# Log specifications
parser.add_argument('--save', type=str, default='test',
help='file name to save')
parser.add_argument('--load', type=str, default='.',
help='file name to load')
parser.add_argument('--print_model', action='store_true',
help='print model')
parser.add_argument('--save_models', action='store_true',
help='save all intermediate models')
parser.add_argument('--print_every', type=int, default=100,
help='how many batches to wait before logging training status')
parser.add_argument('--save_results', action='store_true',
help='save output results')
args = parser.parse_args()
template.setTemplate(args) # set some option here
args.scale = list(map(lambda x: int(x), args.scale.split('+'))) # scale can be the form like "2+3+4"
args.quality = args.quality.split('+')
for i, q in enumerate(args.quality):
if q != '':
args.quality[i] = int(q)
if args.epochs == 0:
args.epochs = 1e8
for arg in vars(args):
if vars(args)[arg] == 'True':
vars(args)[arg] = True
elif vars(args)[arg] == 'False':
vars(args)[arg] = False
default='False',
help='Using the Laplacian method')
parser.add_argument('--fullTargetScale',
default='1',
help='output scale to obtain pretraining')
parser.add_argument('--fullInputScale',
default='2',
help='input scale to obtain pretraining')
parser.add_argument('--pre_train_3', default='.', help='8 to 4')
parser.add_argument('--pre_train_2', default='.', help='4 to 2')
parser.add_argument('--pre_train_1', default='.', help='2 to 1')
args = parser.parse_args()
template.setTemplate(args)
args.scale = list(map(lambda x: int(x), args.scale.split('+')))
args.quality = args.quality.split('+')
for i, q in enumerate(args.quality):
if q != '':
args.quality[i] = int(q)
if args.epochs == 0:
args.epochs = 1e8
for arg in vars(args):
if vars(args)[arg] == 'True':
vars(args)[arg] = True
elif vars(args)[arg] == 'False':
vars(args)[arg] = False
