# Final test
print('Test with best model:')
checkpoint = load_checkpoint(osp.join(args.logs_dir, 'model_best.pth.tar'))
model.module.load_state_dict(checkpoint['state_dict'])
metric.train(model, train_loader)
evaluator.evaluate(test_loader, dataset.query, dataset.gallery, metric)
if __name__ == '__main__':
parser = argparse.ArgumentParser(description="Triplet loss classification")
# data
parser.add_argument('-d',
'--dataset',
type=str,
default='cuhk03',
choices=datasets.names())
parser.add_argument('-b', '--batch-size', type=int, default=256)
parser.add_argument('-j', '--workers', type=int, default=4)
parser.add_argument('--split', type=int, default=0)
parser.add_argument('--height',
type=int,
help="input height, default: 256 for resnet*, "
"144 for inception")
parser.add_argument('--width',
type=int,
help="input width, default: 128 for resnet*, "
"56 for inception")
parser.add_argument('--combine-trainval',
action='store_true',
help="train and val sets together for training, "
"val set alone for validation")
data_file.close()
if (args.clock):
exp_end = time.time()
exp_time = exp_end - exp_start
h, m, s = changetoHSM(exp_time)
print("experiment is over, cost %02d:%02d:%02.6f" % (h, m, s))
time_file.close()
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Snatch Strategy')
parser.add_argument('-d',
'--dataset',
type=str,
default='DukeMTMC-VideoReID',
choices=datasets.names()) #DukeMTMC-VideoReID
parser.add_argument('-b', '--batch-size', type=int, default=16)
parser.add_argument('--epoch', type=int, default=70)
parser.add_argument('--step_size', type=int, default=55)
parser.add_argument('--percent', type=float, default=0) # 第二次加进去的量
working_dir = os.path.dirname(os.path.abspath(__file__))
parser.add_argument('--data_dir',
type=str,
metavar='PATH',
default=os.path.join(working_dir, 'data')) # 加载数据集的根目录
parser.add_argument('--logs_dir',
type=str,
metavar='PATH',
default=os.path.join(working_dir, 'logs')) # 保持日志根目录
parser.add_argument('--exp_name', type=str, default="ero")
parser.add_argument('--exp_order', type=str, default="1")
def __init__(self):
self.parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
self.parser.add_argument('--stage',
type=int,
default=1,
help='training stage [1|2]')
self.parser.add_argument('-d',
'--dataset',
type=str,
default='market1501',
choices=datasets.names())
self.parser.add_argument('-t',
'--target',
type=str,
default='dukemtmc',
choices=datasets.names())
self.parser.add_argument('-s',
'--source',
type=str,
default='market1501',
choices=datasets.names())
# paths
self.parser.add_argument(
'--dataroot',
type=str,
default='./datasets/',
help=
'root path to datasets (should have subfolders market1501, dukemtmc, cuhk03, etc)'
)
self.parser.add_argument('--checkpoints',
type=str,
default='./checkpoints/',
help='root path to save models')
self.parser.add_argument('--name',
type=str,
default='FD-GAN',
help='directory to save models')
self.parser.add_argument(
'--netE-pretrain',
type=str,
default='pretrained model path for net_E in stage 2')
self.parser.add_argument(
'--netG-pretrain',
type=str,
default='pretrained model path for net_G in stage 2')
self.parser.add_argument(
'--tar-netG-pretrain',
type=str,
default='pretrained model path for net_G in stage 2')
self.parser.add_argument(
'--netDp-pretrain',
type=str,
default='pretrained model path for net_Dp in stage 2')
self.parser.add_argument(
'--tar-netDi-pretrain',
type=str,
default='pretrained model path for net_Di in stage 2')
self.parser.add_argument(
'--netDi-pretrain',
type=str,
default='pretrained model path for net_Di in stage 2')
# model structures
self.parser.add_argument('--arch',
type=str,
default='resnet50',
choices=models.names())
self.parser.add_argument(
'--norm',
type=str,
default='batch',
help='instance normalization or batch normalization')
self.parser.add_argument('--drop',
type=float,
default=0.2,
help='dropout for the netG')
self.parser.add_argument('--connect-layers',
type=int,
default=0,
help='skip connections num for netG')
self.parser.add_argument(
'--fuse-mode',
type=str,
default='cat',
help='method to fuse reid feature and pose feature [cat|add]')
self.parser.add_argument('--pose-feature-size',
type=int,
default=128,
help='length of feature vector for pose')
self.parser.add_argument('--noise-feature-size',
type=int,
default=256,
help='length of feature vector for noise')
self.parser.add_argument('--pose-aug',
type=str,
default='no',
help='posemap augmentation [no|erase|gauss]')
# dataloader setting
self.parser.add_argument('-b',
'--batch-size',
type=int,
default=16,
help='input batch size')
self.parser.add_argument('-j',
'--workers',
default=4,
type=int,
help='num threads for loading data')
self.parser.add_argument('--width',
type=int,
default=128,
help='input image width')
self.parser.add_argument('--height',
type=int,
default=256,
help='input image height')
# optimizer setting
self.parser.add_argument('--niter',
type=int,
default=50,
help='# of iter at starting learning rate')
self.parser.add_argument(
'--niter-decay',
type=int,
default=50,
help='# of iter to linearly decay learning rate to zero')
self.parser.add_argument('--lr',
type=float,
default=0.001,
help='initial learning rate')
self.parser.add_argument(
'--save-step',
type=int,
default=2,
help='frequency of saving checkpoints at the end of epochs')
self.parser.add_argument(
'--eval-step',
type=int,
default=10,
help='frequency of evaluate checkpoints at the end of epochs')
# visualization setting
self.parser.add_argument('--display-port',
type=int,
default=6006,
help='visdom port of the web display')
self.parser.add_argument(
'--display-id',
type=int,
default=1,
help='window id of the web display, set 0 for non-usage of visdom')
self.parser.add_argument('--display-winsize',
type=int,
default=256,
help='display window size')
self.parser.add_argument(
'--display-freq',
type=int,
default=10,
help='frequency of showing training results on screen')
self.parser.add_argument(
'--display-single-pane-ncols',
type=int,
default=0,
help=
'if positive, display all images in a single visdom web panel with certain number of images per row.'
