Skip to content

P
PaddleOCR

weixin_41840029 / PaddleOCR
与 Fork 源项目一致

Fork自 PaddlePaddle / PaddleOCR

通知 1
Star 1
Fork 0
P
PaddleOCR
提交 486aa102 编写于 作者: M MissPenguin
浏览文件
操作

update

上级 52b7dee0
显示空白变更内容
内联 并排
Showing with 1395 addition and 603 deletion
README.md
浏览文件 @ 486aa102
...@@ -116,7 +116,7 @@ For a new language request, please refer to [Guideline for new language_requests ...@@ -116,7 +116,7 @@ For a new language request, please refer to [Guideline for new language_requests
- [Knowledge Distillation](./doc/doc_en/knowledge_distillation_en.md) - [Knowledge Distillation](./doc/doc_en/knowledge_distillation_en.md)
- [Model Quantization](./deploy/slim/quantization/README_en.md) - [Model Quantization](./deploy/slim/quantization/README_en.md)
- [Model Pruning](./deploy/slim/prune/README_en.md) - [Model Pruning](./deploy/slim/prune/README_en.md)
- Inference and Deployment - [Inference and Deployment](./deploy/README.md)
- [C++ Inference](./deploy/cpp_infer/readme_en.md) - [C++ Inference](./deploy/cpp_infer/readme_en.md)
- [Serving](./deploy/pdserving/README.md) - [Serving](./deploy/pdserving/README.md)
- [Mobile](./deploy/lite/readme_en.md) - [Mobile](./deploy/lite/readme_en.md)
......
README_ch.md
浏览文件 @ 486aa102
...@@ -93,7 +93,7 @@ PaddleOCR旨在打造一套丰富、领先、且实用的OCR工具库，助力 ...@@ -93,7 +93,7 @@ PaddleOCR旨在打造一套丰富、领先、且实用的OCR工具库，助力
- [模型量化](./deploy/slim/quantization/README.md) - [模型量化](./deploy/slim/quantization/README.md)
- [模型裁剪](./deploy/slim/prune/README.md) - [模型裁剪](./deploy/slim/prune/README.md)
- [知识蒸馏](./doc/doc_ch/knowledge_distillation.md) - [知识蒸馏](./doc/doc_ch/knowledge_distillation.md)
- [推理部署](./deploy/readme_ch.md) - [推理部署](./deploy/README_ch.md)
- [基于Python预测引擎推理](./doc/doc_ch/inference_ppocr.md) - [基于Python预测引擎推理](./doc/doc_ch/inference_ppocr.md)
- [基于C++预测引擎推理](./deploy/cpp_infer/readme.md) - [基于C++预测引擎推理](./deploy/cpp_infer/readme.md)
- [服务化部署](./deploy/pdserving/README_CN.md) - [服务化部署](./deploy/pdserving/README_CN.md)
...@@ -108,7 +108,7 @@ PaddleOCR旨在打造一套丰富、领先、且实用的OCR工具库，助力 ...@@ -108,7 +108,7 @@ PaddleOCR旨在打造一套丰富、领先、且实用的OCR工具库，助力
- [表格识别](./ppstructure/table/README_ch.md) - [表格识别](./ppstructure/table/README_ch.md)
- [关键信息提取](./ppstructure/docs/kie.md) - [关键信息提取](./ppstructure/docs/kie.md)
- [DocVQA](./ppstructure/vqa/README_ch.md) - [DocVQA](./ppstructure/vqa/README_ch.md)
- [推理部署](./deploy/readme_ch.md) - [推理部署](./deploy/README_ch.md)
- [基于Python预测引擎推理](./ppstructure/docs/inference.md) - [基于Python预测引擎推理](./ppstructure/docs/inference.md)
- [基于C++预测引擎推理]() - [基于C++预测引擎推理]()
- [服务化部署](./deploy/pdserving/README_CN.md) - [服务化部署](./deploy/pdserving/README_CN.md)
......
