderr --train_dir = . / models / train --pipeline_config_path = faster_rcnn_resnet101_coc o.config警告：tensorflow：来自models / research / object_detection / trainer.py:257:create_global_step（来自tensorflow.contrib.framewo） rk.python.ops.variables）已弃用，将在以后的版本中删除 . 更新说明：请切换到tf.train.create_global_step Traceback（最近一次调用最后一次）：文件“models / research / object_detection / utils / label_map_util.py”，第135行，在load_labelmap中text_format.Merge（label_map_string，label_map）文件“ /home/user/anaconda3/envs/tf/lib/python3.6/site-packages/google/protobuf/text_format.py“，第525行，在Merge descriptor_pool = descriptor_pool中）文件”/ home / user / anaconda3 / envs /在MergeLines中返回解析器.MergeLines（行，消息）文件“/ home / user / anaconda3 / envs / tf / lib /” python3.6 / site-packages / google / protobuf / text_format.py“，第612行，MergeLines中的self._ParseOrMerge（行，消息）文件”/home/user/anaconda3/envs/tf/lib/python3.6/site -packages / google / protobuf / text_format.py“，第627行，在_ParseOrMerge self._MergeField（tokenizer，message）文件”/home/user/anaconda3/envs/tf/lib/python3.6/site-packages/google/ protobuf / text_format.py“，第727行，在_MergeField合并中（到kenizer，message，field）在_MergeMessageField self._MergeField（tokenizer，sub_message）中输入文件“/home/user/anaconda3/envs/tf/lib/python3.6/site-packages/google/protobuf/text_format.py”，第815行）文件“/home/user/anaconda3/envs/tf/lib/python3.6/site-packages/google/protobuf/text_format.py”，第695行，在_MergeField（message_descriptor.full_name，name）中）google.protobuf . text_format.ParseError：23：20：消息类型“object_detection.protos.StringIntLabelMapItem”没有名为“s”的字段 . 在处理上述异常期间，发生了另一个异常：Traceback（最近一次调用last）：
在<module>中的文件“train.py”，第184行
tf.app.run（）
文件“/home/user/anaconda3/envs/tf/lib/python3.6/site-packages/tensorflow/python/platform/app.py”，
第126行，在run _sys.exit（main（argv））文件“train.py”，第180行，在主graph_hook_fn = graph_rewriter_fn中）文件“models / research / object_detection / trainer.py”，第264行，在train train_config中 . prefetch_queue_capacity，data_augmentation_options）文件“models / research / object_detection / trainer.py”，第59行，在create_input_queue tensor_dict = create_tensor_dict_fn（）文件“train.py”，第121行，在get_next dataset_builder.build（config）中 . ）get_next（）文件“models / research / object_detection / builders / dataset_builder.py”，第155行，在构建label_map_proto_file = label_map_proto_file）文件“models / research / object_detection / data_decoders / tf_example_decoder.py”，第245行，在init use_display_name中）文件“models / research / object_detection / utils / label_map_util.py“，第152行，在get_label_map_dict中label_map = load_labelmap（label_map_path）文件”models / research / object_detection / utils / label_map_util.py“，第137行，在load_labelmap中label_map.ParseFromString（label_map_string）TypeError：一个类似字节的对象请问，不是'str'我不明白是什么问题 . 在tfrecord？在labels.pbtxt中？还是在配置文件中？