w.write('{}\t{}\t{}\n'.format(tid, gold, 'NM'))
# ----------------------------------------------------------------------
# Mode: train
test_label_preds = {}
best_scores = {}
if mode == 'train':
if not os.path.exists(model_dir):
os.mkdir(model_dir)
for target_label in labels:
model_file = os.path.join(model_dir,
'checkpoint_{}.mdl'.format(target_label))
model = models[target_label]
optimizer = optimizers[target_label]
# TODO: combine init_dataset() and shuffle_dataset()
dev_set.init_dataset(target_label)
test_set.init_dataset(target_label)
(
dev_tids, dev_tokens, dev_labels, dev_lens
) = dev_set.get_dataset(max_seq_len, volatile=True, gpu=use_gpu)
(
test_tids, test_tokens, test_labels, test_lens
) = test_set.get_dataset(max_seq_len, volatile=True, gpu=use_gpu)
best_dev_fscore = 0.0
best_test_scores = None
for epoch in range(max_epoch):
epoch_start_time = current_time()
epoch_loss = 0.0
train_set.shuffle_dataset(target_label, balance=True)
batch_num = train_set.batch_num(batch_size)
