BERT-BiLSTM-CRF-NER
BERT-BiLSTM-CRF-NER copied to clipboard
macanv
Tensorflow solution of NER task Using BiLSTM-CRF model with Google BERT Fine-tuning And private Server services
我注意到您的服务框架由bert-serve改写而来，而我的服务器上部署完NER server模型后还需要部署原生的bert-server，这两者是否会相互干扰？还有您的框架是否还保存有原生框架的功能，我该如何启动？
``` File "/usr/local/lib/python3.6/dist-packages/bert_base/server/__init__.py", line 150, in _run addr_front2sink = auto_bind(sink) File "/usr/local/lib/python3.6/dist-packages/bert_base/server/helper.py", line 182, in auto_bind socket.bind('ipc://{}'.format(tmp_dir)) File "zmq/backend/cython/socket.pyx", line 550, in zmq.backend.cython.socket.Socket.bind File "zmq/backend/cython/checkrc.pxd", line 26, in zmq.backend.cython.checkrc._check_rc zmq.error.ZMQError:...
bert-base-serving-start -model_dir -bert_model_dir -mode NER -num_worker 8 48个CPU核，每个核使用率超过95%
add try/finally to ConcurrentBertClient avoid not release BertClient on exception in my case, if pass contents contains space will cause BertClient not released and end up with error message >...
用postman调用 xxxx:5555/encode的时候 postbody写的是： { "id":1, "texts":["1月24日，新华社对外发布了中央对雄安新区的指导意见“], "is_tokenized":false }
**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...
I:VENTILATOR:new config request req id: 0 client: b'e4d5dbdc-97ff-4ec5-8bd3-96e0c11d5c60' Process BertWorker-3: Traceback (most recent call last): File "d:\app\python\python37\lib\multiprocessing\process.py", line 297, in _bootstrap self.run() File "d:\app\python\python37\lib\site-packages\bert_base\server\__init__.py", line 487, in run self._run() File...
为什么验证的时候重新定义了eval_loss，原来tatal_loss此时又代表什么呢？ 代码位置如下： elif mode == tf.estimator.ModeKeys.EVAL: # 针对NER ,进行了修改 def metric_fn(label_ids, pred_ids): return { "eval_loss": tf.metrics.mean_squared_error(labels=label_ids, predictions=pred_ids), } eval_metrics = metric_fn(label_ids, pred_ids) output_spec = tf.estimator.EstimatorSpec( mode=mode, loss=total_loss, eval_metric_ops=eval_metrics )
