def parse_arguments():
paths = hico_config.Paths()
parser = argparse.ArgumentParser(description='HICO dataset')
parser.add_argument('--data-root', default=paths.data_root, help='dataset path')
parser.add_argument('--tmp-root', default=paths.tmp_root, help='intermediate result path')
return parser.parse_args()
def main():
paths = hico_config.Paths()
start_time = time.time()
collect_data(paths)
print('Time elapsed: {:.2f}s'.format(time.time() - start_time))
def main():
paths = hico_config.Paths()
extract_features(paths)
def parse_arguments():
paths = hico_config.Paths()
feature_type = 'resnet'
parser = argparse.ArgumentParser(description='PyTorch ImageNet Training')
parser.add_argument('--feature-type',
default=feature_type,
help='feature_type')
parser.add_argument('--data',
metavar='DIR',
default=paths.data_root,
help='path to dataset')
parser.add_argument('-j',
'--workers',
default=1,
type=int,
metavar='N',
help='number of data loading workers (default: 4)')
parser.add_argument('--epochs',
default=100,
type=int,
metavar='N',
help='number of total epochs to run')
parser.add_argument('--start-epoch',
default=0,
type=int,
metavar='N',
help='manual epoch number (useful on restarts)')
parser.add_argument('-b',
'--batch-size',
default=32,
type=int,
metavar='N',
help='mini-batch size (default: 256)')
parser.add_argument('--lr',
'--learning-rate',
default=1e-4,
type=float,
metavar='LR',
help='initial learning rate')
parser.add_argument('--momentum',
default=0.9,
type=float,
metavar='M',
help='momentum')
parser.add_argument('--weight-decay',
'--wd',
default=1e-3,
type=float,
metavar='W',
help='weight decay (default: 1e-4)')
parser.add_argument('--print-freq',
'-p',
default=30,
type=int,
metavar='N',
help='print frequency (default: 10)')
parser.add_argument(
'--resume',
default=os.path.join(
paths.tmp_root,
'checkpoints/hico/finetune_{}'.format(feature_type)),
type=str,
metavar='PATH',
help='path to latest checkpoint (default: none)')
parser.add_argument('-e',
'--evaluate',
dest='evaluate',
action='store_true',
help='evaluate model on validation set')
parser.add_argument('--pretrained',
dest='pretrained',
default=True,
action='store_true',
help='use pre-trained model')
parser.add_argument('--world-size',
default=1,
type=int,
help='number of distributed processes')
parser.add_argument('--dist-url',
default='tcp://224.66.41.62:23456',
type=str,
help='url used to set up distributed training')
parser.add_argument('--dist-backend',
default='gloo',
type=str,
help='distributed backend')
return parser.parse_args()
def main():
paths = hico_config.Paths()
imagesets = ['train', 'test']
for imageset in imagesets:
extract_features(paths, imageset)
def main():
paths = hico_config.Paths()
find_rare_hoi(paths)