如何从张量中提取值呢?

我需要从tensorflow shard记录中获取数据集中图像的文件名，以便我可以使用这些名称来满足我的神经网络的其他功能。由于随机化的原因，我无法在一段时间内形成一个列表。我需要这些名字在它们被传送到网络之前。 我使用的是运行在tensorflow v1.14上的inception v3。 每个序列化的例子都是用这段代码解析的，我也编辑了这段代码来返回文件名:

def parse_example_proto(example_serialized):
  """Parses an Example proto containing a training example of an image.

  The output of the build_image_data.py image preprocessing script is a dataset
  containing serialized Example protocol buffers. Each Example proto contains
  the following fields:

    image/height: 462
    image/width: 581
    image/colorspace: 'RGB'
    image/channels: 3
    image/class/label: 615
    image/class/synset: 'n03623198'
    image/class/text: 'knee pad'
    image/object/bbox/xmin: 0.1
    image/object/bbox/xmax: 0.9
    image/object/bbox/ymin: 0.2
    image/object/bbox/ymax: 0.6
    image/object/bbox/label: 615
    image/format: 'JPEG'
    image/filename: 'ILSVRC2012_val_00041207.JPEG'
    image/encoded: <JPEG encoded string>

  Args:
    example_serialized: scalar Tensor tf.string containing a serialized
      Example protocol buffer.

  Returns:
    image_buffer: Tensor tf.string containing the contents of a JPEG file.
    label: Tensor tf.int32 containing the label.
    bbox: 3-D float Tensor of bounding boxes arranged [1, num_boxes, coords]
      where each coordinate is [0, 1) and the coordinates are arranged as
      [ymin, xmin, ymax, xmax].
    text: Tensor tf.string containing the human-readable label.
  """
  # Dense features in Example proto.
  if FLAGS.mode == '0_softmax':
    feature_map = {
        'image/encoded': tf.FixedLenFeature([], dtype=tf.string,
                                            default_value=''),
        'image/class/label': tf.FixedLenFeature([1], dtype=tf.int64,
                                                default_value=-1),
        'image/class/text': tf.FixedLenFeature([], dtype=tf.string,
                                               default_value=''),
        'image/filename': tf.FixedLenFeature([], dtype=tf.string,
                                               default_value=''),
    }
  elif FLAGS.mode == '1_sigmoid':
    Vdefault = [0]
    for kk in range(FLAGS.ClassNumber):
      Vdefault.append(0)
    feature_map = {
        'image/encoded': tf.FixedLenFeature([], dtype=tf.string,
                                            default_value=''),
        'image/class/label': tf.FixedLenFeature([1], dtype=tf.int64,
                                                default_value=-1),
        'image/class/text': tf.FixedLenFeature([], dtype=tf.string,
                                               default_value=''),
        'image/filename': tf.FixedLenFeature([], dtype=tf.string,
                                               default_value=''),
    }
  else:
    raise ValueError("You must set the mode option (to 0_softmax or 1_sigmoid for example)")

  sparse_float32 = tf.VarLenFeature(dtype=tf.float32)
  # Sparse features in Example proto.
  feature_map.update(
      {k: sparse_float32 for k in ['image/object/bbox/xmin',
                                   'image/object/bbox/ymin',
                                   'image/object/bbox/xmax',
                                   'image/object/bbox/ymax']})

  features = tf.parse_single_example(example_serialized, feature_map)
  label = tf.cast(features['image/class/label'], dtype=tf.int32)

  xmin = tf.expand_dims(features['image/object/bbox/xmin'].values, 0)
  ymin = tf.expand_dims(features['image/object/bbox/ymin'].values, 0)
  xmax = tf.expand_dims(features['image/object/bbox/xmax'].values, 0)
  ymax = tf.expand_dims(features['image/object/bbox/ymax'].values, 0)

  # Note that we impose an ordering of (y, x) just to make life difficult.
  bbox = tf.concat(axis=0, values=[ymin, xmin, ymax, xmax])

  # Force the variable number of bounding boxes into the shape
  # [1, num_boxes, coords].
  bbox = tf.expand_dims(bbox, 0)
  bbox = tf.transpose(bbox, [0, 2, 1])

  return features['image/encoded'], label, bbox, features['image/filename']

此函数在代码段中调用。inceptionv3的代码库中有很多并行处理代码，我不太理解，但我想我应该做一下。但是，我不知道如何解释tf.train.batch_join的输出。查看vscode调试器中的文件名输出，它是一个<tf。张量'batch_processing/batch_join:2' shape=(32，) dtype=string>。

for thread_id in range(num_preprocess_threads):
      # Parse a serialized Example proto to extract the image and metadata.
      image_buffer, label_index, bbox, filename = parse_example_proto(
          example_serialized)
      image = image_preprocessing(image_buffer, bbox, train, thread_id)
      images_and_labels.append([image, label_index, filename])

    images, label_index_batch, filenames = tf.train.batch_join(
        images_and_labels,
        batch_size=batch_size,
        capacity=3 * num_preprocess_threads * batch_size)

当这返回，我想看看什么值(文件名)在文件名。它看起来应该是一个列表，我应该能够索引到它，但我似乎不能索引到它，更不用说得到每个文件名。 当我使用parsed = _parse_function(raw_record)直接读取记录时，就可以获得文件名 ， fname =解析['image/filename'].numpy()，但这里不起作用。我真的是在飞在我的裤子缝与这个哈哈。 问题来源StackOverflow 地址：/questions/59383969/how-do-i-extract-the-values-from-these-tensors-in-tensorflow