Upload folder using huggingface_hub (part 4)

.gitattributes

@@ -49,3 +49,47 @@ ocr_webapp/PaddleOCR/deploy/cpp_infer/docs/imgs/cmake_step3.png filter=lfs diff=
 ocr_webapp/PaddleOCR/deploy/cpp_infer/docs/imgs/cmake_step4.png filter=lfs diff=lfs merge=lfs -text
 ocr_webapp/PaddleOCR/deploy/cpp_infer/docs/imgs/result.jpg filter=lfs diff=lfs merge=lfs -text
 ocr_webapp/PaddleOCR/deploy/cpp_infer/docs/imgs/vs_step1.png filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/deploy/ios_demo/PaddleOCRDemo/Resources/SampleImages/general_ocr_002.jpg filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/deploy/ios_demo/PaddleOCRDemoTests/Fixtures/ios_ocr_validation_reference.jpg filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/deploy/Jetson/images/00057937.jpg filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/deploy/Jetson/images/det_res_french_0.jpg filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/deploy/paddle2onnx/images/lite_demo_onnx.png filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/deploy/paddle2onnx/images/lite_demo_paddle.png filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/deploy/paddlecloud/images/architecture.jpeg filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/deploy/paddlecloud/images/paddlecloud.png filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/deploy/paddlejs/paddlejs_demo.gif filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/deploy/pdserving/imgs/demo.png filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/deploy/pdserving/imgs/pipeline_result.png filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/deploy/pdserving/imgs/results.png filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/deploy/pdserving/imgs/start_server.png filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/deploy/ppocr-android/ppocr-sdk/src/androidTest/res/raw/android_ocr_benchmark_reference.png filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/doc/banner.png filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/doc/datasets/ArT.jpg filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/doc/datasets/captcha_demo.png filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/doc/datasets/ccpd_demo.png filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/doc/datasets/CDLA_demo/val_0633.jpg filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/doc/datasets/CDLA_demo/val_0941.jpg filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/doc/datasets/ch_street_rec_1.png filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/doc/datasets/ch_street_rec_2.png filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/doc/datasets/doc.jpg filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/doc/datasets/funsd_demo/gt_train_00040534.jpg filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/doc/datasets/funsd_demo/gt_train_00070353.jpg filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/doc/datasets/icdar_rec.png filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/doc/datasets/labelme.jpg filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/doc/datasets/LSVT_1.jpg filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/doc/datasets/publaynet_demo/gt_PMC3724501_00006.jpg filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/doc/datasets/publaynet_demo/gt_PMC5086060_00002.jpg filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/doc/datasets/roLabelImg.png filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/doc/datasets/table_tal_demo/1.jpg filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/doc/datasets/table_tal_demo/2.jpg filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/doc/datasets/tablebank_demo/004.png filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/doc/datasets/tablebank_demo/005.png filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/doc/datasets/VoTT.jpg filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/doc/datasets/wildreceipt_demo/1bbe854b8817dedb8585e0732089fd1f752d2cec.jpeg filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/doc/datasets/wildreceipt_demo/2769.jpeg filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/doc/datasets/xfund_demo/gt_zh_train_0.jpg filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/doc/datasets/xfund_demo/gt_zh_train_1.jpg filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/doc/demo/error.png filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/doc/demo/proxy.png filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/doc/deployment.png filter=lfs diff=lfs merge=lfs -text
+ocr_webapp/PaddleOCR/doc/deployment_en.png filter=lfs diff=lfs merge=lfs -text

ocr_webapp/PaddleOCR/deploy/Jetson/readme.md

@@ -0,0 +1,84 @@
+English | [简体中文](readme_ch.md)
+
+# Jetson Deployment for PaddleOCR
+
+This section introduces the deployment of PaddleOCR on Jetson NX, TX2, nano, AGX and other series of hardware.
+
+
+## 1. Prepare Environment
+
+You need to prepare a Jetson development hardware. If you need TensorRT, you need to prepare the TensorRT environment. It is recommended to use TensorRT version 7.1.3;
+
+1. Install PaddlePaddle in Jetson
+
+The PaddlePaddle download [link](https://www.paddlepaddle.org.cn/inference/user_guides/download_lib.html#python)
+Please select the appropriate installation package for your Jetpack version, cuda version, and trt version. Here, we download paddlepaddle_gpu-2.3.0rc0-cp36-cp36m-linux_aarch64.whl.
+
+Install PaddlePaddle：
+```shell
+pip3 install -U paddlepaddle_gpu-2.3.0rc0-cp36-cp36m-linux_aarch64.whl
+```
+
+
+2. Download PaddleOCR code and install dependencies
+
+Clone the PaddleOCR code:
+```
+git clone https://github.com/PaddlePaddle/PaddleOCR
+```
+
+and install dependencies：
+```
+cd PaddleOCR
+pip3 install -r requirements.txt
+```
+
+*Note: Jetson hardware CPU is poor, dependency installation is slow, please wait patiently*
+
+## 2. Perform prediction
+
+Obtain the PPOCR model from the [document](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/doc/doc_en/ppocr_introduction_en.md#6-model-zoo) model library. The following takes the PP-OCRv3 model as an example to introduce the use of the PPOCR model on Jetson:
+
+Download and unzip the PP-OCRv3 models.
+```
+wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar
+wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar
+tar xf ch_PP-OCRv3_det_infer.tar
+tar xf ch_PP-OCRv3_rec_infer.tar
+```
+
+The text detection inference:
+```
+cd PaddleOCR
+python3 tools/infer/predict_det.py --det_model_dir=./inference/ch_PP-OCRv2_det_infer/  --image_dir=./doc/imgs/french_0.jpg  --use_gpu=True
+```
+
+After executing the command, the predicted information will be printed out in the terminal, and the visualization results will be saved in the `./inference_results/` directory.
+![](./images/det_res_french_0.jpg)
+
+
+The text recognition inference:
+```
+python3 tools/infer/predict_det.py --rec_model_dir=./inference/ch_PP-OCRv2_rec_infer/  --image_dir=./doc/imgs_words/en/word_2.png  --use_gpu=True --rec_image_shape="3,48,320"
+```
+
+After executing the command, the predicted information will be printed on the terminal, and the output is as follows:
+```
+[2022/04/28 15:41:45] root INFO: Predicts of ./doc/imgs_words/en/word_2.png:('yourself', 0.98084533)
+```
+
+The text  detection and text recognition inference:
+
+```
+python3 tools/infer/predict_system.py --det_model_dir=./inference/ch_PP-OCRv2_det_infer/ --rec_model_dir=./inference/ch_PP-OCRv2_rec_infer/ --image_dir=./doc/imgs/00057937.jpg --use_gpu=True --rec_image_shape="3,48,320"
+```
+
+After executing the command, the predicted information will be printed out in the terminal, and the visualization results will be saved in the `./inference_results/` directory.
+![](./images/00057937.jpg)
+
+To enable TRT prediction, you only need to set `--use_tensorrt=True` on the basis of the above command:
+```
+python3 tools/infer/predict_system.py --det_model_dir=./inference/ch_PP-OCRv2_det_infer/ --rec_model_dir=./inference/ch_PP-OCRv2_rec_infer/ --image_dir=./doc/imgs/  --rec_image_shape="3,48,320" --use_gpu=True --use_tensorrt=True
+```
+
+For more ppocr model predictions, please refer to[document](../../doc/doc_en/models_list_en.md)

ocr_webapp/PaddleOCR/deploy/Jetson/readme_ch.md

@@ -0,0 +1,86 @@
+[English](readme.md) | 简体中文
+
+# Jetson部署PaddleOCR模型
+
+本节介绍PaddleOCR在Jetson NX、TX2、nano、AGX等系列硬件的部署。
+
+
+## 1. 环境准备
+
+需要准备一台Jetson开发板，如果需要TensorRT预测，需准备好TensorRT环境，建议使用7.1.3版本的TensorRT；
+
+1. Jetson安装PaddlePaddle
+
+PaddlePaddle下载[链接](https://www.paddlepaddle.org.cn/inference/user_guides/download_lib.html#python)
+请选择适合的您Jetpack版本、cuda版本、trt版本的安装包。
+
+安装命令：
+```shell
+# 安装paddle，以paddlepaddle_gpu-2.3.0rc0-cp36-cp36m-linux_aarch64.whl 为例
+pip3 install -U paddlepaddle_gpu-2.3.0rc0-cp36-cp36m-linux_aarch64.whl
+```
+
+
+2. 下载PaddleOCR代码并安装依赖
+
+首先 clone PaddleOCR 代码：
+```
+git clone https://github.com/PaddlePaddle/PaddleOCR
+```
+
+然后，安装依赖：
+```
+cd PaddleOCR
+pip3 install -r requirements.txt
+```
+
+*注：jetson硬件CPU较差，依赖安装较慢，请耐心等待*
+
+
+## 2. 执行预测
+
+从[文档](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/doc/doc_ch/ppocr_introduction.md#6-%E6%A8%A1%E5%9E%8B%E5%BA%93) 模型库中获取PPOCR模型，下面以PP-OCRv3模型为例，介绍在PPOCR模型在jetson上的使用方式：
+
+下载并解压PP-OCRv3模型
+```
+wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar
+wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar
+tar xf ch_PP-OCRv3_det_infer.tar
+tar xf ch_PP-OCRv3_rec_infer.tar
+```
+
+执行文本检测预测：
+```
+cd PaddleOCR
+python3 tools/infer/predict_det.py --det_model_dir=./inference/ch_PP-OCRv2_det_infer/  --image_dir=./doc/imgs/french_0.jpg  --use_gpu=True
+```
+
+执行命令后在终端会打印出预测的信息，并在 `./inference_results/` 下保存可视化结果。
+![](./images/det_res_french_0.jpg)
+
+
+执行文本识别预测：
+```
+python3 tools/infer/predict_det.py --rec_model_dir=./inference/ch_PP-OCRv2_rec_infer/  --image_dir=./doc/imgs_words/en/word_2.png  --use_gpu=True --rec_image_shape="3,48,320"
+```
+
+执行命令后在终端会打印出预测的信息，输出如下：
+```
+[2022/04/28 15:41:45] root INFO: Predicts of ./doc/imgs_words/en/word_2.png:('yourself', 0.98084533)
+```
+
+执行文本检测+文本识别串联预测：
+
+```
+python3 tools/infer/predict_system.py --det_model_dir=./inference/ch_PP-OCRv2_det_infer/ --rec_model_dir=./inference/ch_PP-OCRv2_rec_infer/ --image_dir=./doc/imgs/ --use_gpu=True --rec_image_shape="3,48,320"
+```
+
+执行命令后在终端会打印出预测的信息，并在 `./inference_results/` 下保存可视化结果。
+![](./images/00057937.jpg)
+
+开启TRT预测只需要在以上命令基础上设置`--use_tensorrt=True`即可：
+```
+python3 tools/infer/predict_system.py --det_model_dir=./inference/ch_PP-OCRv2_det_infer/ --rec_model_dir=./inference/ch_PP-OCRv2_rec_infer/ --image_dir=./doc/imgs/00057937.jpg --use_gpu=True --use_tensorrt=True --rec_image_shape="3,48,320"
+```
+
+更多ppocr模型预测请参考[文档](../../doc/doc_ch/models_list.md)

ocr_webapp/PaddleOCR/deploy/README.md

@@ -0,0 +1,31 @@
+English | [简体中文](README_ch.md)
+
+# PP-OCR Deployment
+
+- [Paddle Deployment Introduction](#1)
+- [PP-OCR Deployment](#2)
+
+<a name="1"></a>
+## Paddle Deployment Introduction
+
+Paddle provides a variety of deployment schemes to meet the deployment requirements of different scenarios. Please choose according to the actual situation: 
+
+<div align="center">
+    <img src="../doc/deployment_en.png" width="800">
+</div>
+
+
+<a name="2"></a>
+## PP-OCR Deployment
+
+PP-OCR has supported muti deployment schemes. Click the link to get the specific tutorial.
+
+- [Python Inference](../doc/doc_en/inference_ppocr_en.md)
+- [C++ Inference](./cpp_infer/readme.md)
+- [Serving (Python/C++)](./pdserving/README.md)
+- [Paddle-Lite (ARM CPU/OpenCL ARM GPU)](./lite/readme.md)
+- [Paddle.js](./paddlejs/README.md)
+- [Jetson Inference](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/deploy/Jetson/readme.md)
+- [Paddle2ONNX](./paddle2onnx/readme.md)
+
+If you need the deployment tutorial of academic algorithm models other than PP-OCR, please directly enter the main page of corresponding algorithms, [entrance](../doc/doc_en/algorithm_overview_en.md)。

