def main(args=None):
# parse arguments
if args is None:
args = sys.argv[1:]
args = parse_args(args)
# create the generators
train_generator, validation_generator = create_generators(args)
num_classes = train_generator.num_classes()
num_anchors = train_generator.num_anchors
# optionally choose specific GPU
if args.gpu:
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu
K.set_session(get_session())
model, prediction_model = efficientdet(
args.phi,
num_classes=num_classes,
num_anchors=num_anchors,
weighted_bifpn=args.weighted_bifpn,
freeze_bn=args.freeze_bn,
detect_quadrangle=args.detect_quadrangle)
# load pretrained weights
if args.snapshot:
if args.snapshot == 'imagenet':
model_name = 'efficientnet-b{}'.format(args.phi)
file_name = '{}_weights_tf_dim_ordering_tf_kernels_autoaugment_notop.h5'.format(
model_name)
file_hash = WEIGHTS_HASHES[model_name][1]
weights_path = 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)
else:
print('Loading model, this may take a second...')
model.load_weights(args.snapshot, by_name=True)
# freeze backbone layers
if args.freeze_backbone:
# 227, 329, 329, 374, 464, 566, 656
for i in range(1, [227, 329, 329, 374, 464, 566, 656][args.phi]):
model.layers[i].trainable = False
if args.gpu and len(args.gpu.split(',')) > 1:
model = keras.utils.multi_gpu_model(model,
gpus=list(
map(int, args.gpu.split(','))))
# compile model
model.compile(
optimizer=Adam(lr=1e-3),
loss={
'regression':
smooth_l1_quad() if args.detect_quadrangle else smooth_l1(),
'classification':
focal()
},
)
# print(model.summary())
# create the callbacks
callbacks = create_callbacks(
model,
prediction_model,
validation_generator,
args,
)
if not args.compute_val_loss:
validation_generator = None
elif args.compute_val_loss and validation_generator is None:
raise ValueError(
'When you have no validation data, you should not specify --compute-val-loss.'
)
# start training
return model.fit_generator(generator=train_generator,
steps_per_epoch=args.steps,
initial_epoch=0,
epochs=args.epochs,
verbose=1,
callbacks=callbacks,
workers=args.workers,
use_multiprocessing=args.multiprocessing,
max_queue_size=args.max_queue_size,
validation_data=validation_generator)
def main(train_csv, val_csv, classes_csv, epoch_num, phi_num, steps_epoch,
batch_num, model_path):
batch_size = batch_num #def 1
phi = phi_num #def 0
is_text_detect = False
is_detect_quadrangle = False
rand_transf_augm = True
train_ann_path = train_csv
train_class_path = classes_csv
val_ann_path = val_csv
val_class_path = classes_csv
epochs = epoch_num
workers = 1
steps_p_epoch = steps_epoch
use_multiproc = True
max_que_size = 10
comp_loss = True
gpu = 0
freeze_bn_arg = True
weighted_bi = False
# create the generators
train_generator, validation_generator = 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)
num_classes = train_generator.num_classes()
num_anchors = train_generator.num_anchors
# optionally choose specific GPU
if gpu:
os.environ['CUDA_VISIBLE_DEVICES'] = gpu
# K.set_session(get_session())
model, prediction_model = efficientdet(
phi,
num_classes=num_classes,
num_anchors=num_anchors,
weighted_bifpn=weighted_bi,
freeze_bn=freeze_bn_arg,
detect_quadrangle=is_detect_quadrangle)
# freeze backbone layers
if freeze_bn_arg:
# 227, 329, 329, 374, 464, 566, 656
for i in range(1, [227, 329, 329, 374, 464, 566, 656][phi]):
model.layers[i].trainable = False
model.compile(
optimizer=Adam(lr=1e-3),
loss={
'regression':
smooth_l1_quad() if is_detect_quadrangle else smooth_l1(),
'classification': focal()
},
)
# print(model.summary())
# create the callbacks
callbacks = create_callbacks(model_path)
if not comp_loss:
validation_generator = None
elif comp_loss and validation_generator is None:
raise ValueError(
'When you have no validation data, you should not specify --compute-val-loss.'
)
# start training
return model.fit_generator(generator=train_generator,
steps_per_epoch=steps_p_epoch,
initial_epoch=0,
epochs=epochs,
verbose=1,
callbacks=callbacks,
workers=workers,
use_multiprocessing=use_multiproc,
max_queue_size=max_que_size,
validation_data=validation_generator)