if status == 'train':
print("Model saved to:", save_model_dir)
# 立即把stdout缓存内容输出
sys.stdout.flush()
if status == 'train':
data = Data()
data.model_name = model_name
data.HP_gpu = gpu
data.use_bichar = conf_dict['use_bichar']
data.HP_batch_size = conf_dict['HP_batch_size'] # 1
data.HP_iteration = conf_dict['HP_iteration'] # 100
data.HP_lr = conf_dict['HP_lr'] # 0.015
data.HP_lr_decay = conf_dict['HP_lr_decay'] # 0.5
data.HP_hidden_dim = conf_dict['HP_hidden_dim']
data.MAX_SENTENCE_LENGTH = conf_dict['MAX_SENTENCE_LENGTH']
data.HP_lstm_layer = conf_dict['HP_lstm_layer']
data_initialization(data, gaz_file, train_file, dev_file, test_file)
if data.model_name in ['CNN_model', 'LSTM_model']:
data.generate_instance_with_gaz_2(train_file, 'train')
data.generate_instance_with_gaz_2(dev_file, 'dev')
data.generate_instance_with_gaz_2(test_file, 'test')
elif data.model_name in ['WC-LSTM_model']:
data.generate_instance_with_gaz_3(train_file, 'train')
data.generate_instance_with_gaz_3(dev_file, 'dev')
data.generate_instance_with_gaz_3(test_file, 'test')
else:
print("model_name is not set!")
sys.exit(1)
data.build_char_pretrain_emb(char_emb)
print("Gaz file:", gaz_file)
if status == 'train':
print("Model saved to:", save_model_dir)
sys.stdout.flush()
if status == 'train':
data = Data()
data.HP_gpu = gpu
data.HP_lr = float(lr)
data.HP_use_char = False
data.HP_batch_size = 1
data.use_bigram = False if bichar_emb is None else True
data.gaz_dropout = 0.5
data.norm_gaz_emb = False
data.HP_fix_gaz_emb = False
data.MAX_SENTENCE_LENGTH = maxlen
data_initialization(data, gaz_file, train_file, dev_file, test_file,
word_sense_map_file)
data_build_gold(data, train_gold, dev_gold, test_gold)
data.generate_instance_with_gaz(train_file, 'train')
data.generate_instance_with_gaz(dev_file, 'dev')
data.generate_instance_with_gaz(test_file, 'test')
data.build_word_pretrain_emb(char_emb)
data.build_biword_pretrain_emb(bichar_emb)
data.build_gaz_pretrain_emb(gaz_file)
train(data, save_model_dir, dataset, seg)
elif status == 'test':
data = load_data_setting(dset_dir)
data.build_word_sense_map(word_sense_map_file)
data.MAX_SENTENCE_LENGTH = maxlen
data_build_gold(data, train_gold, dev_gold, test_gold)
