def parse_args():
parser = argparse.ArgumentParser(
description="Train classification models on ImageNet",
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
models.add_model_args(parser)
fit.add_fit_args(parser)
data.add_data_args(parser)
dali.add_dali_args(parser)
data.add_data_aug_args(parser)
return parser.parse_args()
def main():
parser = argparse.ArgumentParser(
description='train unet',
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
fit.add_fit_args(parser)
seed = 2012310818
np.random.seed(seed)
parser.set_defaults(batch_size=16,
num_epochs=40,
lr=0.0001,
optimizer='adam'
# lr_step_epochs='10',
# lr_factor = 0.8
)
args = parser.parse_args()
kv = mx.kvstore.create(args.kv_store)
unet = segnet(workspace=workspace)
train, val, lt, lv = data_iter(args, kv)
fit.fit(args, unet[2], data_iter)
help='the number of classes')
parser.add_argument('--num-examples',
type=int,
default=60000,
help='the number of training examples')
parser.add_argument(
'--add_stn',
action="store_true",
default=False,
help='Add Spatial Transformer Network Layer (lenet only)')
parser.add_argument('--image_shape',
default='1, 28, 28',
help='shape of training images')
fit.add_fit_args(parser)
choose_labels = [[0, 1], [2, 3], [4, 5], [6, 7], [8, 9]]
for index, choose_label in enumerate(choose_labels):
if index == 0:
train_mission_first(parser=parser,
choose_label=choose_label,
save_dir_thistime=list_to_str(choose_label))
else:
model, reg_params = train_mission_second_update_omega(
parser=parser,
choose_label_lasttime=choose_labels[index - 1],
choose_label=choose_label,
save_dir_lasttime=list_to_str(choose_labels[index - 1]),
save_dir_thistime=list_to_str(choose_label),
