def __init__(self, args, embeddings, tag2label, vocab, paths, config):
self.batch_size = args.batch_size
self.epoch_num = args.epoch
self.hidden_dim = args.hidden_dim
self.embeddings = embeddings
self.CRF = args.CRF
self.update_embedding = args.update_embedding
self.dropout_keep_prob = args.dropout
self.optimizer = args.optimizer
self.lr = args.lr
self.clip_grad = args.clip
self.tag2label = tag2label
self.num_tags = len(tag2label)
self.vocab = vocab
self.shuffle = args.shuffle
self.model_path = paths['model_path']
self.summary_path = paths['summary_path']
self.logger = get_logger(paths['log_path'])
self.result_path = paths['result_path']
self.config = config
timestamp = str(int(time.time())) if args.mode == 'train' else args.demo_model
output_path = os.path.join('.', args.train_data+"_save", timestamp)
if not os.path.exists(output_path): os.makedirs(output_path)
summary_path = os.path.join(output_path, "summaries")
paths['summary_path'] = summary_path
if not os.path.exists(summary_path): os.makedirs(summary_path)
model_path = os.path.join(output_path, "checkpoints/")
if not os.path.exists(model_path): os.makedirs(model_path)
ckpt_prefix = os.path.join(model_path, "model")
paths['model_path'] = ckpt_prefix
result_path = os.path.join(output_path, "results")
paths['result_path'] = result_path
if not os.path.exists(result_path): os.makedirs(result_path)
log_path = os.path.join(result_path, "log.txt")
paths['log_path'] = log_path
get_logger(log_path).info(str(args))
## training Entity Extraction model
if args.mode == 'train':
model = BiLSTM_CRF(args, embeddings, tag2label, word2id, paths, config=config)
model.build_graph()
## hyperparameters-tuning, split train/dev
# dev_data = train_data[:5000]; dev_size = len(dev_data)
# train_data = train_data[5000:]; train_size = len(train_data)
# print("train data: {0}\ndev data: {1}".format(train_size, dev_size))
# model.train(train=train_data, dev=dev_data)
## train model on the whole training data
print("train data: {}".format(len(train_data)))