Welcome to OStack Knowledge Sharing Community for programmer and developer-Open, Learning and Share
Welcome To Ask or Share your Answers For Others

Categories

0 votes
308 views
in Technique[技术] by (71.8m points)

python - tensorflow : .eval() never ends

i am loading the cifar-10 data set , the methods adds the data to tensor array , so to access the data i used .eval() with session , on a normal tf constant it return the value , but on the labels and the train set which are tf array it wont

1- i am using docker tensorflow-jupyter

2- it uses python 3

3- the batch file must be added to data folder

i am using the first batch [data_batch_1.bin]from this file

http://www.cs.toronto.edu/~kriz/cifar-10-binary.tar.gz

As notebook:

https://drive.google.com/open?id=0B_AFMME1kY1obkk1YmJHcjV0ODA

The code[As in tensorflow site but modified to read 1 patch] [check the last 7 lines for the data loading] :

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

import os
import urllib
import tensorflow as tf
from six.moves import xrange  # pylint: disable=redefined-builtin

# Global constants describing the CIFAR-10 data set.
NUM_CLASSES = 10
NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN = 5000
NUM_EXAMPLES_PER_EPOCH_FOR_EVAL = 1000
IMAGE_SIZE = 32

def _generate_image_and_label_batch(image, label, min_queue_examples,
                                    batch_size, shuffle):
  """Construct a queued batch of images and labels.
  Args:
    image: 3-D Tensor of [height, width, 3] of type.float32.
    label: 1-D Tensor of type.int32
    min_queue_examples: int32, minimum number of samples to retain
      in the queue that provides of batches of examples.
    batch_size: Number of images per batch.
    shuffle: boolean indicating whether to use a shuffling queue.
  Returns:
    images: Images. 4D tensor of [batch_size, height, width, 3] size.
    labels: Labels. 1D tensor of [batch_size] size.
  """
  # Create a queue that shuffles the examples, and then
  # read 'batch_size' images + labels from the example queue.
  num_preprocess_threads = 2
  if shuffle:
    images, label_batch = tf.train.shuffle_batch(
        [image, label],
        batch_size=batch_size,
        num_threads=num_preprocess_threads,
        capacity=min_queue_examples + 3 * batch_size,
        min_after_dequeue=min_queue_examples)
  else:
    images, label_batch = tf.train.batch(
        [image, label],
        batch_size=batch_size,
        num_threads=num_preprocess_threads,
        capacity=min_queue_examples + 3 * batch_size)

  # Display the training images in the visualizer.
  tf.image_summary('images', images)

  return images, tf.reshape(label_batch, [batch_size])

def read_cifar10(filename_queue):
  """Reads and parses examples from CIFAR10 data files.
  Recommendation: if you want N-way read parallelism, call this function
  N times.  This will give you N independent Readers reading different
  files & positions within those files, which will give better mixing of
  examples.
  Args:
    filename_queue: A queue of strings with the filenames to read from.
  Returns:
    An object representing a single example, with the following fields:
      height: number of rows in the result (32)
      width: number of columns in the result (32)
      depth: number of color channels in the result (3)
      key: a scalar string Tensor describing the filename & record number
        for this example.
      label: an int32 Tensor with the label in the range 0..9.
      uint8image: a [height, width, depth] uint8 Tensor with the image data
  """

  class CIFAR10Record(object):
    pass
  result = CIFAR10Record()

  # Dimensions of the images in the CIFAR-10 dataset.
  # See http://www.cs.toronto.edu/~kriz/cifar.html for a description of the
  # input format.
  label_bytes = 1  # 2 for CIFAR-100
  result.height = 32
  result.width = 32
  result.depth = 3
  image_bytes = result.height * result.width * result.depth
  # Every record consists of a label followed by the image, with a
  # fixed number of bytes for each.
  record_bytes = label_bytes + image_bytes