ocr_webapp/PaddleOCR/deploy/README_ch.md

@@ -0,0 +1,31 @@
+[English](README.md) | 简体中文
+
+# PP-OCR 模型推理部署
+
+- [Paddle 推理部署方式简介](#1)
+- [PP-OCR 推理部署](#2)
+
+<a name="1"></a>
+## Paddle 推理部署方式简介
+
+飞桨提供多种部署方案，以满足不同场景的部署需求，请根据实际情况进行选择：
+
+<div align="center">
+    <img src="../doc/deployment.png" width="800">
+</div>
+
+
+<a name="2"></a>
+## PP-OCR 推理部署
+
+PP-OCR模型已打通多种场景部署方案，点击链接获取具体的使用教程。
+
+- [Python 推理](../doc/doc_ch/inference_ppocr.md)
+- [C++ 推理](./cpp_infer/readme_ch.md)
+- [Serving 服务化部署（Python/C++）](./pdserving/README_CN.md)
+- [Paddle-Lite 端侧部署（ARM CPU/OpenCL ARM GPU）](./lite/readme_ch.md)
+- [Paddle.js 部署](./paddlejs/README_ch.md)
+- [Jetson 推理](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/deploy/Jetson/readme_ch.md)
+- [Paddle2ONNX 推理](./paddle2onnx/readme_ch.md)
+
+需要PP-OCR以外的学术算法模型的推理部署，请直接进入相应算法主页面，[入口](../doc/doc_ch/algorithm_overview.md)。

ocr_webapp/PaddleOCR/deploy/fastdeploy/sophgo/README.md

@@ -0,0 +1,102 @@
+[English](README.md) | 简体中文
+
+# PaddleOCR 模型在SOPHGO上部署方案-FastDeploy
+
+## 1. 说明  
+PaddleOCR支持通过FastDeploy在SOPHGO上部署相关模型.
+
+## 2.支持模型列表
+
+下表中的模型下载链接由PaddleOCR模型库提供, 详见[PP-OCR系列模型列表](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.6/doc/doc_ch/models_list.md)
+
+| PaddleOCR版本 | 文本框检测 | 方向分类模型 | 文字识别 |字典文件| 说明 |
+|:----|:----|:----|:----|:----|:--------|
+| ch_PP-OCRv3[推荐] |[ch_PP-OCRv3_det](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar) | [ch_ppocr_mobile_v2.0_cls](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) | [ch_PP-OCRv3_rec](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar) | [ppocr_keys_v1.txt](https://bj.bcebos.com/paddlehub/fastdeploy/ppocr_keys_v1.txt) | OCRv3系列原始超轻量模型，支持中英文、多语种文本检测 |
+| en_PP-OCRv3[推荐] |[en_PP-OCRv3_det](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_infer.tar) | [ch_ppocr_mobile_v2.0_cls](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) | [en_PP-OCRv3_rec](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_infer.tar) | [en_dict.txt](https://bj.bcebos.com/paddlehub/fastdeploy/en_dict.txt) | OCRv3系列原始超轻量模型，支持英文与数字识别，除检测模型和识别模型的训练数据与中文模型不同以外，无其他区别 |
+| ch_PP-OCRv2 |[ch_PP-OCRv2_det](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar) | [ch_ppocr_mobile_v2.0_cls](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) | [ch_PP-OCRv2_rec](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar) | [ppocr_keys_v1.txt](https://bj.bcebos.com/paddlehub/fastdeploy/ppocr_keys_v1.txt) | OCRv2系列原始超轻量模型，支持中英文、多语种文本检测 |
+| ch_PP-OCRv2_mobile |[ch_ppocr_mobile_v2.0_det](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) | [ch_ppocr_mobile_v2.0_cls](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) | [ch_ppocr_mobile_v2.0_rec](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) | [ppocr_keys_v1.txt](https://bj.bcebos.com/paddlehub/fastdeploy/ppocr_keys_v1.txt) | OCRv2系列原始超轻量模型，支持中英文、多语种文本检测,比PPOCRv2更加轻量 |
+| ch_PP-OCRv2_server |[ch_ppocr_server_v2.0_det](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) | [ch_ppocr_mobile_v2.0_cls](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) | [ch_ppocr_server_v2.0_rec](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) |[ppocr_keys_v1.txt](https://bj.bcebos.com/paddlehub/fastdeploy/ppocr_keys_v1.txt) | OCRv2服务器系列模型, 支持中英文、多语种文本检测，比超轻量模型更大，但效果更好|
+
+## 3. 准备PP-OCR推理模型以及转换模型
+
+PP-OCRv3包括文本检测模型（ch_PP-OCRv3_det）、方向分类模型（ch_ppocr_mobile_v2.0_cls）、文字识别模型（ch_PP-OCRv3_rec）  
+SOPHGO-TPU部署模型前需要将以上Paddle模型转换成bmodel模型，我们以ch_PP-OCRv3_det模型为例，具体步骤如下:
+- 下载Paddle模型[ch_PP-OCRv3_det](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar)
+- Pddle模型转换为ONNX模型，请参考[Paddle2ONNX](https://github.com/PaddlePaddle/Paddle2ONNX)
+- ONNX模型转换bmodel模型的过程，请参考[TPU-MLIR](https://github.com/sophgo/tpu-mlir)
+下面我们提供一个example, 供用户参考，完成模型的转换.
+
+### 3.1 下载ch_PP-OCRv3_det模型,并转换为ONNX模型
+```shell
+wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar
+tar xvf ch_PP-OCRv3_det_infer.tar
+
+# 修改ch_PP-OCRv3_det模型的输入shape，由动态输入变成固定输入
+python paddle_infer_shape.py --model_dir ch_PP-OCRv3_det_infer \
+                             --model_filename inference.pdmodel \
+                             --params_filename inference.pdiparams \
+                             --save_dir ch_PP-OCRv3_det_infer_fix \
+                             --input_shape_dict="{'x':[1,3,960,608]}"
+
+# 请用户自行安装最新发布版本的paddle2onnx, 转换模型到ONNX格式的模型
+paddle2onnx --model_dir ch_PP-OCRv3_det_infer_fix \
+            --model_filename inference.pdmodel \
+            --params_filename inference.pdiparams \
+            --save_file ch_PP-OCRv3_det_infer_fix.onnx \
+            --enable_dev_version True
+```
+
+### 3.2 导出bmodel模型
+
+以转换BM1684x的bmodel模型为例子，我们需要下载[TPU-MLIR](https://github.com/sophgo/tpu-mlir)工程，安装过程具体参见[TPU-MLIR文档](https://github.com/sophgo/tpu-mlir/blob/master/README.md)。
+#### 3.2.1    安装
+``` shell
+docker pull sophgo/tpuc_dev:latest
+
+# myname1234是一个示例，也可以设置其他名字
+docker run --privileged --name myname1234 -v $PWD:/workspace -it sophgo/tpuc_dev:latest
+
+source ./envsetup.sh
+./build.sh
+```
+
+#### 3.2.2    ONNX模型转换为bmodel模型
+``` shell
+mkdir ch_PP-OCRv3_det && cd ch_PP-OCRv3_det
+
+#在该文件中放入测试图片，同时将上一步转换的ch_PP-OCRv3_det_infer_fix.onnx放入该文件夹中
+cp -rf ${REGRESSION_PATH}/dataset/COCO2017 .
+cp -rf ${REGRESSION_PATH}/image .
+#放入onnx模型文件ch_PP-OCRv3_det_infer_fix.onnx
+
+mkdir workspace && cd workspace
+
+#将ONNX模型转换为mlir模型，其中参数--output_names可以通过NETRON查看
+model_transform.py \
+    --model_name ch_PP-OCRv3_det \
+    --model_def ../ch_PP-OCRv3_det_infer_fix.onnx \
+    --input_shapes [[1,3,960,608]] \
+    --mean 0.0,0.0,0.0 \
+    --scale 0.0039216,0.0039216,0.0039216 \
+    --keep_aspect_ratio \
+    --pixel_format rgb \
+    --output_names sigmoid_0.tmp_0 \
+    --test_input ../image/dog.jpg \
+    --test_result ch_PP-OCRv3_det_top_outputs.npz \
+    --mlir ch_PP-OCRv3_det.mlir
+
+#将mlir模型转换为BM1684x的F32 bmodel模型
+model_deploy.py \
+  --mlir ch_PP-OCRv3_det.mlir \
+  --quantize F32 \
+  --chip bm1684x \
+  --test_input ch_PP-OCRv3_det_in_f32.npz \
+  --test_reference ch_PP-OCRv3_det_top_outputs.npz \
+  --model ch_PP-OCRv3_det_1684x_f32.bmodel
+```
+最终获得可以在BM1684x上能够运行的bmodel模型ch_PP-OCRv3_det_1684x_f32.bmodel。按照上面同样的方法，可以将ch_ppocr_mobile_v2.0_cls，ch_PP-OCRv3_rec转换为bmodel的格式。如果需要进一步对模型进行加速，可以将ONNX模型转换为INT8 bmodel，具体步骤参见[TPU-MLIR文档](https://github.com/sophgo/tpu-mlir/blob/master/README.md)。
+
+
+## 4. 详细部署的部署示例  
+- [Python部署](python)
+- [C++部署](cpp)

ocr_webapp/PaddleOCR/deploy/fastdeploy/sophgo/python/README.md

@@ -0,0 +1,52 @@
+[English](README.md) | 简体中文
+# PP-OCRv3 SOPHGO Python部署示例
+本目录下提供`infer.py`快速完成 PP-OCRv3 在SOPHGO TPU上部署的示例。
+
+## 1. 部署环境准备
+
+在部署前，需自行编译基于算能硬件的FastDeploy python wheel包并安装，参考文档[算能硬件部署环境](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/cn/build_and_install#算能硬件部署环境)
+
+
+## 2.运行部署示例
+
+### 2.1 模型准备
+将Paddle模型转换为SOPHGO bmodel模型, 转换步骤参考[文档](../README.md)  
+
+### 2.2 开始部署
+```bash
+# 下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd  FastDeploy/examples/vision/ocr/PP-OCR/sophgo/python
+
+# 如果您希望从PaddleOCR下载示例代码，请运行
+git clone https://github.com/PaddlePaddle/PaddleOCR.git
+# 注意：如果当前分支找不到下面的fastdeploy测试代码，请切换到dygraph分支
+git checkout dygraph
+cd PaddleOCR/deploy/fastdeploy/sophgo/python
+
+# 下载图片
+wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/doc/imgs/12.jpg
+
+#下载字典文件
+wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/ppocr/utils/ppocr_keys_v1.txt
+
+# 推理
+python3 infer.py --det_model ocr_bmodel/ch_PP-OCRv3_det_1684x_f32.bmodel \
+                 --cls_model ocr_bmodel/ch_ppocr_mobile_v2.0_cls_1684x_f32.bmodel \
+                 --rec_model ocr_bmodel/ch_PP-OCRv3_rec_1684x_f32.bmodel \
+                 --rec_label_file ../ppocr_keys_v1.txt \  
+                 --image ../12.jpg
+
+# 运行完成后返回结果如下所示
+det boxes: [[42,413],[483,391],[484,428],[43,450]]rec text: 上海斯格威铂尔大酒店 rec score:0.952958 cls label: 0 cls score: 1.000000
+det boxes: [[187,456],[399,448],[400,480],[188,488]]rec text: 打浦路15号 rec score:0.897335 cls label: 0 cls score: 1.000000
+det boxes: [[23,507],[513,488],[515,529],[24,548]]rec text: 绿洲仕格维花园公寓 rec score:0.994589 cls label: 0 cls score: 1.000000
+det boxes: [[74,553],[427,542],[428,571],[75,582]]rec text: 打浦路252935号 rec score:0.900663 cls label: 0 cls score: 1.000000
+
+可视化结果保存在sophgo_result.jpg中
+```
+
+## 3. 其它文档
+- [PP-OCRv3 C++部署](../cpp)
+- [转换 PP-OCRv3 SOPHGO模型文档](../README.md)
+- 如果用户想要调整前后处理超参数、单独使用文字检测识别模型、使用其他模型等，更多详细文档与说明请参考[PP-OCR系列在CPU/GPU上的部署](../../cpu-gpu/cpp/README.md)

ocr_webapp/PaddleOCR/deploy/fastdeploy/web/README.md

@@ -0,0 +1,33 @@
+[English](README.md) | 简体中文
+# PP-OCRv3 前端部署示例
+
+本节介绍部署PaddleOCR的PP-OCRv3模型在浏览器中运行，以及@paddle-js-models/ocr npm包中的js接口。
+
+
+## 1. 前端部署PP-OCRv3模型
+PP-OCRv3模型web demo使用[**参考文档**](https://github.com/PaddlePaddle/FastDeploy/tree/develop/examples/application/js/web_demo)
+
+## 2. PP-OCRv3 js接口
+
+```
+import * as ocr from "@paddle-js-models/ocr";
+await ocr.init(detConfig, recConfig);
+const res = await ocr.recognize(img, option, postConfig);
+```
+ocr模型加载和初始化，其中模型为Paddle.js模型格式，js模型转换方式参考[文档](https://github.com/PaddlePaddle/FastDeploy/tree/develop/examples/application/js/web_demo/README.md)
+
+**init函数参数**
+
+> * **detConfig**(dict): 文本检测模型配置参数，默认值为 {modelPath: 'https://js-models.bj.bcebos.com/PaddleOCR/PP-OCRv3/ch_PP-OCRv3_det_infer_js_960/model.json', fill: '#fff', mean: [0.485, 0.456, 0.406],std: [0.229, 0.224, 0.225]}; 其中，modelPath为文本检测模型路径，fill 为图像预处理padding的值，mean和std分别为预处理的均值和标准差
+> * **recConfig**(dict)): 文本识别模型配置参数，默认值为 {modelPath: 'https://js-models.bj.bcebos.com/PaddleOCR/PP-OCRv3/ch_PP-OCRv3_rec_infer_js/model.json', fill: '#000', mean: [0.5, 0.5, 0.5], std: [0.5, 0.5, 0.5]}; 其中，modelPath为文本检测模型路径，fill 为图像预处理padding的值，mean和std分别为预处理的均值和标准差
+
+
+**recognize函数参数**
+
+> * **img**(HTMLImageElement): 输入图像参数，类型为HTMLImageElement。
+> * **option**(dict): 可视化文本检测框的canvas参数，可不用设置。
+> * **postConfig**(dict): 文本检测后处理参数，默认值为：{shape: 960, thresh: 0.3, box_thresh: 0.6, unclip_ratio:1.5}; thresh是输出预测图的二值化阈值；box_thresh是输出框的阈值，低于此值的预测框会被丢弃，unclip_ratio是输出框扩大的比例。
+
+
+## 其它文档
+- [PP-OCRv3 微信小程序部署文档](https://github.com/PaddlePaddle/FastDeploy/tree/develop/examples/application/js/mini_program)

ocr_webapp/PaddleOCR/deploy/hubserving/kie_ser/__init__.py

@@ -0,0 +1,13 @@
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.

