macanv / BERT-BiLSTM-CRF-NER

Tensorflow solution of NER task Using BiLSTM-CRF model with Google BERT Fine-tuning And private Server services
https://github.com/macanv/BERT-BiLSMT-CRF-NER
4.67k stars 1.25k forks source link

关于模型预测,在win端建立一个client,但是在预测时一直卡住。请问如何解决 #369

Open SevenMpp opened 3 years ago

SevenMpp commented 3 years ago

我在服务器上运行了服务,如下所示: I:WORKER-0:[__i:_ru:502]:use device gpu: 0, load graph from /data/mpf/bert/tmp/pb_ner_model/ner_model.pb WARNING:tensorflow:From /home/app_user_5i5j/anaconda3/lib/python3.6/site-packages/bert_base-0.0.9-py3.6.egg/bert_base/server/helper.py:162: The name tf.logging.set_verbosity is deprecated. Please use tf.compat.v1.logging.set_verbosity instead.

WARNING:tensorflow:From /home/app_user_5i5j/anaconda3/lib/python3.6/site-packages/bert_base-0.0.9-py3.6.egg/bert_base/server/helper.py:162: The name tf.logging.ERROR is deprecated. Please use tf.compat.v1.logging.ERROR instead. results: <tensorflow.python.framework.c_api_util.ScopedTFImportGraphDefResults object at 0x7fea7f703b70> missing_unused_input_keys: [] I:WORKER-0:[i:gen:542]:ready and listening! 之后在win上创建了一个文件去访问,服务器接口的线上如下,并且client端一直卡住。不运行也不结束: results: <tensorflow.python.framework.c_api_util.ScopedTFImportGraphDefResults object at 0x7fea7f703b70> missing_unused_input_keys: [] I:WORKER-0:[i:gen:542]:ready and listening! I:VENTILATOR:[i:_ru:217]:new encode request req id: 0 size: 1 client: b'78116aa2-c348-4f76-a07f-ba0ed0550b99' I:SINK:[i:_ru:371]:job register size: 1 job id: b'78116aa2-c348-4f76-a07f-ba0ed0550b99#0' I:WORKER-0:[__i:gen:550]:new job socket: 0 size: 1 client: b'78116aa2-c348-4f76-a07f-ba0ed0550b99#0' 请问这是为什么,应该如何解决呢