deploy/README.md 0 → 100644
浏览文件 @ 486aa102
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](./pdserving/README.md)
- [Paddle-Lite](./lite/readme.md)
- [Paddle.js](./paddlejs/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)。
\ No newline at end of file
deploy/README_ch.md 0 → 100644
浏览文件 @ 486aa102
[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](./pdserving/README_CN.md)
- [Paddle-Lite 端侧部署](./lite/readme_ch.md)
- [Paddle.js 服务化部署](./paddlejs/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)。
\ No newline at end of file
deploy/cpp_infer/readme.md
浏览文件 @ 486aa102
- [服务器端C++预测](#服务器端c预测) - [Server-side C++ Inference](#server-side-c-inference)
- [1. 准备环境](#1-准备环境) - [1. Prepare the Environment](#1-prepare-the-environment)
- [1.0 运行准备](#10-运行准备) - [Environment](#environment)
- [1.1 编译opencv库](#11-编译opencv库) - [1.1 Compile OpenCV](#11-compile-opencv)
- [1.2 下载或者编译Paddle预测库](#12-下载或者编译paddle预测库) - [1.2 Compile or Download or the Paddle Inference Library](#12-compile-or-download-or-the-paddle-inference-library)
- [1.2.1 直接下载安装](#121-直接下载安装) - [1.2.1 Direct download and installation](#121-direct-download-and-installation)
- [1.2.2 预测库源码编译](#122-预测库源码编译) - [1.2.2 Compile the inference source code](#122-compile-the-inference-source-code)
- [2 开始运行](#2-开始运行) - [2. Compile and Run the Demo](#2-compile-and-run-the-demo)
- [2.1 将模型导出为inference model](#21-将模型导出为inference-model) - [2.1 Export the inference model](#21-export-the-inference-model)
- [2.2 编译PaddleOCR C++预测demo](#22-编译paddleocr-c预测demo) - [2.2 Compile PaddleOCR C++ inference demo](#22-compile-paddleocr-c-inference-demo)
- [2.3 运行demo](#23-运行demo) - [Run the demo](#run-the-demo)
- [1. 检测+分类+识别：](#1-检测分类识别) - [1. det+cls+rec：](#1-detclsrec)
- [2. 检测+识别：](#2-检测识别) - [2. det+rec：](#2-detrec)
- [3. 检测：](#3-检测) - [3. det](#3-det)
- [4. 分类+识别：](#4-分类识别) - [4. cls+rec：](#4-clsrec)
- [5. 识别：](#5-识别) - [5. rec](#5-rec)
- [6. 分类：](#6-分类) - [6. cls](#6-cls)
- [3. FAQ](#3-faq) - [3. FAQ](#3-faq)
# 服务器端C++预测 # Server-side C++ Inference
本章节介绍PaddleOCR 模型的的C++部署方法，与之对应的python预测部署方式参考[文档](../../doc/doc_ch/inference.md)。 This chapter introduces the C++ deployment steps of the PaddleOCR model. The corresponding Python predictive deployment method refers to [document](../../doc/doc_ch/inference.md).
C++在性能计算上优于python，因此，在大多数CPU、GPU部署场景，多采用C++的部署方式，本节将介绍如何在Linux\Windows (CPU\GPU)环境下配置C++环境并完成 C++ is better than python in terms of performance. Therefore, in CPU and GPU deployment scenarios, C++ deployment is mostly used.
PaddleOCR模型部署。 This section will introduce how to configure the C++ environment and deploy PaddleOCR in Linux (CPU\GPU) environment. For Windows deployment please refer to [Windows](./docs/windows_vs2019_build.md) compilation guidelines.
<a name="1"></a> ## 1. Prepare the Environment
## 1. 准备环境 ### Environment
<a name="10"></a> - Linux, docker is recommended.
- Windows.
### 1.0 运行准备
- Linux环境，推荐使用docker。 ### 1.1 Compile OpenCV
- Windows环境。
* 该文档主要介绍基于Linux环境的PaddleOCR C++预测流程，如果需要在Windows下基于预测库进行C++预测，具体编译方法请参考[Windows下编译教程](./docs/windows_vs2019_build.md) * First of all, you need to download the source code compiled package in the Linux environment from the OpenCV official website. Taking OpenCV 3.4.7 as an example, the download command is as follows.
<a name="11"></a>
### 1.1 编译opencv库
* 首先需要从opencv官网上下载在Linux环境下源码编译的包，以opencv3.4.7为例，下载命令如下。
```bash ```bash
cd deploy/cpp_infer cd deploy/cpp_infer
...@@ -49,18 +42,18 @@ wget https://paddleocr.bj.bcebos.com/libs/opencv/opencv-3.4.7.tar.gz ...@@ -49,18 +42,18 @@ wget https://paddleocr.bj.bcebos.com/libs/opencv/opencv-3.4.7.tar.gz
tar -xf opencv-3.4.7.tar.gz tar -xf opencv-3.4.7.tar.gz
``` ```
最终可以在当前目录下看到`opencv-3.4.7/`的文件夹。 Finally, you will see the folder of `opencv-3.4.7/` in the current directory.
* Compile OpenCV, the OpenCV source path (`root_path`) and installation path (`install_path`) should be set by yourself. Enter the OpenCV source code path and compile it in the following way.
