def create_generators(args):
"""
Create generators for training and validation.
Args
args: parseargs object containing configuration for generators.
preprocess_image: Function that preprocesses an image for the network.
"""
common_args = {
'batch_size': args.batch_size,
'phi': args.phi,
}
# create random transform generator for augmenting training data
if args.random_transform:
misc_effect = MiscEffect()
visual_effect = VisualEffect()
else:
misc_effect = None
visual_effect = None
if args.dataset_type == 'pascal':
from generators.pascal import PascalVocGenerator
train_generator = PascalVocGenerator(args.pascal_path,
'trainval',
skip_difficult=True,
misc_effect=misc_effect,
visual_effect=visual_effect,
**common_args)
validation_generator = PascalVocGenerator(args.pascal_path,
'val',
skip_difficult=True,
shuffle_groups=False,
**common_args)
elif args.dataset_type == 'csv':
from generators.csv_ import CSVGenerator
train_generator = CSVGenerator(args.annotations_path,
args.classes_path,
misc_effect=misc_effect,
visual_effect=visual_effect,
**common_args)
if args.val_annotations_path:
validation_generator = CSVGenerator(args.val_annotations_path,
args.classes_path,
shuffle_groups=False,
**common_args)
else:
validation_generator = None
else:
raise ValueError('Invalid data type received: {}'.format(
args.dataset_type))
return train_generator, validation_generator
def create_generators(batch_size, phi, is_text_detect, is_detect_quadrangle,
rand_transf_augm, train_ann_path, val_ann_path,
train_class_path, val_class_path):
"""
Create generators for training and validation.
Args
args: parseargs object containing configuration for generators.
preprocess_image: Function that preprocesses an image for the network.
"""
common_args = {
'batch_size': batch_size,
'phi': phi,
'detect_text': is_text_detect,
'detect_quadrangle': is_detect_quadrangle
}
# create random transform generator for augmenting training data
if rand_transf_augm:
misc_effect = MiscEffect()
visual_effect = VisualEffect()
else:
misc_effect = None
visual_effect = None
from generators.csv_ import CSVGenerator
train_generator = CSVGenerator(train_ann_path,
train_class_path,
misc_effect=misc_effect,
visual_effect=visual_effect,
**common_args)
if val_ann_path:
validation_generator = CSVGenerator(val_ann_path,
val_class_path,
shuffle_groups=False,
**common_args)
else:
validation_generator = None
return train_generator, validation_generator
def create_generators(args):
"""
Create generators for training and validation.
Args
args: parseargs object containing configuration for generators.
preprocess_image: Function that preprocesses an image for the network.
"""
common_args = {
'batch_size': args.batch_size,
'input_size': args.input_size,
}
# create random transform generator for augmenting training data
if args.random_transform:
misc_effect = MiscEffect(border_value=0)
visual_effect = VisualEffect()
else:
misc_effect = None
visual_effect = None
if args.dataset_type == 'coco':
from generators.coco import CocoGenerator
train_generator = CocoGenerator(args.coco_path,
'train',
misc_effect=misc_effect,
visual_effect=visual_effect,
**common_args)
validation_generator = CocoGenerator(args.coco_path,
'val',
shuffle_groups=False,
**common_args)
else:
raise ValueError('Invalid data type received: {}'.format(
args.dataset_type))
return train_generator, validation_generator
except ET.ParseError as e:
raise_from(
ValueError('invalid annotations file: {}: {}'.format(
filename, e)), None)
except ValueError as e:
raise_from(
ValueError('invalid annotations file: {}: {}'.format(
filename, e)), None)
if __name__ == '__main__':
from augmentor.misc import MiscEffect
from augmentor.color import VisualEffect
misc_effect = MiscEffect(multi_scale_prob=0.9,
rotate_prob=0.05,
flip_prob=0.8,
crop_prob=0.5,
translate_prob=0.7,
border_value=(128, 128, 128))
visual_effect = VisualEffect()
train_generator = PascalVocGenerator(
r'G:\datasets\PASCALVOC\VOC2012',
'train',
phi=0,
skip_difficult=True,
batch_size=1,
misc_effect=misc_effect,
visual_effect=visual_effect,
)
mean = [0.485, 0.456, 0.406]
std = [0.229, 0.224, 0.225]
def create_generators(args):
"""
Create generators for training and validation.
Args
args: parseargs object containing configuration for generators.
preprocess_image: Function that preprocesses an image for the network.
