Tensorflow solution of NER task Using BiLSTM-CRF model with Google BERT Fine-tuning And private Server services
4.68k
stars
1.25k
forks
source link
部署后,提示This is a development server. Do not use it in a production deployment #350
Closed
modoojunko closed 4 years ago
先赞下这个BERT-BASE,BERT模型微调出来后,让我吃尽了部署成服务的苦头。BERT-BASE一键式成功启动起来,并且有个/encode能直接输入待预测的句子分类,完全满足我需要。
但是根据以往搞APP的经验,flask直接启动是开发模式。要用WSGI来启动才能在生产环境。
这里有现成解决办法么?