  # Read a record, getting filenames from the filename_queue.  No
  # header or footer in the CIFAR-10 format, so we leave header_bytes
  # and footer_bytes at their default of 0.
  reader = tf.FixedLengthRecordReader(record_bytes=record_bytes)
  result.key, value = reader.read(filename_queue)

  # Convert from a string to a vector of uint8 that is record_bytes long.
  record_bytes = tf.decode_raw(value, tf.uint8)

  # The first bytes represent the label, which we convert from uint8->int32.
  result.label = tf.cast(
      tf.slice(record_bytes, [0], [label_bytes]), tf.int32)

  # The remaining bytes after the label represent the image, which we reshape
  # from [depth * height * width] to [depth, height, width].
  depth_major = tf.reshape(tf.slice(record_bytes, [label_bytes], [image_bytes]),
                           [result.depth, result.height, result.width])
  # Convert from [depth, height, width] to [height, width, depth].
  result.uint8image = tf.transpose(depth_major, [1, 2, 0])

  return result

def inputs(eval_data, data_dir, batch_size):
  """Construct input for CIFAR evaluation using the Reader ops.
  Args:
    eval_data: bool, indicating if one should use the train or eval data set.
    data_dir: Path to the CIFAR-10 data directory.
    batch_size: Number of images per batch.
  Returns:
    images: Images. 4D tensor of [batch_size, IMAGE_SIZE, IMAGE_SIZE, 3] size.
    labels: Labels. 1D tensor of [batch_size] size.
  """
  filenames=[];
  filenames.append(os.path.join(data_dir, 'data_batch_1.bin')  )   
  num_examples_per_epoch = NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN


  print(filenames)


  # Create a queue that produces the filenames to read.
  filename_queue = tf.train.string_input_producer(filenames)

  # Read examples from files in the filename queue.
  read_input = read_cifar10(filename_queue)
  reshaped_image = tf.cast(read_input.uint8image, tf.float32)

  height = IMAGE_SIZE
  width = IMAGE_SIZE

  # Image processing for evaluation.
  # Crop the central [height, width] of the image.
  resized_image = tf.image.resize_image_with_crop_or_pad(reshaped_image,
                                                         width, height)

  # Subtract off the mean and divide by the variance of the pixels.
  float_image = tf.image.per_image_whitening(resized_image)

  # Ensure that the random shuffling has good mixing properties.
  min_fraction_of_examples_in_queue = 0.4
  min_queue_examples = int(num_examples_per_epoch *
                           min_fraction_of_examples_in_queue)

  # Generate a batch of images and labels by building up a queue of examples.
  return _generate_image_and_label_batch(float_image, read_input.label,
                                         min_queue_examples, batch_size,
                                         shuffle=False)
sess = tf.InteractiveSession()
train_data,train_labels = inputs(False,"data",6000)
print (train_data,train_labels)
train_data=train_data.eval()
train_labels=train_labels.eval()
print(train_data)
print(train_labels)
sess.close()
See Question&Answers more detail:os

与恶龙缠斗过久,自身亦成为恶龙;凝视深渊过久,深渊将回以凝视…
Welcome To Ask or Share your Answers For Others

1 Answer

0 votes
by (71.8m points)

You must call tf.train.start_queue_runners(sess) before you call train_data.eval() or train_labels.eval().

This is a(n unfortunate) consequence of how TensorFlow input pipelines are implemented: the tf.train.string_input_producer(), tf.train.shuffle_batch(), and tf.train.batch() functions internally create queues that buffer records between different stages in the input pipeline. The tf.train.start_queue_runners() call tells TensorFlow to start fetching records into these buffers; without calling it the buffers remain empty and eval() hangs indefinitely.


与恶龙缠斗过久,自身亦成为恶龙;凝视深渊过久,深渊将回以凝视…
Welcome to OStack Knowledge Sharing Community for programmer and developer-Open, Learning and Share
Click Here to Ask a Question

...