在这种情况下有可能提取这些张量的值吗

我正在训练一个使用tensorflow碎片作为训练输入的神经网络。我需要在向网络显示图像之前提取图像的文件名，因为我需要将模型的输入与与该文件相关的其他数据同步。因此，我需要通过随机化和多线程处理的图像推动相关的文件名。问题是我不知道如何维护模型的功能，同时从持有它值的张量中提取文件名。 如果我尝试文件名[I].eval()，我得到一个错误，说没有注册默认会话。当我尝试

sess = tf.Session()
thefile = fname_splits[i]
sess.run(thefile.eval(session=sess))

我的程序锁定和停止。 当我简单地打印(fname[I])输出是 张量("split_2:0"， shape=(50，)， dtype=string, device=/device:CPU:0) 下面是我需要获取名称的代码片段 会议概述在!!我需要文件名在哪里

def train(dataset):
  """Train on dataset for a number of steps."""
  with tf.Graph().as_default(), tf.device('/cpu:0'):
    # Create a variable to count the number of train() calls. This equals the
    # number of batches processed * FLAGS.num_gpus.
    global_step = tf.get_variable(
        'global_step', [],
        initializer=tf.constant_initializer(0), trainable=False)

    # Calculate the learning rate schedule.
    num_batches_per_epoch = (dataset.num_examples_per_epoch() /
                             FLAGS.batch_size)
    decay_steps = int(num_batches_per_epoch * FLAGS.num_epochs_per_decay)

    # Decay the learning rate exponentially based on the number of steps.
    lr = tf.train.exponential_decay(FLAGS.initial_learning_rate,
                                    global_step,
                                    decay_steps,
                                    FLAGS.learning_rate_decay_factor,
                                    staircase=True)

    # Create an optimizer that performs gradient descent.
    opt = tf.train.RMSPropOptimizer(lr, RMSPROP_DECAY,
                                    momentum=RMSPROP_MOMENTUM,
                                    epsilon=RMSPROP_EPSILON)

    # Get images and labels for ImageNet and split the batch across GPUs.
    assert FLAGS.batch_size % FLAGS.num_gpus == 0, (
        'Batch size must be divisible by number of GPUs')
    split_batch_size = int(FLAGS.batch_size / FLAGS.num_gpus)

    # Override the number of preprocessing threads to account for the increased
    # number of GPU towers.
    num_preprocess_threads = FLAGS.num_preprocess_threads * FLAGS.num_gpus
    images, labels, filenames = image_processing.distorted_inputs(
        dataset,
        num_preprocess_threads=num_preprocess_threads)

    input_summaries = copy.copy(tf.get_collection(tf.GraphKeys.SUMMARIES))

    # Number of classes in the Dataset label set plus 1.
    # Label 0 is reserved for an (unused) background class.
    num_classes = dataset.num_classes() + 1

     # Split the batch of images and labels for towers.
    images_splits = tf.split(axis=0, num_or_size_splits=FLAGS.num_gpus, value=images)
    labels_splits = tf.split(axis=0, num_or_size_splits=FLAGS.num_gpus, value=labels)
    fname_splits = tf.split(axis=0, num_or_size_splits=FLAGS.num_gpus, value=labels)

    !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
    !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
    I need to know what fname_splits[i] is so I can feed correct input to "my_otherfeatures"
    in _tower_loss() below.


    # Calculate the gradients for each model tower.
    tower_grads = []
    reuse_variables = None
    for i in range(FLAGS.num_gpus):
      with tf.device('/gpu:%d' % i):
        with tf.name_scope('%s_%d' % (inception.TOWER_NAME, i)) as scope:
          # Force all Variables to reside on the CPU.
          with slim.arg_scope([slim.variables.variable], device='/cpu:0'):
            # Calculate the loss for one tower of the ImageNet model. This
            # function constructs the entire ImageNet model but shares the
            # variables across all towers.
            loss = _tower_loss(images_splits[i], labels_splits[i], my_otherfeatures, num_classes,
                               scope, reuse_variables)

          # Reuse variables for the next tower.
          reuse_variables = True

          # Retain the summaries from the final tower.
          summaries = tf.get_collection(tf.GraphKeys.SUMMARIES, scope)

          # Retain the Batch Normalization updates operations only from the
          # final tower. Ideally, we should grab the updates from all towers
          # but these stats accumulate extremely fast so we can ignore the
          # other stats from the other towers without significant detriment.
          batchnorm_updates = tf.get_collection(slim.ops.UPDATE_OPS_COLLECTION,
                                                scope)

          # Calculate the gradients for the batch of data on this ImageNet
          # tower.
          grads = opt.compute_gradients(loss)