ocr_webapp/PaddleOCR/deploy/hubserving/kie_ser/config.json

@@ -0,0 +1,16 @@
+{
+    "modules_info": {
+        "kie_ser": {
+            "init_args": {
+                "version": "1.0.0",
+                "use_gpu": true
+            },
+            "predict_args": {
+            }
+        }
+    },
+    "port": 8871,
+    "use_multiprocess": false,
+    "workers": 2
+}
+

ocr_webapp/PaddleOCR/deploy/hubserving/kie_ser/module.py

@@ -0,0 +1,145 @@
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import os
+import sys
+sys.path.insert(0, ".")
+import copy
+
+import time
+import paddlehub
+from paddlehub.common.logger import logger
+from paddlehub.module.module import moduleinfo, runnable, serving
+import cv2
+import numpy as np
+import paddlehub as hub
+
+from tools.infer.utility import base64_to_cv2
+from ppstructure.kie.predict_kie_token_ser import SerPredictor
+from ppstructure.utility import parse_args
+
+from deploy.hubserving.kie_ser.params import read_params
+
+
+@moduleinfo(
+    name="kie_ser",
+    version="1.0.0",
+    summary="kie ser service",
+    author="paddle-dev",
+    author_email="paddle-dev@baidu.com",
+    type="cv/KIE_SER")
+class KIESer(hub.Module):
+    def _initialize(self, use_gpu=False, enable_mkldnn=False):
+        """
+        initialize with the necessary elements
+        """
+        cfg = self.merge_configs()
+
+        cfg.use_gpu = use_gpu
+        if use_gpu:
+            try:
+                _places = os.environ["CUDA_VISIBLE_DEVICES"]
+                int(_places[0])
+                print("use gpu: ", use_gpu)
+                print("CUDA_VISIBLE_DEVICES: ", _places)
+                cfg.gpu_mem = 8000
+            except:
+                raise RuntimeError(
+                    "Environment Variable CUDA_VISIBLE_DEVICES is not set correctly. If you wanna use gpu, please set CUDA_VISIBLE_DEVICES via export CUDA_VISIBLE_DEVICES=cuda_device_id."
+                )
+        cfg.ir_optim = True
+        cfg.enable_mkldnn = enable_mkldnn
+
+        self.ser_predictor = SerPredictor(cfg)
+
+    def merge_configs(self, ):
+        # deafult cfg
+        backup_argv = copy.deepcopy(sys.argv)
+        sys.argv = sys.argv[:1]
+        cfg = parse_args()
+
+        update_cfg_map = vars(read_params())
+
+        for key in update_cfg_map:
+            cfg.__setattr__(key, update_cfg_map[key])
+
+        sys.argv = copy.deepcopy(backup_argv)
+        return cfg
+
+    def read_images(self, paths=[]):
+        images = []
+        for img_path in paths:
+            assert os.path.isfile(
+                img_path), "The {} isn't a valid file.".format(img_path)
+            img = cv2.imread(img_path)
+            if img is None:
+                logger.info("error in loading image:{}".format(img_path))
+                continue
+            images.append(img)
+        return images
+
+    def predict(self, images=[], paths=[]):
+        """
+        Get the chinese texts in the predicted images.
+        Args:
+            images (list(numpy.ndarray)): images data, shape of each is [H, W, C]. If images not paths
+            paths (list[str]): The paths of images. If paths not images
+        Returns:
+            res (list): The result of chinese texts and save path of images.
+        """
+        if images != [] and isinstance(images, list) and paths == []:
+            predicted_data = images
+        elif images == [] and isinstance(paths, list) and paths != []:
+            predicted_data = self.read_images(paths)
+        else:
+            raise TypeError("The input data is inconsistent with expectations.")
+
+        assert predicted_data != [], "There is not any image to be predicted. Please check the input data."
+
+        all_results = []
+        for img in predicted_data:
+            if img is None:
+                logger.info("error in loading image")
+                all_results.append([])
+                continue
+            starttime = time.time()
+            ser_res, _, elapse = self.ser_predictor(img)
+            elapse = time.time() - starttime
+            logger.info("Predict time: {}".format(elapse))
+            all_results.append(ser_res)
+        return all_results
+
+    @serving
+    def serving_method(self, images, **kwargs):
+        """
+        Run as a service.
+        """
+        images_decode = [base64_to_cv2(image) for image in images]
+        results = self.predict(images_decode, **kwargs)
+        return results
+
+
+if __name__ == '__main__':
+    ocr = OCRSystem()
+    ocr._initialize()
+    image_path = [
+        './doc/imgs/11.jpg',
+        './doc/imgs/12.jpg',
+    ]
+    res = ocr.predict(paths=image_path)
+    print(res)

ocr_webapp/PaddleOCR/deploy/hubserving/kie_ser/params.py

@@ -0,0 +1,38 @@
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+from deploy.hubserving.ocr_system.params import read_params as pp_ocr_read_params
+
+
+class Config(object):
+    pass
+
+
+def read_params():
+    cfg = pp_ocr_read_params()
+
+    # SER params
+    cfg.kie_algorithm = "LayoutXLM"
+    cfg.use_visual_backbone = False
+
+    cfg.ser_model_dir = "./inference/ser_vi_layoutxlm_xfund_infer"
+    cfg.ser_dict_path = "train_data/XFUND/class_list_xfun.txt"
+    cfg.vis_font_path = "./doc/fonts/simfang.ttf"
+    cfg.ocr_order_method = "tb-yx"
+
+    return cfg

ocr_webapp/PaddleOCR/deploy/hubserving/kie_ser_re/__init__.py

@@ -0,0 +1,13 @@
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.

ocr_webapp/PaddleOCR/deploy/hubserving/kie_ser_re/config.json

@@ -0,0 +1,16 @@
+{
+    "modules_info": {
+        "kie_ser_re": {
+            "init_args": {
+                "version": "1.0.0",
+                "use_gpu": true
+            },
+            "predict_args": {
+            }
+        }
+    },
+    "port": 8872,
+    "use_multiprocess": false,
+    "workers": 2
+}
+

ocr_webapp/PaddleOCR/deploy/hubserving/kie_ser_re/module.py

@@ -0,0 +1,147 @@
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import os
+import sys
+sys.path.insert(0, ".")
+import copy
+
+import time
+import paddlehub
+from paddlehub.common.logger import logger
+from paddlehub.module.module import moduleinfo, runnable, serving
+import cv2
+import numpy as np
+import paddlehub as hub
+
+from tools.infer.utility import base64_to_cv2
+from ppstructure.kie.predict_kie_token_ser_re import SerRePredictor
+from ppstructure.utility import parse_args
+
+from deploy.hubserving.kie_ser_re.params import read_params
+
+
+@moduleinfo(
+    name="kie_ser_re",
+    version="1.0.0",
+    summary="kie ser re service",
+    author="paddle-dev",
+    author_email="paddle-dev@baidu.com",
+    type="cv/KIE_SER_RE")
+class KIESerRE(hub.Module):
+    def _initialize(self, use_gpu=False, enable_mkldnn=False):
+        """
+        initialize with the necessary elements
+        """
+        cfg = self.merge_configs()
+
+        cfg.use_gpu = use_gpu
+        if use_gpu:
+            try:
+                _places = os.environ["CUDA_VISIBLE_DEVICES"]
+                int(_places[0])
+                print("use gpu: ", use_gpu)
+                print("CUDA_VISIBLE_DEVICES: ", _places)
+                cfg.gpu_mem = 8000
+            except:
+                raise RuntimeError(
+                    "Environment Variable CUDA_VISIBLE_DEVICES is not set correctly. If you wanna use gpu, please set CUDA_VISIBLE_DEVICES via export CUDA_VISIBLE_DEVICES=cuda_device_id."
+                )
+        cfg.ir_optim = True
+        cfg.enable_mkldnn = enable_mkldnn
+
+        self.ser_re_predictor = SerRePredictor(cfg)
+
+    def merge_configs(self, ):
+        # deafult cfg
+        backup_argv = copy.deepcopy(sys.argv)
+        sys.argv = sys.argv[:1]
+        cfg = parse_args()
+
+        update_cfg_map = vars(read_params())
+
+        for key in update_cfg_map:
+            cfg.__setattr__(key, update_cfg_map[key])
+
+        sys.argv = copy.deepcopy(backup_argv)
+        return cfg
+
+    def read_images(self, paths=[]):
+        images = []
+        for img_path in paths:
+            assert os.path.isfile(
+                img_path), "The {} isn't a valid file.".format(img_path)
+            img = cv2.imread(img_path)
+            if img is None:
+                logger.info("error in loading image:{}".format(img_path))
+                continue
+            images.append(img)
+        return images
+
+    def predict(self, images=[], paths=[]):
+        """
+        Get the chinese texts in the predicted images.
+        Args:
+            images (list(numpy.ndarray)): images data, shape of each is [H, W, C]. If images not paths
+            paths (list[str]): The paths of images. If paths not images
+        Returns:
+            res (list): The result of chinese texts and save path of images.
+        """
+        if images != [] and isinstance(images, list) and paths == []:
+            predicted_data = images
+        elif images == [] and isinstance(paths, list) and paths != []:
+            predicted_data = self.read_images(paths)
+        else:
+            raise TypeError("The input data is inconsistent with expectations.")
+
+        assert predicted_data != [], "There is not any image to be predicted. Please check the input data."
+
+        all_results = []
+        for img in predicted_data:
+            if img is None:
+                logger.info("error in loading image")
+                all_results.append([])
+                continue
+            print(img.shape)
+            starttime = time.time()
+            re_res, _ = self.ser_re_predictor(img)
+            print(re_res)
+            elapse = time.time() - starttime
+            logger.info("Predict time: {}".format(elapse))
+            all_results.append(re_res)
+        return all_results
+
+    @serving
+    def serving_method(self, images, **kwargs):
+        """
+        Run as a service.
+        """
+        images_decode = [base64_to_cv2(image) for image in images]
+        results = self.predict(images_decode, **kwargs)
+        return results
+
+
+if __name__ == '__main__':
+    ocr = OCRSystem()
+    ocr._initialize()
+    image_path = [
+        './doc/imgs/11.jpg',
+        './doc/imgs/12.jpg',
+    ]
+    res = ocr.predict(paths=image_path)
+    print(res)

ocr_webapp/PaddleOCR/deploy/hubserving/kie_ser_re/params.py

@@ -0,0 +1,40 @@
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+from deploy.hubserving.ocr_system.params import read_params as pp_ocr_read_params
+
+
+class Config(object):
+    pass
+
+
+def read_params():
+    cfg = pp_ocr_read_params()
+
+    # SER params
+    cfg.kie_algorithm = "LayoutXLM"
+    cfg.use_visual_backbone = False
+
+    cfg.ser_model_dir = "./inference/ser_vi_layoutxlm_xfund_infer"
+    cfg.re_model_dir = "./inference/re_vi_layoutxlm_xfund_infer"
+
+    cfg.ser_dict_path = "train_data/XFUND/class_list_xfun.txt"
+    cfg.vis_font_path = "./doc/fonts/simfang.ttf"
+    cfg.ocr_order_method = "tb-yx"
+
+    return cfg

ocr_webapp/PaddleOCR/deploy/hubserving/ocr_cls/__init__.py

@@ -0,0 +1,13 @@
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.

