Comment les données de renforcement mis en œuvre dans Tensorflow?

Basé sur la Tensorflow tutoriel pour ConvNet, certains points ne sont pas évidentes pour moi:

• sont les images soient déformées en fait ajouté à la piscine de l'image originale?
• ou sont les images déformées utilisé au lieu des originaux?
• combien d'images déformées sont produites? (c'est à dire que l'augmentation du facteur a été défini?)

Le flux de fonctions pour le tutoriel semble être comme suit:

cifar_10_train.py

def train
    """Train CIFAR-10 for a number of steps."""
    with tf.Graph().as_default():
        [...]
        # Get images and labels for CIFAR-10.
        images, labels = cifar10.distorted_inputs()
        [...]

cifar10.py

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

    Returns:
      images: Images. 4D tensor of [batch_size, IMAGE_SIZE, IMAGE_SIZE, 3] size.
      labels: Labels. 1D tensor of [batch_size] size.

    Raises:
      ValueError: If no data_dir
    """
    if not FLAGS.data_dir:
        raise ValueError('Please supply a data_dir')
    data_dir = os.path.join(FLAGS.data_dir, 'cifar-10-batches-bin')
    return cifar10_input.distorted_inputs(data_dir=data_dir,
                                          batch_size=FLAGS.batch_size)

et enfin cifar10_input.py

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)

    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_whitening(distorted_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_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)

OriginalL'auteur pepe | 2016-05-30