CIFAR10 代码分析详解——cifar10_input.py

这一部分代码需要留意的主要是如何构建队列,并从中读取数据的方法。

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

import os

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

# Process images of this size. Note that this differs from the original CIFAR
# image size of 32 x 32. If one alters this number, then the entire model
# architecture will change and any model would need to be retrained.
IMAGE_SIZE = 24

# Global constants describing the CIFAR-10 data set.
NUM_CLASSES = 10
NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN = 50000
NUM_EXAMPLES_PER_EPOCH_FOR_EVAL = 10000

先看函数定义及说明,输入的是 filename_queue ,输出的是单个图像及其标签。注释还提示要想有 N 路并行读取,可以调用该函数 N 次,从而使读取更为乱序。

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
  """

result 记录存储要输出的信息。

  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

下面这段代码很重要,是用队列生成 batch 的常用方法。先生成一个 reader (在这里的 reader 是定长的),然后从队列中读取单个文件的文件名及其相应的数据 (key, value)。

  # 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)

下面对读取的数据进行处理,生成所需形式的 (image, label),并最终返回 result 。

  # 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.strided_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.strided_slice(record_bytes, [label_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

下面的函数用 queue 来生成 batch 。

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.
  """

tf.train.shuffle_batch/tf.train.batchqueue 中 乱序/直接取 batch ,虽然输入 [image, label] 指明了需要 batch 的tensor 同时[image, label] 又包含了数据处理,所以取出的是处理过的 batch 。关于 queue 的解释,参看这里。

  # Create a queue that shuffles the examples, and then
  # read 'batch_size' images + labels from the example queue.
  num_preprocess_threads = 16
  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.summary.image('images', images)

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

该函数生成扭曲后的图像用于扩充训练集。 tf.train.string_input_producer(filename) 生成文件名队列用于读取数据。

def distorted_inputs(data_dir, batch_size):
  """Construct distorted input for CIFAR training using the Reader ops.
  Args:
    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 = [os.path.join(data_dir, 'data_batch_%d.bin' % i)
               for i in xrange(1, 6)]
  for f in filenames:
    if not tf.gfile.Exists(f):
      raise ValueError('Failed to find file: ' + f)

  # 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)

对原始图像进行扭曲处理。

  height = IMAGE_SIZE
  width = IMAGE_SIZE

  # Image processing for training the network. Note the many random
  # distortions applied to the image.

  # Randomly crop a [height, width] section of the image.
  distorted_image = tf.random_crop(reshaped_image, [height, width, 3])

  # Randomly flip the image horizontally.
  distorted_image = tf.image.random_flip_left_right(distorted_image)

  # Because these operations are not commutative, consider randomizing
  # the order their operation.
  distorted_image = tf.image.random_brightness(distorted_image,
                                               max_delta=63)
  distorted_image = tf.image.random_contrast(distorted_image,
                                             lower=0.2, upper=1.8)

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

  # Set the shapes of tensors.
  float_image.set_shape([height, width, 3])
  read_input.label.set_shape([1])

设置所需队列的参数,队列始终维持一个最小的数目,每次并不全部读出。

  # 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_FOR_TRAIN *
                           min_fraction_of_examples_in_queue)
  print ('Filling queue with %d CIFAR images before starting to train. '
         'This will take a few minutes.' % min_queue_examples)

  # 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=True)

下面的 input 与上面的 distorted_input 基本上是一样的。

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.
  """
  if not eval_data:
    filenames = [os.path.join(data_dir, 'data_batch_%d.bin' % i)
                 for i in xrange(1, 6)]
    num_examples_per_epoch = NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN
  else:
    filenames = [os.path.join(data_dir, 'test_batch.bin')]
    num_examples_per_epoch = NUM_EXAMPLES_PER_EPOCH_FOR_EVAL

  for f in filenames:
    if not tf.gfile.Exists(f):
      raise ValueError('Failed to find file: ' + f)

  # 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,
                                                         height, width)

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

  # Set the shapes of tensors.
  float_image.set_shape([height, width, 3])
  read_input.label.set_shape([1])

  # 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)


你可能感兴趣的:(Tensorflow代码分析)