)
self.parser.add_argument(
'--update-html-freq',
type=int,
default=100,
help='frequency of saving training results to html')
self.parser.add_argument(
'--no_html',
action='store_true',
help=
'do not save intermediate training results to [opt.checkpoints]/name/web/'
)
self.parser.add_argument(
'--print-freq',
type=int,
default=10,
help='frequency of showing training results on console')
# training schedule
self.parser.add_argument('--lambda-recon',
type=float,
default=1.0,
help='loss weight of loss_r')
self.parser.add_argument('--lambda-veri',
type=float,
default=1.0,
help='loss weight of loss_v')
self.parser.add_argument('--lambda-sp',
type=float,
default=1.0,
help='loss weight of loss_sp')
self.parser.add_argument('--lambda-mmd',
type=float,
default=1.0,
help='loss weight of loss_mmd')
self.parser.add_argument('--lambda-tri',
type=float,
default=10.0,
help='loss weight of loss_tri')
self.parser.add_argument('--smooth-label',
action='store_true',
help='smooth label or not for GANloss')
self.parser.add_argument('--tri-margin',
type=float,
default=0.5,
help='margin for Tripletloss')
self.opt = self.parser.parse_args()
self.show_opt()
criterion.load_state_dict(checkpoint['adapt_metric'])
# metric.train(model, train_loader)
# evaluator.evaluate(test_loader, dataset.query, dataset.gallery, metric)
if len(args.dataset) > 1:
for dataset_name in args.dataset:
print("{} test result:".format(dataset_name))
evaluator.evaluate(test_loader[dataset_name], dataset.query[dataset_name],
dataset.gallery[dataset_name])
else:
evaluator.evaluate(test_loader, dataset.query, dataset.gallery)
if __name__ == '__main__':
parser = argparse.ArgumentParser(description="Softmax loss classification")
# data
parser.add_argument('-d', '--dataset', nargs='+', default='market1501',
choices=datasets.names())
parser.add_argument('-b', '--batch-size', type=int, default=60)
parser.add_argument('-j', '--workers', type=int, default=4)
parser.add_argument('--split', type=int, default=0)
parser.add_argument('--height', type=int,
help="input height, default: 256 for resnet*, "
"144 for inception")
parser.add_argument('--width', type=int,
help="input width, default: 128 for resnet*, "
"56 for inception")
parser.add_argument('--combine-trainval', action='store_true',
help="train and val sets together for training, "
"val set alone for validation")
parser.add_argument('--num-instances', type=int, default=4,
help="each minibatch consist of "
"(batch_size // num_instances) identities, and "
def __init__(self):
self.parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter)
self.parser.add_argument('--stage', type=int, default=0, help='training stage [0|1|2](0 is end-to-end, 1 is train only resnet, and 2 is fintuning)')
self.parser.add_argument('-d', '--dataset', type=str, default='DanceReID', choices=datasets.names())
# paths
self.parser.add_argument('--dataroot', type=str, default='./datasets/', help='root path to datasets (should have subfolders market1501, dukemtmc, DanceReID, etc)')
self.parser.add_argument('--checkpoints', type=str, default='./checkpoints/', help='root path to save models')
self.parser.add_argument('--name', type=str, default='my_session', help='directory to save models')
self.parser.add_argument('--netE-pretrain', type=str, default='', help='pretrained model path for net_E in stage 2')
self.parser.add_argument('--netG-pretrain', type=str, default='', help='pretrained model path for net_G in stage 2')
self.parser.add_argument('--netDp-pretrain', type=str, default='', help='pretrained model path for net_Dp in stage 2')
self.parser.add_argument('--netDi-pretrain', type=str, default='', help='pretrained model path for net_Di in stage 2')
# model structures
self.parser.add_argument('--arch', type=str, default='resnet50', help='basemodeltype')
self.parser.add_argument('--norm', type=str, default='batch', help='instance normalization or batch normalization')
self.parser.add_argument('--drop', type=float, default=0.2, help='dropout for the netG')
self.parser.add_argument('--connect-layers', type=int, default=0, help='skip connections num for netG')
self.parser.add_argument('--fuse-mode', type=str, default='cat', help='method to fuse reid feature and pose feature [cat|add]')
self.parser.add_argument('--pose-feature-size', type=int, default=128, help='length of feature vector for pose')
self.parser.add_argument('--noise-feature-size', type=int, default=256, help='length of feature vector for noise')
self.parser.add_argument('--pose-aug', type=str, default='no', help='posemap augmentation [no|erase|gauss]')
# dataloader setting
self.parser.add_argument('-b', '--batch-size', type=int, default=16, help='input batch size')
self.parser.add_argument('-j', '--workers', default=4, type=int, help='num threads for loading data')
self.parser.add_argument('--width', type=int, default=128, help='input image width')
self.parser.add_argument('--height', type=int, default=256, help='input image height')
self.parser.add_argument('--skip-frame', type=int, default=20, help='ST-sampling skipping frames')
self.parser.add_argument('--inter-rate', type=float, default=0.7, help='probability to sample same video (ST-sampling)')
# optimizer setting
self.parser.add_argument('--niter', type=int, default=50, help='# of iter at starting learning rate')
self.parser.add_argument('--niter-decay', type=int, default=50, help='# of iter to linearly decay learning rate to zero')
self.parser.add_argument('--lr', type=float, default=0.001, help='initial learning rate')
self.parser.add_argument('--save-step', type=int, default=20, help='frequency of saving checkpoints at the end of epochs')
self.parser.add_argument('--eval-step', type=int, default=5, help='frequency of evaluate checkpoints at the end of epochs')
# visualization setting
self.parser.add_argument('--display-port', type=int, default=6006, help='visdom port of the web display')
self.parser.add_argument('--display-id', type=int, default=1, help='window id of the web display, set 0 for non-usage of visdom')
self.parser.add_argument('--display-winsize', type=int, default=256, help='display window size')
self.parser.add_argument('--display-freq', type=int, default=10, help='frequency of showing training results on screen')
self.parser.add_argument('--display-single-pane-ncols', type=int, default=0, help='if positive, display all images in a single visdom web panel with certain number of images per row.')