* 编译opencv，设置opencv源码路径(`root_path`)以及安装路径(`install_path`)。进入opencv源码路径下，按照下面的方式进行编译。
```shell ```shell
root_path="your_opencv_root_path" root_path=your_opencv_root_path
install_path=${root_path}/opencv3 install_path=${root_path}/opencv3
build_dir=${root_path}/build
rm -rf ${build_dir} rm -rf build
mkdir ${build_dir} mkdir build
cd ${build_dir} cd build
cmake .. \ cmake .. \
-DCMAKE_INSTALL_PREFIX=${install_path} \ -DCMAKE_INSTALL_PREFIX=${install_path} \
...@@ -84,15 +77,11 @@ make -j ...@@ -84,15 +77,11 @@ make -j
make install make install
``` ```
也可以直接修改`tools/build_opencv.sh`的内容，然后直接运行下面的命令进行编译。 In the above commands, `root_path` is the downloaded OpenCV source code path, and `install_path` is the installation path of OpenCV. After `make install` is completed, the OpenCV header file and library file will be generated in this folder for later OCR source code compilation.
```shell
sh tools/build_opencv.sh
```
其中`root_path`为下载的opencv源码路径，`install_path`为opencv的安装路径，`make install`完成之后，会在该文件夹下生成opencv头文件和库文件，用于后面的OCR代码编译。
最终在安装路径下的文件结构如下所示。 The final file structure under the OpenCV installation path is as follows.
``` ```
opencv3/ opencv3/
...@@ -103,35 +92,34 @@ opencv3/ ...@@ -103,35 +92,34 @@ opencv3/
|-- share |-- share
``` ```
<a name="12"></a> ### 1.2 Compile or Download or the Paddle Inference Library
### 1.2 下载或者编译Paddle预测库 * There are 2 ways to obtain the Paddle inference library, described in detail below.
* 有2种方式获取Paddle预测库，下面进行详细介绍。 #### 1.2.1 Direct download and installation
[Paddle inference library official website](https://paddleinference.paddlepaddle.org.cn/user_guides/download_lib.html#linux). You can review and select the appropriate version of the inference library on the official website.
#### 1.2.1 直接下载安装
* [Paddle预测库官网](https://paddleinference.paddlepaddle.org.cn/user_guides/download_lib.html#linux) 上提供了不同cuda版本的Linux预测库，可以在官网查看并选择合适的预测库版本（*建议选择paddle版本>=2.0.1版本的预测库* ）。 * After downloading, use the following command to extract files.
* 下载之后使用下面的方法解压。
``` ```
tar -xf paddle_inference.tgz tar -xf paddle_inference.tgz
``` ```
最终会在当前的文件夹中生成`paddle_inference/`的子文件夹。 Finally you will see the the folder of `paddle_inference/` in the current path.
#### 1.2.2 Compile the inference source code
* If you want to get the latest Paddle inference library features, you can download the latest code from Paddle GitHub repository and compile the inference library from the source code. It is recommended to download the inference library with paddle version greater than or equal to 2.0.1.
* You can refer to [Paddle inference library] (https://www.paddlepaddle.org.cn/documentation/docs/en/advanced_guide/inference_deployment/inference/build_and_install_lib_en.html) to get the Paddle source code from GitHub, and then compile To generate the latest inference library. The method of using git to access the code is as follows.
#### 1.2.2 预测库源码编译
* 如果希望获取最新预测库特性，可以从Paddle github上克隆最新代码，源码编译预测库。
* 可以参考[Paddle预测库安装编译说明](https://www.paddlepaddle.org.cn/documentation/docs/zh/2.0/guides/05_inference_deployment/inference/build_and_install_lib_cn.html#congyuanmabianyi) 的说明，从github上获取Paddle代码，然后进行编译，生成最新的预测库。使用git获取代码方法如下。
```shell ```shell
git clone https://github.com/PaddlePaddle/Paddle.git git clone https://github.com/PaddlePaddle/Paddle.git
git checkout develop git checkout develop
``` ```
* 进入Paddle目录后，编译方法如下。 * Enter the Paddle directory and run the following commands to compile the paddle inference library.
```shell ```shell
rm -rf build rm -rf build
...@@ -151,10 +139,10 @@ make -j ...@@ -151,10 +139,10 @@ make -j
make inference_lib_dist make inference_lib_dist
``` ```
更多编译参数选项介绍可以参考[文档说明](https://www.paddlepaddle.org.cn/documentation/docs/zh/2.0/guides/05_inference_deployment/inference/build_and_install_lib_cn.html#congyuanmabianyi)。 For more compilation parameter options, please refer to the [document](https://www.paddlepaddle.org.cn/documentation/docs/zh/2.0/guides/05_inference_deployment/inference/build_and_install_lib_cn.html#congyuanmabianyi).
* 编译完成之后，可以在`build/paddle_inference_install_dir/`文件下看到生成了以下文件及文件夹。 * After the compilation process, you can see the following files in the folder of `build/paddle_inference_install_dir/`.
``` ```
build/paddle_inference_install_dir/ build/paddle_inference_install_dir/
...@@ -164,17 +152,14 @@ build/paddle_inference_install_dir/ ...@@ -164,17 +152,14 @@ build/paddle_inference_install_dir/
|-- version.txt |-- version.txt
``` ```
其中`paddle`就是C++预测所需的Paddle库，`version.txt`中包含当前预测库的版本信息。 `paddle` is the Paddle library required for C++ prediction later, and `version.txt` contains the version information of the current inference library.
