为目标检测任务创建tf记录

Question

我正在使用tensorflow对象检测api为微调任务创建数据集。

我的目录结构是：

训练/

--imgs/

----img1。jpg

安

----img1。csv

其中，每幅图像一个csv是标签，x、y、w、h

我使用此脚本保存TFR记录：

    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，我得到了这个错误

Pythontrain.py--logtostderr-train_dir=。/模型/训练-pipeline_config_path=faster_rcnn_resnet101_coco.config
警告：tensorflow：来自模型/研究/object_detection/trainer.py:257：create_global_step（来自tensorflow.contrib.framework.python.ops.variables）不建议使用在未来版本中删除。更新说明：请切换到tf.train.create_global_stepTraceback（最近一次调用最后一次）：文件“模型/研究/object_detection/utils/label_map_util.py”，第135行，load_labelmaptext_format。合并（label_map_string，label_map）File"/home/user/anaconda3/envs/tf/lib/python3.6/site-包/谷歌/原型包/text_format.py"，第525行，在合并descriptor_pool=descriptor_pool）File"/home/user/anaconda3/envs/tf/lib/python3.6/site-包/谷歌/原型包/text_format.py"，行579，在MergeLines返回解析器中。MergeLines（行，消息）File"/home/user/anaconda3/envs/tf/lib/python3.6/site-包/谷歌/原型/text_format.py"，第612行，在MergeLines自我。_ParseOrMerge（行，html" target="_blank">消息）文件"/home/user/anaconda3/envs/tf/lib/python3.6/site-包/google/原型/text_format.py"，第627行，_ParseOrMerge。_MergeField（令牌，消息）File"/home/user/anaconda3/envs/tf/lib/python3.6/site-包/谷歌/原型包/text_format.py"，第727行，在_MergeField合并（令牌，消息，字段）File"/home/user/anaconda3/envs/tf/lib/python3.6/site-包/谷歌/原型包/text_format.py》，第815行，_MergeMessageField自我。_MergeField（令牌，sub_message）File"/home/user/anaconda3/envs/tf/lib/python3.6/site-包/谷歌/原型/text_format.py"，第695行，_MergeField（message_descriptor.full_name，名称）google.protobuf.text_format。消息类型"object_detection.protos.StringIntLabelMapItem"没有名为"s"的字段。

在处理上述异常时，发生了另一个异常：

    Traceback (most recent call last):
      File "train.py", line 184, in <module>
        tf.app.run()
      File "/home/user/anaconda3/envs/tf/lib/python3.6/site-packages/tensorflow/python/platform/app.py",

第126行，运行系统中。退出（主（argv））文件“train.py”，第180行，在train train配置中的主图形\u hook\u fn=图形\u rewriter\u fn）文件“models/research/object\u detection/trainer.py”，第264行。预回迁队列容量、数据扩充选项）文件“models/research/object\u detection/trainer.py”，第59行，在get\u next dataset\u builder中的创建队列张量dict=create\u张量dict\u fn（）文件“train.py”，第121行。构建（配置）。get_next（）文件“models/research/object_detection/builders/dataset_builder.py”，第155行，内置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）文件“models/research/object_detection/util/label_-map_-util.py”第152行，在load_labelmap标签映射的第137行，获取标签映射=加载labelmap（标签映射路径）文件“models/research/object_detection/utils/label_map_util.py”中。ParseFromString（label\u map\u string）类型错误：需要类似字节的对象，而不是“str”

我不明白有什么问题。在电视唱片里？在labels.pbtxt?或配置文件中？

Answer 1

好的，我刚刚解决了tensorflow的调试问题。最后，我的标签虽然是utf-8格式的，但由于一些奇怪的字符，比如