def __init__(self,
tensor_key,
label_map_proto_file,
shape_keys=None,
shape=None,
default_value=''):
"""Initializes the LookupTensor handler.
Simply calls a vocabulary (most often, a label mapping) lookup.
Args:
tensor_key: the name of the `TFExample` feature to read the tensor from.
label_map_proto_file: File path to a text format LabelMapProto message
mapping class text to id.
shape_keys: Optional name or list of names of the TF-Example feature in
which the tensor shape is stored. If a list, then each corresponds to
one dimension of the shape.
shape: Optional output shape of the `Tensor`. If provided, the `Tensor` is
reshaped accordingly.
default_value: The value used when the `tensor_key` is not found in a
particular `TFExample`.
Raises:
ValueError: if both `shape_keys` and `shape` are specified.
"""
name_to_id = label_map_util.get_label_map_dict(
label_map_proto_file, use_display_name=False)
# We use a default_value of -1, but we expect all labels to be contained
# in the label map.
try:
# Dynamically try to load the tf v2 lookup, falling back to contrib
lookup = tf.compat.v2.lookup
hash_table_class = tf.compat.v2.lookup.StaticHashTable
except AttributeError:
lookup = tf.contrib.lookup
hash_table_class = tf.contrib.lookup.HashTable
name_to_id_table = hash_table_class(
initializer=lookup.KeyValueTensorInitializer(
keys=tf.constant(list(name_to_id.keys())),
values=tf.constant(list(name_to_id.values()), dtype=tf.int64)),
default_value=-1)
display_name_to_id = label_map_util.get_label_map_dict(
label_map_proto_file, use_display_name=True)
# We use a default_value of -1, but we expect all labels to be contained
# in the label map.
display_name_to_id_table = hash_table_class(
initializer=lookup.KeyValueTensorInitializer(
keys=tf.constant(list(display_name_to_id.keys())),
values=tf.constant(
list(display_name_to_id.values()), dtype=tf.int64)),
default_value=-1)
self._name_to_id_table = name_to_id_table
self._display_name_to_id_table = display_name_to_id_table
super(_ClassTensorHandler, self).__init__(tensor_key, shape_keys, shape,
default_value)
def main(_):
tf.logging.set_verbosity(tf.logging.INFO)
required_flags = [
'input_box_annotations_csv', 'input_images_directory',
'input_label_map', 'output_tf_record_path_prefix'
]
for flag_name in required_flags:
if not getattr(FLAGS, flag_name):
raise ValueError('Flag --{} is required'.format(flag_name))
label_map = label_map_util.get_label_map_dict(FLAGS.input_label_map)
all_box_annotations = pd.read_csv(FLAGS.input_box_annotations_csv)
if FLAGS.input_image_label_annotations_csv:
all_label_annotations = pd.read_csv(
FLAGS.input_image_label_annotations_csv)
all_label_annotations.rename(
columns={'Confidence': 'ConfidenceImageLabel'}, inplace=True)
else:
all_label_annotations = None
all_images = tf.gfile.Glob(
os.path.join(FLAGS.input_images_directory, '*.jpg'))
all_image_ids = [
os.path.splitext(os.path.basename(v))[0] for v in all_images
]
all_image_ids = pd.DataFrame({'ImageID': all_image_ids})
all_annotations = pd.concat(
[all_box_annotations, all_image_ids, all_label_annotations])
tf.logging.log(tf.logging.INFO, 'Found %d images...', len(all_image_ids))
with contextlib2.ExitStack() as tf_record_close_stack:
output_tfrecords = tf_record_creation_util.open_sharded_output_tfrecords(
tf_record_close_stack, FLAGS.output_tf_record_path_prefix,
FLAGS.num_shards)
for counter, image_data in enumerate(
all_annotations.groupby('ImageID')):
tf.logging.log_every_n(tf.logging.INFO, 'Processed %d images...',
1000, counter)
image_id, image_annotations = image_data
# In OID image file names are formed by appending ".jpg" to the image ID.
image_path = os.path.join(FLAGS.input_images_directory,
image_id + '.jpg')
with tf.gfile.Open(image_path) as image_file:
encoded_image = image_file.read()
tf_example = oid_tfrecord_creation.tf_example_from_annotations_data_frame(
image_annotations, label_map, encoded_image)
if tf_example:
shard_idx = int(image_id, 16) % FLAGS.num_shards
output_tfrecords[shard_idx].write(
tf_example.SerializeToString())
def main(_):
data_dir = FLAGS.data_dir
label_map_dict = label_map_util.get_label_map_dict(FLAGS.label_map_path)
logging.info('Reading from Pet dataset.')
image_dir = os.path.join(data_dir, 'images')
annotations_dir = os.path.join(data_dir, 'annotations')
examples_path = os.path.join(annotations_dir, 'trainval.txt')
examples_list = dataset_util.read_examples_list(examples_path)