<a name="2"></a>
## 2 开始运行 ## 2. Compile and Run the Demo
<a name="21"></a> ### 2.1 Export the inference model
### 2.1 将模型导出为inference model * You can refer to [Model inference](../../doc/doc_ch/inference.md) and export the inference model. After the model is exported, assuming it is placed in the `inference` directory, the directory structure is as follows.
* 可以参考[模型预测章节](../../doc/doc_ch/inference.md)，导出inference model，用于模型预测。模型导出之后，假设放在`inference`目录下，则目录结构如下。
``` ```
inference/ inference/
...@@ -189,41 +174,42 @@ inference/ ...@@ -189,41 +174,42 @@ inference/
| |--inference.pdmodel | |--inference.pdmodel
``` ```
<a name="22"></a>
### 2.2 编译PaddleOCR C++预测demo ### 2.2 Compile PaddleOCR C++ inference demo
* 编译命令如下，其中Paddle C++预测库、opencv等其他依赖库的地址需要换成自己机器上的实际地址。 * The compilation commands are as follows. The addresses of Paddle C++ inference library, opencv and other Dependencies need to be replaced with the actual addresses on your own machines.
```shell ```shell
sh tools/build.sh sh tools/build.sh
``` ```
* 具体的，需要修改`tools/build.sh`中环境路径，相关内容如下： Specifically, you should modify the paths in `tools/build.sh`. The related content is as follows.
```shell ```shell
OPENCV_DIR=your_opencv_dir OPENCV_DIR=your_opencv_dir
LIB_DIR=your_paddle_inference_dir LIB_DIR=your_paddle_inference_dir
CUDA_LIB_DIR=your_cuda_lib_dir CUDA_LIB_DIR=your_cuda_lib_dir
CUDNN_LIB_DIR=/your_cudnn_lib_dir CUDNN_LIB_DIR=your_cudnn_lib_dir
``` ```
其中，`OPENCV_DIR`为opencv编译安装的地址；`LIB_DIR`为下载(`paddle_inference`文件夹)或者编译生成的Paddle预测库地址(`build/paddle_inference_install_dir`文件夹)；`CUDA_LIB_DIR`为cuda库文件地址，在docker中为`/usr/local/cuda/lib64`；`CUDNN_LIB_DIR`为cudnn库文件地址，在docker中为`/usr/lib/x86_64-linux-gnu/`。**注意：以上路径都写绝对路径，不要写相对路径。** `OPENCV_DIR` is the OpenCV installation path; `LIB_DIR` is the download (`paddle_inference` folder)
or the generated Paddle inference library path (`build/paddle_inference_install_dir` folder);
`CUDA_LIB_DIR` is the CUDA library file path, in docker; it is `/usr/local/cuda/lib64`; `CUDNN_LIB_DIR` is the cuDNN library file path, in docker it is `/usr/lib/x86_64-linux-gnu/`.
* 编译完成之后，会在`build`文件夹下生成一个名为`ppocr`的可执行文件。
<a name="23"></a> * After the compilation is completed, an executable file named `ppocr` will be generated in the `build` folder.
### 2.3 运行demo
运行方式： ### Run the demo
Execute the built executable file:
```shell ```shell
./build/ppocr [--param1] [--param2] [...] ./build/ppocr [--param1] [--param2] [...]
``` ```
具体命令如下：
##### 1. 检测+分类+识别： Specifically,
##### 1. det+cls+rec：
```shell ```shell
./build/ppocr --det_model_dir=inference/det_db \ ./build/ppocr --det_model_dir=inference/det_db \
--rec_model_dir=inference/rec_rcnn \ --rec_model_dir=inference/rec_rcnn \
...@@ -235,7 +221,7 @@ CUDNN_LIB_DIR=/your_cudnn_lib_dir ...@@ -235,7 +221,7 @@ CUDNN_LIB_DIR=/your_cudnn_lib_dir
--cls=true \ --cls=true \
``` ```
##### 2. 检测+识别： ##### 2. det+rec：
```shell ```shell
./build/ppocr --det_model_dir=inference/det_db \ ./build/ppocr --det_model_dir=inference/det_db \
--rec_model_dir=inference/rec_rcnn \ --rec_model_dir=inference/rec_rcnn \
...@@ -246,7 +232,7 @@ CUDNN_LIB_DIR=/your_cudnn_lib_dir ...@@ -246,7 +232,7 @@ CUDNN_LIB_DIR=/your_cudnn_lib_dir
--cls=false \ --cls=false \
``` ```
##### 3. 检测： ##### 3. det
```shell ```shell
./build/ppocr --det_model_dir=inference/det_db \ ./build/ppocr --det_model_dir=inference/det_db \