self.parser.add_argument('--update-html-freq', type=int, default=100, help='frequency of saving training results to html')
self.parser.add_argument('--no_html', action='store_true', help='do not save intermediate training results to [opt.checkpoints]/name/web/')
self.parser.add_argument('--print-freq', type=int, default=10, help='frequency of showing training results on console')
# training
self.parser.add_argument('--lambda-dp', type=float, default=1.0, help='weight of Dp')
self.parser.add_argument('--lambda-d', type=float, default=1.0, help='weight of D')
self.parser.add_argument('--lambda-recon', type=float, default=1.0, help='loss weight of reconstruction')
self.parser.add_argument('--lambda-tri', type=float, default=1.0, help='loss weight of triplet loss')
self.parser.add_argument('--lambda-class', type=float, default=1.0, help='loss weight of classification')
self.parser.add_argument('--smooth-label', action='store_true', help='smooth label or not for GANloss')
self.parser.add_argument('--margin', type=float, default=1.0, help='margin for triplet loss')
self.parser.add_argument('--soft-margin', action='store_true', help='use soft margin for triplet loss')
self.parser.add_argument('--batch-hard', action='store_true', help='batch hard mining for tri-loss')
self.parser.add_argument('--emb-type', type=str, default='Single', help='ReID embedding model type [Single|Siamese]')
# apply training tricks
self.parser.add_argument('--mask', action='store_true', help='use pose mask for human reconstruction or not')
self.parser.add_argument('--eraser', action='store_true', help='use random eraser during training')
self.parser.add_argument('--emb-smooth', action='store_true', help='use label smoothing for computing classification loss')
self.parser.add_argument('--last-stride', type=int, default=2, help='resnet50 last stride')
self.parser.add_argument('--seed', type=int, default=1)
self.opt = self.parser.parse_args()
self.show_opt()
def main(args):
cudnn.deterministic = False
cudnn.benchmark = True
exp_database_dir = osp.join(args.exp_dir, string.capwords(args.dataset))
output_dir = osp.join(exp_database_dir, args.method, args.sub_method)
log_file = osp.join(output_dir, 'log.txt')
# Redirect print to both console and log file
sys.stdout = Logger(log_file)
# Create model
ibn_type = args.ibn
if ibn_type == 'none':
ibn_type = None
model = resmap.create(args.arch,
ibn_type=ibn_type,
final_layer=args.final_layer,
neck=args.neck).cuda()
num_features = model.num_features
# print(model)
# print('\n')
feamap_factor = {'layer2': 8, 'layer3': 16, 'layer4': 32}
hei = args.height // feamap_factor[args.final_layer]
wid = args.width // feamap_factor[args.final_layer]
matcher = QAConv(num_features, hei, wid).cuda()
for arg in sys.argv:
print('%s ' % arg, end='')
print('\n')
# Criterion
criterion = TripletLoss(matcher, args.margin).cuda()
# Optimizer
base_param_ids = set(map(id, model.base.parameters()))
new_params = [p for p in model.parameters() if id(p) not in base_param_ids]
param_groups = [{
'params': model.base.parameters(),
'lr': 0.1 * args.lr
}, {
'params': new_params,
'lr': args.lr
}, {
'params': matcher.parameters(),
'lr': args.lr
}]
optimizer = torch.optim.SGD(param_groups,
lr=args.lr,
momentum=0.9,
weight_decay=5e-4,
nesterov=True)
# Load from checkpoint
start_epoch = 0
base_loss = None
final_epochs = args.max_epochs
lr_stepped = False
if args.resume or args.evaluate:
print('Loading checkpoint...')
if args.resume and (args.resume != 'ori'):
checkpoint = load_checkpoint(args.resume)
else:
checkpoint = load_checkpoint(
osp.join(output_dir, 'checkpoint.pth.tar'))
model.load_state_dict(checkpoint['model'])
criterion.load_state_dict(checkpoint['criterion'])
optimizer.load_state_dict(checkpoint['optim'])
start_epoch = checkpoint['epoch']
base_loss = checkpoint['base_loss']
final_epochs = checkpoint['final_epochs']
lr_stepped = checkpoint['lr_stepped']
if lr_stepped:
print('Decay the learning rate by a factor of 0.1.')
for group in optimizer.param_groups:
group['lr'] *= 0.1
print("=> Start epoch {} ".format(start_epoch))
model = nn.DataParallel(model).cuda()
# Create data loaders
save_path = None
if args.gs_save:
save_path = output_dir
dataset, num_classes, train_loader, _, _ = get_data(
args.dataset, args.data_dir, model, matcher, save_path, args)
if not args.evaluate:
# Trainer
trainer = Trainer(model, criterion, args.clip_value)
t0 = time.time()
# Start training
for epoch in range(start_epoch, args.max_epochs):
loss, acc = trainer.train(epoch, train_loader, optimizer)
if epoch == 1:
base_loss = loss
lr = list(map(lambda group: group['lr'], optimizer.param_groups))
train_time = time.time() - t0
epoch1 = epoch + 1
print(
'* Finished epoch %d at lr=[%g, %g, %g]. Loss: %.3f. Acc: %.2f%%. Training time: %.0f seconds. \n'
% (epoch1, lr[0], lr[1], lr[2], loss, acc * 100, train_time))
if (not lr_stepped) and (base_loss is not None) and (
loss < base_loss * args.step_factor):
lr_stepped = True
final_epochs = min(args.max_epochs, epoch1 + epoch1 // 2)
print(
'Decay the learning rate by a factor of 0.1. Final epochs: %d.\n'
% final_epochs)
for group in optimizer.param_groups:
group['lr'] *= 0.1
save_checkpoint(
{
'model': model.module.state_dict(),
'criterion': criterion.state_dict(),
'optim': optimizer.state_dict(),
'epoch': epoch1,
'final_epochs': final_epochs,
'base_loss': base_loss,
'lr_stepped': lr_stepped,
},
fpath=osp.join(output_dir, 'checkpoint.pth.tar'))
if epoch1 == final_epochs:
print('The learning converges at epoch %d.\n' % epoch1)
break
json_file = osp.join(output_dir, 'results.json')
if not args.evaluate:
arg_dict = {
'train_dataset': args.dataset,
'exp_dir': args.exp_dir,
'method': args.method,
'sub_method': args.sub_method
}
with open(json_file, 'a') as f:
json.dump(arg_dict, f)
f.write('\n')
train_dict = {
'train_dataset': args.dataset,
'loss': loss,
'acc': acc,
'epochs': epoch1,
'train_time': train_time
}
with open(json_file, 'a') as f:
json.dump(train_dict, f)
f.write('\n')
# Final test
print('Evaluate the learned model:')
t0 = time.time()
# Evaluator
evaluator = Evaluator(model)
