SevenMpp

Process BertWorker-3: Traceback (most recent call last): File "/home/anaconda3/lib/python3.6/multiprocessing/process.py", line 258, in _bootstrap self.run() File "/home/anaconda3/lib/python3.6/site-packages/bert_base-0.0.9-py3.6.egg/bert_base/server/__init__.py", line 492, in run self._run() File "/home/anaconda3/lib/python3.6/site-packages/zmq/decorators.py", line 75, in wrapper return func(*args, **kwargs)...

Process BertWorker-3: Traceback (most recent call last): File "/home/anaconda3/lib/python3.6/multiprocessing/process.py", line 258, in _bootstrap self.run() File "/home/anaconda3/lib/python3.6/site-packages/bert_base-0.0.9-py3.6.egg/bert_base/server/__init__.py", line 492, in run self._run() File "/home/anaconda3/lib/python3.6/site-packages/zmq/decorators.py", line 75, in wrapper return func(*args, **kwargs)...

**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...

加载自定义词典，发现好像不起作用。 示例： '胆石利通片山东步长制药' 分词结果：['胆石利通', '片', '山东步长制药'] 期望结果： ['胆石利通片', '山东步长制药'] 即使加入”胆石利通片“ 也不能分出来，但如果未加自定义词典就可以正常分出 ['胆石利通片', '山东步长制药']。已确定自定义词典中不包含”片“这个单个字的词。不明白其中原因是什么！！！！！！！ 加载方式如下： lac = LAC(mode='seg') lac.load_customization(customization_file='../dict/dict.txt', sep=None) 使用方式如下： lac.run(str) txt文件格式如下： 胆石利通片 布洛怪法师卡雷拉 晶水村 马蒂奥尼

Hello, excuse me, there was no problem during the training, but this error occurred during the prediction. I'm actually extracting predict as a function PATH = './snapshot/best_steps_8600.pt' args = confog_args()...

您好，我使用的是word2vec的400维的bin文件，请问这个是为什么，是要t和4*size相同吗，但是我尝试了也不可以。

您好 请问在使用 save 时报如下错误 Traceback (most recent call last): File "save_model.py", line 132, in main(max_seq_len, model_dir, num_labels) File "save_model.py", line 85, in main input_ids=input_ids, input_mask=input_mask, segment_ids=None, labels=None, num_labels=num_labels) File "save_model.py",...

请问您是将ckpt转成PB，使用pb进行预测的吗。或者您有什么好的方式转化为pb吗？我现在只知道需要知道输出节点，如何确定哪个节点呢。但是输出节点输入后，会出现 pred:0 这样的错误。

您好根据您的代码，我在同一台服务器，去连接tensorflow-serving服务。报 status = StatusCode.INVALID_ARGUMENT details = "input size does not match signature: 1!=5 len({examples}) != len({input_ids,input_mask,label_ids,mask,segment_ids}). Sent extra: {examples}. Missing but required: {input_ids,input_mask,label_ids,mask,segment_ids}."

1

raise _InactiveRpcError(state) grpc._channel._InactiveRpcError: