Question

我使用this script下载并将cifar10数据转换为tfrecord文件...它完成没有问题，我有一个合适的二进制文件。
我然后尝试使用此脚本导入我的文件：

 """Provides data for the Cifar10 dataset.
 The dataset scripts used to create the dataset can be found at:
 tensorflow/models/slim/datasets/download_and_convert_cifar10.py
 """

 from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function

 import os
 import tensorflow as tf

 import dataset_utils

 slim = tf.contrib.slim

 _FILE_PATTERN = 'cifar10_%s.tfrecord'

 SPLITS_TO_SIZES = {'train': 50000, 'test': 10000}

 _NUM_CLASSES = 10

 _ITEMS_TO_DESCRIPTIONS = {
     'image': 'A [32 x 32 x 3] color image.',
     'label': 'A single integer between 0 and 9',
 }


 def get_split(split_name, dataset_dir, file_pattern=None, reader=None):
     """Gets a dataset tuple with instructions for reading cifar10.
   Args:
     split_name: A train/test split name.
     dataset_dir: The base directory of the dataset sources.
     file_pattern: The file pattern to use when matching the dataset sources.
       It is assumed that the pattern contains a '%s' string so that the split
       name can be inserted.
     reader: The TensorFlow reader type.
   Returns:
     A `Dataset` namedtuple.
   Raises:
     ValueError: if `split_name` is not a valid train/test split.
   """
     if split_name not in SPLITS_TO_SIZES:
         raise ValueError('split name %s was not recognized.' % split_name)

     if not file_pattern:
         file_pattern = _FILE_PATTERN
     file_pattern = os.path.join(dataset_dir, file_pattern % split_name)

     # Allowing None in the signature so that dataset_factory can use the default.
     if not reader:
         reader = tf.TFRecordReader

     keys_to_features = {
         'image/encoded':
         tf.FixedLenFeature((), tf.string, default_value=''),
         'image/format':
         tf.FixedLenFeature((), tf.string, default_value='png'),
         'image/class/label':
         tf.FixedLenFeature(
             [], tf.int64, default_value=tf.zeros([], dtype=tf.int64)),
     }

     items_to_handlers = {
         'image': slim.tfexample_decoder.Image(shape=[32, 32, 3]),
         'label': slim.tfexample_decoder.Tensor('image/class/label'),
     }

     decoder = slim.tfexample_decoder.TFExampleDecoder(keys_to_features,
                                                       items_to_handlers)

     labels_to_names = None
     if dataset_utils.has_labels(dataset_dir):
         labels_to_names = dataset_utils.read_label_file(dataset_dir)

     return slim.dataset.Dataset(
         data_sources=file_pattern,
         reader=reader,
         decoder=decoder,
         num_samples=SPLITS_TO_SIZES[split_name],
         items_to_descriptions=_ITEMS_TO_DESCRIPTIONS,
         num_classes=_NUM_CLASSES,
         labels_to_names=labels_to_names)


 data = get_split('test', '/path/to/cifar10_dir')

 sess = tf.Session(config=tf.ConfigProto(
     allow_soft_placement=True, log_device_placement=False))

 coord = tf.train.Coordinator()
 threads = tf.train.start_queue_runners(coord=coord, sess=sess)

 data_provider = slim.dataset_data_provider.DatasetDataProvider(
     data, num_readers=10, shuffle=True)
 img, lbl = data_provider.get(['image', 'label'])

它也没有给我任何错误，但是当我尝试时：

  sess.run(img)

这个过程永远不会停止。 tensorflow正在启动会话但是没有读取文件，它不会释放提示并且基本上什么都不做。我真的很生气，因为我不知道从哪里开始。有人有任何建议吗？

Answer 1

您应该在queue runners之后开始DatasetDataProvider，这也是一个队列。因此，请将其更改为以下顺序：

data_provider = slim.dataset_data_provider.DatasetDataProvider(
data, num_readers=10, shuffle=True)
img, lbl = data_provider.get(['image', 'label'])

sess = tf.Session(config=tf.ConfigProto(allow_soft_placement=True, log_device_placement=False))

coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord, sess=sess)

读取tfrecord文件永远不会完成

1 个答案: