def __init__(
self,
labels_file,
augmentation_map,
workers=32,
converted_coordinates_file=None,
image_folder=None,
):
"""
Initialize augmentation session.
Args:
labels_file: cvv file containing relative image labels
augmentation_map: A structured dictionary containing categorized augmentation
sequences.
workers: Parallel threads.
converted_coordinates_file: csv file containing converted from relative
to coordinates.
image_folder: Folder containing images other than data/photos/
"""
assert all([ia, iaa, iap])
self.labels_file = labels_file
self.mapping = pd.read_csv(labels_file)
self.image_folder = Path('data', 'photos').absolute().resolve()
if image_folder:
self.image_folder = Path(image_folder).absolute().resolve()
self.image_paths = [
(Path(self.image_folder) / image).absolute().resolve()
for image in os.listdir(self.image_folder)
if not image.startswith('.')
]
self.image_paths_copy = self.image_paths.copy()
if not self.image_paths:
LOGGER.error(
f'Augmentation aborted: no photos found in {self.image_folder}'
)
raise ValueError(f'No photos given')
self.image_width, self.image_height = imagesize.get(
self.image_paths[0])
self.converted_coordinates = (pd.read_csv(converted_coordinates_file)
if converted_coordinates_file else
self.relative_to_coordinates())
self.converted_groups = self.converted_coordinates.groupby('image')
self.augmentation_data = []
self.augmentation_sequences = []
self.augmentation_map = augmentation_map
self.workers = workers
self.augmented_images = 0
self.total_images = len(self.image_paths)
self.session_id = np.random.randint(10**6, (10**7))
def write_tf_record(output_path, groups, data, trainer=None):
"""
Write data to TFRecord.
Args:
output_path: Full path to save.
groups: pandas GroupBy object.
data: pandas DataFrame
trainer: core.Trainer object.
Returns:
None
"""
print(f'Processing {os.path.split(output_path)[-1]}')
if trainer:
if 'train' in output_path:
trainer.train_tf_record = output_path
if 'test' in output_path:
trainer.valid_tf_record = output_path
with tf.io.TFRecordWriter(output_path) as r_writer:
for current_image, (image_path, objects) in enumerate(groups, 1):
print(
f'\rBuilding example: {current_image}/{len(groups)} ... '
f'{os.path.split(image_path)[-1]} '
f'{round(100 * (current_image / len(groups)))}% completed',
end='',
)
separate_data = pd.DataFrame(objects,
columns=data.columns).T.to_numpy()
(
image_width,
image_height,
x_min,
y_min,
x_max,
y_max,
) = separate_data[2:8]
x_min /= image_width
x_max /= image_width
y_min /= image_height
y_max /= image_height
try:
image_data = open(image_path, 'rb').read()
key = hashlib.sha256(image_data).hexdigest()
training_example = create_example(separate_data, key,
image_data)
r_writer.write(training_example.SerializeToString())
except Exception as e:
LOGGER.error(e)
print()
def check_tf_records(self):
"""
Ensure tfrecords are specified to start training.
Returns:
None
"""
if not self.train_tf_record:
issue = 'No training TFRecord specified'
LOGGER.error(issue)
raise ValueError(issue)
if not self.valid_tf_record:
issue = 'No validation TFRecord specified'
LOGGER.error(issue)
raise ValueError(issue)
def get_dataset_next(dataset):
try:
return next(dataset)
except tf.errors.UnknownError as e:
LOGGER.error(f'Error occurred during reading from dataset\n{e}')
def get_dataset_next(dataset):
try:
return next(dataset)
except tf.errors.UnknownError as e: # sometimes encountered when reading from google drive
LOGGER.error(f'Error occurred during reading from dataset\n{e}')