--image_dir=../../doc/imgs/12.jpg \ --image_dir=../../doc/imgs/12.jpg \
...@@ -254,7 +240,7 @@ CUDNN_LIB_DIR=/your_cudnn_lib_dir ...@@ -254,7 +240,7 @@ CUDNN_LIB_DIR=/your_cudnn_lib_dir
--rec=false --rec=false
``` ```
##### 4. 分类+识别： ##### 4. cls+rec：
```shell ```shell
./build/ppocr --rec_model_dir=inference/rec_rcnn \ ./build/ppocr --rec_model_dir=inference/rec_rcnn \
--cls_model_dir=inference/cls \ --cls_model_dir=inference/cls \
...@@ -265,7 +251,7 @@ CUDNN_LIB_DIR=/your_cudnn_lib_dir ...@@ -265,7 +251,7 @@ CUDNN_LIB_DIR=/your_cudnn_lib_dir
--cls=true \ --cls=true \
``` ```
##### 5. 识别： ##### 5. rec
```shell ```shell
./build/ppocr --rec_model_dir=inference/rec_rcnn \ ./build/ppocr --rec_model_dir=inference/rec_rcnn \
--image_dir=../../doc/imgs_words/ch/word_1.jpg \ --image_dir=../../doc/imgs_words/ch/word_1.jpg \
...@@ -275,7 +261,7 @@ CUDNN_LIB_DIR=/your_cudnn_lib_dir ...@@ -275,7 +261,7 @@ CUDNN_LIB_DIR=/your_cudnn_lib_dir
--cls=false \ --cls=false \
``` ```
##### 6. 分类： ##### 6. cls
```shell ```shell
./build/ppocr --cls_model_dir=inference/cls \ ./build/ppocr --cls_model_dir=inference/cls \
--cls_model_dir=inference/cls \ --cls_model_dir=inference/cls \
...@@ -286,61 +272,62 @@ CUDNN_LIB_DIR=/your_cudnn_lib_dir ...@@ -286,61 +272,62 @@ CUDNN_LIB_DIR=/your_cudnn_lib_dir
--cls=true \ --cls=true \
``` ```
更多支持的可调节参数解释如下： More parameters are as follows,
- 通用参数 - Common parameters
|参数名称|类型|默认参数|意义| |parameter|data type|default|meaning|
| :---: | :---: | :---: | :---: | | --- | --- | --- | --- |
|use_gpu|bool|false|是否使用GPU| |use_gpu|bool|false|Whether to use GPU|
|gpu_id|int|0|GPU id，使用GPU时有效| |gpu_id|int|0|GPU id when use_gpu is true|
|gpu_mem|int|4000|申请的GPU内存| |gpu_mem|int|4000|GPU memory requested|
|cpu_math_library_num_threads|int|10|CPU预测时的线程数，在机器核数充足的情况下，该值越大，预测速度越快| |cpu_math_library_num_threads|int|10|Number of threads when using CPU inference. When machine cores is enough, the large the value, the faster the inference speed|
|enable_mkldnn|bool|true|是否使用mkldnn库| |enable_mkldnn|bool|true|Whether to use mkdlnn library|
|output|str|./output|可视化结果保存的路径| |output|str|./output|Path where visualization results are saved|
- 前向相关
|参数名称|类型|默认参数|意义| - forward
|parameter|data type|default|meaning|
| :---: | :---: | :---: | :---: | | :---: | :---: | :---: | :---: |
|det|bool|true|前向是否执行文字检测| |det|bool|true|前向是否执行文字检测|
|rec|bool|true|前向是否执行文字识别| |rec|bool|true|前向是否执行文字识别|
|cls|bool|false|前向是否执行文字方向分类| |cls|bool|false|前向是否执行文字方向分类|
- 检测模型相关 - Detection related parameters
|参数名称|类型|默认参数|意义| |parameter|data type|default|meaning|
| :---: | :---: | :---: | :---: | | --- | --- | --- | --- |
|det_model_dir|string|-|检测模型inference model地址| |det_model_dir|string|-|Address of detection inference model|
|max_side_len|int|960|输入图像长宽大于960时，等比例缩放图像，使得图像最长边为960| |max_side_len|int|960|Limit the maximum image height and width to 960|
|det_db_thresh|float|0.3|用于过滤DB预测的二值化图像，设置为0.-0.3对结果影响不明显| |det_db_thresh|float|0.3|Used to filter the binarized image of DB prediction, setting 0.-0.3 has no obvious effect on the result|
|det_db_box_thresh|float|0.5|DB后处理过滤box的阈值，如果检测存在漏框情况，可酌情减小| |det_db_box_thresh|float|0.5|DB post-processing filter box threshold, if there is a missing box detected, it can be reduced as appropriate|
