info = sys.argv[7]
train_file = './data/intermediate/' + dataset + '/rm/train.data'
dev_file = './data/intermediate/' + dataset + '/rm/dev.data'
test_file = './data/intermediate/' + dataset + '/rm/test.data'
feature_file = './data/intermediate/' + dataset + '/rm/feature.txt'
type_file = './data/intermediate/' + dataset + '/rm/type.txt'
type_file_test = './data/intermediate/' + dataset + '/rm/type_test.txt'
none_ind = utils.get_none_id(type_file)
print("None id:", none_ind)
label_distribution = utils.get_distribution(type_file)
label_distribution_test = utils.get_distribution(type_file_test)
word_size, pos_embedding_tensor = utils.initialize_embedding(
feature_file, embLen)
_, type_size, _, _, _ = utils.load_corpus(train_file)
nocluster = noCluster.noCluster(embLen, word_size, type_size, drop_prob,
label_distribution, label_distribution_test)
nocluster.load_state_dict(
torch.load('./dumped_models/ffnn_dump_' + '_'.join(sys.argv[1:7]) +
'.pth'))
torch.cuda.set_device(0)
nocluster.cuda()
if_cuda = True
packer = pack.repack(repack_ratio, 20, if_cuda)
print('in the order of: train, dev, test...\n')
print('Using Random Seed: ' + str(SEED))
torch.manual_seed(SEED)
np.random.seed(SEED)
random.seed(SEED)
# read data
data_dir = os.path.join(opt['data_dir'], opt['dataset'], 'rm')
train_file = os.path.join(data_dir, 'train.data')
dev_file = os.path.join(data_dir, 'dev.data')
test_file = os.path.join(data_dir, 'test.data')
feature_file = os.path.join(data_dir, 'feature.txt')
type_file = os.path.join(data_dir, 'type.txt')
type_file_test = os.path.join(data_dir, 'type_test.txt')
none_ind = utils.get_none_id(type_file)
word_size, pos_embedding_tensor = utils.initialize_embedding(
feature_file, opt['emb_len'])
doc_size, type_size, feature_list, label_list, type_list = utils.load_corpus(
train_file)
doc_size_test, _, feature_list_test, label_list_test, type_list_test = utils.load_corpus(
test_file)
doc_size_dev, _, feature_list_dev, label_list_dev, type_list_dev = utils.load_corpus(
dev_file)
# set up configs
opt['none_ind'] = none_ind
opt['label_distribution'] = utils.get_distribution(type_file)
opt['word_size'], opt['type_size'] = word_size, type_size
opt['if_average'] = False
bat_size = opt['batch_size']
# initialize model