"""
common_args = {
'batch_size': args.batch_size,
'phi': args.phi,
'detect_text': args.detect_text,
'detect_quadrangle': args.detect_quadrangle
}
# create random transform generator for augmenting training data
if args.random_transform:
misc_effect = MiscEffect()
visual_effect = VisualEffect()
else:
misc_effect = None
visual_effect = None
if args.dataset_type == 'pascal':
from generators.pascal import PascalVocGenerator
train_generator = PascalVocGenerator(
args.pascal_path,
'trainval',
skip_difficult=True,
misc_effect=misc_effect,
visual_effect=visual_effect,
image_extension=".png",
**common_args
)
validation_generator = PascalVocGenerator(
args.pascal_path,
'val',
skip_difficult=True,
shuffle_groups=False,
image_extension=".png",
**common_args
)
elif args.dataset_type == 'csv':
from generators.csv_ import CSVGenerator
train_generator = CSVGenerator(
args.annotations_path,
args.classes_path,
misc_effect=misc_effect,
visual_effect=visual_effect,
**common_args
)
if args.val_annotations_path:
validation_generator = CSVGenerator(
args.val_annotations_path,
args.classes_path,
shuffle_groups=False,
**common_args
)
else:
validation_generator = None
elif args.dataset_type == 'coco':
# import here to prevent unnecessary dependency on cocoapi
from generators.coco import CocoGenerator
train_generator = CocoGenerator(
args.coco_path,
'train2017',
misc_effect=misc_effect,
visual_effect=visual_effect,
group_method='random',
**common_args
)
validation_generator = CocoGenerator(
args.coco_path,
'val2017',
shuffle_groups=False,
**common_args
)
else:
raise ValueError('Invalid data type received: {}'.format(args.dataset_type))
return train_generator, validation_generator
filename = self.image_names[image_index] + '.xml'
try:
tree = ET.parse(
os.path.join(self.data_dir, 'Annotations', filename))
return self.__parse_annotations(tree.getroot())
except ET.ParseError as e:
raise_from(
ValueError('invalid annotations file: {}: {}'.format(
filename, e)), None)
except ValueError as e:
raise_from(
ValueError('invalid annotations file: {}: {}'.format(
filename, e)), None)
if __name__ == '__main__':
from augmentor.misc import MiscEffect
from augmentor.color import VisualEffect
misc_effect = MiscEffect(border_value=0)
visual_effect = VisualEffect()
generator = PascalVocGenerator(r'D:\datasets\voc_dataset',
'trainval',
skip_difficult=True,
misc_effect=misc_effect,
visual_effect=visual_effect,
batch_size=1)
for inputs, targets in generator:
print('hi')
return self.__parse_annotations(tree.getroot())
except ET.ParseError as e:
raise_from(
ValueError('invalid annotations file: {}: {}'.format(
filename, e)), None)
except ValueError as e:
raise_from(
ValueError('invalid annotations file: {}: {}'.format(
filename, e)), None)
if __name__ == '__main__':
from augmentor.misc import MiscEffect
from augmentor.color import VisualEffect
misc_effect = MiscEffect()
visual_effect = VisualEffect()
train_generator = PascalVocGenerator(
'datasets/VOC0712',
'trainval',
skip_difficult=True,
anchors_path='voc_anchors_416.txt',
batch_size=1,
misc_effect=misc_effect,
visual_effect=visual_effect,
)
for i in range(len(train_generator)):
group = train_generator.groups[i]
image_group, annotations_group = train_generator.get_augmented_data(
group)
image = (image_group[0] * 255.).astype(np.uint8)
def create_generators(args):
"""
Create generators for training and validation.
Args
args: parseargs object containing configuration for generators.
preprocess_image: Function that preprocesses an image for the network.