|det_db_unclip_ratio|float|1.6|表示文本框的紧致程度，越小则文本框更靠近文本| |det_db_unclip_ratio|float|1.6|Indicates the compactness of the text box, the smaller the value, the closer the text box to the text|
|det_db_score_mode|string|slow|slow:使用多边形框计算bbox score，fast:使用矩形框计算。矩形框计算速度更快，多边形框对弯曲文本区域计算更准确。| |det_db_score_mode|string|slow| slow: use polygon box to calculate bbox score, fast: use rectangle box to calculate. Use rectangular box to calculate faster, and polygonal box more accurate for curved text area.|
|visualize|bool|true|是否对结果进行可视化，为1时，预测结果会保存在`output`字段指定的文件夹下和输入图像同名的图像上。| |visualize|bool|true|Whether to visualize the results，when it is set as true, the prediction results will be saved in the folder specified by the `output` field on an image with the same name as the input image.|
- 方向分类器相关 - Classifier related parameters
|参数名称|类型|默认参数|意义| |parameter|data type|default|meaning|
| :---: | :---: | :---: | :---: | | --- | --- | --- | --- |
|use_angle_cls|bool|false|是否使用方向分类器| |use_angle_cls|bool|false|Whether to use the direction classifier|
|cls_model_dir|string|-|方向分类器inference model地址| |cls_model_dir|string|-|Address of direction classifier inference model|
|cls_thresh|float|0.9|方向分类器的得分阈值| |cls_thresh|float|0.9|Score threshold of the direction classifier|
|cls_batch_num|int|1|方向分类器batchsize| |cls_batch_num|int|1|batch size of classifier|
- 识别模型相关 - Recognition related parameters
|参数名称|类型|默认参数|意义| |parameter|data type|default|meaning|
| :---: | :---: | :---: | :---: | | --- | --- | --- | --- |
|rec_model_dir|string|-|识别模型inference model地址| |rec_model_dir|string|-|Address of recognition inference model|
|rec_char_dict_path|string|../../ppocr/utils/ppocr_keys_v1.txt|字典文件| |rec_char_dict_path|string|../../ppocr/utils/ppocr_keys_v1.txt|dictionary file|
|rec_batch_num|int|6|识别模型batchsize| |rec_batch_num|int|6|batch size of recognition|
* Multi-language inference is also supported in PaddleOCR, you can refer to [recognition tutorial](../../doc/doc_en/recognition_en.md) for more supported languages and models in PaddleOCR. Specifically, if you want to infer using multi-language models, you just need to modify values of `rec_char_dict_path` and `rec_model_dir`.
* PaddleOCR也支持多语言的预测，更多支持的语言和模型可以参考[识别文档](../../doc/doc_ch/recognition.md)中的多语言字典与模型部分，如果希望进行多语言预测，只需将修改`rec_char_dict_path`（字典文件路径）以及`rec_model_dir`（inference模型路径）字段即可。
最终屏幕上会输出检测结果如下。 The detection results will be shown on the screen, which is as follows.
```bash ```bash
predict img: ../../doc/imgs/12.jpg predict img: ../../doc/imgs/12.jpg
...@@ -352,6 +339,7 @@ predict img: ../../doc/imgs/12.jpg ...@@ -352,6 +339,7 @@ predict img: ../../doc/imgs/12.jpg
The detection visualized image saved in ./output//12.jpg The detection visualized image saved in ./output//12.jpg
``` ```
## 3. FAQ ## 3. FAQ
1. 遇到报错 `unable to access 'https://github.com/LDOUBLEV/AutoLog.git/': gnutls_handshake() failed: The TLS connection was non-properly terminated.`， 将 `deploy/cpp_infer/external-cmake/auto-log.cmake` 中的github地址改为 https://gitee.com/Double_V/AutoLog 地址即可。 1. Encountered the error `unable to access 'https://github.com/LDOUBLEV/AutoLog.git/': gnutls_handshake() failed: The TLS connection was non-properly terminated.`, change the github address in `deploy/cpp_infer/external-cmake/auto-log.cmake` to the https://gitee.com/Double_V/AutoLog address.
