A service to serve bert_multitask_learning models(server)
Project description
bert-multitask-as-service
A serving service for bert-multitask-learning
Install
pip install bert-multitask-server pip install bert-multitask-client
Getting Started
-
Train and export model.
A typical trained checkpoint dir looks like below.
bert_serving_ckpt/ ├── *_label_encoder.pkl ├── bert_config.json ├── export_model ├── params.json └── vocab.txt
-
Start server using CLI
bert-multitask-serving-start -model_dir ~/CWS_NER_POS_ckpt/ -num_worker=4 -problem "CWS|NER|POS"
-
Use Client to Get Prediction
from bert_serving.client import BertClient bc = BertClient() bc.encode(['我爱北京天安门'])
Bert多任务学习服务
一个部署Bert多任务学习的服务
安装
pip install bert-multitask-server pip install bert-multitask-client
开始使用
-
训练模型并导出模型.
导出后的模型目录应该有以下文件
bert_serving_ckpt/ ├── *_label_encoder.pkl ├── bert_config.json ├── export_model ├── params.json └── vocab.txt
-
用CLI启动服务
bert-multitask-serving-start -model_dir models/ -num_worker=4 -problem "fake_problem"
-
用客户端获取预测结果
from bert_serving.client import BertClient bc = BertClient() bc.encode(['我爱北京天安门'])
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Built Distribution
Close
Hashes for bert_multitask_server-0.1.2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 2d60bcb1a44a507f5b9b1e1f834eb7af36be111940807705c72d0ec19b9ea03e |
|
MD5 | ed3bffae68f451d976d1782887f4a03f |
|
BLAKE2-256 | 6c52fc72966d16bc84b87db50e1b0702bdda1bbe2d1168decb321e51f35bf49b |