"""
common_args = {
"batch_size": args.batch_size,
"phi": args.phi,
"detect_text": args.detect_text,
"detect_quadrangle": args.detect_quadrangle,
}
# create random transform generator for augmenting training data
if args.random_transform:
misc_effect = MiscEffect()
visual_effect = VisualEffect()
else:
misc_effect = None
visual_effect = None
if args.dataset_type == "pascal":
from generators.pascal import PascalVocGenerator
train_generator = PascalVocGenerator(
args.pascal_path,
"trainval",
skip_difficult=True,
misc_effect=misc_effect,
visual_effect=visual_effect,
**common_args,
)
validation_generator = PascalVocGenerator(
args.pascal_path,
"val",
skip_difficult=True,
shuffle_groups=False,
**common_args,
)
elif args.dataset_type == "csv":
from generators.csv_ import CSVGenerator
train_generator = CSVGenerator(
args.annotations_path,
args.classes_path,
misc_effect=misc_effect,
visual_effect=visual_effect,
**common_args,
)
if args.val_annotations_path:
validation_generator = CSVGenerator(
args.val_annotations_path,
args.classes_path,
shuffle_groups=False,
**common_args,
)
else:
validation_generator = None
elif args.dataset_type == "coco":
# import here to prevent unnecessary dependency on cocoapi
from generators.coco import CocoGenerator
train_generator = CocoGenerator(
args.coco_path,
"train2017",
misc_effect=misc_effect,
visual_effect=visual_effect,
group_method="random",
**common_args,
)
validation_generator = CocoGenerator(args.coco_path,
"val2017",
shuffle_groups=False,
**common_args)
else:
raise ValueError("Invalid data type received: {}".format(
args.dataset_type))
return train_generator, validation_generator
def load_efficient_det(config, LOCAL_ANNOTATIONS_PATH, LOCAL_ROOT_PATH,
LOCAL_CLASSES_PATH, LOCAL_VALIDATIONS_PATH,
LOCAL_LOGS_PATH, LOCAL_SNAPSHOTS_PATH):
common_args = {
'phi': config['phi'],
'detect_text': config['detect_text'],
'detect_quadrangle': config['detect_quadrangle']
}
# create random transform generator for augmenting training data
if config['random_transform']:
misc_effect = MiscEffect()
visual_effect = VisualEffect()
else:
misc_effect = None
visual_effect = None
annotations_df = pd.read_csv(LOCAL_ANNOTATIONS_PATH, header=None)
# stratified sampling
N = int(len(annotations_df) * 0.15)
evaluation_df = annotations_df.groupby(
5, group_keys=False).apply(lambda x: x.sample(
int(np.rint(N * len(x) / len(annotations_df))))).sample(frac=1)
evaluation_path = f'{LOCAL_ROOT_PATH}/evaluation.csv'
evaluation_df.to_csv(evaluation_path, index=False, header=None)
config['steps_per_epoch'] = annotations_df.iloc[:, 0].nunique(
) / config['batch_size']
train_generator = CSVGenerator(LOCAL_ANNOTATIONS_PATH,
LOCAL_CLASSES_PATH,
batch_size=config['batch_size'],
misc_effect=misc_effect,
visual_effect=visual_effect,
**common_args)
if config['train_evaluation']:
evaluation_generator = CSVGenerator(evaluation_path,
LOCAL_CLASSES_PATH,
batch_size=config['batch_size'],
misc_effect=misc_effect,
visual_effect=visual_effect,
**common_args)
else:
evaluation_generator = None
if config['validation']:
validation_generator = CSVGenerator(LOCAL_VALIDATIONS_PATH,
LOCAL_CLASSES_PATH,
batch_size=config['batch_size'],
misc_effect=misc_effect,
visual_effect=visual_effect,
**common_args)
else:
validation_generator = None
num_classes = train_generator.num_classes()
num_anchors = train_generator.num_anchors
model, prediction_model = efficientdet(
config['phi'],
num_classes=num_classes,
num_anchors=num_anchors,
weighted_bifpn=config['weighted_bifpn'],
freeze_bn=config['freeze_bn'],
detect_quadrangle=config['detect_quadrangle'])
# freeze backbone layers
if config['freeze_backbone']:
# 227, 329, 329, 374, 464, 566, 656
for i in range(1, [227, 329, 329, 374, 464, 566, 656][config['phi']]):
model.layers[i].trainable = False
# optionally choose specific GPU
gpu = config['gpu']
device = gpu.split(':')[0]
if gpu:
os.environ['CUDA_VISIBLE_DEVICES'] = device
if gpu and len(gpu.split(':')) > 1:
gpus = gpu.split(':')[1]
model = tf.keras.utils.multi_gpu_model(model,
gpus=list(
map(int, gpus.split(','))))
if config['snapshot'] == 'imagenet':
model_name = 'efficientnet-b{}'.format(config['phi'])
file_name = '{}_weights_tf_dim_ordering_tf_kernels_autoaugment_notop.h5'.format(
model_name)
file_hash = WEIGHTS_HASHES[model_name][1]
weights_path = tf.keras.utils.get_file(file_name,
BASE_WEIGHTS_PATH + file_name,
cache_subdir='models',
file_hash=file_hash)
model.load_weights(weights_path, by_name=True)
elif config['snapshot']:
print('Loading model, this may take a second...')
model.load_weights(config['snapshot'], by_name=True)
return (model, prediction_model, train_generator, evaluation_generator,
validation_generator, config)