ocr_webapp/PaddleOCR/deploy/hubserving/ocr_cls/config.json

@@ -0,0 +1,15 @@
+{
+    "modules_info": {
+        "ocr_cls": {
+            "init_args": {
+                "version": "1.0.0",
+                "use_gpu": true
+            },
+            "predict_args": {
+            }
+        }
+    },
+    "port": 8866,
+    "use_multiprocess": false,
+    "workers": 2
+}

ocr_webapp/PaddleOCR/deploy/hubserving/ocr_cls/module.py

@@ -0,0 +1,151 @@
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import os
+import sys
+sys.path.insert(0, ".")
+import copy
+import paddlehub
+from paddlehub.common.logger import logger
+from paddlehub.module.module import moduleinfo, runnable, serving
+import cv2
+import paddlehub as hub
+
+from tools.infer.utility import base64_to_cv2
+from tools.infer.predict_cls import TextClassifier
+from tools.infer.utility import parse_args
+from deploy.hubserving.ocr_cls.params import read_params
+
+
+@moduleinfo(
+    name="ocr_cls",
+    version="1.0.0",
+    summary="ocr angle cls service",
+    author="paddle-dev",
+    author_email="paddle-dev@baidu.com",
+    type="cv/text_angle_cls")
+class OCRCls(hub.Module):
+    def _initialize(self, use_gpu=False, enable_mkldnn=False):
+        """
+        initialize with the necessary elements
+        """
+        cfg = self.merge_configs()
+
+        cfg.use_gpu = use_gpu
+        if use_gpu:
+            try:
+                _places = os.environ["CUDA_VISIBLE_DEVICES"]
+                int(_places[0])
+                print("use gpu: ", use_gpu)
+                print("CUDA_VISIBLE_DEVICES: ", _places)
+                cfg.gpu_mem = 8000
+            except:
+                raise RuntimeError(
+                    "Environment Variable CUDA_VISIBLE_DEVICES is not set correctly. If you wanna use gpu, please set CUDA_VISIBLE_DEVICES via export CUDA_VISIBLE_DEVICES=cuda_device_id."
+                )
+        cfg.ir_optim = True
+        cfg.enable_mkldnn = enable_mkldnn
+
+        self.text_classifier = TextClassifier(cfg)
+
+    def merge_configs(self, ):
+        # deafult cfg
+        backup_argv = copy.deepcopy(sys.argv)
+        sys.argv = sys.argv[:1]
+        cfg = parse_args()
+
+        update_cfg_map = vars(read_params())
+
+        for key in update_cfg_map:
+            cfg.__setattr__(key, update_cfg_map[key])
+
+        sys.argv = copy.deepcopy(backup_argv)
+        return cfg
+
+    def read_images(self, paths=[]):
+        images = []
+        for img_path in paths:
+            assert os.path.isfile(
+                img_path), "The {} isn't a valid file.".format(img_path)
+            img = cv2.imread(img_path)
+            if img is None:
+                logger.info("error in loading image:{}".format(img_path))
+                continue
+            images.append(img)
+        return images
+
+    def predict(self, images=[], paths=[]):
+        """
+        Get the text angle in the predicted images.
+        Args:
+            images (list(numpy.ndarray)): images data, shape of each is [H, W, C]. If images not paths
+            paths (list[str]): The paths of images. If paths not images
+        Returns:
+            res (list): The result of text detection box and save path of images.
+        """
+
+        if images != [] and isinstance(images, list) and paths == []:
+            predicted_data = images
+        elif images == [] and isinstance(paths, list) and paths != []:
+            predicted_data = self.read_images(paths)
+        else:
+            raise TypeError("The input data is inconsistent with expectations.")
+
+        assert predicted_data != [], "There is not any image to be predicted. Please check the input data."
+
+        img_list = []
+        for img in predicted_data:
+            if img is None:
+                continue
+            img_list.append(img)
+
+        rec_res_final = []
+        try:
+            img_list, cls_res, predict_time = self.text_classifier(img_list)
+            for dno in range(len(cls_res)):
+                angle, score = cls_res[dno]
+                rec_res_final.append({
+                    'angle': angle,
+                    'confidence': float(score),
+                })
+        except Exception as e:
+            print(e)
+            return [[]]
+
+        return [rec_res_final]
+
+    @serving
+    def serving_method(self, images, **kwargs):
+        """
+        Run as a service.
+        """
+        images_decode = [base64_to_cv2(image) for image in images]
+        results = self.predict(images_decode, **kwargs)
+        return results
+
+
+if __name__ == '__main__':
+    ocr = OCRCls()
+    ocr._initialize()
+    image_path = [
+        './doc/imgs_words/ch/word_1.jpg',
+        './doc/imgs_words/ch/word_2.jpg',
+        './doc/imgs_words/ch/word_3.jpg',
+    ]
+    res = ocr.predict(paths=image_path)
+    print(res)

ocr_webapp/PaddleOCR/deploy/hubserving/ocr_cls/params.py

@@ -0,0 +1,37 @@
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+
+class Config(object):
+    pass
+
+
+def read_params():
+    cfg = Config()
+
+    #params for text classifier
+    cfg.cls_model_dir = "./inference/ch_ppocr_mobile_v2.0_cls_infer/"
+    cfg.cls_image_shape = "3, 48, 192"
+    cfg.label_list = ['0', '180']
+    cfg.cls_batch_num = 30
+    cfg.cls_thresh = 0.9
+
+    cfg.use_pdserving = False
+    cfg.use_tensorrt = False
+
+    return cfg

ocr_webapp/PaddleOCR/deploy/hubserving/ocr_det/__init__.py

@@ -0,0 +1,13 @@
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.

ocr_webapp/PaddleOCR/deploy/hubserving/ocr_det/config.json

@@ -0,0 +1,15 @@
+{
+    "modules_info": {
+        "ocr_det": {
+            "init_args": {
+                "version": "1.0.0",
+                "use_gpu": true
+            },
+            "predict_args": {
+            }
+        }
+    },
+    "port": 8865,
+    "use_multiprocess": false,
+    "workers": 2    
+}

ocr_webapp/PaddleOCR/deploy/hubserving/ocr_det/module.py

@@ -0,0 +1,148 @@
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import os
+import sys
+sys.path.insert(0, ".")
+
+import copy
+import paddlehub
+from paddlehub.common.logger import logger
+from paddlehub.module.module import moduleinfo, runnable, serving
+import cv2
+import numpy as np
+import paddlehub as hub
+
+from tools.infer.utility import base64_to_cv2
+from tools.infer.predict_det import TextDetector
+from tools.infer.utility import parse_args
+from deploy.hubserving.ocr_system.params import read_params
+
+
+@moduleinfo(
+    name="ocr_det",
+    version="1.0.0",
+    summary="ocr detection service",
+    author="paddle-dev",
+    author_email="paddle-dev@baidu.com",
+    type="cv/text_detection")
+class OCRDet(hub.Module):
+    def _initialize(self, use_gpu=False, enable_mkldnn=False):
+        """
+        initialize with the necessary elements
+        """
+        cfg = self.merge_configs()
+
+        cfg.use_gpu = use_gpu
+        if use_gpu:
+            try:
+                _places = os.environ["CUDA_VISIBLE_DEVICES"]
+                int(_places[0])
+                print("use gpu: ", use_gpu)
+                print("CUDA_VISIBLE_DEVICES: ", _places)
+                cfg.gpu_mem = 8000
+            except:
+                raise RuntimeError(
+                    "Environment Variable CUDA_VISIBLE_DEVICES is not set correctly. If you wanna use gpu, please set CUDA_VISIBLE_DEVICES via export CUDA_VISIBLE_DEVICES=cuda_device_id."
+                )
+        cfg.ir_optim = True
+        cfg.enable_mkldnn = enable_mkldnn
+
+        self.text_detector = TextDetector(cfg)
+
+    def merge_configs(self, ):
+        # deafult cfg
+        backup_argv = copy.deepcopy(sys.argv)
+        sys.argv = sys.argv[:1]
+        cfg = parse_args()
+
+        update_cfg_map = vars(read_params())
+
+        for key in update_cfg_map:
+            cfg.__setattr__(key, update_cfg_map[key])
+
+        sys.argv = copy.deepcopy(backup_argv)
+        return cfg
+
+    def read_images(self, paths=[]):
+        images = []
+        for img_path in paths:
+            assert os.path.isfile(
+                img_path), "The {} isn't a valid file.".format(img_path)
+            img = cv2.imread(img_path)
+            if img is None:
+                logger.info("error in loading image:{}".format(img_path))
+                continue
+            images.append(img)
+        return images
+
+    def predict(self, images=[], paths=[]):
+        """
+        Get the text box in the predicted images.
+        Args:
+            images (list(numpy.ndarray)): images data, shape of each is [H, W, C]. If images not paths
+            paths (list[str]): The paths of images. If paths not images
+        Returns:
+            res (list): The result of text detection box and save path of images.
+        """
+
+        if images != [] and isinstance(images, list) and paths == []:
+            predicted_data = images
+        elif images == [] and isinstance(paths, list) and paths != []:
+            predicted_data = self.read_images(paths)
+        else:
+            raise TypeError("The input data is inconsistent with expectations.")
+
+        assert predicted_data != [], "There is not any image to be predicted. Please check the input data."
+
+        all_results = []
+        for img in predicted_data:
+            if img is None:
+                logger.info("error in loading image")
+                all_results.append([])
+                continue
+            dt_boxes, elapse = self.text_detector(img)
+            logger.info("Predict time : {}".format(elapse))
+
+            rec_res_final = []
+            for dno in range(len(dt_boxes)):
+                rec_res_final.append({
+                    'text_region': dt_boxes[dno].astype(np.int32).tolist()
+                })
+            all_results.append(rec_res_final)
+        return all_results
+
+    @serving
+    def serving_method(self, images, **kwargs):
+        """
+        Run as a service.
+        """
+        images_decode = [base64_to_cv2(image) for image in images]
+        results = self.predict(images_decode, **kwargs)
+        return results
+
+
+if __name__ == '__main__':
+    ocr = OCRDet()
+    ocr._initialize()
+    image_path = [
+        './doc/imgs/11.jpg',
+        './doc/imgs/12.jpg',
+    ]
+    res = ocr.predict(paths=image_path)
+    print(res)

ocr_webapp/PaddleOCR/deploy/hubserving/ocr_det/params.py

@@ -0,0 +1,48 @@
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+
+class Config(object):
+    pass
+
+
+def read_params():
+    cfg = Config()
+
+    #params for text detector
+    cfg.det_algorithm = "DB"
+    cfg.det_model_dir = "./inference/ch_PP-OCRv3_det_infer/"
+    cfg.det_limit_side_len = 960
+    cfg.det_limit_type = 'max'
+
+    #DB parmas
+    cfg.det_db_thresh = 0.3
+    cfg.det_db_box_thresh = 0.6
+    cfg.det_db_unclip_ratio = 1.5
+    cfg.use_dilation = False
+    cfg.det_db_score_mode = "fast"
+
+    # #EAST parmas
+    # cfg.det_east_score_thresh = 0.8
+    # cfg.det_east_cover_thresh = 0.1
+    # cfg.det_east_nms_thresh = 0.2
+
+    cfg.use_pdserving = False
+    cfg.use_tensorrt = False
+
+    return cfg

ocr_webapp/PaddleOCR/deploy/hubserving/ocr_rec/__init__.py

@@ -0,0 +1,13 @@
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.

ocr_webapp/PaddleOCR/deploy/hubserving/ocr_rec/config.json

@@ -0,0 +1,15 @@
+{
+    "modules_info": {
+        "ocr_rec": {
+            "init_args": {
+                "version": "1.0.0",
+                "use_gpu": true
+            },
+            "predict_args": {
+            }
+        }
+    },
+    "port": 8867,
+    "use_multiprocess": false,
+    "workers": 2
+}

ocr_webapp/PaddleOCR/deploy/hubserving/ocr_rec/module.py

@@ -0,0 +1,151 @@
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import os
+import sys
+sys.path.insert(0, ".")
+import copy
+import paddlehub
+from paddlehub.common.logger import logger
+from paddlehub.module.module import moduleinfo, runnable, serving
+import cv2
+import paddlehub as hub
+
+from tools.infer.utility import base64_to_cv2
+from tools.infer.predict_rec import TextRecognizer
+from tools.infer.utility import parse_args
+from deploy.hubserving.ocr_rec.params import read_params
+
+
+@moduleinfo(
+    name="ocr_rec",
+    version="1.0.0",
+    summary="ocr recognition service",
+    author="paddle-dev",
+    author_email="paddle-dev@baidu.com",
+    type="cv/text_recognition")
+class OCRRec(hub.Module):
+    def _initialize(self, use_gpu=False, enable_mkldnn=False):
+        """
+        initialize with the necessary elements
+        """
+        cfg = self.merge_configs()
+
+        cfg.use_gpu = use_gpu
+        if use_gpu:
+            try:
+                _places = os.environ["CUDA_VISIBLE_DEVICES"]
+                int(_places[0])
+                print("use gpu: ", use_gpu)
+                print("CUDA_VISIBLE_DEVICES: ", _places)
+                cfg.gpu_mem = 8000
+            except:
+                raise RuntimeError(
+                    "Environment Variable CUDA_VISIBLE_DEVICES is not set correctly. If you wanna use gpu, please set CUDA_VISIBLE_DEVICES via export CUDA_VISIBLE_DEVICES=cuda_device_id."
+                )
+        cfg.ir_optim = True
+        cfg.enable_mkldnn = enable_mkldnn
+
+        self.text_recognizer = TextRecognizer(cfg)
+
+    def merge_configs(self, ):
+        # deafult cfg
+        backup_argv = copy.deepcopy(sys.argv)
+        sys.argv = sys.argv[:1]
+        cfg = parse_args()
+
+        update_cfg_map = vars(read_params())
+
+        for key in update_cfg_map:
+            cfg.__setattr__(key, update_cfg_map[key])
+
+        sys.argv = copy.deepcopy(backup_argv)
+        return cfg
+
+    def read_images(self, paths=[]):
+        images = []
+        for img_path in paths:
+            assert os.path.isfile(
+                img_path), "The {} isn't a valid file.".format(img_path)
+            img = cv2.imread(img_path)
+            if img is None:
+                logger.info("error in loading image:{}".format(img_path))
+                continue
+            images.append(img)
+        return images
+
+    def predict(self, images=[], paths=[]):
+        """
+        Get the text box in the predicted images.
+        Args:
+            images (list(numpy.ndarray)): images data, shape of each is [H, W, C]. If images not paths
+            paths (list[str]): The paths of images. If paths not images
+        Returns:
+            res (list): The result of text detection box and save path of images.
+        """
+
+        if images != [] and isinstance(images, list) and paths == []:
+            predicted_data = images
+        elif images == [] and isinstance(paths, list) and paths != []:
+            predicted_data = self.read_images(paths)
+        else:
+            raise TypeError("The input data is inconsistent with expectations.")
+
+        assert predicted_data != [], "There is not any image to be predicted. Please check the input data."
+
+        img_list = []
+        for img in predicted_data:
+            if img is None:
+                continue
+            img_list.append(img)
+
+        rec_res_final = []
+        try:
+            rec_res, predict_time = self.text_recognizer(img_list)
+            for dno in range(len(rec_res)):
+                text, score = rec_res[dno]
+                rec_res_final.append({
+                    'text': text,
+                    'confidence': float(score),
+                })
+        except Exception as e:
+            print(e)
+            return [[]]
+
+        return [rec_res_final]
+
+    @serving
+    def serving_method(self, images, **kwargs):
+        """
+        Run as a service.
+        """
+        images_decode = [base64_to_cv2(image) for image in images]
+        results = self.predict(images_decode, **kwargs)
+        return results
+
+
+if __name__ == '__main__':
+    ocr = OCRRec()
+    ocr._initialize()
+    image_path = [
+        './doc/imgs_words/ch/word_1.jpg',
+        './doc/imgs_words/ch/word_2.jpg',
+        './doc/imgs_words/ch/word_3.jpg',
+    ]
+    res = ocr.predict(paths=image_path)
+    print(res)

