def parse_args():
parser = argparse.ArgumentParser(description='Train Faster R-CNN network')
# general
parser.add_argument('--network', help='network name', default=default.network, type=str)
parser.add_argument('--dataset', help='dataset name', default=default.dataset, type=str)
args, rest = parser.parse_known_args()
generate_config(args.network, args.dataset)
parser.add_argument('--image_set', help='image_set name', default=default.image_set, type=str)
parser.add_argument('--root_path', help='output data folder', default=default.root_path, type=str)
parser.add_argument('--dataset_path', help='dataset path', default=default.dataset_path, type=str)
# training
parser.add_argument('--frequent', help='frequency of logging', default=default.frequent, type=int)
parser.add_argument('--kvstore', help='the kv-store type', default=default.kvstore, type=str)
parser.add_argument('--work_load_list', help='work load for different devices', default=None, type=list)
parser.add_argument('--no_flip', help='disable flip images', action='store_true')
parser.add_argument('--no_shuffle', help='disable random shuffle', action='store_true')
parser.add_argument('--resume', help='continue training', action='store_true')
# e2e
parser.add_argument('--gpus', help='GPU device to train with', default='0', type=str)
parser.add_argument('--pretrained', help='pretrained model prefix', default=default.pretrained, type=str)
parser.add_argument('--pretrained_epoch', help='pretrained model epoch', default=default.pretrained_epoch, type=int)
parser.add_argument('--prefix', help='new model prefix', default=default.e2e_prefix, type=str)
parser.add_argument('--begin_epoch', help='begin epoch of training, use with resume', default=0, type=int)
parser.add_argument('--end_epoch', help='end epoch of training', default=default.e2e_epoch, type=int)
parser.add_argument('--lr', help='base learning rate', default=default.e2e_lr, type=float)
parser.add_argument('--lr_step', help='learning rate steps (in epoch)', default=default.e2e_lr_step, type=str)
args = parser.parse_args()
return args
def parse_args():
parser = argparse.ArgumentParser(description='Train Faster R-CNN network')
# general
parser.add_argument('--network', help='network name', default=default.network, type=str)
parser.add_argument('--dataset', help='dataset name', default=default.dataset, type=str)
args, rest = parser.parse_known_args()
generate_config(args.network, args.dataset)
parser.add_argument('--image_set', help='image_set name', default=default.image_set, type=str)
parser.add_argument('--root_path', help='output data folder', default=default.root_path, type=str)
parser.add_argument('--dataset_path', help='dataset path', default=default.dataset_path, type=str)
# training
parser.add_argument('--frequent', help='frequency of logging', default=default.frequent, type=int)
parser.add_argument('--kvstore', help='the kv-store type', default=default.kvstore, type=str)
parser.add_argument('--work_load_list', help='work load for different devices', default=None, type=list)
parser.add_argument('--no_flip', help='disable flip images', action='store_true')
parser.add_argument('--no_shuffle', help='disable random shuffle', action='store_true')
parser.add_argument('--resume', help='continue training', action='store_true')
# e2e
parser.add_argument('--gpus', help='GPU device to train with', default='0', type=str)
parser.add_argument('--pretrained', help='pretrained model prefix', default=default.pretrained, type=str)
parser.add_argument('--pretrained_epoch', help='pretrained model epoch', default=default.pretrained_epoch, type=int)
parser.add_argument('--prefix', help='new model prefix', default=default.e2e_prefix, type=str)
parser.add_argument('--begin_epoch', help='begin epoch of training, use with resume', default=0, type=int)
parser.add_argument('--end_epoch', help='end epoch of training', default=default.e2e_epoch, type=int)
parser.add_argument('--lr', help='base learning rate', default=default.e2e_lr, type=float)
parser.add_argument('--lr_step', help='learning rate steps (in epoch)', default=default.e2e_lr_step, type=str)
# tricks
parser.add_argument('--use_global_context', help='use roi global context for classification', action='store_true')
parser.add_argument('--use_data_augmentation', help='randomly transform image in color, brightness, contrast, sharpness',\
action='store_true')
parser.add_argument('--use_roi_align', help='replace ROIPooling with ROIAlign', action='store_true')
