def main():
parser = argparse.ArgumentParser()
# input and output
parser.add_argument('--input_dir', required=True)
parser.add_argument('--save_dir',
required=True,
help='path to save checkpoints and logs')
parser.add_argument('--ckpt', required=True)
# training parameters
parser.add_argument('--batch_size', default=256, type=int)
parser.add_argument('--seed', type=int, default=666, help='random seed')
# validating parameters
# parser.add_argument('--num_return_sequences', default=1, type=int)
# parser.add_argument('--top_p', default=)
# model hyperparameters
parser.add_argument('--dim_hidden', default=1024, type=int)
parser.add_argument('--alpha', default=1e-4, type=float)
args = parser.parse_args()
if not os.path.exists(args.save_dir):
os.makedirs(args.save_dir)
time_ = time.strftime("%Y-%m-%d-%H:%M:%S", time.localtime())
fileHandler = logging.FileHandler(
os.path.join(args.save_dir, '{}.predict.log'.format(time_)))
fileHandler.setFormatter(logFormatter)
rootLogger.addHandler(fileHandler)
# args display
for k, v in vars(args).items():
logging.info(k + ':' + str(v))
seed_everything(666)
train(args)
def main():
parser = argparse.ArgumentParser()
# input and output
parser.add_argument('--input_dir', required=True)
parser.add_argument('--output_dir', required=True)
parser.add_argument('--save_dir', required=True, help='path to save checkpoints and logs')
parser.add_argument('--model_name_or_path', required = True)
parser.add_argument('--ckpt')
# training parameters
parser.add_argument('--weight_decay', default=1e-5, type=float)
parser.add_argument('--batch_size', default=16, type=int)
parser.add_argument('--seed', type=int, default=666, help='random seed')
parser.add_argument('--learning_rate', default=3e-5, type = float)
parser.add_argument('--num_train_epochs', default=25, type = int)
parser.add_argument('--save_steps', default=448, type = int)
parser.add_argument('--logging_steps', default=448, type = int)
parser.add_argument('--warmup_proportion', default=0.1, type = float,
help="Proportion of training to perform linear learning rate warmup for,E.g., 0.1 = 10% of training.")
parser.add_argument("--adam_epsilon", default=1e-8, type=float,
help="Epsilon for Adam optimizer.")
parser.add_argument("--gradient_accumulation_steps", type=int, default=1,
help="Number of updates steps to accumulate before performing a backward/update pass.", )
parser.add_argument("--max_grad_norm", default=1.0, type=float,
help="Max gradient norm.")
# validating parameters
# parser.add_argument('--num_return_sequences', default=1, type=int)
# parser.add_argument('--top_p', default=)
# model hyperparameters
parser.add_argument('--dim_hidden', default=1024, type=int)
parser.add_argument('--alpha', default = 1e-4, type = float)
args = parser.parse_args()
if not os.path.exists(args.save_dir):
os.makedirs(args.save_dir)
time_ = time.strftime("%Y-%m-%d-%H:%M:%S", time.localtime())
fileHandler = logging.FileHandler(os.path.join(args.save_dir, '{}.log'.format(time_)))
fileHandler.setFormatter(logFormatter)
rootLogger.addHandler(fileHandler)
# args display
for k, v in vars(args).items():
logging.info(k+':'+str(v))
seed_everything(666)
train(args)
help='Test dataset size'
)
parser.add_argument('--image_size', default=224, type=int,
help='Desired image size'
)
parser.add_argument('--num_workers', default=2, type=int,
help='Number of processes for PyTorch data loaders'
)
parser.add_argument('--random_state', default=42, type=int,
help='Random seed for all random operations'
)
args = parser.parse_args()
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
args.gpu = args.gpu if torch.cuda.is_available() else 0
seed_everything(args.random_state)
# target_column has unique values in set -1, 0, 1
# -1 corresponds to the unlabeled data
df = pd.read_csv(args.csv)
labeled = df[df[args.target_column] > -1]
if args.ssl:
print("Semi-supervised learning model is on...")
unlabeled = df[df[args.target_column] == -1]
# weights to initialize bias of FC layer of classifier
weight = labeled.groupby(args.target_column).count()["path"] / labeled.shape[0]
weight = torch.Tensor(weight.values).log()
train_labeled, test_labeled = train_test_split(labeled, test_size=args.test_size, stratify=labeled[args.target_column], random_state=args.random_state)