ocr_webapp/PaddleOCR/deploy/hubserving/ocr_rec/params.py

@@ -0,0 +1,41 @@
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+
+class Config(object):
+    pass
+
+
+def read_params():
+    cfg = Config()
+
+    #params for text recognizer
+    cfg.rec_algorithm = "CRNN"
+    cfg.rec_model_dir = "./inference/ch_PP-OCRv3_rec_infer/"
+
+    cfg.rec_image_shape = "3, 48, 320"
+    cfg.rec_batch_num = 6
+    cfg.max_text_length = 25
+
+    cfg.rec_char_dict_path = "./ppocr/utils/ppocr_keys_v1.txt"
+    cfg.use_space_char = True
+
+    cfg.use_pdserving = False
+    cfg.use_tensorrt = False
+
+    return cfg

ocr_webapp/PaddleOCR/deploy/hubserving/ocr_system/__init__.py

@@ -0,0 +1,13 @@
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.

ocr_webapp/PaddleOCR/deploy/hubserving/ocr_system/config.json

@@ -0,0 +1,16 @@
+{
+    "modules_info": {
+        "ocr_system": {
+            "init_args": {
+                "version": "1.0.0",
+                "use_gpu": true
+            },
+            "predict_args": {
+            }
+        }
+    },
+    "port": 8868,
+    "use_multiprocess": false,
+    "workers": 2
+}
+

ocr_webapp/PaddleOCR/deploy/hubserving/ocr_system/module.py

@@ -0,0 +1,156 @@
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import os
+import sys
+sys.path.insert(0, ".")
+import copy
+
+import time
+import paddlehub
+from paddlehub.common.logger import logger
+from paddlehub.module.module import moduleinfo, runnable, serving
+import cv2
+import numpy as np
+import paddlehub as hub
+
+from tools.infer.utility import base64_to_cv2
+from tools.infer.predict_system import TextSystem
+from tools.infer.utility import parse_args
+from deploy.hubserving.ocr_system.params import read_params
+
+
+@moduleinfo(
+    name="ocr_system",
+    version="1.0.0",
+    summary="ocr system service",
+    author="paddle-dev",
+    author_email="paddle-dev@baidu.com",
+    type="cv/PP-OCR_system")
+class OCRSystem(hub.Module):
+    def _initialize(self, use_gpu=False, enable_mkldnn=False):
+        """
+        initialize with the necessary elements
+        """
+        cfg = self.merge_configs()
+
+        cfg.use_gpu = use_gpu
+        if use_gpu:
+            try:
+                _places = os.environ["CUDA_VISIBLE_DEVICES"]
+                int(_places[0])
+                print("use gpu: ", use_gpu)
+                print("CUDA_VISIBLE_DEVICES: ", _places)
+                cfg.gpu_mem = 8000
+            except:
+                raise RuntimeError(
+                    "Environment Variable CUDA_VISIBLE_DEVICES is not set correctly. If you wanna use gpu, please set CUDA_VISIBLE_DEVICES via export CUDA_VISIBLE_DEVICES=cuda_device_id."
+                )
+        cfg.ir_optim = True
+        cfg.enable_mkldnn = enable_mkldnn
+
+        self.text_sys = TextSystem(cfg)
+
+    def merge_configs(self, ):
+        # deafult cfg
+        backup_argv = copy.deepcopy(sys.argv)
+        sys.argv = sys.argv[:1]
+        cfg = parse_args()
+
+        update_cfg_map = vars(read_params())
+
+        for key in update_cfg_map:
+            cfg.__setattr__(key, update_cfg_map[key])
+
+        sys.argv = copy.deepcopy(backup_argv)
+        return cfg
+
+    def read_images(self, paths=[]):
+        images = []
+        for img_path in paths:
+            assert os.path.isfile(
+                img_path), "The {} isn't a valid file.".format(img_path)
+            img = cv2.imread(img_path)
+            if img is None:
+                logger.info("error in loading image:{}".format(img_path))
+                continue
+            images.append(img)
+        return images
+
+    def predict(self, images=[], paths=[]):
+        """
+        Get the chinese texts in the predicted images.
+        Args:
+            images (list(numpy.ndarray)): images data, shape of each is [H, W, C]. If images not paths
+            paths (list[str]): The paths of images. If paths not images
+        Returns:
+            res (list): The result of chinese texts and save path of images.
+        """
+
+        if images != [] and isinstance(images, list) and paths == []:
+            predicted_data = images
+        elif images == [] and isinstance(paths, list) and paths != []:
+            predicted_data = self.read_images(paths)
+        else:
+            raise TypeError("The input data is inconsistent with expectations.")
+
+        assert predicted_data != [], "There is not any image to be predicted. Please check the input data."
+
+        all_results = []
+        for img in predicted_data:
+            if img is None:
+                logger.info("error in loading image")
+                all_results.append([])
+                continue
+            starttime = time.time()
+            dt_boxes, rec_res, _ = self.text_sys(img)
+            elapse = time.time() - starttime
+            logger.info("Predict time: {}".format(elapse))
+
+            dt_num = len(dt_boxes)
+            rec_res_final = []
+
+            for dno in range(dt_num):
+                text, score = rec_res[dno]
+                rec_res_final.append({
+                    'text': text,
+                    'confidence': float(score),
+                    'text_region': dt_boxes[dno].astype(np.int32).tolist()
+                })
+            all_results.append(rec_res_final)
+        return all_results
+
+    @serving
+    def serving_method(self, images, **kwargs):
+        """
+        Run as a service.
+        """
+        images_decode = [base64_to_cv2(image) for image in images]
+        results = self.predict(images_decode, **kwargs)
+        return results
+
+
+if __name__ == '__main__':
+    ocr = OCRSystem()
+    ocr._initialize()
+    image_path = [
+        './doc/imgs/11.jpg',
+        './doc/imgs/12.jpg',
+    ]
+    res = ocr.predict(paths=image_path)
+    print(res)

ocr_webapp/PaddleOCR/deploy/hubserving/ocr_system/params.py

@@ -0,0 +1,68 @@
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+
+class Config(object):
+    pass
+
+
+def read_params():
+    cfg = Config()
+
+    #params for text detector
+    cfg.det_algorithm = "DB"
+    cfg.det_model_dir = "./inference/ch_PP-OCRv3_det_infer/"
+    cfg.det_limit_side_len = 960
+    cfg.det_limit_type = 'max'
+
+    #DB parmas
+    cfg.det_db_thresh = 0.3
+    cfg.det_db_box_thresh = 0.5
+    cfg.det_db_unclip_ratio = 1.6
+    cfg.use_dilation = False
+    cfg.det_db_score_mode = "fast"
+
+    #EAST parmas
+    cfg.det_east_score_thresh = 0.8
+    cfg.det_east_cover_thresh = 0.1
+    cfg.det_east_nms_thresh = 0.2
+
+    #params for text recognizer
+    cfg.rec_algorithm = "CRNN"
+    cfg.rec_model_dir = "./inference/ch_PP-OCRv3_rec_infer/"
+
+    cfg.rec_image_shape = "3, 48, 320"
+    cfg.rec_batch_num = 6
+    cfg.max_text_length = 25
+
+    cfg.rec_char_dict_path = "./ppocr/utils/ppocr_keys_v1.txt"
+    cfg.use_space_char = True
+
+    #params for text classifier
+    cfg.use_angle_cls = True
+    cfg.cls_model_dir = "./inference/ch_ppocr_mobile_v2.0_cls_infer/"
+    cfg.cls_image_shape = "3, 48, 192"
+    cfg.label_list = ['0', '180']
+    cfg.cls_batch_num = 30
+    cfg.cls_thresh = 0.9
+
+    cfg.use_pdserving = False
+    cfg.use_tensorrt = False
+    cfg.drop_score = 0.5
+
+    return cfg

