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')
print("dev_file done")
data.generate_instance(test_file, 'test')
print("test_file done")
print('random seed: ' + str(seed_num))
# 模型的声明
model = BiLSTM_CRF(data)
print("打印模型可优化的参数名称")
for name, param in model.named_parameters():
if param.requires_grad:
logger.info("Train file:" + train_file)
logger.info("Dev file:" + dev_file)
logger.info("Test file:" + test_file)
logger.info("Char emb:" + char_emb)
logger.info("Bichar emb:" + bichar_emb)
logger.info("Gaz file:" + gaz_file)
logger.info("Save dir:" + save_dir)
sys.stdout.flush()
if args.status == 'train':
data = Data()
data.HP_use_char = False
data.use_bigram = True # ner: False, cws: True
data.gaz_dropout = args.gaz_dropout
data.HP_lr = args.HP_lr # cws
data.HP_dropout = args.HP_dropout # cws
data.HP_use_glyph = args.HP_use_glyph
data.HP_glyph_ratio = args.HP_glyph_ratio
data.HP_font_channels = args.HP_font_channels
data.HP_glyph_highway = args.HP_glyph_highway
data.HP_glyph_embsize = args.HP_glyph_embsize
data.HP_glyph_output_size = args.HP_glyph_output_size
data.HP_glyph_dropout = args.HP_glyph_dropout
data.HP_glyph_cnn_dropout = args.HP_glyph_cnn_dropout
data.HP_iteration = 50 # cws
data.norm_gaz_emb = True # ner: False, cws: True
data.HP_fix_gaz_emb = False
data_initialization(data, gaz_file, train_file, dev_file, test_file)
data.generate_instance_with_gaz(train_file, 'train')
data.use_bigram = args.use_biword
data.HP_use_char = args.use_char
data.HP_hidden_dim = args.hidden_dim
data.HP_dropout = args.drop
data.HP_use_count = args.use_count
data.model_type = args.model_type
data.use_bert = args.use_bert
else:
data = Data()
data.HP_gpu = gpu
data.HP_use_char = args.use_char
data.HP_batch_size = args.batch_size
data.HP_num_layer = args.num_layer
data.HP_iteration = args.num_iter
data.use_bigram = args.use_biword
data.HP_dropout = args.drop
data.norm_gaz_emb = False
data.HP_fix_gaz_emb = False
data.label_comment = args.labelcomment
data.result_file = args.resultfile
data.HP_lr = args.lr
data.HP_hidden_dim = args.hidden_dim
data.HP_use_count = args.use_count
data.model_type = args.model_type
data.use_bert = args.use_bert
data_initialization(data, gaz_file, train_file, dev_file,
test_file)
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)
