def _add_to_tfrecord(data_filename, labels_filename, num_images,
tfrecord_writer):
"""Loads data from the binary MNIST files and writes files to a TFRecord.
Args:
data_filename: The filename of the MNIST images.
labels_filename: The filename of the MNIST labels.
num_images: The number of images in the dataset.
tfrecord_writer: The TFRecord writer to use for writing.
"""
images = _extract_images(data_filename, num_images)
labels = _extract_labels(labels_filename, num_images)
shape = (_IMAGE_SIZE, _IMAGE_SIZE, _NUM_CHANNELS)
with tf.Graph().as_default():
image = tf.placeholder(dtype=tf.uint8, shape=shape)
encoded_png = tf.image.encode_png(image)
with tf.Session('') as sess:
for j in range(num_images):
sys.stdout.write('\r>> Converting image %d/%d' %
(j + 1, num_images))
sys.stdout.flush()
png_string = sess.run(encoded_png,
feed_dict={image: images[j]})
example = dataset_utils.image_to_tfexample(
png_string, 'png'.encode(), _IMAGE_SIZE, _IMAGE_SIZE,
labels[j])
tfrecord_writer.write(example.SerializeToString())
def _convert_dataset(split_name, filenames, class_names_to_ids, dataset_dir):
"""Converts the given filenames to a TFRecord dataset.
Args:
split_name: The name of the dataset, either 'train' or 'validation'.
filenames: A list of absolute paths to png or jpg images.
class_names_to_ids: A dictionary from class names (strings) to ids
(integers).
dataset_dir: The directory where the converted datasets are stored.
"""
assert split_name in ['train', 'validation']
num_per_shard = int(math.ceil(len(filenames) / float(_NUM_SHARDS)))
with tf.Graph().as_default():
image_reader = ImageReader()
with tf.Session('') as sess:
for shard_id in range(_NUM_SHARDS):
output_filename = _get_dataset_filename(
dataset_dir, split_name, shard_id)
with tf.python_io.TFRecordWriter(output_filename) as tfrecord_writer:
start_ndx = shard_id * num_per_shard
end_ndx = min((shard_id + 1) * num_per_shard, len(filenames))
for i in range(start_ndx, end_ndx):
sys.stdout.write('\r>> Converting image %d/%d shard %d' % (
i + 1, len(filenames), shard_id))
sys.stdout.flush()
# Read the filename:
image_data = tf.gfile.FastGFile(filenames[i], 'rb').read()
height, width = image_reader.read_image_dims(sess, image_data)
class_name = os.path.basename(os.path.dirname(filenames[i]))
class_id = class_names_to_ids[class_name]
example = dataset_utils.image_to_tfexample(
image_data, b'jpg', height, width, class_id)
tfrecord_writer.write(example.SerializeToString())
sys.stdout.write('\n')
sys.stdout.flush()
def _add_to_tfrecord(filename, tfrecord_writer, offset=0):
"""Loads data from the cifar10 pickle files and writes files to a TFRecord.
Args:
filename: The filename of the cifar10 pickle file.
tfrecord_writer: The TFRecord writer to use for writing.
offset: An offset into the absolute number of images previously written.
Returns:
The new offset.
"""
with tf.gfile.Open(filename, 'rb') as f:
if sys.version_info < (3,):
data = cPickle.load(f)
else:
data = cPickle.load(f, encoding='bytes')
images = data[b'data']
num_images = images.shape[0]
images = images.reshape((num_images, 3, 32, 32))
labels = data[b'labels']
with tf.Graph().as_default():
image_placeholder = tf.placeholder(dtype=tf.uint8)
encoded_image = tf.image.encode_png(image_placeholder)
with tf.Session('') as sess:
for j in range(num_images):
sys.stdout.write('\r>> Reading file [%s] image %d/%d' % (
filename, offset + j + 1, offset + num_images))
sys.stdout.flush()
image = np.squeeze(images[j]).transpose((1, 2, 0))
label = labels[j]
png_string = sess.run(encoded_image,
feed_dict={image_placeholder: image})
example = dataset_utils.image_to_tfexample(
png_string, b'png', _IMAGE_SIZE, _IMAGE_SIZE, label)
tfrecord_writer.write(example.SerializeToString())
return offset + num_images