ocr_webapp/PaddleOCR/deploy/hubserving/readme.md

@@ -0,0 +1,250 @@
+[English](readme_en.md) | 简体中文
+
+- [基于PaddleHub Serving的服务部署](#基于paddlehub-serving的服务部署)
+  - [1. 近期更新](#1-近期更新)
+  - [2. 快速启动服务](#2-快速启动服务)
+    - [2.1 安装PaddleHub](#21-安装PaddleHub)
+    - [2.2 下载推理模型](#22-下载推理模型)
+    - [2.3 安装服务模块](#23-安装服务模块)
+    - [2.4 启动服务](#24-启动服务)
+      - [2.4.1. 命令行命令启动（仅支持CPU）](#241-命令行命令启动仅支持cpu)
+      - [2.4.2 配置文件启动（支持CPU、GPU）](#242-配置文件启动支持cpugpu)
+  - [3. 发送预测请求](#3-发送预测请求)
+  - [4. 返回结果格式说明](#4-返回结果格式说明)
+  - [5. 自定义修改服务模块](#5-自定义修改服务模块)
+
+
+PaddleOCR提供2种服务部署方式：
+- 基于PaddleHub Serving的部署：代码路径为`./deploy/hubserving`，按照本教程使用；
+- 基于PaddleServing的部署：代码路径为`./deploy/pdserving`，使用方法参考[文档](../../deploy/pdserving/README_CN.md)。
+
+# 基于PaddleHub Serving的服务部署
+
+hubserving服务部署目录下包括文本检测、文本方向分类，文本识别、文本检测+文本方向分类+文本识别3阶段串联，版面分析、表格识别和PP-Structure七种服务包，请根据需求选择相应的服务包进行安装和启动。目录结构如下：
+```
+deploy/hubserving/
+  └─  ocr_cls     文本方向分类模块服务包
+  └─  ocr_det     文本检测模块服务包
+  └─  ocr_rec     文本识别模块服务包
+  └─  ocr_system  文本检测+文本方向分类+文本识别串联服务包
+  └─  structure_layout  版面分析服务包
+  └─  structure_table  表格识别服务包
+  └─  structure_system  PP-Structure服务包
+  └─  kie_ser  关键信息抽取-SER服务包
+  └─  kie_ser_re  关键信息抽取-SER+RE服务包
+```
+
+每个服务包下包含3个文件。以2阶段串联服务包为例，目录如下：
+```
+deploy/hubserving/ocr_system/
+  └─  __init__.py    空文件，必选
+  └─  config.json    配置文件，可选，使用配置启动服务时作为参数传入
+  └─  module.py      主模块，必选，包含服务的完整逻辑
+  └─  params.py      参数文件，必选，包含模型路径、前后处理参数等参数
+```
+## 1. 近期更新
+
+* 2022.10.09 新增关键信息抽取服务。
+* 2022.08.23 新增版面分析服务。
+* 2022.05.05 新增PP-OCRv3检测和识别模型。
+* 2022.03.30 新增PP-Structure和表格识别两种服务。
+
+## 2. 快速启动服务
+以下步骤以检测+识别2阶段串联服务为例，如果只需要检测服务或识别服务，替换相应文件路径即可。
+### 2.1 安装PaddleHub
+paddlehub 需要 python>3.6.2
+```bash
+pip3 install paddlehub==2.1.0 --upgrade -i https://mirror.baidu.com/pypi/simple
+```
+
+### 2.2 下载推理模型
+安装服务模块前，需要准备推理模型并放到正确路径。默认使用的是PP-OCRv3模型，默认模型路径为：
+| 模型 | 路径 |
+| ------- | - |
+| 检测模型 | `./inference/ch_PP-OCRv3_det_infer/` |
+| 识别模型 | `./inference/ch_PP-OCRv3_rec_infer/` |
+| 方向分类器 | `./inference/ch_ppocr_mobile_v2.0_cls_infer/` |
+| 版面分析模型 | `./inference/picodet_lcnet_x1_0_fgd_layout_infer/` |
+| 表格结构识别模型 | `./inference/ch_ppstructure_mobile_v2.0_SLANet_infer/` |
+| 关键信息抽取SER模型 | `./inference/ser_vi_layoutxlm_xfund_infer/` |
+| 关键信息抽取RE模型 | `./inference/re_vi_layoutxlm_xfund_infer/` |
+
+**模型路径可在`params.py`中查看和修改。**
+
+更多模型可以从PaddleOCR提供的模型库[PP-OCR](../../doc/doc_ch/models_list.md)和[PP-Structure](../../ppstructure/docs/models_list.md)下载，也可以替换成自己训练转换好的模型。
+
+### 2.3 安装服务模块
+PaddleOCR提供5种服务模块，根据需要安装所需模块。
+
+在Linux环境（Windows环境请将`/`替换为`\`）下，安装模块命令如下表：
+| 服务模块 | 命令 |
+| ------- | - |
+| 检测 | `hub install deploy/hubserving/ocr_det` |
+| 分类 | `hub install deploy/hubserving/ocr_cls` |
+| 识别 | `hub install deploy/hubserving/ocr_rec` |
+| 检测+识别串联 | `hub install deploy/hubserving/ocr_system` |
+| 表格识别 | `hub install deploy/hubserving/structure_table` |
+| PP-Structure | `hub install deploy/hubserving/structure_system` |
+| 版面分析 | `hub install deploy/hubserving/structure_layout` |
+| 关键信息抽取SER | `hub install deploy/hubserving/kie_ser` |
+| 关键信息抽取SER+RE | `hub install deploy/hubserving/kie_ser_re` |
+
+### 2.4 启动服务
+#### 2.4.1. 命令行命令启动（仅支持CPU）
+**启动命令：**
+```bash
+hub serving start --modules Module1==Version1, Module2==Version2, ... \
+                  --port 8866 \
+                  --use_multiprocess \
+                  --workers \
+```
+
+**参数：**
+|参数|用途|
+|---|---|
+|`--modules`/`-m`|PaddleHub Serving预安装模型，以多个Module==Version键值对的形式列出<br>**当不指定Version时，默认选择最新版本**|
+|`--port`/`-p`|服务端口，默认为8866|
+|`--use_multiprocess`|是否启用并发方式，默认为单进程方式，推荐多核CPU机器使用此方式<br>**Windows操作系统只支持单进程方式**|
+|`--workers`|在并发方式下指定的并发任务数，默认为`2*cpu_count-1`，其中`cpu_count`为CPU核数|
+
+如启动串联服务：
+```bash
+hub serving start -m ocr_system
+```
+
+这样就完成了一个服务化API的部署，使用默认端口号8866。
+
+#### 2.4.2 配置文件启动（支持CPU、GPU）
+**启动命令：**
+```bash
+hub serving start -c config.json
+```
+
+其中，`config.json`格式如下：
+```json
+{
+    "modules_info": {
+        "ocr_system": {
+            "init_args": {
+                "version": "1.0.0",
+                "use_gpu": true
+            },
+            "predict_args": {
+            }
+        }
+    },
+    "port": 8868,
+    "use_multiprocess": false,
+    "workers": 2
+}
+```
+
+- `init_args`中的可配参数与`module.py`中的`_initialize`函数接口一致。
+
+   **当`use_gpu`为`true`时，表示使用GPU启动服务。**
+- `predict_args`中的可配参数与`module.py`中的`predict`函数接口一致。
+
+**注意：**
+- 使用配置文件启动服务时，其他参数会被忽略。
+- 如果使用GPU预测(即，`use_gpu`置为`true`)，则需要在启动服务之前，设置CUDA_VISIBLE_DEVICES环境变量，如：
+  ```bash
+  export CUDA_VISIBLE_DEVICES=0
+  ```
+- **`use_gpu`不可与`use_multiprocess`同时为`true`**。
+
+如，使用GPU 3号卡启动串联服务：
+```bash
+export CUDA_VISIBLE_DEVICES=3
+hub serving start -c deploy/hubserving/ocr_system/config.json
+```
+
+## 3. 发送预测请求
+配置好服务端，可使用以下命令发送预测请求，获取预测结果：
+```bash
+python tools/test_hubserving.py --server_url=server_url --image_dir=image_path
+```
+
+需要给脚本传递2个参数：
+- `server_url`：服务地址，格式为`http://[ip_address]:[port]/predict/[module_name]`
+
+   例如，如果使用配置文件启动分类，检测、识别，检测+分类+识别3阶段，表格识别和PP-Structure服务
+
+   并为每个服务修改了port，那么发送请求的url将分别是：
+   ```
+   http://127.0.0.1:8865/predict/ocr_det
+   http://127.0.0.1:8866/predict/ocr_cls
+   http://127.0.0.1:8867/predict/ocr_rec
+   http://127.0.0.1:8868/predict/ocr_system
+   http://127.0.0.1:8869/predict/structure_table
+   http://127.0.0.1:8870/predict/structure_system
+   http://127.0.0.1:8870/predict/structure_layout
+   http://127.0.0.1:8871/predict/kie_ser
+   http://127.0.0.1:8872/predict/kie_ser_re
+   ```
+- `image_dir`：测试图像路径，可以是单张图片路径，也可以是图像集合目录路径
+- `visualize`：是否可视化结果，默认为False
+- `output`：可视化结果保存路径，默认为`./hubserving_result`
+
+访问示例：
+```bash
+python tools/test_hubserving.py --server_url=http://127.0.0.1:8868/predict/ocr_system --image_dir=./doc/imgs/ --visualize=false
+```
+
+## 4. 返回结果格式说明
+返回结果为列表（list），列表中的每一项为词典（dict），词典一共可能包含3种字段，信息如下：
+|字段名称|数据类型|意义|
+|---|---|---|
+|angle|str|文本角度|
+|text|str|文本内容|
+|confidence|float| 文本识别置信度或文本角度分类置信度|
+|text_region|list|文本位置坐标|
+|html|str|表格的html字符串|
+|regions|list|版面分析+表格识别+OCR的结果，每一项为一个list<br>包含表示区域坐标的`bbox`，区域类型的`type`和区域结果的`res`三个字段|
+|layout|list|版面分析的结果，每一项一个dict，包含版面区域坐标的`bbox`，区域类型的`label`|
+
+不同模块返回的字段不同，如，文本识别服务模块返回结果不含`text_region`字段，具体信息如下：
+|字段名/模块名     |ocr_det |ocr_cls |ocr_rec |ocr_system |structure_table |structure_system |structure_layout |kie_ser |kie_re |
+|---             |---     |---     |---     |---        |---             |---              |---              |---     |---    |
+|angle           |        |✔       |        |✔          |                |                 |                 |
+|text            |        |        |✔       |✔          |                |✔                |                 |✔       |✔      |
+|confidence      |        |✔       |✔       |✔          |                |✔                |                 |✔       |✔      |
+|text_region     |✔       |        |        |✔          |                |✔                |                 |✔       |✔      |
+|html            |        |        |        |           |✔               |✔                |                 |        |       |
+|regions         |        |        |        |           |✔               |✔                |                 |        |       |
+|layout          |        |        |        |           |                |                 |✔                |        |       |
+|ser_res         |        |        |        |           |                |                 |                 |✔       |       |
+|re_res          |        |        |        |           |                |                 |                 |        |✔      |
+
+**说明：** 如果需要增加、删除、修改返回字段，可在相应模块的`module.py`文件中进行修改，完整流程参考下一节自定义修改服务模块。
+
+## 5. 自定义修改服务模块
+如果需要修改服务逻辑，一般需要操作以下步骤（以修改`deploy/hubserving/ocr_system`为例）：
+
+1. 停止服务：
+   ```bash
+   hub serving stop --port/-p XXXX
+   ```
+2. 到`deploy/hubserving/ocr_system`下的`module.py`和`params.py`等文件中根据实际需求修改代码。
+
+   例如，如果需要替换部署服务所用模型，则需要到`params.py`中修改模型路径参数`det_model_dir`和`rec_model_dir`，如果需要关闭文本方向分类器，则将参数`use_angle_cls`置为`False`
+
+   当然，同时可能还需要修改其他相关参数，请根据实际情况修改调试。
+
+   **强烈建议修改后先直接运行`module.py`调试，能正确运行预测后再启动服务测试。**
+
+   **注意：** PPOCR-v3识别模型使用的图片输入shape为`3,48,320`,因此需要修改`params.py`中的`cfg.rec_image_shape = "3, 48, 320"`，如果不使用PPOCR-v3识别模型，则无需修改该参数。
+3. （可选）如果想要重命名模块需要更改`module.py`文件中的以下行：
+   - [`from deploy.hubserving.ocr_system.params import read_params`中的`ocr_system`](https://github.com/PaddlePaddle/PaddleOCR/blob/a923f35de57b5e378f8dd16e54d0a3e4f51267fd/deploy/hubserving/ocr_system/module.py#L35)
+   - [`name="ocr_system",`中的`ocr_system`](https://github.com/PaddlePaddle/PaddleOCR/blob/a923f35de57b5e378f8dd16e54d0a3e4f51267fd/deploy/hubserving/ocr_system/module.py#L39)
+4. （可选）可能需要删除`__pycache__`目录以强制刷新CPython缓存：
+   ```bash
+   find deploy/hubserving/ocr_system -name '__pycache__' -exec rm -r {} \;
+   ```
+5. 安装修改后的新服务包：
+   ```bash
+   hub install deploy/hubserving/ocr_system
+   ```
+6. 重新启动服务：
+   ```bash
+   hub serving start -m ocr_system
+   ```