# Test images are not included in the downloaded data set, so we shall perform
# our own split.
random.seed(42)
random.shuffle(examples_list)
num_examples = len(examples_list)
num_train = int(0.7 * num_examples)
train_examples = examples_list[:num_train]
val_examples = examples_list[num_train:]
logging.info('%d training and %d validation examples.',
len(train_examples), len(val_examples))
train_output_path = os.path.join(FLAGS.output_dir,
'pet_faces_train.record')
val_output_path = os.path.join(FLAGS.output_dir, 'pet_faces_val.record')
if not FLAGS.faces_only:
train_output_path = os.path.join(
FLAGS.output_dir, 'pets_fullbody_with_masks_train.record')
val_output_path = os.path.join(FLAGS.output_dir,
'pets_fullbody_with_masks_val.record')
create_tf_record(train_output_path,
FLAGS.num_shards,
label_map_dict,
annotations_dir,
image_dir,
train_examples,
faces_only=FLAGS.faces_only,
mask_type=FLAGS.mask_type)
create_tf_record(val_output_path,
FLAGS.num_shards,
label_map_dict,
annotations_dir,
image_dir,
val_examples,
faces_only=FLAGS.faces_only,
mask_type=FLAGS.mask_type)
def test_get_label_map_dict(self):
label_map_string = """
item {
id:2
name:'cat'
}
item {
id:1
name:'dog'
}
"""
label_map_path = os.path.join(self.get_temp_dir(), 'label_map.pbtxt')
with tf.gfile.Open(label_map_path, 'wb') as f:
f.write(label_map_string)
label_map_dict = label_map_util.get_label_map_dict(label_map_path)
self.assertEqual(label_map_dict['dog'], 1)
self.assertEqual(label_map_dict['cat'], 2)
def test_get_label_map_dict_with_fill_in_gaps_and_background(self):
label_map_string = """
item {
id:3
name:'cat'
}
item {
id:1
name:'dog'
}
"""
label_map_path = os.path.join(self.get_temp_dir(), 'label_map.pbtxt')
with tf.gfile.Open(label_map_path, 'wb') as f:
f.write(label_map_string)
label_map_dict = label_map_util.get_label_map_dict(
label_map_path, fill_in_gaps_and_background=True)
self.assertEqual(label_map_dict['background'], 0)
self.assertEqual(label_map_dict['dog'], 1)
self.assertEqual(label_map_dict['2'], 2)
self.assertEqual(label_map_dict['cat'], 3)
self.assertEqual(len(label_map_dict), max(label_map_dict.values()) + 1)
def main(_):
if FLAGS.set not in SETS:
raise ValueError('set must be in : {}'.format(SETS))
if FLAGS.year not in YEARS:
raise ValueError('year must be in : {}'.format(YEARS))
data_dir = FLAGS.data_dir
years = ['VOC2007', 'VOC2012']
if FLAGS.year != 'merged':
years = [FLAGS.year]
writer = tf.python_io.TFRecordWriter(FLAGS.output_path)
label_map_dict = label_map_util.get_label_map_dict(FLAGS.label_map_path)
for year in years:
logging.info('Reading from PASCAL %s dataset.', year)
examples_path = os.path.join(data_dir, year, 'ImageSets', 'Main',
'aeroplane_' + FLAGS.set + '.txt')
annotations_dir = os.path.join(data_dir, year, FLAGS.annotations_dir)
examples_list = dataset_util.read_examples_list(examples_path)
for idx, example in enumerate(examples_list):
if idx % 100 == 0:
logging.info('On image %d of %d', idx, len(examples_list))
path = os.path.join(annotations_dir, example + '.xml')
with tf.gfile.GFile(path, 'r') as fid:
xml_str = fid.read()
xml = etree.fromstring(xml_str)
data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']
tf_example = dict_to_tf_example(data, FLAGS.data_dir,
label_map_dict,
FLAGS.ignore_difficult_instances)
writer.write(tf_example.SerializeToString())
writer.close()
def convert_kitti_to_tfrecords(data_dir, output_path, classes_to_use,
label_map_path, validation_set_size):
"""Convert the KITTI detection dataset to TFRecords.
Args:
data_dir: The full path to the unzipped folder containing the unzipped data
from data_object_image_2 and data_object_label_2.zip.
Folder structure is assumed to be: data_dir/training/label_2 (annotations)
and data_dir/data_object_image_2/training/image_2 (images).
output_path: The path to which TFRecord files will be written. The TFRecord
with the training set will be located at: <output_path>_train.tfrecord
And the TFRecord with the validation set will be located at:
<output_path>_val.tfrecord
classes_to_use: List of strings naming the classes for which data should be
converted. Use the same names as presented in the KIITI README file.
Adding dontcare class will remove all other bounding boxes that overlap
with areas marked as dontcare regions.
label_map_path: Path to label map proto
validation_set_size: How many images should be left as the validation set.
(Ffirst `validation_set_size` examples are selected to be in the
validation set).
"""
label_map_dict = label_map_util.get_label_map_dict(label_map_path)
train_count = 0
val_count = 0
annotation_dir = os.path.join(data_dir, 'training', 'label_2')
image_dir = os.path.join(data_dir, 'data_object_image_2', 'training',
'image_2')
train_writer = tf.python_io.TFRecordWriter('%s_train.tfrecord' %
output_path)
val_writer = tf.python_io.TFRecordWriter('%s_val.tfrecord' % output_path)
images = sorted(tf.gfile.ListDirectory(image_dir))
for img_name in images:
img_num = int(img_name.split('.')[0])
is_validation_img = img_num < validation_set_size
img_anno = read_annotation_file(
os.path.join(annotation_dir,
str(img_num).zfill(6) + '.txt'))
image_path = os.path.join(image_dir, img_name)
# Filter all bounding boxes of this frame that are of a legal class, and
# don't overlap with a dontcare region.
# TODO(talremez) filter out targets that are truncated or heavily occluded.
annotation_for_image = filter_annotations(img_anno, classes_to_use)
example = prepare_example(image_path, annotation_for_image,
label_map_dict)
if is_validation_img:
val_writer.write(example.SerializeToString())
val_count += 1
else:
train_writer.write(example.SerializeToString())
train_count += 1
train_writer.close()
val_writer.close()