apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 16:48:03 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity
Files
bae93cebc60c883e3728e7f25a39cd7eddf9f11a
FastDeploy/examples/text/uie/cpp
History
Jack Zhou bae93cebc6 Add uie cpp deploy (#120) 
* implement PredictUIEInput

* remove batch size

* Add GetCandidateIdx

* add GetCandidateIdx GetSpan GetSpanIdxAndProbs

* Add Predict of UIEModel

* Add relation schema

* Fix uie unicode bug

* rename information_extraction/ernie -> uie

* Add more uie task

* Add cross task extraction

* use CharToBytesOffsetConverter

* Add faster_tokenizer dir

* Add RuntimeOption args

* Add todo comments

* Add some readme

* fix readme

* Fix readme

Co-authored-by: Jason <jiangjiajun@baidu.com>
2022-08-24 20:20:47 +08:00
..
CMakeLists.txt
Add uie cpp deploy (#120)
2022-08-24 20:20:47 +08:00
infer.cc
Add uie cpp deploy (#120)
2022-08-24 20:20:47 +08:00
README.md
Add uie cpp deploy (#120)
2022-08-24 20:20:47 +08:00
uie.cc
Add uie cpp deploy (#120)
2022-08-24 20:20:47 +08:00
uie.h
Add uie cpp deploy (#120)
2022-08-24 20:20:47 +08:00

README.md

通用信息抽取 UIE C++部署示例

本目录下提供infer.cc快速完成UIE模型在CPU/GPU的示例。

在部署前，需确认以下两个步骤

以Linux上uie-base模型推理为例，在本目录执行如下命令即可完成编译测试。

# UIE目前还未发布，当前需开发者自行编译FastDeploy，通过如下脚本编译得到部署库fastdeploy-linux-x64-dev
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy
mkdir build && cd build
cmake .. -DENABLE_ORT_BACKEND=ON  \
               -DENABLE_VISION=ON \
               -DENABLE_PADDLE_BACKEND=ON \
               -DENABLE_TEXT=ON \
               -DWITH_GPU=ON \
               -DCMAKE_INSTALL_PREFIX=${PWD}/fastdeploy-linux-x64-gpu-dev

make -j8
make install

# 编译模型examples代码（SDK中包含了examples代码）
cd ../examples/text/uie/cpp
mkdir build
cd build
cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/../../../../../build/fastdeploy-linux-x64-gpu-dev
make -j

# 下载uie-base模型以及词表
wget https://bj.bcebos.com/fastdeploy/models/uie/uie-base.tgz
tar -xvfz uie-base.tgz


# CPU 推理
./infer_demo uie-base 0

# GPU 推理
./infer_demo uie-base 1

模型获取

UIE 模型介绍可以参考https://github.com/PaddlePaddle/PaddleNLP/tree/develop/model_zoo/uie 。其中，在完成训练后，需要将训练后的模型导出成推理模型。该步骤可参考该文档完成导出：https://github.com/PaddlePaddle/PaddleNLP/tree/develop/model_zoo/uie#%E6%A8%A1%E5%9E%8B%E9%83%A8%E7%BD%B2 。