          # Keep track of the gradients across all towers.
          tower_grads.append(grads)

    # We must calculate the mean of each gradient. Note that this is the
    # synchronization point across all towers.
    grads = _average_gradients(tower_grads)

    # Add a summaries for the input processing and global_step.
    summaries.extend(input_summaries)

    # Add a summary to track the learning rate.
    summaries.append(tf.summary.scalar('learning_rate', lr))

    # Add histograms for gradients.
    for grad, var in grads:
      if grad is not None:
        summaries.append(
            tf.summary.histogram(var.op.name + '/gradients', grad))

    # Apply the gradients to adjust the shared variables.
    apply_gradient_op = opt.apply_gradients(grads, global_step=global_step)

    # Add histograms for trainable variables.
    for var in tf.trainable_variables():
      summaries.append(tf.summary.histogram(var.op.name, var))

    # Track the moving averages of all trainable variables.
    # Note that we maintain a "double-average" of the BatchNormalization
    # global statistics. This is more complicated then need be but we employ
    # this for backward-compatibility with our previous models.
    variable_averages = tf.train.ExponentialMovingAverage(
        inception.MOVING_AVERAGE_DECAY, global_step)

    # Another possibility is to use tf.slim.get_variables().
    variables_to_average = (tf.trainable_variables() +
                            tf.moving_average_variables())
    variables_averages_op = variable_averages.apply(variables_to_average)

    # Group all updates to into a single train op.
    batchnorm_updates_op = tf.group(*batchnorm_updates)
    train_op = tf.group(apply_gradient_op, variables_averages_op,
                        batchnorm_updates_op)

    # Create a saver.
    # saver = tf.train.Saver(tf.global_variables())
    saver = tf.train.Saver(tf.global_variables(), max_to_keep=100)

    # Build the summary operation from the last tower summaries.
    summary_op = tf.summary.merge(summaries)

    # Build an initialization operation to run below.
    init = tf.global_variables_initializer()

    # Start running operations on the Graph. allow_soft_placement must be set to
    # True to build towers on GPU, as some of the ops do not have GPU
    # implementations.
    sess = tf.Session(config=tf.ConfigProto(
        allow_soft_placement=True,
        log_device_placement=FLAGS.log_device_placement))
    sess.run(init)

    if FLAGS.pretrained_model_checkpoint_path:
      try:
        assert tf.gfile.Exists(FLAGS.pretrained_model_checkpoint_path)
        variables_to_restore = tf.get_collection(
            slim.variables.VARIABLES_TO_RESTORE)
        restorer = tf.train.Saver(variables_to_restore)
        restorer.restore(sess, FLAGS.pretrained_model_checkpoint_path)
        print('%s: Pre-trained model restored from %s' %
              (datetime.now(), FLAGS.pretrained_model_checkpoint_path))
      except:
        #restorer = tf.train.import_meta_graph(FLAGS.pretrained_model_checkpoint_path + '.meta')
        variables_to_restore = tf.get_collection(
            slim.variables.VARIABLES_TO_RESTORE)
        restorer = tf.train.Saver(variables_to_restore)
        restorer.restore(sess, FLAGS.pretrained_model_checkpoint_path)

    # Start the queue runners.
    tf.train.start_queue_runners(sess=sess)

    summary_writer = tf.summary.FileWriter(
        FLAGS.train_dir,
        graph=sess.graph)

    for step in range(FLAGS.max_steps):
      start_time = time.time()
      _, loss_value = sess.run([train_op, loss])
      duration = time.time() - start_time

      assert not np.isnan(loss_value), 'Model diverged with loss = NaN'

      if step % 10 == 0:
        examples_per_sec = FLAGS.batch_size / float(duration)
        format_str = ('%s: step %d, loss = %.2f (%.1f examples/sec; %.3f '
                      'sec/batch)')
        print(format_str % (datetime.now(), step, loss_value,
                            examples_per_sec, duration))
        with open(os.path.join(FLAGS.train_dir, 'training_loss.txt'), "a") as myfile:
          myfile.write(format_str % (datetime.now(), step, loss_value,
                            examples_per_sec, duration))
          myfile.write("\n")
      if step % 100 == 0:
        summary_str = sess.run(summary_op)
        summary_writer.add_summary(summary_str, step)

      # Save the model checkpoint periodically.
      if step % FLAGS.save_step_for_chekcpoint == 0 or (step + 1) == FLAGS.max_steps:
        checkpoint_path = os.path.join(FLAGS.train_dir, 'model.ckpt')
        saver.save(sess, checkpoint_path, global_step=step)

问题来源StackOverflow 地址：/questions/59387187/is-it-possible-to-extract-the-value-of-these-tensors-within-this-context