def transform(dataset_reader, data_dir, output_dir, splits, only_classes,
only_images, limit_examples, limit_classes, seed, overrides,
debug):
"""
Prepares dataset for ingestion.
Converts the dataset into different (one per split) TFRecords files.
"""
if debug:
tf.logging.set_verbosity(tf.logging.DEBUG)
else:
tf.logging.set_verbosity(tf.logging.INFO)
# We forcefully save modified datasets into subfolders to avoid
# overwriting and/or unnecessary clutter.
output_subfolder = get_output_subfolder(
only_classes, only_images, limit_examples, limit_classes
)
if output_subfolder:
output_dir = os.path.join(output_dir, output_subfolder)
try:
reader = get_reader(dataset_reader)
except ValueError as e:
tf.logging.error('Error getting reader: {}'.format(e))
return
# All splits must have a consistent set of classes.
classes = None
reader_kwargs = parse_override(overrides)
try:
for split in splits:
# Create instance of reader.
split_reader = reader(
data_dir, split,
only_classes=only_classes, only_images=only_images,
limit_examples=limit_examples, limit_classes=limit_classes,
seed=seed, **reader_kwargs
)
if classes is None:
# "Save" classes from the first split reader
classes = split_reader.classes
else:
# Overwrite classes after first split for consistency.
split_reader.set_classes(classes)
# We assume we are saving object detection objects, but it should
# be easy to modify once we have different types of objects.
writer = ObjectDetectionWriter(split_reader, output_dir, split)
writer.save()
except InvalidDataDirectory as e:
tf.logging.error('Error reading dataset: {}'.format(e))
def transform(dataset_reader, data_dir, output_dir, splits, only_classes,
only_images, limit_examples, class_examples, overrides, debug):
"""
Prepares dataset for ingestion.
Converts the dataset into different (one per split) TFRecords files.
"""
tf.logging.set_verbosity(tf.logging.INFO)
if debug:
tf.logging.set_verbosity(tf.logging.DEBUG)
try:
reader = get_reader(dataset_reader)
except ValueError as e:
tf.logging.error('Error getting reader: {}'.format(e))
return
# All splits must have a consistent set of classes.
classes = None
reader_kwargs = parse_override(overrides)
try:
for split in splits:
# Create instance of reader.
split_reader = reader(data_dir,
split,
only_classes=only_classes,
only_images=only_images,
limit_examples=limit_examples,
class_examples=class_examples,
**reader_kwargs)
if classes is None:
# "Save" classes from the first split reader
classes = split_reader.classes
else:
# Overwrite classes after first split for consistency.
split_reader.classes = classes
# We assume we are saving object detection objects, but it should
# be easy to modify once we have different types of objects.
writer = ObjectDetectionWriter(split_reader, output_dir, split)
writer.save()
tf.logging.info('Composition per class ({}):'.format(split))
for label, count in split_reader._per_class_counter.most_common():
tf.logging.info('\t%s: %d', split_reader.pretty_name(label),
count)
except InvalidDataDirectory as e:
tf.logging.error('Error reading dataset: {}'.format(e))