deploy/cpp_infer/readme_en.md → deploy/cpp_infer/readme_ch.md
浏览文件 @ 486aa102
- [Server-side C++ Inference](#server-side-c-inference) - [服务器端C++预测](#服务器端c预测)
- [1. Prepare the Environment](#1-prepare-the-environment) - [1. 准备环境](#1-准备环境)
- [Environment](#environment) - [1.0 运行准备](#10-运行准备)
- [1.1 Compile OpenCV](#11-compile-opencv) - [1.1 编译opencv库](#11-编译opencv库)
- [1.2 Compile or Download or the Paddle Inference Library](#12-compile-or-download-or-the-paddle-inference-library) - [1.2 下载或者编译Paddle预测库](#12-下载或者编译paddle预测库)
- [1.2.1 Direct download and installation](#121-direct-download-and-installation) - [1.2.1 直接下载安装](#121-直接下载安装)
- [1.2.2 Compile the inference source code](#122-compile-the-inference-source-code) - [1.2.2 预测库源码编译](#122-预测库源码编译)
- [2. Compile and Run the Demo](#2-compile-and-run-the-demo) - [2 开始运行](#2-开始运行)
- [2.1 Export the inference model](#21-export-the-inference-model) - [2.1 将模型导出为inference model](#21-将模型导出为inference-model)
- [2.2 Compile PaddleOCR C++ inference demo](#22-compile-paddleocr-c-inference-demo) - [2.2 编译PaddleOCR C++预测demo](#22-编译paddleocr-c预测demo)
- [Run the demo](#run-the-demo) - [2.3 运行demo](#23-运行demo)
- [1. det+cls+rec：](#1-detclsrec) - [1. 检测+分类+识别：](#1-检测分类识别)
- [2. det+rec：](#2-detrec) - [2. 检测+识别：](#2-检测识别)
- [3. det](#3-det) - [3. 检测：](#3-检测)
- [4. cls+rec：](#4-clsrec) - [4. 分类+识别：](#4-分类识别)
- [5. rec](#5-rec) - [5. 识别：](#5-识别)
- [6. cls](#6-cls) - [6. 分类：](#6-分类)
- [3. FAQ](#3-faq) - [3. FAQ](#3-faq)
# Server-side C++ Inference # 服务器端C++预测
This chapter introduces the C++ deployment steps of the PaddleOCR model. The corresponding Python predictive deployment method refers to [document](../../doc/doc_ch/inference.md). 本章节介绍PaddleOCR 模型的的C++部署方法，与之对应的python预测部署方式参考[文档](../../doc/doc_ch/inference.md)。
C++ is better than python in terms of performance. Therefore, in CPU and GPU deployment scenarios, C++ deployment is mostly used. C++在性能计算上优于python，因此，在大多数CPU、GPU部署场景，多采用C++的部署方式，本节将介绍如何在Linux\Windows (CPU\GPU)环境下配置C++环境并完成
This section will introduce how to configure the C++ environment and deploy PaddleOCR in Linux (CPU\GPU) environment. For Windows deployment please refer to [Windows](./docs/windows_vs2019_build.md) compilation guidelines. PaddleOCR模型部署。
## 1. Prepare the Environment <a name="1"></a>
### Environment ## 1. 准备环境
- Linux, docker is recommended. <a name="10"></a>
- Windows.
### 1.0 运行准备
### 1.1 Compile OpenCV - Linux环境，推荐使用docker。
- Windows环境。
* First of all, you need to download the source code compiled package in the Linux environment from the OpenCV official website. Taking OpenCV 3.4.7 as an example, the download command is as follows. * 该文档主要介绍基于Linux环境的PaddleOCR C++预测流程，如果需要在Windows下基于预测库进行C++预测，具体编译方法请参考[Windows下编译教程](./docs/windows_vs2019_build.md)
<a name="11"></a>
### 1.1 编译opencv库
* 首先需要从opencv官网上下载在Linux环境下源码编译的包，以opencv3.4.7为例，下载命令如下。
```bash ```bash
cd deploy/cpp_infer cd deploy/cpp_infer
...@@ -42,18 +49,18 @@ wget https://paddleocr.bj.bcebos.com/libs/opencv/opencv-3.4.7.tar.gz ...@@ -42,18 +49,18 @@ wget https://paddleocr.bj.bcebos.com/libs/opencv/opencv-3.4.7.tar.gz
tar -xf opencv-3.4.7.tar.gz tar -xf opencv-3.4.7.tar.gz
``` ```
Finally, you will see the folder of `opencv-3.4.7/` in the current directory. 最终可以在当前目录下看到`opencv-3.4.7/`的文件夹。
* Compile OpenCV, the OpenCV source path (`root_path`) and installation path (`install_path`) should be set by yourself. Enter the OpenCV source code path and compile it in the following way.
* 编译opencv，设置opencv源码路径(`root_path`)以及安装路径(`install_path`)。进入opencv源码路径下，按照下面的方式进行编译。
```shell ```shell
root_path=your_opencv_root_path root_path="your_opencv_root_path"
install_path=${root_path}/opencv3 install_path=${root_path}/opencv3
build_dir=${root_path}/build
rm -rf build rm -rf ${build_dir}
mkdir build mkdir ${build_dir}
cd build cd ${build_dir}
cmake .. \ cmake .. \
-DCMAKE_INSTALL_PREFIX=${install_path} \ -DCMAKE_INSTALL_PREFIX=${install_path} \
...@@ -77,11 +84,15 @@ make -j ...@@ -77,11 +84,15 @@ make -j
make install make install
``` ```
In the above commands, `root_path` is the downloaded OpenCV source code path, and `install_path` is the installation path of OpenCV. After `make install` is completed, the OpenCV header file and library file will be generated in this folder for later OCR source code compilation. 也可以直接修改`tools/build_opencv.sh`的内容，然后直接运行下面的命令进行编译。
```shell
sh tools/build_opencv.sh
```
其中`root_path`为下载的opencv源码路径，`install_path`为opencv的安装路径，`make install`完成之后，会在该文件夹下生成opencv头文件和库文件，用于后面的OCR代码编译。
The final file structure under the OpenCV installation path is as follows. 最终在安装路径下的文件结构如下所示。
``` ```
opencv3/ opencv3/
...@@ -92,34 +103,35 @@ opencv3/ ...@@ -92,34 +103,35 @@ opencv3/
|-- share |-- share
``` ```
### 1.2 Compile or Download or the Paddle Inference Library <a name="12"></a>
* There are 2 ways to obtain the Paddle inference library, described in detail below. ### 1.2 下载或者编译Paddle预测库
#### 1.2.1 Direct download and installation * 有2种方式获取Paddle预测库，下面进行详细介绍。
[Paddle inference library official website](https://paddleinference.paddlepaddle.org.cn/user_guides/download_lib.html#linux). You can review and select the appropriate version of the inference library on the official website.