test_names = args.testset.strip().split(',')
for test_name in test_names:
if test_name not in datasets.names():
print('Unknown dataset: %s.' % test_name)
continue
t1 = time.time()
testset, test_query_loader, test_gallery_loader = \
get_test_data(test_name, args.data_dir, args.height, args.width, args.workers, args.test_fea_batch)
if not args.do_tlift:
testset.has_time_info = False
test_rank1, test_mAP, test_rank1_rerank, test_mAP_rerank, test_rank1_tlift, test_mAP_tlift, test_dist, \
test_dist_rerank, test_dist_tlift, pre_tlift_dict = \
evaluator.evaluate(matcher, testset, test_query_loader, test_gallery_loader,
args.test_gal_batch, args.test_prob_batch,
args.tau, args.sigma, args.K, args.alpha)
test_time = time.time() - t1
if testset.has_time_info:
test_dict = {
'test_dataset': test_name,
'rank1': test_rank1,
'mAP': test_mAP,
'rank1_rerank': test_rank1_rerank,
'mAP_rerank': test_mAP_rerank,
'rank1_tlift': test_rank1_tlift,
'mAP_tlift': test_mAP_tlift,
'test_time': test_time
}
print(
' %s: rank1=%.1f, mAP=%.1f, rank1_rerank=%.1f, mAP_rerank=%.1f,'
' rank1_rerank_tlift=%.1f, mAP_rerank_tlift=%.1f.\n' %
(test_name, test_rank1 * 100, test_mAP * 100,
test_rank1_rerank * 100, test_mAP_rerank * 100,
test_rank1_tlift * 100, test_mAP_tlift * 100))
else:
test_dict = {
'test_dataset': test_name,
'rank1': test_rank1,
'mAP': test_mAP,
'test_time': test_time
}
print(' %s: rank1=%.1f, mAP=%.1f.\n' %
(test_name, test_rank1 * 100, test_mAP * 100))
with open(json_file, 'a') as f:
json.dump(test_dict, f)
f.write('\n')
if args.save_score:
test_gal_list = np.array(
[fname for fname, _, _, _ in testset.gallery], dtype=np.object)
test_prob_list = np.array(
[fname for fname, _, _, _ in testset.query], dtype=np.object)
test_gal_ids = [pid for _, pid, _, _ in testset.gallery]
test_prob_ids = [pid for _, pid, _, _ in testset.query]
test_gal_cams = [c for _, _, c, _ in testset.gallery]
test_prob_cams = [c for _, _, c, _ in testset.query]
test_score_file = osp.join(exp_database_dir, args.method,
args.sub_method,
'%s_score.mat' % test_name)
sio.savemat(test_score_file, {
'score': 1. - test_dist,
'score_rerank': 1. - test_dist_rerank,
'score_tlift': 1. - test_dist_tlift,
'gal_time': pre_tlift_dict['gal_time'],
'prob_time': pre_tlift_dict['prob_time'],
'gal_list': test_gal_list,
'prob_list': test_prob_list,
'gal_ids': test_gal_ids,
'prob_ids': test_prob_ids,
'gal_cams': test_gal_cams,
'prob_cams': test_prob_cams
},
oned_as='column',
do_compression=True)
test_time = time.time() - t0
if not args.evaluate:
print('Finished training at epoch %d, loss = %.3f, acc = %.2f%%.\n' %
(epoch1, loss, acc * 100))
print(
"Total training time: %.3f sec. Average training time per epoch: %.3f sec."
% (train_time, train_time / (epoch1 - start_epoch)))
print("Total testing time: %.3f sec.\n" % test_time)
for arg in sys.argv:
print('%s ' % arg, end='')
print('\n')
nums_to_select = new_nums_to_select
step = step + 1
data_file.close()
if (args.clock):
exp_end = time.time()
exp_time = exp_end - exp_start
h, m, s = changetoHSM(exp_time)
print("experiment is over, cost %02d:%02d:%02.6f" % ( h, m, s))
time_file.close()
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Snatch Strategy')
parser.add_argument('-d', '--dataset', type=str, default='DukeMTMC-VideoReID',choices=datasets.names()) #s
parser.add_argument('-b', '--batch-size', type=int, default=16)
parser.add_argument('--epoch',type=int,default=70)
parser.add_argument('--step_size',type=int,default=55)
parser.add_argument('--EF', type=float, default=5) # 渐进采样系数
parser.add_argument('--q', type=float, default=1) # 渐进采样指数
parser.add_argument('--yita', type=int, default=100) #big start based number
parser.add_argument('--step_s', type=int, default=10) #big start 饱和度控制
working_dir = os.path.dirname(os.path.abspath(__file__))
parser.add_argument('--data_dir', type=str, metavar='PATH',default=os.path.join(working_dir, 'data')) # 加载数据集的根目录
parser.add_argument('--logs_dir', type=str, metavar='PATH',default=os.path.join(working_dir, 'logs')) # 保持日志根目录
parser.add_argument('--exp_name',type=str,default="gradully_supplement")
parser.add_argument('--exp_order',type=str,default="1")
parser.add_argument('--resume', type=bool, default=True)
parser.add_argument('--mode', type=str, choices=["Classification", "Dissimilarity"], default="Dissimilarity") #这个考虑要不要取消掉
parser.add_argument('--max_frames', type=int, default=100)
def main(args):
cudnn.deterministic = False
cudnn.benchmark = True
exp_database_dir = osp.join(args.exp_dir, string.capwords(args.dataset))
output_dir = osp.join(exp_database_dir, args.method, args.sub_method)
log_file = osp.join(output_dir, 'log.txt')
# Redirect print to both console and log file
sys.stdout = Logger(log_file)
# Create data loaders
dataset, num_classes, train_loader, query_loader, gallery_loader = \
get_data(args.dataset, args.data_dir, args.height, args.width, args.batch_size, args.combine_all,
args.min_size, args.max_size, args.workers, args.test_fea_batch)
# Create model
model = resmap.create(args.arch,
final_layer=args.final_layer,
neck=args.neck).cuda()
num_features = model.num_features
# print(model)
print('\n')
for arg in sys.argv:
print('%s ' % arg, end='')
print('\n')
# Criterion
feamap_factor = {'layer2': 8, 'layer3': 16, 'layer4': 32}
hei = args.height // feamap_factor[args.final_layer]
wid = args.width // feamap_factor[args.final_layer]
criterion = QAConvLoss(num_classes, num_features, hei, wid,
args.mem_batch_size).cuda()
# Optimizer
base_param_ids = set(map(id, model.base.parameters()))
new_params = [p for p in model.parameters() if id(p) not in base_param_ids]
param_groups = [{
'params': model.base.parameters(),
'lr': 0.1 * args.lr
}, {
'params': new_params,
'lr': args.lr
}, {
'params': criterion.parameters(),
'lr': args.lr
}]
optimizer = torch.optim.SGD(param_groups,
lr=args.lr,
momentum=0.9,
weight_decay=5e-4,
nesterov=True)
# Decay LR by a factor of 0.1 every step_size epochs
lr_scheduler = StepLR(optimizer, step_size=args.step_size, gamma=0.1)
# Load from checkpoint
start_epoch = 0
if args.resume or args.evaluate:
print('Loading checkpoint...')
