def check_and_download_vgg_checkpoint():
if not tf.gfile.Exists(checkpoints_dir):
tf.gfile.MakeDirs(checkpoints_dir)
from models.research.slim.datasets import dataset_utils
url = "http://download.tensorflow.org/models/vgg_16_2016_08_28.tar.gz"
dataset_utils.download_and_uncompress_tarball(url, checkpoints_dir)
def main():
"""Runs the download and conversion operation."""
args = _parse_args()
dataset_dir = args.data_dir
if not tf.gfile.Exists(dataset_dir):
tf.gfile.MakeDirs(dataset_dir)
training_filename = _get_output_filename(dataset_dir, 'train')
testing_filename = _get_output_filename(dataset_dir, 'test')
if tf.gfile.Exists(training_filename) and tf.gfile.Exists(
testing_filename):
print('Dataset files already exist. Exiting without re-creating them.')
return
dataset_utils.download_and_uncompress_tarball(_DATA_URL, dataset_dir)
# First, process the training data:
with tf.python_io.TFRecordWriter(training_filename) as tfrecord_writer:
offset = 0
for i in range(_NUM_TRAIN_FILES):
filename = os.path.join(dataset_dir, 'cifar-10-batches-py',
'data_batch_%d' % (i + 1)) # 1-indexed.
offset = _add_to_tfrecord(filename, tfrecord_writer, offset)
# Next, process the testing data:
with tf.python_io.TFRecordWriter(testing_filename) as tfrecord_writer:
filename = os.path.join(dataset_dir, 'cifar-10-batches-py',
'test_batch')
_add_to_tfrecord(filename, tfrecord_writer)
# Finally, write the labels file:
labels_to_class_names = dict(zip(range(len(_CLASS_NAMES)), _CLASS_NAMES))
dataset_utils.write_label_file(labels_to_class_names, dataset_dir)
_clean_up_temporary_files(dataset_dir)
print('\nFinished converting the Cifar10 dataset!')
for index in range(start_index, stop_index):
prepared_images.append(preprocess(X[index]))
labels.append(y[index])
X_batch = np.stack(prepared_images)
y_batch = np.array(labels, dtype=np.int32)
return X_batch, y_batch
if not tf.gfile.Exists("models/cnn"):
tf.gfile.MakeDirs("models/cnn")
if not os.path.exists("models/cnn/inception_v3.ckpt"):
dataset_utils.download_and_uncompress_tarball(
"http://download.tensorflow.org/models/inception_v3_2016_08_28.tar.gz",
"models/cnn")
if not os.path.exists("tmp/faces"):
os.makedirs("tmp/faces")
if not os.path.exists("tmp/faces/lfw-deepfunneled.tgz"):
dataset_utils.download_and_uncompress_tarball(
"http://vis-www.cs.umass.edu/lfw/lfw-deepfunneled.tgz", "tmp/faces")
class_mapping = {}
class_images = {}
dir = enumerate(os.listdir("images/faces/"))
for index, directory in dir:
a = directory.split(" ")
from os.path import isfile, isdir
from tqdm import tqdm
data_dir = 'data/'
url = "http://download.tensorflow.org/models/inception_v3_2016_08_28.tar.gz"
checkpoints_dir = "model_checkpoint/"
nrof_labelled = 1000
if not isdir(data_dir):
raise Exception("Data directory doesn't exist!")
if not tf.gfile.Exists(checkpoints_dir):
tf.gfile.MakeDirs(checkpoints_dir)
dataset_utils.download_and_uncompress_tarball(url, checkpoints_dir)
class DLProgress(tqdm):
last_block = 0
def hook(self, block_num=1, block_size=1, total_size=None):
self.total = total_size
self.update((block_num - self.last_block) * block_size)
self.last_block = block_num
# Load the training and testing datasets
trainset = loadmat(data_dir +
'train_64x64.mat') # read the images as .mat format
testset = loadmat(data_dir + 'test_64x64.mat')