ocr_webapp/PaddleOCR/deploy/hubserving/readme_en.md

@@ -0,0 +1,249 @@
+English | [简体中文](readme.md)
+
+- [Service deployment based on PaddleHub Serving](#service-deployment-based-on-paddlehub-serving)
+  - [1. Update](#1-update)
+  - [2. Quick start service](#2-quick-start-service)
+    - [2.1 Install PaddleHub](#21-install-paddlehub)
+    - [2.2 Download inference model](#22-download-inference-model)
+    - [2.3 Install Service Module](#23-install-service-module)
+    - [2.4 Start service](#24-start-service)
+      - [2.4.1 Start with command line parameters (CPU only)](#241-start-with-command-line-parameters-cpu-only)
+      - [2.4.2 Start with configuration file（CPU and GPU）](#242-start-with-configuration-filecpugpu)
+  - [3. Send prediction requests](#3-send-prediction-requests)
+  - [4. Returned result format](#4-returned-result-format)
+  - [5. User-defined service module modification](#5-user-defined-service-module-modification)
+
+PaddleOCR provides 2 service deployment methods:
+- Based on **PaddleHub Serving**: Code path is `./deploy/hubserving`. Please follow this tutorial.
+- Based on **PaddleServing**: Code path is `./deploy/pdserving`. Please refer to the [tutorial](../../deploy/pdserving/README.md) for usage.
+
+# Service deployment based on PaddleHub Serving
+
+The hubserving service deployment directory includes seven service packages: text detection, text angle class, text recognition, text detection+text angle class+text recognition three-stage series connection, layout analysis, table recognition, and PP-Structure. Please select the corresponding service package to install and start the service according to your needs. The directory is as follows:
+```
+deploy/hubserving/
+  └─  ocr_det     text detection module service package
+  └─  ocr_cls     text angle class module service package
+  └─  ocr_rec     text recognition module service package
+  └─  ocr_system  text detection+text angle class+text recognition three-stage series connection service package
+  └─  structure_layout  layout analysis service package
+  └─  structure_table  table recognition service package
+  └─  structure_system  PP-Structure service package
+  └─  kie_ser  KIE(SER) service package
+  └─  kie_ser_re  KIE(SER+RE) service package
+```
+
+Each service pack contains 3 files. Take the 2-stage series connection service package as an example, the directory is as follows:
+```
+deploy/hubserving/ocr_system/
+  └─  __init__.py    Empty file, required
+  └─  config.json    Configuration file, optional, passed in as a parameter when using configuration to start the service
+  └─  module.py      Main module file, required, contains the complete logic of the service
+  └─  params.py      Parameter file, required, including parameters such as model path, pre and post-processing parameters
+```
+## 1. Update
+
+* 2022.10.09 add KIE services.
+* 2022.08.23 add layout analysis services.
+* 2022.03.30 add PP-Structure and table recognition services.
+* 2022.05.05 add PP-OCRv3 text detection and recognition services.
+
+## 2. Quick start service
+The following steps take the 2-stage series service as an example. If only the detection service or recognition service is needed, replace the corresponding file path.
+
+### 2.1 Install PaddleHub
+```bash
+pip3 install paddlehub==2.1.0 --upgrade
+```
+
+### 2.2 Download inference model
+Before installing the service module, you need to prepare the inference model and put it in the correct path. By default, the PP-OCRv3 models are used, and the default model path is:
+| Model | Path |
+| ------- | - |
+| text detection model | ./inference/ch_PP-OCRv3_det_infer/ |
+| text recognition model | ./inference/ch_PP-OCRv3_rec_infer/ |
+| text angle classifier | ./inference/ch_ppocr_mobile_v2.0_cls_infer/ |
+| layout parse model | ./inference/picodet_lcnet_x1_0_fgd_layout_infer/ |
+| tanle recognition | ./inference/ch_ppstructure_mobile_v2.0_SLANet_infer/ |
+| KIE(SER) | ./inference/ser_vi_layoutxlm_xfund_infer/ |
+| KIE(SER+RE) | ./inference/re_vi_layoutxlm_xfund_infer/ |
+
+**The model path can be found and modified in `params.py`.**
+More models provided by PaddleOCR can be obtained from the [model library](../../doc/doc_en/models_list_en.md). You can also use models trained by yourself.
+
+### 2.3 Install Service Module
+PaddleOCR provides 5 kinds of service modules, install the required modules according to your needs.
+
+* On the Linux platform(replace `/` with `\` if using Windows), the examples are as the following table:
+| Service model | Command |
+| text detection | `hub install deploy/hubserving/ocr_det` |
+| text angle class: | `hub install deploy/hubserving/ocr_cls` |
+| text recognition: | `hub install deploy/hubserving/ocr_rec` |
+| 2-stage series: | `hub install deploy/hubserving/ocr_system` |
+| table recognition | `hub install deploy/hubserving/structure_table` |
+| PP-Structure | `hub install deploy/hubserving/structure_system` |
+| KIE(SER) | `hub install deploy/hubserving/kie_ser` |
+| KIE(SER+RE) | `hub install deploy/hubserving/kie_ser_re` |
+
+### 2.4 Start service
+#### 2.4.1 Start with command line parameters (CPU only)
+**start command:**
+```bash
+hub serving start --modules Module1==Version1, Module2==Version2, ... \
+                  --port 8866 \
+                  --use_multiprocess \
+                  --workers \
+```
+
+**Parameters:**
+|parameters|usage|
+|---|---|
+|`--modules`/`-m`|PaddleHub Serving pre-installed model, listed in the form of multiple Module==Version key-value pairs<br>**When Version is not specified, the latest version is selected by default**|
+|`--port`/`-p`|Service port, default is 8866|
+|`--use_multiprocess`|Enable concurrent mode, by default using the single-process mode, this mode is recommended for multi-core CPU machines<br>**Windows operating system only supports single-process mode**|
+|`--workers`|The number of concurrent tasks specified in concurrent mode, the default is `2*cpu_count-1`, where `cpu_count` is the number of CPU cores|
+
+For example, start the 2-stage series service:
+```bash
+hub serving start -m ocr_system
+```
+
+This completes the deployment of a service API, using the default port number 8866.
+
+#### 2.4.2 Start with configuration file（CPU and GPU）
+**start command:**
+```bash
+hub serving start --config/-c config.json
+```
+
+In which the format of `config.json` is as follows:
+```json
+{
+    "modules_info": {
+        "ocr_system": {
+            "init_args": {
+                "version": "1.0.0",
+                "use_gpu": true
+            },
+            "predict_args": {
+            }
+        }
+    },
+    "port": 8868,
+    "use_multiprocess": false,
+    "workers": 2
+}
+```
+- The configurable parameters in `init_args` are consistent with the `_initialize` function interface in `module.py`.
+
+  **When `use_gpu` is `true`, it means that the GPU is used to start the service**.
+- The configurable parameters in `predict_args` are consistent with the `predict` function interface in `module.py`.
+
+  **Note:**
+  - When using the configuration file to start the service, other parameters will be ignored.
+  - If you use GPU prediction (that is, `use_gpu` is set to `true`), you need to set the environment variable CUDA_VISIBLE_DEVICES before starting the service, such as:
+    ```bash
+    export CUDA_VISIBLE_DEVICES=0
+    ```
+  - **`use_gpu` and `use_multiprocess` cannot be `true` at the same time.**
+
+For example, use GPU card No. 3 to start the 2-stage series service:
+```bash
+export CUDA_VISIBLE_DEVICES=3
+hub serving start -c deploy/hubserving/ocr_system/config.json
+```
+
+## 3. Send prediction requests
+After the service starts, you can use the following command to send a prediction request to obtain the prediction result:
+```bash
+python tools/test_hubserving.py --server_url=server_url --image_dir=image_path
+```
+
+Two parameters need to be passed to the script:
+- **server_url**:service address, the format of which is
+`http://[ip_address]:[port]/predict/[module_name]`
+
+  For example, if using the configuration file to start the text angle classification, text detection, text recognition, detection+classification+recognition 3 stages, table recognition and PP-Structure service,
+
+  also modified the port for each service, then the `server_url` to send the request will be:
+
+  ```
+  http://127.0.0.1:8865/predict/ocr_det
+  http://127.0.0.1:8866/predict/ocr_cls
+  http://127.0.0.1:8867/predict/ocr_rec
+  http://127.0.0.1:8868/predict/ocr_system
+  http://127.0.0.1:8869/predict/structure_table
+  http://127.0.0.1:8870/predict/structure_system
+  http://127.0.0.1:8870/predict/structure_layout
+  http://127.0.0.1:8871/predict/kie_ser
+  http://127.0.0.1:8872/predict/kie_ser_re
+  ```
+- **image_dir**:Test image path, which can be a single image path or an image directory path
+- **visualize**:Whether to visualize the results, the default value is False
+- **output**:The folder to save the Visualization result, the default value is `./hubserving_result`
+
+Example:
+```bash
+python tools/test_hubserving.py --server_url=http://127.0.0.1:8868/predict/ocr_system --image_dir=./doc/imgs/ --visualize=false`
+```
+
+## 4. Returned result format
+The returned result is a list. Each item in the list is a dictionary which may contain three fields. The information is as follows:
+
+|field name|data type|description|
+|----|----|----|
+|angle|str|angle|
+|text|str|text content|
+|confidence|float|text recognition confidence|
+|text_region|list|text location coordinates|
+|html|str|table HTML string|
+|regions|list|The result of layout analysis + table recognition + OCR, each item is a list<br>including `bbox` indicating area coordinates, `type` of area type and `res` of area results|
+|layout|list|The result of layout analysis, each item is a dict, including `bbox` indicating area coordinates, `label` of area type|
+
+The fields returned by different modules are different. For example, the results returned by the text recognition service module do not contain `text_region`, detailed table is as follows:
+
+|field name/module name |ocr_det |ocr_cls |ocr_rec |ocr_system |structure_table |structure_system |structure_layout |kie_ser |kie_re |
+|---                    |---     |---     |---     |---        |---             |---              |---              |---     |---    |
+|angle                  |        |✔       |        |✔          |                |                 |                 |
+|text                   |        |        |✔       |✔          |                |✔                |                 |✔       |✔      |
+|confidence             |        |✔       |✔       |✔          |                |✔                |                 |✔       |✔      |
+|text_region            |✔       |        |        |✔          |                |✔                |                 |✔       |✔      |
+|html                   |        |        |        |           |✔               |✔                |                 |        |       |
+|regions                |        |        |        |           |✔               |✔                |                 |        |       |
+|layout                 |        |        |        |           |                |                 |✔                |        |       |
+|ser_res                |        |        |        |           |                |                 |                 |✔       |       |
+|re_res                 |        |        |        |           |                |                 |                 |        |✔      |
+
+**Note:** If you need to add, delete or modify the returned fields, you can modify the file `module.py` of the corresponding module. For the complete process, refer to the user-defined modification service module in the next section.
+
+## 5. User-defined service module modification
+If you need to modify the service logic, the following steps are generally required (take the modification of `deploy/hubserving/ocr_system` for example):
+
+1. Stop service:
+```bash
+hub serving stop --port/-p XXXX
+```
+2. Modify the code in the corresponding files under `deploy/hubserving/ocr_system`, such as `module.py` and `params.py`, to your actual needs.
+
+   For example, if you need to replace the model used by the deployed service, you need to modify model path parameters `det_model_dir` and `rec_model_dir` in `params.py`. If you want to turn off the text direction classifier, set the parameter `use_angle_cls` to `False`.
+
+   Of course, other related parameters may need to be modified at the same time. Please modify and debug according to the actual situation.
+
+   **It is suggested to run `module.py` directly for debugging after modification before starting the service test.**
+
+   **Note** The image input shape used by the PPOCR-v3 recognition model is `3, 48, 320`, so you need to modify `cfg.rec_image_shape = "3, 48, 320"` in `params.py`, if you do not use the PPOCR-v3 recognition model, then there is no need to modify this parameter.
+3. (Optional) If you want to rename the module, the following lines should be modified:
+   - [`ocr_system` within `from deploy.hubserving.ocr_system.params import read_params`](https://github.com/PaddlePaddle/PaddleOCR/blob/a923f35de57b5e378f8dd16e54d0a3e4f51267fd/deploy/hubserving/ocr_system/module.py#L35)
+   - [`ocr_system` within `name="ocr_system",`](https://github.com/PaddlePaddle/PaddleOCR/blob/a923f35de57b5e378f8dd16e54d0a3e4f51267fd/deploy/hubserving/ocr_system/module.py#L39)
+4. (Optional) It may require you to delete the directory `__pycache__` to force flush build cache of CPython:
+   ```bash
+   find deploy/hubserving/ocr_system -name '__pycache__' -exec rm -r {} \;
+   ```
+5. Install modified service module:
+   ```bash
+   hub install deploy/hubserving/ocr_system/
+   ```
+6. Restart service:
+   ```bash
+   hub serving start -m ocr_system
+   ```

ocr_webapp/PaddleOCR/deploy/hubserving/structure_layout/__init__.py

@@ -0,0 +1,13 @@
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.

ocr_webapp/PaddleOCR/deploy/hubserving/structure_layout/config.json

@@ -0,0 +1,16 @@
+{
+    "modules_info": {
+        "structure_layout": {
+            "init_args": {
+                "version": "1.0.0",
+                "use_gpu": true
+            },
+            "predict_args": {
+            }
+        }
+    },
+    "port": 8871,
+    "use_multiprocess": false,
+    "workers": 2
+}
+

ocr_webapp/PaddleOCR/deploy/hubserving/structure_layout/module.py

@@ -0,0 +1,143 @@
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import os
+import sys
+sys.path.insert(0, ".")
+import copy
+
+import time
+import paddlehub
+from paddlehub.common.logger import logger
+from paddlehub.module.module import moduleinfo, runnable, serving
+import cv2
+import paddlehub as hub
+
+from tools.infer.utility import base64_to_cv2
+from ppstructure.layout.predict_layout import LayoutPredictor as _LayoutPredictor
+from ppstructure.utility import parse_args
+from deploy.hubserving.structure_layout.params import read_params
+
+
+@moduleinfo(
+    name="structure_layout",
+    version="1.0.0",
+    summary="PP-Structure layout service",
+    author="paddle-dev",
+    author_email="paddle-dev@baidu.com",
+    type="cv/structure_layout")
+class LayoutPredictor(hub.Module):
+    def _initialize(self, use_gpu=False, enable_mkldnn=False):
+        """
+        initialize with the necessary elements
+        """
+        cfg = self.merge_configs()
+        cfg.use_gpu = use_gpu
+        if use_gpu:
+            try:
+                _places = os.environ["CUDA_VISIBLE_DEVICES"]
+                int(_places[0])
+                print("use gpu: ", use_gpu)
+                print("CUDA_VISIBLE_DEVICES: ", _places)
+                cfg.gpu_mem = 8000
+            except:
+                raise RuntimeError(
+                    "Environment Variable CUDA_VISIBLE_DEVICES is not set correctly. If you wanna use gpu, please set CUDA_VISIBLE_DEVICES via export CUDA_VISIBLE_DEVICES=cuda_device_id."
+                )
+        cfg.ir_optim = True
+        cfg.enable_mkldnn = enable_mkldnn
+
+        self.layout_predictor = _LayoutPredictor(cfg)
+
+    def merge_configs(self):
+        # deafult cfg
+        backup_argv = copy.deepcopy(sys.argv)
+        sys.argv = sys.argv[:1]
+        cfg = parse_args()
+
+        update_cfg_map = vars(read_params())
+
+        for key in update_cfg_map:
+            cfg.__setattr__(key, update_cfg_map[key])
+
+        sys.argv = copy.deepcopy(backup_argv)
+        return cfg
+
+    def read_images(self, paths=[]):
+        images = []
+        for img_path in paths:
+            assert os.path.isfile(
+                img_path), "The {} isn't a valid file.".format(img_path)
+            img = cv2.imread(img_path)
+            if img is None:
+                logger.info("error in loading image:{}".format(img_path))
+                continue
+            images.append(img)
+        return images
+
+    def predict(self, images=[], paths=[]):
+        """
+        Get the chinese texts in the predicted images.
+        Args:
+            images (list(numpy.ndarray)): images data, shape of each is [H, W, C]. If images not paths
+            paths (list[str]): The paths of images. If paths not images
+        Returns:
+            res (list): The layout results of images.
+        """
+
+        if images != [] and isinstance(images, list) and paths == []:
+            predicted_data = images
+        elif images == [] and isinstance(paths, list) and paths != []:
+            predicted_data = self.read_images(paths)
+        else:
+            raise TypeError("The input data is inconsistent with expectations.")
+
+        assert predicted_data != [], "There is not any image to be predicted. Please check the input data."
+
+        all_results = []
+        for img in predicted_data:
+            if img is None:
+                logger.info("error in loading image")
+                all_results.append([])
+                continue
+            starttime = time.time()
+            res, _ = self.layout_predictor(img)
+            elapse = time.time() - starttime
+            logger.info("Predict time: {}".format(elapse))
+
+            for item in res:
+                item['bbox'] = item['bbox'].tolist()
+            all_results.append({'layout': res})
+        return all_results
+
+    @serving
+    def serving_method(self, images, **kwargs):
+        """
+        Run as a service.
+        """
+        images_decode = [base64_to_cv2(image) for image in images]
+        results = self.predict(images_decode, **kwargs)
+        return results
+
+
+if __name__ == '__main__':
+    layout = LayoutPredictor()
+    layout._initialize()
+    image_path = ['./ppstructure/docs/table/1.png']
+    res = layout.predict(paths=image_path)
+    print(res)

ocr_webapp/PaddleOCR/deploy/hubserving/structure_layout/params.py

@@ -0,0 +1,32 @@
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+
+class Config(object):
+    pass
+
+
+def read_params():
+    cfg = Config()
+
+    # params for layout analysis
+    cfg.layout_model_dir = './inference/picodet_lcnet_x1_0_fgd_layout_infer/'
+    cfg.layout_dict_path = './ppocr/utils/dict/layout_dict/layout_publaynet_dict.txt'
+    cfg.layout_score_threshold = 0.5
+    cfg.layout_nms_threshold = 0.5
+    return cfg

ocr_webapp/PaddleOCR/deploy/hubserving/structure_system/__init__.py

@@ -0,0 +1,13 @@
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.

