def create_callbacks(model, training_model, prediction_model,
validation_generator, args):
callbacks = []
# save the prediction model
if args.snapshots:
checkpoint = keras.callbacks.ModelCheckpoint(os.path.join(
args.snapshot_path,
'resnet50_{dataset_type}_{{epoch:02d}}.h5'.format(
dataset_type=args.dataset_type)),
verbose=1)
checkpoint = RedirectModel(checkpoint, prediction_model)
callbacks.append(checkpoint)
if args.dataset_type == 'coco' and args.evaluation:
from keras_retinanet.callbacks.coco import CocoEval
# use prediction model for evaluation
evaluation = CocoEval(validation_generator)
evaluation = RedirectModel(evaluation, prediction_model)
callbacks.append(evaluation)
lr_scheduler = keras.callbacks.ReduceLROnPlateau(monitor='loss',
factor=0.1,
patience=2,
verbose=1,
mode='auto',
epsilon=0.0001,
cooldown=0,
min_lr=0)
callbacks.append(lr_scheduler)
return callbacks
def create_callbacks(model, training_model, prediction_model, validation_generator, args):
callbacks = []
# save the model
if args.snapshots:
# ensure directory created first; otherwise h5py will error after epoch.
makedirs(args.snapshot_path)
checkpoint = keras.callbacks.ModelCheckpoint(
os.path.join(
args.snapshot_path,
'{backbone}_{dataset_type}_{{epoch:02d}}.h5'.format(backbone=args.backbone, dataset_type=args.dataset_type)
),
verbose=1
)
checkpoint = RedirectModel(checkpoint, model)
callbacks.append(checkpoint)
tensorboard_callback = None
if args.tensorboard_dir:
tensorboard_callback = keras.callbacks.TensorBoard(
log_dir = args.tensorboard_dir,
histogram_freq = 0,
batch_size = args.batch_size,
write_graph = False,
write_grads = False,
write_images = False,
embeddings_freq = 0,
embeddings_layer_names = None,
embeddings_metadata = None
)
callbacks.append(tensorboard_callback)
if args.evaluation and validation_generator:
if args.dataset_type == 'coco':
from keras_retinanet.callbacks.coco import CocoEval
# use prediction model for evaluation
evaluation = CocoEval(validation_generator, tensorboard=tensorboard_callback)
else:
evaluation = Evaluate(validation_generator, tensorboard=tensorboard_callback)
evaluation = RedirectModel(evaluation, prediction_model)
callbacks.append(evaluation)
callbacks.append(keras.callbacks.ReduceLROnPlateau(
monitor = 'loss',
factor = 0.1,
patience = 2,
verbose = 1,
mode = 'auto',
epsilon = 0.0001,
cooldown = 0,
min_lr = 0
))
return callbacks
def create_callbacks(model, training_model, prediction_model,
validation_generator, args):
""" Creates the callbacks to use during training.
Args
model: The base model.
training_model: The model that is used for training.
prediction_model: The model that should be used for validation.
validation_generator: The generator for creating validation data.
args: parseargs args object.
Returns:
A list of callbacks used for training.
"""
callbacks = []
tensorboard_callback = None
if args.tensorboard_dir:
tensorboard_callback = keras.callbacks.TensorBoard(
log_dir=args.tensorboard_dir,
histogram_freq=0,
batch_size=args.batch_size,
write_graph=True,
write_grads=False,
write_images=False,
embeddings_freq=0,
embeddings_layer_names=None,
embeddings_metadata=None)
callbacks.append(tensorboard_callback)
if args.evaluation and validation_generator:
if args.dataset_type == 'coco':
from keras_retinanet.callbacks.coco import CocoEval
# use prediction model for evaluation
evaluation = CocoEval(validation_generator,
tensorboard=tensorboard_callback)
else:
evaluation = Evaluate(validation_generator,
tensorboard=tensorboard_callback,
weighted_average=args.weighted_average)
evaluation = RedirectModel(evaluation, prediction_model)
callbacks.append(evaluation)
# save the model
if args.snapshots:
# ensure directory created first; otherwise h5py will error after epoch.
makedirs(args.snapshot_path)
checkpoint = keras.callbacks.ModelCheckpoint(
os.path.join(
args.snapshot_path,
'{backbone}_{dataset_type}_{{epoch:02d}}.h5'.format(
backbone=args.backbone, dataset_type=args.dataset_type)),
verbose=1,
# save_best_only=True,
# monitor="mAP",
# mode='max'
)
checkpoint = RedirectModel(checkpoint, model)
callbacks.append(checkpoint)
callbacks.append(
keras.callbacks.ReduceLROnPlateau(monitor='loss',
factor=0.1,
patience=2,
verbose=1,
mode='auto',
min_delta=0.0001,
cooldown=0,
min_lr=0))
return callbacks