args = parser.parse_args()
return args
def parse_args():
parser = argparse.ArgumentParser(description='Train Faster R-CNN Network')
# general
parser.add_argument('--network', help='network name', default=default.network, type=str)
parser.add_argument('--dataset', help='dataset name', default=default.dataset, type=str)
args, rest = parser.parse_known_args()
generate_config(args.network, args.dataset)
parser.add_argument('--image_set', help='image_set name', default=default.image_set, type=str)
parser.add_argument('--root_path', help='output data folder', default=default.root_path, type=str)
parser.add_argument('--dataset_path', help='dataset path', default=default.dataset_path, type=str)
# training
parser.add_argument('--frequent', help='frequency of logging', default=default.frequent, type=int)
parser.add_argument('--kvstore', help='the kv-store type', default=default.kvstore, type=str)
parser.add_argument('--work_load_list', help='work load for different devices', default=None, type=list)
parser.add_argument('--no_flip', help='disable flip images', action='store_true')
parser.add_argument('--no_shuffle', help='disable random shuffle', action='store_true')
parser.add_argument('--resume', help='continue training', action='store_true')
# alternate
parser.add_argument('--gpus', help='GPU device to train with', default='0', type=str)
parser.add_argument('--pretrained', help='pretrained model prefix', default=default.pretrained, type=str)
parser.add_argument('--pretrained_epoch', help='pretrained model epoch', default=default.pretrained_epoch, type=int)
parser.add_argument('--rpn_epoch', help='end epoch of rpn training', default=default.rpn_epoch, type=int)
parser.add_argument('--rpn_lr', help='base learning rate', default=default.rpn_lr, type=float)
parser.add_argument('--rpn_lr_step', help='learning rate steps (in epoch)', default=default.rpn_lr_step, type=str)
parser.add_argument('--rcnn_epoch', help='end epoch of rcnn training', default=default.rcnn_epoch, type=int)
parser.add_argument('--rcnn_lr', help='base learning rate', default=default.rcnn_lr, type=float)
parser.add_argument('--rcnn_lr_step', help='learning rate steps (in epoch)', default=default.rcnn_lr_step, type=str)
args = parser.parse_args()
return args
def parse_args():
parser = argparse.ArgumentParser(description='Train RetinaFace')
# general
parser.add_argument('--network', help='network name', default=default.network, type=str)
parser.add_argument('--dataset', help='dataset name', default=default.dataset, type=str)
args, rest = parser.parse_known_args()
generate_config(args.network, args.dataset)
parser.add_argument('--image_set', help='image_set name', default=default.image_set, type=str)
parser.add_argument('--root_path', help='output data folder', default=default.root_path, type=str)
parser.add_argument('--dataset_path', help='dataset path', default=default.dataset_path, type=str)
# training
parser.add_argument('--frequent', help='frequency of logging', default=default.frequent, type=int)
parser.add_argument('--kvstore', help='the kv-store type', default=default.kvstore, type=str)
parser.add_argument('--work_load_list', help='work load for different devices', default=None, type=list)
parser.add_argument('--no_flip', help='disable flip images', action='store_true')
parser.add_argument('--no_shuffle', help='disable random shuffle', action='store_true')
# e2e
#parser.add_argument('--gpus', help='GPU device to train with', default='0,1,2,3', type=str)
parser.add_argument('--pretrained', help='pretrained model prefix', default=default.pretrained, type=str)
parser.add_argument('--pretrained_epoch', help='pretrained model epoch', default=default.pretrained_epoch, type=int)
parser.add_argument('--prefix', help='new model prefix', default=default.prefix, type=str)
parser.add_argument('--begin_epoch', help='begin epoch of training, use with resume', default=0, type=int)
parser.add_argument('--end_epoch', help='end epoch of training', default=default.end_epoch, type=int)
parser.add_argument('--lr', help='base learning rate', default=default.lr, type=float)
parser.add_argument('--lr_step', help='learning rate steps (in epoch)', default=default.lr_step, type=str)
parser.add_argument('--no_ohem', help='disable online hard mining', action='store_true')
args = parser.parse_args()
return args
def parse_args():
parser = argparse.ArgumentParser(description='Train Faster R-CNN network')
# general
parser.add_argument('--network', help='network name', default=default.network, type=str)