if args.resume and (args.resume != 'ori'):
checkpoint = load_checkpoint(args.resume)
else:
checkpoint = load_checkpoint(
osp.join(output_dir, 'checkpoint.pth.tar'))
model.load_state_dict(checkpoint['model'])
criterion.load_state_dict(checkpoint['criterion'])
optimizer.load_state_dict(checkpoint['optim'])
start_epoch = checkpoint['epoch']
print("=> Start epoch {} ".format(start_epoch))
model = nn.DataParallel(model).cuda()
criterion = nn.DataParallel(criterion).cuda()
if not args.evaluate:
# Trainer
trainer = Trainer(model, criterion)
t0 = time.time()
# Start training
for epoch in range(start_epoch, args.epochs):
loss, acc = trainer.train(epoch, train_loader, optimizer)
lr = list(map(lambda group: group['lr'], optimizer.param_groups))
lr_scheduler.step(epoch + 1)
train_time = time.time() - t0
print(
'* Finished epoch %d at lr=[%g, %g, %g]. Loss: %.3f. Acc: %.2f%%. Training time: %.0f seconds.\n'
%
(epoch + 1, lr[0], lr[1], lr[2], loss, acc * 100, train_time))
save_checkpoint(
{
'model': model.module.state_dict(),
'criterion': criterion.module.state_dict(),
'optim': optimizer.state_dict(),
'epoch': epoch + 1,
},
fpath=osp.join(output_dir, 'checkpoint.pth.tar'))
# Final test
print('Evaluate the learned model:')
t0 = time.time()
# Evaluator
evaluator = Evaluator(model)
test_names = args.testset.strip().split(',')
for test_name in test_names:
if test_name not in datasets.names():
print('Unknown dataset: %s.' % test_name)
continue
testset, test_query_loader, test_gallery_loader = \
get_test_data(test_name, args.data_dir, args.height, args.width, args.test_fea_batch)
test_rank1, test_mAP, test_rank1_rerank, test_mAP_rerank, test_rank1_tlift, test_mAP_tlift, test_dist, \
test_dist_rerank, test_dist_tlift, pre_tlift_dict = \
evaluator.evaluate(test_query_loader, test_gallery_loader, testset, criterion.module,
args.test_gal_batch, args.test_prob_batch,
args.tau, args.sigma, args.K, args.alpha)
print(' %s: rank1=%.1f, mAP=%.1f, rank1_rerank=%.1f, mAP_rerank=%.1f,'
' rank1_rerank_tlift=%.1f, mAP_rerank_tlift=%.1f.\n' %
(test_name, test_rank1 * 100, test_mAP * 100,
test_rank1_rerank * 100, test_mAP_rerank * 100,
test_rank1_tlift * 100, test_mAP_tlift * 100))
result_file = osp.join(exp_database_dir, args.method,
test_name + '_results.txt')
with open(result_file, 'a') as f:
f.write('%s/%s:\n' % (args.method, args.sub_method))
f.write(
'\t%s: rank1=%.1f, mAP=%.1f, rank1_rerank=%.1f, mAP_rerank=%.1f, rank1_rerank_tlift=%.1f, '
'mAP_rerank_tlift=%.1f.\n\n' %
(test_name, test_rank1 * 100, test_mAP * 100,
test_rank1_rerank * 100, test_mAP_rerank * 100,
test_rank1_tlift * 100, test_mAP_tlift * 100))
if args.save_score:
test_gal_list = np.array(
[fname for fname, _, _, _ in testset.gallery], dtype=np.object)
test_prob_list = np.array(
[fname for fname, _, _, _ in testset.query], dtype=np.object)
test_gal_ids = [pid for _, pid, _, _ in testset.gallery]
test_prob_ids = [pid for _, pid, _, _ in testset.query]
test_gal_cams = [c for _, _, c, _ in testset.gallery]
test_prob_cams = [c for _, _, c, _ in testset.query]
test_score_file = osp.join(exp_database_dir, args.method,
args.sub_method,
'%s_score.mat' % test_name)
sio.savemat(test_score_file, {
'score': 1. - test_dist,
'score_rerank': 1. - test_dist_rerank,
'score_tlift': 1. - test_dist_tlift,
'gal_time': pre_tlift_dict['gal_time'],
'prob_time': pre_tlift_dict['prob_time'],
'gal_list': test_gal_list,
'prob_list': test_prob_list,
'gal_ids': test_gal_ids,
'prob_ids': test_prob_ids,
'gal_cams': test_gal_cams,
'prob_cams': test_prob_cams
},
oned_as='column',
do_compression=True)
test_time = time.time() - t0
if not args.evaluate:
print('Finished training at epoch %d, loss %.3f, acc %.2f%%.\n' %
(epoch + 1, loss, acc * 100))
print(
"Total training time: %.3f sec. Average training time per epoch: %.3f sec."
