def main(argv=None): # pylint: disable=unused-argument
logging.basicConfig(datefmt="%d/%Y %I:%M:%S", level=logging.INFO,
format='%(asctime)s [%(levelname)s] (%(filename)s:%(lineno)s) %(message)s'
)
if not gfile.Exists(FLAGS.parameter_dir):
print ("parameter_dir {} not exists.".format(FLAGS.parameter_dir))
sys.exit(-1)
if gfile.Exists(FLAGS.eval_log_dir):
gfile.DeleteRecursively(FLAGS.eval_log_dir)
gfile.MakeDirs(FLAGS.eval_log_dir)
print(config.get_config_str())
evaluate()
def main(argv=None):
logging.basicConfig(
datefmt="%d/%Y %I:%M:%S",
level=logging.INFO,
format=
'%(asctime)s [%(levelname)s] (%(filename)s:%(lineno)s) %(message)s')
if gfile.Exists(FLAGS.parameter_dir):
gfile.DeleteRecursively(FLAGS.parameter_dir)
if gfile.Exists(FLAGS.train_log_dir):
gfile.DeleteRecursively(FLAGS.train_log_dir)
gfile.MakeDirs(FLAGS.parameter_dir)
gfile.MakeDirs(FLAGS.train_log_dir)
print(config.get_config_str())
start_train()
action='store_true',
help='resume from checkpoint')
parser.add_argument('--seed',
type=int,
default=1,
metavar='S',
help='random seed (default: 1)')
args = parser.parse_args()
torch.manual_seed(args.seed)
config_file = 'config.yaml'
model_type = 'UNET'
config = config.Configuration(model_type, config_file)
print(config.get_config_str())
config = config.config_dict
device = 'cuda' if torch.cuda.is_available() else 'cpu'
best_acc = 0 # best test accuracy
start_epoch = 0 # start from epoch 0 or last checkpoint epoch
# Data
print('==> Preparing data..')
transform_train = transforms.Compose([
transforms.RandomCrop(32, padding=4),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),
])
