def inputs(eval_data):
"""
Construct input for captcha evaluation using the Reader ops.
Args:
eval_data: bool, indicating if one should use the train or eval data set.
Raises:
ValueError: if no data_dir
Returns:
images: Images. 4D tensor of [batch_size, IMAGE_SIZE[0], IMAGE_SIZE[1], 1] size.
labels: Labels. 2D tensor of [batch_size, 6] size.
"""
if not eval_data:
filenames = TRAIN_FNAMES
num_examples_per_epoch = NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN
print("Using files {} for training".format(TRAIN_FNAMES))
else:
filenames = TEST_FNAMES
num_examples_per_epoch = NUM_EXAMPLES_PER_EPOCH_FOR_EVAL
print("Using files {} for testing".format(TEST_FNAMES))
for f in filenames:
if not 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.
key, string = input_data.read_string(filename_queue, FULL_IMAGE_SIZE,
NUM_CHANNELS, LABEL_BYTES, NUM_LABELS)
labels, im = input_data.string_to_data_multilabel(string, NUM_LABELS,
FULL_IMAGE_SIZE,
NUM_CHANNELS,
LABEL_BYTES)
reshaped_image = tf.cast(im, tf.float32)
height = IMAGE_SIZE[0]
width = IMAGE_SIZE[1]
# 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_whitening(resized_image)
# Ensure that the random shuffling has good mixing properties.
min_fraction_of_examples_in_queue = 0.04
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, labels,
min_queue_examples)
def inputs(eval_data):
"""
Construct input for captcha evaluation using the Reader ops.
Args:
eval_data: bool, indicating if one should use the train or eval data set.
Raises:
ValueError: if no data_dir
Returns:
images: Images. 4D tensor of [batch_size, IMAGE_SIZE[0], IMAGE_SIZE[1], 1] size.
labels: Labels. 2D tensor of [batch_size, 6] size.
"""
if not eval_data:
filenames = TRAIN_FNAMES
num_examples_per_epoch = NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN
print("Using files {} for training".format(TRAIN_FNAMES))
else:
filenames = TEST_FNAMES
num_examples_per_epoch = NUM_EXAMPLES_PER_EPOCH_FOR_EVAL
print("Using files {} for testing".format(TEST_FNAMES))
for f in filenames:
if not 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.
key, string = input_data.read_string(filename_queue, FULL_IMAGE_SIZE, NUM_CHANNELS, LABEL_BYTES, NUM_LABELS)
labels, im = input_data.string_to_data_multilabel(string, NUM_LABELS, FULL_IMAGE_SIZE, NUM_CHANNELS, LABEL_BYTES)
reshaped_image = tf.cast(im, tf.float32)
height = IMAGE_SIZE[0]
width = IMAGE_SIZE[1]
# 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_whitening(resized_image)
# Ensure that the random shuffling has good mixing properties.
min_fraction_of_examples_in_queue = 0.04
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, labels,
min_queue_examples)
def distorted_inputs():
"""
Construct distorted input for captcha training using the Reader ops.
Raises:
ValueError: if no data_dir
Returns:
images: Images. 4D tensor of [batch_size, IMAGE_SIZE[0], IMAGE_SIZE[1], 1] size.
labels: Labels. 2D tensor of [batch_size, 6] size.
"""
filenames = TRAIN_FNAMES
for f in filenames:
if not gfile.Exists(f):
raise ValueError('Failed to find file: ' + f)
print("Using files {} for training".format(TRAIN_FNAMES))
# 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.
key, string = input_data.read_string(filename_queue, FULL_IMAGE_SIZE,
NUM_CHANNELS, LABEL_BYTES, NUM_LABELS)
labels, im = input_data.string_to_data_multilabel(string, NUM_LABELS,
FULL_IMAGE_SIZE,
NUM_CHANNELS,
LABEL_BYTES)
reshaped_image = tf.cast(im, tf.float32)
height = IMAGE_SIZE[0]
width = IMAGE_SIZE[1]
# Randomly crop a [height, width] section of the image.
distorted_image = tf.image.random_crop(reshaped_image, [height, width])
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 = 0.1
min_queue_examples = int(NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN *
min_fraction_of_examples_in_queue)
print('Filling queue with %d 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, labels,
min_queue_examples)
def distorted_inputs():
"""
Construct distorted input for captcha training using the Reader ops.
Raises:
ValueError: if no data_dir
Returns:
images: Images. 4D tensor of [batch_size, IMAGE_SIZE[0], IMAGE_SIZE[1], 1] size.
labels: Labels. 2D tensor of [batch_size, 6] size.
"""
filenames = TRAIN_FNAMES
for f in filenames:
if not gfile.Exists(f):
raise ValueError('Failed to find file: ' + f)
print("Using files {} for training".format(TRAIN_FNAMES))
# 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.
key, string = input_data.read_string(filename_queue, FULL_IMAGE_SIZE, NUM_CHANNELS, LABEL_BYTES, NUM_LABELS)
labels, im = input_data.string_to_data_multilabel(string, NUM_LABELS, FULL_IMAGE_SIZE, NUM_CHANNELS, LABEL_BYTES)
reshaped_image = tf.cast(im, tf.float32)
height = IMAGE_SIZE[0]
width = IMAGE_SIZE[1]
# Randomly crop a [height, width] section of the image.
distorted_image = tf.image.random_crop(reshaped_image, [height, width])
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 = 0.1
min_queue_examples = int(NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN *
min_fraction_of_examples_in_queue)
print ('Filling queue with %d 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, labels,
min_queue_examples)