% (train_time, train_time / (args.epochs - start_epoch + 1)))
print("Total testing time: %.3f sec.\n" % test_time)
for arg in sys.argv:
print('%s ' % arg, end='')
print('\n')
def main(args):
cudnn.deterministic = False
cudnn.benchmark = True
exp_database_dir = osp.join(args.exp_dir, string.capwords(args.dataset))
output_dir = osp.join(exp_database_dir, args.method, args.sub_method)
log_file = osp.join(output_dir, 'log.txt')
# Redirect print to both console and log file
sys.stdout = Logger(log_file)
# Create data loaders
dataset, num_classes, train_loader, _, _ = \
get_data(args.dataset, args.data_dir, args.height, args.width, args.batch_size, args.combine_all,
args.workers, args.test_fea_batch)
# Create model
#model = seTest.resnst50().cuda()
model = resmap.create(args.arch,
ibn_type=args.ibn,
final_layer=args.final_layer,
neck=args.neck).cuda()
num_features = model.num_features
#num_features = 64
# print(model)
# print('\n')
feamap_factor = {'layer2': 8, 'layer3': 16, 'layer4': 32}
hei = args.height // feamap_factor[args.final_layer]
wid = args.width // feamap_factor[args.final_layer]
matcher = QAConv(num_features, hei, wid).cuda()
for arg in sys.argv:
print('%s ' % arg, end='')
print('\n')
# Criterion
criterion = ClassMemoryLoss(matcher, num_classes, num_features, hei, wid,
args.mem_batch_size).cuda()
# Optimizer
base_param_ids = set(map(id, model.base.parameters()))
new_params = [p for p in model.parameters() if id(p) not in base_param_ids]
param_groups = [{
'params': model.base.parameters(),
'lr': 0.1 * args.lr
}, {
'params': new_params,
'lr': args.lr
}, {
'params': criterion.parameters(),
'lr': args.lr
}]
optimizer = torch.optim.SGD(param_groups,
lr=args.lr,
momentum=0.9,
weight_decay=5e-4,
nesterov=True)
# Load from checkpoint
start_epoch = 0
if args.resume or args.evaluate:
print('Loading checkpoint...')
if args.resume and (args.resume != 'ori'):
checkpoint = load_checkpoint(args.resume)
else:
checkpoint = load_checkpoint(
osp.join(output_dir, 'checkpoint.pth.tar'))
model.load_state_dict(checkpoint['model'])
criterion.load_state_dict(checkpoint['criterion'])
optimizer.load_state_dict(checkpoint['optim'])
start_epoch = checkpoint['epoch']
print("=> Start epoch {} ".format(start_epoch))
elif args.pre_epochs > 0:
pre_tr = PreTrainer(model, criterion, optimizer, train_loader,
args.pre_epochs, args.max_steps, args.num_trials)
result_file = osp.join(exp_database_dir, args.method,
'pretrain_metric.txt')
model, criterion, optimizer = pre_tr.train(result_file, args.method,
args.sub_method)
# Decay LR by a factor of 0.1 every step_size epochs
lr_scheduler = StepLR(optimizer,
step_size=args.step_size,
gamma=0.1,
last_epoch=start_epoch - 1)
model = nn.DataParallel(model).cuda()
criterion = nn.DataParallel(criterion).cuda()
enhance_data_aug = False
if not args.evaluate:
# Trainer
trainer = Trainer(model, criterion)
t0 = time.time()
# Start training
for epoch in range(start_epoch, args.epochs):
loss, acc = trainer.train(epoch, train_loader, optimizer)
lr = list(map(lambda group: group['lr'], optimizer.param_groups))
lr_scheduler.step()
train_time = time.time() - t0
print(
'* Finished epoch %d at lr=[%g, %g, %g]. Loss: %.3f. Acc: %.2f%%. Training time: %.0f seconds. \n'
%
(epoch + 1, lr[0], lr[1], lr[2], loss, acc * 100, train_time))
save_checkpoint(
{
'model': model.module.state_dict(),
'criterion': criterion.module.state_dict(),
'optim': optimizer.state_dict(),
'epoch': epoch + 1,
},
fpath=osp.join(output_dir, 'checkpoint.pth.tar'))
if not enhance_data_aug and epoch < args.epochs - 1 and acc > args.acc_thr:
enhance_data_aug = True
print('\nAcc = %.2f%% > %.2f%%. Start to Flip and Block.\n' %
(acc * 100, args.acc_thr * 100))
train_transformer = T.Compose([
T.Resize((args.height, args.width), interpolation=3),
T.Pad(10),
T.RandomCrop((args.height, args.width)),
T.RandomHorizontalFlip(0.5),
T.RandomRotation(5),
T.ColorJitter(brightness=(0.5, 2.0),
contrast=(0.5, 2.0),
saturation=(0.5, 2.0),
hue=(-0.1, 0.1)),
T.RandomOcclusion(args.min_size, args.max_size),
T.ToTensor(),
])
train_loader = DataLoader(Preprocessor(
dataset.train,
root=osp.join(dataset.images_dir, dataset.train_path),
transform=train_transformer),
batch_size=args.batch_size,
num_workers=args.workers,
shuffle=True,
pin_memory=True,
drop_last=True)
# Final test
print('Evaluate the learned model:')
t0 = time.time()
# Evaluator
evaluator = Evaluator(model)
avg_rank1 = 0
avg_mAP = 0
num_testsets = 0
results = {}
test_names = args.testset.strip().split(',')
for test_name in test_names:
if test_name not in datasets.names():
print('Unknown dataset: %s.' % test_name)
continue
testset, test_query_loader, test_gallery_loader = \
get_test_data(test_name, args.data_dir, args.height, args.width, args.workers, args.test_fea_batch)
if not args.do_tlift:
testset.has_time_info = False
test_rank1, test_mAP, test_rank1_rerank, test_mAP_rerank, test_rank1_tlift, test_mAP_tlift, test_dist, \
test_dist_rerank, test_dist_tlift, pre_tlift_dict = \
evaluator.evaluate(matcher, testset, test_query_loader, test_gallery_loader,
args.test_gal_batch, args.test_prob_batch,
args.tau, args.sigma, args.K, args.alpha)
