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
4.71k stars 1.26k forks source link

classification as a service #169

Open DawnDoe opened 5 years ago

DawnDoe commented 5 years ago

I start the server by command as following:

python3 run.py \
    -mode CLASS \
    -bert_model_dir ~/home/Deployed/bert/pre-trained/chinese_L-12_H-768_A-12 \
    -model_dir ~/home/Deployed/BERT-BiLSTM-CRF-NER/task_model/text_class \
    -model_pb_dir ~/home/Deployed/BERT-BiLSTM-CRF-NER/task_model/output/ \
    -num_worker 2

Then I test the classification service by the class_test() method in client_test.py. The whole information is as following: Screenshot from 2019-06-26 15-21-16

It seems that no classification info is returned. My client also show no result. The classification_model.pb and label2id.pkl are all downloaded from repository and placed under model_pb_dir and model_dir respectively. I can't finger out the problem. Thank you very much !

dolphin-Jia commented 3 years ago

I start the server by command as following:

python3 run.py \
    -mode CLASS \
    -bert_model_dir ~/home/Deployed/bert/pre-trained/chinese_L-12_H-768_A-12 \
    -model_dir ~/home/Deployed/BERT-BiLSTM-CRF-NER/task_model/text_class \
    -model_pb_dir ~/home/Deployed/BERT-BiLSTM-CRF-NER/task_model/output/ \
    -num_worker 2

Then I test the classification service by the class_test() method in client_test.py. The whole information is as following: Screenshot from 2019-06-26 15-21-16

It seems that no classification info is returned. My client also show no result. The classification_model.pb and label2id.pkl are all downloaded from repository and placed under model_pb_dir and model_dir respectively. I can't finger out the problem. Thank you very much !

I meet the same issue , have you solve the problem