parser.add_argument('--dataset', help='dataset name', default=default.dataset, type=str)
args, rest = parser.parse_known_args()
generate_config(args.network, args.dataset)
data_root = os.path.join(os.getcwd(),default.root_path)
parser.add_argument('--root_path', help='output data folder', default=data_root, type=str)
parser.add_argument('--subset',help='subset of dataset,only for refer dataset',default=default.subset,type=str)
parser.add_argument('--split',help='split of dataset,only for refer dataset',default=default.split,type=str)
# training
parser.add_argument('--frequent', help='frequency of logging', default=default.frequent, type=int)
parser.add_argument('--kvstore', help='the kv-store type', default=default.kvstore, type=str)
parser.add_argument('--work_load_list', help='work load for different devices', default=None, type=list)
parser.add_argument('--no_flip', help='disable flip images', action='store_true')
parser.add_argument('--no_shuffle', help='disable random shuffle', action='store_true')
parser.add_argument('--resume', help='continue training', default=False,type=bool)
# e2e
parser.add_argument('--gpus', help='GPU device to train with', default='0', type=str)
parser.add_argument('--pretrained', help='pretrained model prefix', default=default.pretrained, type=str)
parser.add_argument('--pretrained_epoch', help='pretrained model epoch', default=default.pretrained_epoch, type=int)
parser.add_argument('--prefix', help='new model prefix', default=default.e2e_prefix, type=str)
parser.add_argument('--begin_epoch', help='begin epoch of training, use with resume', default=0, type=int)
parser.add_argument('--end_epoch', help='end epoch of training', default=default.e2e_epoch, type=int)
parser.add_argument('--lr', help='base learning rate', default=default.e2e_lr, type=float)
parser.add_argument('--lr_step', help='learning rate steps (in epoch)', default=default.e2e_lr_step, type=str)
args = parser.parse_args()
return args
def parse_args():
parser = argparse.ArgumentParser(description='Test a Fast R-CNN network')
# general
parser.add_argument('--network',
help='network name',
default='resnet_fpn',
type=str)
parser.add_argument('--dataset',
help='dataset name',
default='Cityscape',
type=str)
args, rest = parser.parse_known_args()
generate_config(args.network, args.dataset)
parser.add_argument('--image_set',
help='image_set name',
default=default.test_image_set,
type=str)
parser.add_argument('--root_path',
help='output data folder',
default=default.root_path,
type=str)
parser.add_argument('--dataset_path',
help='dataset path',
default=default.dataset_path,
type=str)
parser.add_argument('--result_path',
help='result path',
default='data/cityscape/results/',
type=str)
# testing
parser.add_argument('--prefix',
help='model to test with',
default='model/final',
type=str)
parser.add_argument('--epoch',
help='model to test with',
default=0,
type=int)
parser.add_argument('--gpu',
help='GPU device to test with',
default=0,
type=int)
# rcnn
parser.add_argument('--vis', help='turn on visualization', default=True)
parser.add_argument('--thresh',
help='valid detection threshold',
default=1e-3,
type=float)
parser.add_argument('--shuffle',
help='shuffle data on visualization',
default=False)
parser.add_argument('--has_rpn',
help='generate proposals on the fly',
default=True)
parser.add_argument('--proposal',
help='can be ss for selective search or rpn',
default='rpn',
type=str)
args = parser.parse_args()
return args
def parse_args():
parser = argparse.ArgumentParser(description='Train Faster R-CNN network')
# general
parser.add_argument('--network', help='network name', default=default.network, type=str)
parser.add_argument('--dataset', help='dataset name', default=default.dataset, type=str)
args, rest = parser.parse_known_args()
generate_config(args.network, args.dataset)
parser.add_argument('--image_set', help='image_set name', default=default.image_set, type=str)
parser.add_argument('--root_path', help='output data folder', default=default.root_path, type=str)
parser.add_argument('--dataset_path', help='dataset path', default=default.dataset_path, type=str)
# training
parser.add_argument('--frequent', help='frequency of logging', default=default.frequent, type=int)
parser.add_argument('--kvstore', help='the kv-store type', default=default.kvstore, type=str)
parser.add_argument('--work_load_list', help='work load for different devices', default=None, type=list)