results[test_name] = [test_rank1, test_mAP]
if test_name != args.dataset:
avg_rank1 += test_rank1
avg_mAP += test_mAP
num_testsets += 1
if testset.has_time_info:
print(
' %s: rank1=%.1f, mAP=%.1f, rank1_rerank=%.1f, mAP_rerank=%.1f,'
' rank1_rerank_tlift=%.1f, mAP_rerank_tlift=%.1f.\n' %
(test_name, test_rank1 * 100, test_mAP * 100,
test_rank1_rerank * 100, test_mAP_rerank * 100,
test_rank1_tlift * 100, test_mAP_tlift * 100))
else:
print(' %s: rank1=%.1f, mAP=%.1f.\n' %
(test_name, test_rank1 * 100, test_mAP * 100))
result_file = osp.join(exp_database_dir, args.method,
test_name + '_results.txt')
with open(result_file, 'a') as f:
f.write('%s/%s:\n' % (args.method, args.sub_method))
if testset.has_time_info:
f.write(
'\t%s: rank1=%.1f, mAP=%.1f, rank1_rerank=%.1f, mAP_rerank=%.1f, rank1_rerank_tlift=%.1f, '
'mAP_rerank_tlift=%.1f.\n\n' %
(test_name, test_rank1 * 100, test_mAP * 100,
test_rank1_rerank * 100, test_mAP_rerank * 100,
test_rank1_tlift * 100, test_mAP_tlift * 100))
else:
f.write('\t%s: rank1=%.1f, mAP=%.1f.\n\n' %
(test_name, test_rank1 * 100, test_mAP * 100))
if args.save_score:
test_gal_list = np.array(
[fname for fname, _, _, _ in testset.gallery], dtype=np.object)
test_prob_list = np.array(
[fname for fname, _, _, _ in testset.query], dtype=np.object)
test_gal_ids = [pid for _, pid, _, _ in testset.gallery]
test_prob_ids = [pid for _, pid, _, _ in testset.query]
test_gal_cams = [c for _, _, c, _ in testset.gallery]
test_prob_cams = [c for _, _, c, _ in testset.query]
test_score_file = osp.join(exp_database_dir, args.method,
args.sub_method,
'%s_score.mat' % test_name)
sio.savemat(test_score_file, {
'score': 1. - test_dist,
'score_rerank': 1. - test_dist_rerank,
'score_tlift': 1. - test_dist_tlift,
'gal_time': pre_tlift_dict['gal_time'],
'prob_time': pre_tlift_dict['prob_time'],
'gal_list': test_gal_list,
'prob_list': test_prob_list,
'gal_ids': test_gal_ids,
'prob_ids': test_prob_ids,
'gal_cams': test_gal_cams,
'prob_cams': test_prob_cams
},
oned_as='column',
do_compression=True)
test_time = time.time() - t0
avg_rank1 /= num_testsets
avg_mAP /= num_testsets
for key in results.keys():
print('%s: rank1=%.1f%%, mAP=%.1f%%.' %
(key, results[key][0] * 100, results[key][1] * 100))
print('Average: rank1=%.2f%%, mAP=%.2f%%.\n\n' %
(avg_rank1 * 100, avg_mAP * 100))
result_file = osp.join(exp_database_dir, args.method,
args.sub_method[:-5] + '_avg_results.txt')
with open(result_file, 'a') as f:
f.write('%s/%s:\n' % (args.method, args.sub_method))
if not args.evaluate:
f.write('\t Loss: %.3f, acc: %.2f%%. ' % (loss, acc * 100))
f.write("Train: %.0fs. " % train_time)
f.write("Test: %.0fs. " % test_time)
f.write('Rank1: %.2f%%, mAP: %.2f%%.\n' %
(avg_rank1 * 100, avg_mAP * 100))
for key in results.keys():
f.write('\t %s: Rank1: %.1f%%, mAP: %.1f%%.\n' %
(key, results[key][0] * 100, results[key][1] * 100))
f.write('\n')
if not args.evaluate:
print('Finished training at epoch %d, loss = %.3f, acc = %.2f%%.\n' %
(epoch + 1, loss, acc * 100))
print(
"Total training time: %.3f sec. Average training time per epoch: %.3f sec."
% (train_time, train_time / (args.epochs - start_epoch + 1)))
print("Total testing time: %.3f sec.\n" % test_time)
for arg in sys.argv:
print('%s ' % arg, end='')
print('\n')
def main(args):
cudnn.deterministic = False
cudnn.benchmark = True
exp_database_dir = osp.join(args.exp_dir, string.capwords(args.dataset))
output_dir = osp.join(exp_database_dir, args.method, args.sub_method)
log_file = osp.join(output_dir, 'log.txt')
# Redirect print to both console and log file
sys.stdout = Logger(log_file)
# Create model
ibn_type = args.ibn
if ibn_type == 'none':
ibn_type = None
model = resmap.create(args.arch,
ibn_type=ibn_type,
final_layer=args.final_layer,
neck=args.neck).cuda()
num_features = model.num_features
# print(model)
# print('\n')
feamap_factor = {'layer2': 8, 'layer3': 16, 'layer4': 32}
hei = args.height // feamap_factor[args.final_layer]
wid = args.width // feamap_factor[args.final_layer]
matcher = QAConv(num_features, hei, wid).cuda()
for arg in sys.argv:
print('%s ' % arg, end='')
print('\n')
# Criterion
criterion = PairwiseMatchingLoss(matcher).cuda()
# Optimizer
base_param_ids = set(map(id, model.base.parameters()))
new_params = [p for p in model.parameters() if id(p) not in base_param_ids]
param_groups = [{
'params': model.base.parameters(),
'lr': 0.1 * args.lr
}, {
'params': new_params,
'lr': args.lr
}, {
'params': matcher.parameters(),
'lr': args.lr
}]
optimizer = torch.optim.SGD(param_groups,
lr=args.lr,
momentum=0.9,
weight_decay=5e-4,
nesterov=True)
# Load from checkpoint
start_epoch = 0
if args.resume or args.evaluate:
print('Loading checkpoint...')
if args.resume and (args.resume != 'ori'):
checkpoint = load_checkpoint(args.resume)
else:
checkpoint = load_checkpoint(
osp.join(output_dir, 'checkpoint.pth.tar'))
model.load_state_dict(checkpoint['model'])
criterion.load_state_dict(checkpoint['criterion'])
optimizer.load_state_dict(checkpoint['optim'])
start_epoch = checkpoint['epoch']
print("=> Start epoch {} ".format(start_epoch))
model = nn.DataParallel(model).cuda()
