tf_cifar10_dataset.py

# Copyright 2015 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""
@author: jiankaiwang
@date: 2019/03
@version:
  keras: 2.1.6
  tensorflow: 1.11.0
@notice:
  add function _load_cifar10_dataset()
"""

import tensorflow as tf
from tensorflow.keras.datasets import cifar10 as keras_cifar10

# In[]

# 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

NUM_CLASSES = 10
NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN = 50000
NUM_EXAMPLES_PER_EPOCH_FOR_EVAL = 10000

# In[]

def _load_cifar10_dataset(image_id_queue):
  """Load the cifar10 dataset directly from Keras library.
  
  Args:
    image_id_queue: a queue stores image indexes in (random) order
  
  Returns:
    image: a single image with shape of (32, 32, 3)
    laebl: the label of the image with shape of (1,)
  """
  
  (x_train, y_train), (_, _) = keras_cifar10.load_data()
  
  x_train_tensor = tf.convert_to_tensor(x_train)
  y_train_tensor = tf.convert_to_tensor(y_train)
  
  select_id = tf.cast(image_id_queue.dequeue(), tf.int32)
  
  x_train_slice = tf.slice(x_train_tensor, 
                           [select_id, 0, 0, 0], 
                           [1, 32, 32, 3])
  y_train_slice = tf.slice(y_train_tensor, 
                           [select_id, 0], 
                           [1, 1])
  
  image = tf.squeeze(x_train_slice, 0)
  label = tf.squeeze(y_train_slice, 1)
    
  return image, label 

# In[]

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 = 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])

# In[]

def distorted_inputs(batch_size):
  """Construct distorted input for CIFAR training using the Reader ops.

  Args:
    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.
  """
  
  image_id = [i for i in range(1, NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN)]

  # Create a queue that produces the filenames to read.
  image_id_queue = tf.train.input_producer(image_id)

  with tf.name_scope('data_augmentation'):
    # Read examples from files in the filename queue.
    # shape of image: (32, 32, 3)
    # shape of label: (1,)
    image, label = _load_cifar10_dataset(image_id_queue)
    reshaped_image = tf.cast(image, tf.float32)

    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.
    # NOTE: since per_image_standardization zeros the mean and makes
    # the stddev unit, this likely has no effect see tensorflow#1458.
    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])
    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_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, label,
                                         min_queue_examples, batch_size,
                                         shuffle=True)