parser.add_argument('--no_flip', help='disable flip images', action='store_true')
parser.add_argument('--no_shuffle', help='disable random shuffle', action='store_true')
parser.add_argument('--resume', help='continue training', action='store_true')
# e2e
parser.add_argument('--gpus', help='GPU device to train with', default='0', type=str)
parser.add_argument('--pretrained', help='pretrained model prefix', default=default.pretrained, type=str)
parser.add_argument('--pretrained_epoch', help='pretrained model epoch', default=default.pretrained_epoch, type=int)
parser.add_argument('--prefix', help='new model prefix', default=default.e2e_prefix, type=str)
parser.add_argument('--begin_epoch', help='begin epoch of training, use with resume', default=0, type=int)
parser.add_argument('--end_epoch', help='end epoch of training', default=default.e2e_epoch, type=int)
parser.add_argument('--lr', help='base learning rate', default=default.e2e_lr, type=float)
parser.add_argument('--lr_step', help='learning rate steps (in epoch)', default=default.e2e_lr_step, type=str)
# <EcoSys> nvprof
parser.add_argument('--nvprof-on', help='turn on the nvprof profiler by setting True', default=False, type=bool)
parser.add_argument('--nvprof-start-batch', type=int, default=1000, help='the batch number where nvprof begins')
parser.add_argument('--nvprof-start-epoch', type=int, default=0, help='the epoch number where nvprof begins')
parser.add_argument('--nvprof-stop-batch', type=int, default=1050, help='the batch number where nvprof ends')
parser.add_argument('--nvprof-stop-epoch', type=int, default=0, help='the epoch number where nvprof ends')
# </EcoSys>
args = parser.parse_args()
return args
def parse_args():
parser = argparse.ArgumentParser(description='Demonstrate a Faster R-CNN network')
parser.add_argument('--network', help='network name', default=default.network, type=str)
args, rest = parser.parse_known_args()
generate_config(args.network, None)
parser.add_argument('--image', help='custom image', type=str)
parser.add_argument('--prefix', help='saved model prefix', type=str)
parser.add_argument('--epoch', help='epoch of pretrained model', type=int)
parser.add_argument('--gpu', help='GPU device to use', default=1, type=int)
parser.add_argument('--vis', help='display result', action='store_true')
args = parser.parse_args()
return args
def parse_args():
parser = argparse.ArgumentParser(
description='Test a Region Proposal Network')
# general
parser.add_argument('--network',
help='network name',
default=default.network,
type=str)
parser.add_argument('--dataset',
help='dataset name',
default=default.dataset,
type=str)
args, rest = parser.parse_known_args()
generate_config(args.network, args.dataset)
parser.add_argument('--image_set',
help='image_set name',
default=default.test_image_set,
type=str)
parser.add_argument('--root_path',
help='output data folder',
default=default.root_path,
type=str)
parser.add_argument('--dataset_path',
help='dataset path',
default=default.dataset_path,
type=str)
# testing
parser.add_argument('--prefix',
help='model to test with',
default=default.rpn_prefix,
type=str)
parser.add_argument('--epoch',
help='model to test with',
default=default.rpn_epoch,
type=int)
# rpn
parser.add_argument('--gpu',
help='GPU device to test with',
default='0',
type=str)
parser.add_argument('--vis',
help='turn on visualization',
action='store_true')
parser.add_argument('--thresh',
help='rpn proposal threshold',
default=0,
type=float)
parser.add_argument('--shuffle',
help='shuffle data on visualization',
action='store_true')
args = parser.parse_args()
return args
def parse_args():
parser = argparse.ArgumentParser(
description='Demonstrate a Faster R-CNN network')
parser.add_argument('--network',
help='network name',
default=default.network,
type=str)
parser.add_argument('--dataset',
help='dataset name',
default=default.dataset,
type=str)
args, rest = parser.parse_known_args()
generate_config(args.network, args.dataset)
parser.add_argument('--image_set',
help='image_set name',
default=default.test_image_set,
type=str)
parser.add_argument('--root_path',
help='output data folder',
default=default.root_path,
type=str)
parser.add_argument('--dataset_path',
help='dataset path',
default=default.dataset_path,
type=str)
parser.add_argument('--prefix', help='saved model prefix', type=str)
parser.add_argument('--epoch', help='epoch of pretrained model', type=int)
parser.add_argument('--gpu', help='GPU device to use', default=0, type=int)
