default=None,
help="no improvement tolerance")
config = parser.parse_args()
# os environment
os.environ['TF_CPP_MIN_LOG_LEVEL'] = "3"
os.environ["CUDA_VISIBLE_DEVICES"] = config.gpu_idx
print("load dataset...")
src_datasets, tgt_datasets, vocab = process_transfer(config)
train_rate = int(
config.train_rate) if float(config.train_rate) > 1.0 else float(
config.train_rate)
src_dataset = Dataset(src_datasets, batch_size=config.batch_size, shuffle=True)
tgt_dataset = Dataset(tgt_datasets,
batch_size=config.batch_size,
train_rate=train_rate,
shuffle=True)
print("build model and train...")
model = DATNetPModel(config, vocab)
if config.restore_model:
model.restore_last_session()
if config.train:
model.train(src_dataset, tgt_dataset)
model.restore_last_session()
model.evaluate_data(tgt_dataset.test_batches(),
"target_test",
resource="target")
model.close_session()
parser.add_argument("--optimizer", type=str, default="lazyadam", help="optimizer: [rmsprop | adadelta | adam | ...]")
parser.add_argument("--grad_clip", type=float, default=5.0, help="maximal gradient norm")
parser.add_argument("--epochs", type=int, default=50, help="train epochs")
parser.add_argument("--batch_size", type=int, default=32, help="batch size")
parser.add_argument("--emb_drop_rate", type=float, default=0.2, help="dropout rate for embeddings")
parser.add_argument("--rnn_drop_rate", type=float, default=0.5, help="dropout rate for embeddings")
parser.add_argument("--max_to_keep", type=int, default=1, help="maximum trained model to be saved")
parser.add_argument("--model_name", type=str, default="datnetf_model", help="model name")
parser.add_argument("--no_imprv_tolerance", type=int, default=None, help="no improvement tolerance")
config = parser.parse_args()
# os environment
os.environ['TF_CPP_MIN_LOG_LEVEL'] = "3"
os.environ["CUDA_VISIBLE_DEVICES"] = config.gpu_idx
print("load dataset...")
src_datasets, tgt_datasets, vocab = process_transfer(config)
train_rate = int(config.train_rate) if float(config.train_rate) > 1.0 else float(config.train_rate)
src_dataset = Dataset(src_datasets, batch_size=config.batch_size, shuffle=True)
tgt_dataset = Dataset(tgt_datasets, batch_size=config.batch_size, train_rate=train_rate, shuffle=True)
print("build model...")
model = DATNetFModel(config, vocab)
if config.restore_model:
model.restore_last_session()
if config.train:
model.train(src_dataset, tgt_dataset)
model.restore_last_session()
model.evaluate_data(tgt_dataset.test_batches(), name="target_test", resource="target")
model.close_session()
help="maximum trained model to be saved")
parser.add_argument("--no_imprv_tolerance",
type=int,
default=None,
help="no improvement tolerance")
config = parser.parse_args()
# os environment
os.environ['TF_CPP_MIN_LOG_LEVEL'] = "3"
os.environ["CUDA_VISIBLE_DEVICES"] = config.gpu_idx
print("load dataset...")
datasets, vocab = process_base(config)
train_rate = int(
config.train_rate) if float(config.train_rate) > 1.0 else float(
config.train_rate)
dataset = Dataset(datasets,
batch_size=config.batch_size,
train_rate=train_rate,
shuffle=True)
print("build model and train...")
model = BaseModel(config, vocab)
if config.restore_model:
model.restore_last_session()
if config.train:
model.train(dataset)
model.restore_last_session()
model.evaluate_data(dataset.test_batches(), name="test")
model.close_session()