def create_generators(args, preprocess_image):
"""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,
'config': args.config,
'image_min_side': args.image_min_side,
'image_max_side': args.image_max_side,
'preprocess_image': preprocess_image,
}
# create random transform generator for augmenting training data
if args.random_transform:
transform_generator = random_transform_generator(
min_rotation=-0.1,
max_rotation=0.1,
min_translation=(-0.1, -0.1),
max_translation=(0.1, 0.1),
min_shear=-0.1,
max_shear=0.1,
min_scaling=(0.9, 0.9),
max_scaling=(1.1, 1.1),
flip_x_chance=0.5,
flip_y_chance=0.5,
)
visual_effect_generator = random_visual_effect_generator(
contrast_range=(0.9, 1.1),
brightness_range=(-.1, .1),
hue_range=(-0.05, 0.05),
saturation_range=(0.95, 1.05))
else:
transform_generator = random_transform_generator(flip_x_chance=0.5)
visual_effect_generator = None
if args.dataset_type == 'csv':
train_generator = CSVGenerator(
args.annotations,
args.classes,
transform_generator=transform_generator,
visual_effect_generator=visual_effect_generator,
**common_args)
if args.val_annotations:
validation_generator = CSVGenerator(args.val_annotations,
args.classes,
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 _generate():
while True:
yield ImageAdjustment(
contrast_factor=_uniform(contrast_range),
brightness_delta=_uniform(brightness_range),
hue_delta=_uniform(hue_range),
saturation_factor=_uniform(saturation_range),
)
return _generate()
if __name__ == "__main__":
from keras_retinanet.utils.image import VisualEffect, random_visual_effect_generator
effect_generator = random_visual_effect_generator()
effect = next(effect_generator)
# Test contrast
contrast_effect = VisualEffect(effect.contrast_factor, None, None, None)
image = np.random.randint(0, 255, size=(3, 3, 2), dtype=np.uint8)
contrast_old = contrast_effect(image)
contrast_adjustment = ImageAdjustment(effect.contrast_factor, None, None,
None)
contrast_new = contrast_adjustment(image)
if np.array_equal(contrast_old, contrast_new):
print("[OK] Contrast backward compatibility.")
else:
print("[FAILED] Contrast backward compatibility.")
print("Old:")
print(contrast_old)
def create_generators(args, preprocess_image):
""" 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,
'config' : args.config,
'image_min_side' : args.image_min_side,
'image_max_side' : args.image_max_side,
'no_resize' : args.no_resize,
'preprocess_image' : preprocess_image,
}
# create random transform generator for augmenting training data
if args.random_transform:
transform_generator = random_transform_generator(
min_rotation=-0.1,
max_rotation=0.1,
min_translation=(-0.1, -0.1),
max_translation=(0.1, 0.1),
min_shear=-0.1,
max_shear=0.1,
min_scaling=(0.9, 0.9),
max_scaling=(1.1, 1.1),
flip_x_chance=0.5,
flip_y_chance=0.5,
)
visual_effect_generator = random_visual_effect_generator(
contrast_range=(0.9, 1.1),
brightness_range=(-.1, .1),
hue_range=(-0.05, 0.05),
saturation_range=(0.95, 1.05)
)
else:
transform_generator = random_transform_generator(flip_x_chance=0.5)
#transform_generator = None
visual_effect_generator = None
if args.dataset_type == 'coco':
# import here to prevent unnecessary dependency on cocoapi
from ..preprocessing.coco import CocoGenerator
train_generator = CocoGenerator(
args.coco_path,
'train2017',
transform_generator=transform_generator,
visual_effect_generator=visual_effect_generator,
**common_args
)
validation_generator = CocoGenerator(
args.coco_path,
'val2017',
shuffle_groups=False,
**common_args
)
elif args.dataset_type == 'pascal':
train_generator = PascalVocGenerator(
args.pascal_path,
'train',
image_extension=args.image_extension,
transform_generator=transform_generator,
visual_effect_generator=visual_effect_generator,
**common_args
)
validation_generator = PascalVocGenerator(
args.pascal_path,
'val',
image_extension=args.image_extension,
shuffle_groups=False,
**common_args
)
elif args.dataset_type == 'csv':
train_generator = CSVGenerator(
args.annotations,
args.classes,
transform_generator=transform_generator,
visual_effect_generator=visual_effect_generator,
**common_args
)
if args.val_annotations:
validation_generator = CSVGenerator(
args.val_annotations,
args.classes,
shuffle_groups=False,
**common_args
)
else:
validation_generator = None
elif args.dataset_type == 'oid':
train_generator = OpenImagesGenerator(
args.main_dir,
subset='train',
version=args.version,
labels_filter=args.labels_filter,
annotation_cache_dir=args.annotation_cache_dir,
parent_label=args.parent_label,
transform_generator=transform_generator,
visual_effect_generator=visual_effect_generator,
**common_args
)
validation_generator = OpenImagesGenerator(
args.main_dir,
subset='validation',
version=args.version,
labels_filter=args.labels_filter,
annotation_cache_dir=args.annotation_cache_dir,
parent_label=args.parent_label,
shuffle_groups=False,
**common_args
)
elif args.dataset_type == 'kitti':
train_generator = KittiGenerator(
args.kitti_path,
subset='train',
transform_generator=transform_generator,
visual_effect_generator=visual_effect_generator,
**common_args
)
validation_generator = KittiGenerator(
args.kitti_path,
subset='val',
shuffle_groups=False,
**common_args
)
else:
raise ValueError('Invalid data type received: {}'.format(args.dataset_type))
return train_generator, validation_generator