parser.add_argument('--vis', help='display result', action='store_true')
parser.add_argument('--vis_image_dir',
help='if vis, image results are saved in this folder',
default='data/vis',
type=str)
parser.add_argument('--use_global_context',
help='use roi global context for classification',
action='store_true')
parser.add_argument('--use_roi_align',
help='replace ROIPooling with ROIAlign',
action='store_true')
parser.add_argument('--use_box_voting',
help='use box voting in test',
action='store_true')
args = parser.parse_args()
return args
def parse_args():
parser = argparse.ArgumentParser(description='Test a Fast R-CNN network')
# general
parser.add_argument('--network',
help='network name',
default=default.network,
type=str)
parser.add_argument('--dataset',
help='dataset name',
default=default.dataset,
type=str)
args, rest = parser.parse_known_args()
generate_config(args.network, args.dataset)
# testing
parser.add_argument('--prefix',
help='model to test with',
default=default.rcnn_prefix,
type=str)
parser.add_argument('--epoch',
help='model to test with',
default=0,
type=int)
parser.add_argument('--gpu',
help='GPU device to test with',
default=0,
type=int)
parser.add_argument('--name', help='test name', default='submit', type=str)
# rcnn
parser.add_argument('--vis',
help='turn on visualization',
action='store_true')
parser.add_argument('--thresh',
help='valid detection threshold',
default=0.3,
type=float)
parser.add_argument('--scale',
help='test image size',
default='960',
type=str)
args = parser.parse_args()
return args
def parse_args():
parser = argparse.ArgumentParser(description='Test a Faster R-CNN network')
# general
parser.add_argument('--network', help='network name', default=default.network, type=str)
parser.add_argument('--dataset', help='dataset name', default=default.dataset, type=str)
args, rest = parser.parse_known_args()
generate_config(args.network, args.dataset)
parser.add_argument('--image_set', help='image_set name', default=default.test_image_set, type=str)
parser.add_argument('--root_path', help='output data folder', default=default.root_path, type=str)
parser.add_argument('--dataset_path', help='dataset path', default=default.dataset_path, type=str)
# testing
parser.add_argument('--prefix', help='model to test with', default=default.e2e_prefix, type=str)
parser.add_argument('--epoch', help='model to test with', default=default.e2e_epoch, type=int)
parser.add_argument('--gpu', help='GPU device to test with', default=0, type=int)
# rcnn
parser.add_argument('--vis', help='turn on visualization', action='store_true')
parser.add_argument('--thresh', help='valid detection threshold', default=1e-3, type=float)
parser.add_argument('--shuffle', help='shuffle data on visualization', action='store_true')
parser.add_argument('--has_rpn', help='generate proposals on the fly', action='store_true', default=True)
parser.add_argument('--proposal', help='can be ss for selective search or rpn', default='rpn', type=str)
args = parser.parse_args()
return args
def parse_args():
parser = argparse.ArgumentParser(description='Test a Faster R-CNN network')
# general
parser.add_argument('--network',
help='network name',
default=default.network,
type=str)
parser.add_argument('--dataset',
help='dataset name',
default=default.dataset,
type=str)
args, rest = parser.parse_known_args()
generate_config(args.network, args.dataset)
args, rest = parser.parse_known_args()
data_root = os.path.join(os.getcwd(), default.root_path)
parser.add_argument('--root_path',
help='output data folder',
default=data_root,
type=str)
parser.add_argument('--subset',
help='subset of dataset,only for refer dataset',
default=default.subset,
type=str)
parser.add_argument('--split',
help='split of dataset,only for refer dataset',
default=default.split,
type=str)
# testing
parser.add_argument('--prefix',
help='model to test with',
default=default.e2e_prefix,
type=str)
parser.add_argument('--epoch',
help='model to test with',
default=default.e2e_epoch,
type=int)
parser.add_argument('--gpu',
help='GPU device to test with',
default=0,
type=int)
# rcnn
parser.add_argument('--vis',
help='turn on visualization',
action='store_true')
parser.add_argument('--thresh',
help='valid detection threshold',
default=1e-1,
type=float)
parser.add_argument('--shuffle',
help='shuffle data on visualization',
action='store_true')
parser.add_argument('--has_rpn',
help='generate proposals on the fly',
action='store_true',
default=True)
parser.add_argument('--proposal',