ocr_webapp/PaddleOCR/deploy/hubserving/structure_system/config.json

@@ -0,0 +1,16 @@
+{
+    "modules_info": {
+        "structure_system": {
+            "init_args": {
+                "version": "1.0.0",
+                "use_gpu": true
+            },
+            "predict_args": {
+            }
+        }
+    },
+    "port": 8870,
+    "use_multiprocess": false,
+    "workers": 2
+}
+

ocr_webapp/PaddleOCR/deploy/hubserving/structure_system/module.py

@@ -0,0 +1,149 @@
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import os
+import sys
+sys.path.insert(0, ".")
+import copy
+
+import time
+import paddlehub
+from paddlehub.common.logger import logger
+from paddlehub.module.module import moduleinfo, runnable, serving
+import cv2
+import numpy as np
+import paddlehub as hub
+
+from tools.infer.utility import base64_to_cv2
+from ppstructure.predict_system import StructureSystem as PPStructureSystem
+from ppstructure.predict_system import save_structure_res
+from ppstructure.utility import parse_args
+from deploy.hubserving.structure_system.params import read_params
+
+
+@moduleinfo(
+    name="structure_system",
+    version="1.0.0",
+    summary="PP-Structure system service",
+    author="paddle-dev",
+    author_email="paddle-dev@baidu.com",
+    type="cv/structure_system")
+class StructureSystem(hub.Module):
+    def _initialize(self, use_gpu=False, enable_mkldnn=False):
+        """
+        initialize with the necessary elements
+        """
+        cfg = self.merge_configs()
+
+        cfg.use_gpu = use_gpu
+        if use_gpu:
+            try:
+                _places = os.environ["CUDA_VISIBLE_DEVICES"]
+                int(_places[0])
+                print("use gpu: ", use_gpu)
+                print("CUDA_VISIBLE_DEVICES: ", _places)
+                cfg.gpu_mem = 8000
+            except:
+                raise RuntimeError(
+                    "Environment Variable CUDA_VISIBLE_DEVICES is not set correctly. If you wanna use gpu, please set CUDA_VISIBLE_DEVICES via export CUDA_VISIBLE_DEVICES=cuda_device_id."
+                )
+        cfg.ir_optim = True
+        cfg.enable_mkldnn = enable_mkldnn
+
+        self.table_sys = PPStructureSystem(cfg)
+
+    def merge_configs(self):
+        # deafult cfg
+        backup_argv = copy.deepcopy(sys.argv)
+        sys.argv = sys.argv[:1]
+        cfg = parse_args()
+
+        update_cfg_map = vars(read_params())
+
+        for key in update_cfg_map:
+            cfg.__setattr__(key, update_cfg_map[key])
+
+        sys.argv = copy.deepcopy(backup_argv)
+        return cfg
+
+    def read_images(self, paths=[]):
+        images = []
+        for img_path in paths:
+            assert os.path.isfile(
+                img_path), "The {} isn't a valid file.".format(img_path)
+            img = cv2.imread(img_path)
+            if img is None:
+                logger.info("error in loading image:{}".format(img_path))
+                continue
+            images.append(img)
+        return images
+
+    def predict(self, images=[], paths=[]):
+        """
+        Get the chinese texts in the predicted images.
+        Args:
+            images (list(numpy.ndarray)): images data, shape of each is [H, W, C]. If images not paths
+            paths (list[str]): The paths of images. If paths not images
+        Returns:
+            res (list): The result of chinese texts and save path of images.
+        """
+
+        if images != [] and isinstance(images, list) and paths == []:
+            predicted_data = images
+        elif images == [] and isinstance(paths, list) and paths != []:
+            predicted_data = self.read_images(paths)
+        else:
+            raise TypeError("The input data is inconsistent with expectations.")
+
+        assert predicted_data != [], "There is not any image to be predicted. Please check the input data."
+
+        all_results = []
+        for img in predicted_data:
+            if img is None:
+                logger.info("error in loading image")
+                all_results.append([])
+                continue
+            starttime = time.time()
+            res, _ = self.table_sys(img)
+            elapse = time.time() - starttime
+            logger.info("Predict time: {}".format(elapse))
+
+            # parse result
+            res_final = []
+            for region in res:
+                region.pop('img')
+                res_final.append(region)
+            all_results.append({'regions': res_final})
+        return all_results
+
+    @serving
+    def serving_method(self, images, **kwargs):
+        """
+        Run as a service.
+        """
+        images_decode = [base64_to_cv2(image) for image in images]
+        results = self.predict(images_decode, **kwargs)
+        return results
+
+
+if __name__ == '__main__':
+    structure_system = StructureSystem()
+    structure_system._initialize()
+    image_path = ['./ppstructure/docs/table/1.png']
+    res = structure_system.predict(paths=image_path)
+    print(res)

ocr_webapp/PaddleOCR/deploy/hubserving/structure_system/params.py

@@ -0,0 +1,33 @@
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+from deploy.hubserving.structure_table.params import read_params as table_read_params
+
+
+def read_params():
+    cfg = table_read_params()
+
+    # params for layout parser model
+    cfg.layout_model_dir = ''
+    cfg.layout_dict_path = './ppocr/utils/dict/layout_publaynet_dict.txt'
+    cfg.layout_score_threshold = 0.5
+    cfg.layout_nms_threshold = 0.5
+
+    cfg.mode = 'structure'
+    cfg.output = './output'
+    return cfg

ocr_webapp/PaddleOCR/deploy/hubserving/structure_table/__init__.py

@@ -0,0 +1,13 @@
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.

ocr_webapp/PaddleOCR/deploy/hubserving/structure_table/config.json

@@ -0,0 +1,16 @@
+{
+    "modules_info": {
+        "structure_table": {
+            "init_args": {
+                "version": "1.0.0",
+                "use_gpu": true
+            },
+            "predict_args": {
+            }
+        }
+    },
+    "port": 8869,
+    "use_multiprocess": false,
+    "workers": 2
+}
+

ocr_webapp/PaddleOCR/deploy/hubserving/structure_table/module.py

@@ -0,0 +1,143 @@
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import os
+import sys
+sys.path.insert(0, ".")
+import copy
+
+import time
+import paddlehub
+from paddlehub.common.logger import logger
+from paddlehub.module.module import moduleinfo, runnable, serving
+import cv2
+import numpy as np
+import paddlehub as hub
+
+from tools.infer.utility import base64_to_cv2
+from ppstructure.table.predict_table import TableSystem as _TableSystem
+from ppstructure.predict_system import save_structure_res
+from ppstructure.utility import parse_args
+from deploy.hubserving.structure_table.params import read_params
+
+
+@moduleinfo(
+    name="structure_table",
+    version="1.0.0",
+    summary="PP-Structure table service",
+    author="paddle-dev",
+    author_email="paddle-dev@baidu.com",
+    type="cv/structure_table")
+class TableSystem(hub.Module):
+    def _initialize(self, use_gpu=False, enable_mkldnn=False):
+        """
+        initialize with the necessary elements
+        """
+        cfg = self.merge_configs()
+        cfg.use_gpu = use_gpu
+        if use_gpu:
+            try:
+                _places = os.environ["CUDA_VISIBLE_DEVICES"]
+                int(_places[0])
+                print("use gpu: ", use_gpu)
+                print("CUDA_VISIBLE_DEVICES: ", _places)
+                cfg.gpu_mem = 8000
+            except:
+                raise RuntimeError(
+                    "Environment Variable CUDA_VISIBLE_DEVICES is not set correctly. If you wanna use gpu, please set CUDA_VISIBLE_DEVICES via export CUDA_VISIBLE_DEVICES=cuda_device_id."
+                )
+        cfg.ir_optim = True
+        cfg.enable_mkldnn = enable_mkldnn
+
+        self.table_sys = _TableSystem(cfg)
+
+    def merge_configs(self):
+        # deafult cfg
+        backup_argv = copy.deepcopy(sys.argv)
+        sys.argv = sys.argv[:1]
+        cfg = parse_args()
+
+        update_cfg_map = vars(read_params())
+
+        for key in update_cfg_map:
+            cfg.__setattr__(key, update_cfg_map[key])
+
+        sys.argv = copy.deepcopy(backup_argv)
+        return cfg
+
+    def read_images(self, paths=[]):
+        images = []
+        for img_path in paths:
+            assert os.path.isfile(
+                img_path), "The {} isn't a valid file.".format(img_path)
+            img = cv2.imread(img_path)
+            if img is None:
+                logger.info("error in loading image:{}".format(img_path))
+                continue
+            images.append(img)
+        return images
+
+    def predict(self, images=[], paths=[]):
+        """
+        Get the chinese texts in the predicted images.
+        Args:
+            images (list(numpy.ndarray)): images data, shape of each is [H, W, C]. If images not paths
+            paths (list[str]): The paths of images. If paths not images
+        Returns:
+            res (list): The result of chinese texts and save path of images.
+        """
+
+        if images != [] and isinstance(images, list) and paths == []:
+            predicted_data = images
+        elif images == [] and isinstance(paths, list) and paths != []:
+            predicted_data = self.read_images(paths)
+        else:
+            raise TypeError("The input data is inconsistent with expectations.")
+
+        assert predicted_data != [], "There is not any image to be predicted. Please check the input data."
+
+        all_results = []
+        for img in predicted_data:
+            if img is None:
+                logger.info("error in loading image")
+                all_results.append([])
+                continue
+            starttime = time.time()
+            res, _ = self.table_sys(img)
+            elapse = time.time() - starttime
+            logger.info("Predict time: {}".format(elapse))
+
+            all_results.append({'html': res['html']})
+        return all_results
+
+    @serving
+    def serving_method(self, images, **kwargs):
+        """
+        Run as a service.
+        """
+        images_decode = [base64_to_cv2(image) for image in images]
+        results = self.predict(images_decode, **kwargs)
+        return results
+
+
+if __name__ == '__main__':
+    table_system = TableSystem()
+    table_system._initialize()
+    image_path = ['./ppstructure/docs/table/table.jpg']
+    res = table_system.predict(paths=image_path)
+    print(res)

ocr_webapp/PaddleOCR/deploy/hubserving/structure_table/params.py

@@ -0,0 +1,30 @@
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+from deploy.hubserving.ocr_system.params import read_params as pp_ocr_read_params
+
+
+def read_params():
+    cfg = pp_ocr_read_params()
+
+    # params for table structure model
+    cfg.table_max_len = 488
+    cfg.table_model_dir = './inference/en_ppocr_mobile_v2.0_table_structure_infer/'
+    cfg.table_char_dict_path = './ppocr/utils/dict/table_structure_dict.txt'
+    cfg.show_log = False
+    return cfg

ocr_webapp/PaddleOCR/deploy/ios_demo/.gitignore

@@ -0,0 +1,21 @@
+# CocoaPods
+Pods/
+
+# Xcode
+PaddleOCRDemo.xcworkspace/xcuserdata/
+PaddleOCRDemo.xcodeproj/xcuserdata/
+PaddleOCRDemo.xcodeproj/project.xcworkspace/xcuserdata/
+*.xcuserstate
+DerivedData/
+build/
+
+# fetch_ios_demo_models.sh download cache
+.fetch_ios_demo_models_work/
+
+# Models — ignore all files under Models/; track only `.gitkeep` so det/, rec/, … stay in the tree
+PaddleOCRDemo/Models/**
+!PaddleOCRDemo/Models/*/
+!PaddleOCRDemo/Models/*/.gitkeep
+
+# Local validation reports
+out/

ocr_webapp/PaddleOCR/deploy/ios_demo/NOTICE

@@ -0,0 +1,25 @@
+PaddleOCR iOS demo — third-party notices
+===============================================================================
+
+This demo application is part of the PaddleOCR project (Apache License 2.0).
+It may bundle or link third-party components in addition to the PaddleOCR
+repository LICENSE. The following components are included in **source** form
+in this tree:
+
+Clipper / polyclipping (polygon clipping and offsetting)
+--------------------------------------------------------------------------------------------
+  • Upstream: polyclipping clipper 6.4.2 (Angus Johnson)  
+  • Bundled:   `PaddleOCRDemo/ThirdParty/Clipper1/` (clipper.cpp, clipper.hpp)  
+  • SPDX:      BSL-1.0 (Boost Software License 1.0)  
+  • Full text: `PaddleOCRDemo/ThirdParty/Clipper1/LICENSE`  
+
+CocoaPods dependencies (onnxruntime-objc, OpenCV, Yams, etc.)
+-------------------------------------------------------------
+  • Versions and upstream packages are recorded in `Podfile.lock` after
+    `pod install`. Each pod is subject to its own license as published by
+    the respective project; consult the Pods project and upstream repos
+    for notices required by those licenses.
+
+If you distribute binaries built from this demo, ensure your product’s
+open-source / third-party attribution (e.g. in-app “Licenses” or
+distribution packaging) satisfies your legal and policy requirements.