print("Bichar emb:", bichar_emb)
print("Gaz file:", gaz_file)
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!")
train_file = "data/Weibo/weiboNER.train"
dev_file = "data/Weibo/weiboNER.dev"
test_file = "data/Weibo/weiboNER.test"
word_emb_file = "data/gigaword_chn.all.a2b.uni.ite50.vec"
print(train_file)
data = Data()
data.HP_gpu = False #是否使用GPU
data.norm_gaz_emb = False #词向量是否归一化
data.HP_fix_gaz_emb = True #词向量表大小是否固定
data.HP_bilstm = True
data.random_seed = seed_num
# 整体参数设定位置
data.HP_lr = 0.01
data.HP_lr_decay = 0.01
data.HP_iteration = 150
data.HP_batch_size = 20
data.gaz_dropout = 0.4
data.weight_decay = 0.00000005
data.use_clip = False #是否控制梯度
data.HP_clip = 30 #最大梯度
# LSTM参数
data.HP_hidden_dim = 300
data.HP_dropout = 0.7
data_initialization(data, train_file, dev_file, test_file)
data.build_word_pretrain_emb(word_emb_file)
print('finish loading')
data.generate_instance(train_file, 'train')
print("train_file done")
data.generate_instance(dev_file, 'dev')