help='can be ss for selective search or rpn',
default='rpn',
type=str)
args = parser.parse_args()
return args
def parse_args():
parser = argparse.ArgumentParser(description='Test a Faster R-CNN network')
# general
parser.add_argument('--network',
help='network name',
default=default.network,
type=str)
parser.add_argument('--dataset',
help='dataset name',
default=default.dataset,
type=str)
args, rest = parser.parse_known_args()
generate_config(args.network, args.dataset)
parser.add_argument('--image_set',
help='image_set name',
default=default.test_image_set,
type=str)
parser.add_argument('--root_path',
help='output data folder',
default=default.root_path,
type=str)
parser.add_argument('--dataset_path',
help='dataset path',
default=default.dataset_path,
type=str)
# testing
parser.add_argument('--prefix',
help='model to test with',
default=default.e2e_prefix,
type=str)
parser.add_argument('--epoch',
help='model to test with',
default=0,
type=int)
parser.add_argument('--gpu',
help='GPU device to test with',
default=7,
type=int)
parser.add_argument('--output',
help='output folder',
default=os.path.join(default.root_path, 'output'),
type=str)
parser.add_argument('--pyramid',
help='enable pyramid test',
action='store_true')
# rcnn
parser.add_argument('--vis',
help='turn on visualization',
action='store_true')
parser.add_argument('--thresh',
help='valid detection threshold',
default=0.05,
type=float)
parser.add_argument('--shuffle',
help='shuffle data on visualization',
action='store_true')
parser.add_argument('--has_rpn',
help='generate proposals on the fly',
action='store_true',
default=True)
parser.add_argument('--proposal',
help='can be ss for selective search or rpn',
default='rpn',
type=str)
args = parser.parse_args()
return args
from rcnn.processing.nms import py_nms_wrapper, cpu_nms_wrapper, gpu_nms_wrapper
from tqdm import tqdm
import cPickle
import copy
os.environ['MXNET_BACKWARD_DO_MIRROR'] = '1'
os.environ['MXNET_CUDNN_AUTOTUNE_DEFAULT'] = '0'
epoch = 4
thresh = 0.05
symbol = "model/vgg"
network = "vgg"
dataset = "noaa_lions"
generate_config(network, dataset)
with open("/home/aakuzin/dataset/noaa_sealines/Val.txt") as f:
val = map(
lambda x: os.path.join(default.dataset_path, "images", x.strip()),
f.readlines())
ims = [cv2.imread(i) for i in val[:]]
def predict():
name = "{}/cache/{}_general_val_detections_val_{}.pkl".format(
default.dataset_path, network, epoch)
if os.path.exists(name):
with open(name, 'rb') as fid:
all_boxes = cPickle.load(fid)
else:
all_boxes = test_predict(network,
def parse_args():
parser = argparse.ArgumentParser(description='Test a Faster R-CNN network')
# general
parser.add_argument('--network',
help='network name',
default=default.network,
type=str)
parser.add_argument('--dataset',
help='dataset name',
default=default.dataset,
type=str)
args, rest = parser.parse_known_args()
generate_config(args.network, args.dataset)
parser.add_argument('--image_set',
help='image_set name',
default=default.test_image_set,
type=str)
parser.add_argument('--root_path',
help='output data folder',
default=default.root_path,
type=str)
parser.add_argument('--dataset_path',
help='dataset path',
default=default.dataset_path,
type=str)
# testing
parser.add_argument('--prefix',
help='model to test with',
default=default.e2e_prefix,
type=str)
parser.add_argument('--epoch',
help='model to test with',
default=default.e2e_epoch,
type=int)
parser.add_argument('--gpu',
help='GPU device to test with',
default=0,
type=int)
# rcnn
parser.add_argument('--vis',
help='turn on visualization',
action='store_true')
parser.add_argument('--thresh',
help='valid detection threshold',
default=1e-3,
type=float)
parser.add_argument('--shuffle',
help='shuffle data on visualization',
action='store_true')
parser.add_argument('--has_rpn',
help='generate proposals on the fly',
action='store_true',
default=True)
parser.add_argument('--proposal',
help='can be ss for selective search or rpn',
default='rpn',
type=str)
# tricks
parser.add_argument('--use_global_context',
help='use roi global context for classification',
action='store_true')
parser.add_argument('--use_roi_align',
help='replace ROIPooling with ROIAlign',
action='store_true')
parser.add_argument('--use_box_voting',
help='use box voting in test',
action='store_true')
# analysis
parser.add_argument(
'--detailed_analysis',
help=
'give detailed analysis result, e.g. APs in different scale ranges',
action='store_true')
args = parser.parse_args()
return args
