print('Char Embedding: ', char_emb_file)
name = 'BaseLSTM' # catnlp
config = Config()
config.layers = 2
config.optim = 'Adam'
config.char_features = 'CNN'
config.lr = 0.015
config.hidden_dim = 200
config.bid_flag = True
config.number_normalized = True
data_initialization(config, train_file, dev_file, test_file)
config.gpu = gpu
config.word_features = name
print('Word features: ', config.word_features)
config.generate_instance(train_file, 'train')
config.generate_instance(dev_file, 'dev')
config.generate_instance(test_file, 'test')
if emb_file:
print('load word emb file...norm: ', config.norm_word_emb)
config.build_word_pretain_emb(emb_file)
if char_emb_file != 'none':
print('load char emb file...norm: ', config.norm_char_emb)
config.build_char_pretrain_emb(char_emb_file)
name = 'joint-disease' # catnlp
train(config, name, dset_dir, save_model_dir, seg, ignore=True)
elif status == 'test':
data = load_data_setting(dset_dir)
data.generate_instance(dev_file, 'dev')
load_model_decode(model_dir, data, 'dev', gpu, seg)
test_file = os.path.join(line, args.test)
print('Train file: ', train_file)
print('Dev file: ', devel_file)
print('Test file: ', test_file)
data_initialization(config, train_file, devel_file, test_file)
# config.fix_alphabet()
config.num_corpus = count
with open(args.dataset, 'r') as f:
for line in f:
line = line.strip()
train_file = os.path.join(line, args.train)
devel_file = os.path.join(line, args.devel)
test_file = os.path.join(line, args.test)
config.generate_instance(train_file, 'train')
config.generate_instance(devel_file, 'dev')
config.generate_instance(test_file, 'test')
if emb_file:
print('load word emb file...norm: ', config.norm_word_emb)
config.build_word_pretain_emb(emb_file)
if char_emb_file != 'none':
print('load char emb file...norm: ', config.norm_char_emb)
config.build_char_pretrain_emb(char_emb_file)
for label in config.label_alphabet.instances:
print(label)
name = 'MultiMetaLSTM'
train(config, name, dset_dir, save_model_dir, seg)
# elif status == 'test':
