parser.add_argument("--minibatch", dest="minibatch", type=int, default=30)
parser.add_argument("--optimizer", dest="optimizer", type=str, default="adagrad")
parser.add_argument("--epochs", dest="epochs", type=int, default=20)
parser.add_argument("--step", dest="step", type=float, default=0.01)
parser.add_argument("--hiddenDim", dest="hiddenDim", type=int, default=50)
parser.add_argument("--lstmDim", dest="lstmDim", type=int, default=30)
parser.add_argument("--task", dest="task", type=str, default=None)
args = parser.parse_args()
print ("Loading data...")
base_dir = os.path.dirname(os.path.realpath(__file__))
data_dir = os.path.join(base_dir, "data")
sick_dir = os.path.join(data_dir, "sick")
X1_train, X1_mask_train, X2_train, X2_mask_train, Y_labels_train, Y_scores_train, Y_scores_pred_train = read_sequence_dataset(
sick_dir, "train"
)
X1_dev, X1_mask_dev, X2_dev, X2_mask_dev, Y_labels_dev, Y_scores_dev, Y_scores_pred_dev = read_sequence_dataset(
sick_dir, "dev"
)
X1_test, X1_mask_test, X2_test, X2_mask_test, Y_labels_test, Y_scores_test, Y_scores_pred_test = read_sequence_dataset(
sick_dir, "test"
)
input1_var = T.imatrix("inputs_1")
input2_var = T.imatrix("inputs_2")
input1_mask_var = T.matrix("inputs_mask_1")
input2_mask_var = T.matrix("inputs_mask_2")
target_var = T.fmatrix("targets")
wordEmbeddings = loadWord2VecMap(os.path.join(sick_dir, "word2vec.bin"))
parser = argparse.ArgumentParser(description="Usage")
parser.add_argument("--minibatch", dest="minibatch", type=int, default=30)
parser.add_argument("--optimizer", dest="optimizer", type=str, default="adagrad")
parser.add_argument("--epochs", dest="epochs", type=int, default=2)
parser.add_argument("--step", dest="step", type=float, default=0.01)
parser.add_argument("--hiddenDim", dest="hiddenDim", type=int, default=50)
args = parser.parse_args()
# Load the dataset
print("Loading data...")
base_dir = os.path.dirname(os.path.realpath(__file__))
data_dir = os.path.join(base_dir, "data")
X_train, X_mask_train, Y_labels_train = read_sequence_dataset(data_dir, "train")
X_dev, X_mask_dev, Y_labels_dev = read_sequence_dataset(data_dir, "dev")
X_test, X_mask_test, Y_labels_test = read_sequence_dataset(data_dir, "test")
input_var = T.imatrix("inputs")
target_var = T.fmatrix("targets")
wordEmbeddings = loadWord2VecMap(os.path.join(data_dir, "word2vec.bin"))
wordEmbeddings = wordEmbeddings.astype(np.float32)
train_fn, val_fn = build_network_2dconv(args, input_var, target_var, wordEmbeddings)
print("Starting training...")
best_val_acc = 0
best_val_pearson = 0
for epoch in range(args.epochs):
parser.add_argument("--epochs",dest="epochs",type=int,default=20)
parser.add_argument("--step",dest="step",type=float,default=0.01)
parser.add_argument("--hiddenDim",dest="hiddenDim",type=int,default=50)
parser.add_argument("--lstmDim",dest="lstmDim",type=int,default=30)
parser.add_argument("--task",dest="task",type=str,default=None)
args = parser.parse_args()
print("Loading data...")
base_dir = os.path.dirname(os.path.realpath(__file__))
data_dir = os.path.join(base_dir, 'data')
sick_dir = os.path.join(data_dir, 'sick')
wordEmbeddings = loadWord2VecMap(os.path.join(sick_dir, 'word2vec.bin'))
X1_train, X1_mask_train, X2_train, X2_mask_train, Y_labels_train, Y_scores_train, Y_scores_pred_train = \
read_sequence_dataset(sick_dir, "train")
X1_dev, X1_mask_dev, X2_dev, X2_mask_dev, Y_labels_dev, Y_scores_dev, Y_scores_pred_dev = \
read_sequence_dataset(sick_dir, "dev")
X1_test, X1_mask_test, X2_test, X2_mask_test, Y_labels_test, Y_scores_test, Y_scores_pred_test = \
read_sequence_dataset(sick_dir, "test")
wordEmbeddings = loadWord2VecMap(os.path.join(sick_dir, 'word2vec.bin'))
wordEmbeddings = wordEmbeddings.astype(np.float32)
train_fn, val_fn, predict_proba= build_network(args, wordEmbeddings)
print("Starting training...")
best_val_acc = 0
best_val_pearson = 0
for epoch in range(args.epochs):
train_err = 0