# Create data loaders
# Warning: this training data loader cannot be used elsewhere other than a continueous training, otherwise the
# switch between the PK sampler and GS sampler will be incorrect!
save_path = None
if args.gs_save:
save_path = output_dir
dataset, num_classes, train_loader, _, _ = get_data(
args.dataset, args.data_dir, model, matcher, start_epoch - 1,
save_path, args)
# Decay LR by a factor of 0.1 every step_size epochs
lr_scheduler = StepLR(optimizer,
step_size=args.step_size,
gamma=0.1,
last_epoch=start_epoch - 1)
if not args.evaluate:
# Trainer
trainer = Trainer(model, criterion, args.clip_value)
t0 = time.time()
# Start training
for epoch in range(start_epoch, args.epochs):
loss, acc = trainer.train(epoch, train_loader, optimizer)
lr = list(map(lambda group: group['lr'], optimizer.param_groups))
lr_scheduler.step()
train_time = time.time() - t0
print(
'* Finished epoch %d at lr=[%g, %g, %g]. Loss: %.3f. Acc: %.2f%%. Training time: %.0f seconds. \n'
%
(epoch + 1, lr[0], lr[1], lr[2], loss, acc * 100, train_time))
save_checkpoint(
{
'model': model.module.state_dict(),
'criterion': criterion.state_dict(),
'optim': optimizer.state_dict(),
'epoch': epoch + 1,
},
fpath=osp.join(output_dir, 'checkpoint.pth.tar'))
# Final test
print('Evaluate the learned model:')
t0 = time.time()
# Evaluator
evaluator = Evaluator(model)
avg_rank1 = 0
avg_mAP = 0
num_testsets = 0
results = {}
test_names = args.testset.strip().split(',')
for test_name in test_names:
if test_name not in datasets.names():
print('Unknown dataset: %s.' % test_name)
continue
testset, test_query_loader, test_gallery_loader = \
get_test_data(test_name, args.data_dir, args.height, args.width, args.workers, args.test_fea_batch)
if not args.do_tlift:
testset.has_time_info = False
test_rank1, test_mAP, test_rank1_rerank, test_mAP_rerank, test_rank1_tlift, test_mAP_tlift, test_dist, \
test_dist_rerank, test_dist_tlift, pre_tlift_dict = \
evaluator.evaluate(matcher, testset, test_query_loader, test_gallery_loader,
args.test_gal_batch, args.test_prob_batch,
args.tau, args.sigma, args.K, args.alpha)
results[test_name] = [test_rank1, test_mAP]
if test_name != args.dataset:
avg_rank1 += test_rank1
avg_mAP += test_mAP
num_testsets += 1
if testset.has_time_info:
print(
' %s: rank1=%.1f, mAP=%.1f, rank1_rerank=%.1f, mAP_rerank=%.1f,'
' rank1_rerank_tlift=%.1f, mAP_rerank_tlift=%.1f.\n' %
(test_name, test_rank1 * 100, test_mAP * 100,
test_rank1_rerank * 100, test_mAP_rerank * 100,
test_rank1_tlift * 100, test_mAP_tlift * 100))
else:
print(' %s: rank1=%.1f, mAP=%.1f.\n' %
(test_name, test_rank1 * 100, test_mAP * 100))
result_file = osp.join(exp_database_dir, args.method,
test_name + '_results.txt')
with open(result_file, 'a') as f:
f.write('%s/%s:\n' % (args.method, args.sub_method))
if testset.has_time_info:
f.write(
'\t%s: rank1=%.1f, mAP=%.1f, rank1_rerank=%.1f, mAP_rerank=%.1f, rank1_rerank_tlift=%.1f, '
'mAP_rerank_tlift=%.1f.\n\n' %
(test_name, test_rank1 * 100, test_mAP * 100,
test_rank1_rerank * 100, test_mAP_rerank * 100,
test_rank1_tlift * 100, test_mAP_tlift * 100))
else:
f.write('\t%s: rank1=%.1f, mAP=%.1f.\n\n' %
(test_name, test_rank1 * 100, test_mAP * 100))
if args.save_score:
test_gal_list = np.array(
[fname for fname, _, _, _ in testset.gallery], dtype=np.object)
test_prob_list = np.array(
[fname for fname, _, _, _ in testset.query], dtype=np.object)
test_gal_ids = [pid for _, pid, _, _ in testset.gallery]
test_prob_ids = [pid for _, pid, _, _ in testset.query]
test_gal_cams = [c for _, _, c, _ in testset.gallery]
test_prob_cams = [c for _, _, c, _ in testset.query]
test_score_file = osp.join(exp_database_dir, args.method,
args.sub_method,
'%s_score.mat' % test_name)
sio.savemat(test_score_file, {
'score': 1. - test_dist,
'score_rerank': 1. - test_dist_rerank,
'score_tlift': 1. - test_dist_tlift,
'gal_time': pre_tlift_dict['gal_time'],
'prob_time': pre_tlift_dict['prob_time'],
'gal_list': test_gal_list,
'prob_list': test_prob_list,
'gal_ids': test_gal_ids,
'prob_ids': test_prob_ids,
'gal_cams': test_gal_cams,
'prob_cams': test_prob_cams
},
oned_as='column',
do_compression=True)
test_time = time.time() - t0
avg_rank1 /= num_testsets
avg_mAP /= num_testsets
for key in results.keys():
print('%s: rank1=%.1f%%, mAP=%.1f%%.' %
(key, results[key][0] * 100, results[key][1] * 100))
print('Average: rank1=%.2f%%, mAP=%.2f%%.\n\n' %
(avg_rank1 * 100, avg_mAP * 100))
result_file = osp.join(exp_database_dir, args.method,
args.sub_method[:-5] + '_avg_results.txt')
with open(result_file, 'a') as f:
f.write('%s/%s:\n' % (args.method, args.sub_method))
if not args.evaluate:
f.write('\t Loss: %.3f, acc: %.2f%%. ' % (loss, acc * 100))
f.write("Train: %.0fs. " % train_time)
f.write("Test: %.0fs. " % test_time)
f.write('Rank1: %.2f%%, mAP: %.2f%%.\n' %
(avg_rank1 * 100, avg_mAP * 100))
for key in results.keys():
f.write('\t %s: Rank1: %.1f%%, mAP: %.1f%%.\n' %
(key, results[key][0] * 100, results[key][1] * 100))
f.write('\n')
if not args.evaluate:
print('Finished training at epoch %d, loss = %.3f, acc = %.2f%%.\n' %
(epoch + 1, loss, acc * 100))
print(
"Total training time: %.3f sec. Average training time per epoch: %.3f sec."
% (train_time, train_time / (args.epochs - start_epoch + 1)))
print("Total testing time: %.3f sec.\n" % test_time)
for arg in sys.argv:
print('%s ' % arg, end='')
print('\n')