#### 1.2.1 直接下载安装
* After downloading, use the following command to extract files. * [Paddle预测库官网](https://paddleinference.paddlepaddle.org.cn/user_guides/download_lib.html#linux) 上提供了不同cuda版本的Linux预测库，可以在官网查看并选择合适的预测库版本（*建议选择paddle版本>=2.0.1版本的预测库* ）。
* 下载之后使用下面的方法解压。
``` ```
tar -xf paddle_inference.tgz tar -xf paddle_inference.tgz
``` ```
Finally you will see the the folder of `paddle_inference/` in the current path. 最终会在当前的文件夹中生成`paddle_inference/`的子文件夹。
#### 1.2.2 Compile the inference source code
* If you want to get the latest Paddle inference library features, you can download the latest code from Paddle GitHub repository and compile the inference library from the source code. It is recommended to download the inference library with paddle version greater than or equal to 2.0.1.
* You can refer to [Paddle inference library] (https://www.paddlepaddle.org.cn/documentation/docs/en/advanced_guide/inference_deployment/inference/build_and_install_lib_en.html) to get the Paddle source code from GitHub, and then compile To generate the latest inference library. The method of using git to access the code is as follows.
#### 1.2.2 预测库源码编译
* 如果希望获取最新预测库特性，可以从Paddle github上克隆最新代码，源码编译预测库。
* 可以参考[Paddle预测库安装编译说明](https://www.paddlepaddle.org.cn/documentation/docs/zh/2.0/guides/05_inference_deployment/inference/build_and_install_lib_cn.html#congyuanmabianyi) 的说明，从github上获取Paddle代码，然后进行编译，生成最新的预测库。使用git获取代码方法如下。
```shell ```shell
git clone https://github.com/PaddlePaddle/Paddle.git git clone https://github.com/PaddlePaddle/Paddle.git
git checkout develop git checkout develop
``` ```
* Enter the Paddle directory and run the following commands to compile the paddle inference library. * 进入Paddle目录后，编译方法如下。
```shell ```shell
rm -rf build rm -rf build
...@@ -139,10 +151,10 @@ make -j ...@@ -139,10 +151,10 @@ make -j
make inference_lib_dist make inference_lib_dist
``` ```
For more compilation parameter options, please refer to the [document](https://www.paddlepaddle.org.cn/documentation/docs/zh/2.0/guides/05_inference_deployment/inference/build_and_install_lib_cn.html#congyuanmabianyi). 更多编译参数选项介绍可以参考[文档说明](https://www.paddlepaddle.org.cn/documentation/docs/zh/2.0/guides/05_inference_deployment/inference/build_and_install_lib_cn.html#congyuanmabianyi)。
* After the compilation process, you can see the following files in the folder of `build/paddle_inference_install_dir/`. * 编译完成之后，可以在`build/paddle_inference_install_dir/`文件下看到生成了以下文件及文件夹。
``` ```
build/paddle_inference_install_dir/ build/paddle_inference_install_dir/
...@@ -152,14 +164,17 @@ build/paddle_inference_install_dir/ ...@@ -152,14 +164,17 @@ build/paddle_inference_install_dir/
|-- version.txt |-- version.txt
``` ```
`paddle` is the Paddle library required for C++ prediction later, and `version.txt` contains the version information of the current inference library. 其中`paddle`就是C++预测所需的Paddle库，`version.txt`中包含当前预测库的版本信息。
<a name="2"></a>
## 2. Compile and Run the Demo ## 2 开始运行
### 2.1 Export the inference model <a name="21"></a>
* You can refer to [Model inference](../../doc/doc_ch/inference.md) and export the inference model. After the model is exported, assuming it is placed in the `inference` directory, the directory structure is as follows. ### 2.1 将模型导出为inference model
* 可以参考[模型预测章节](../../doc/doc_ch/inference.md)，导出inference model，用于模型预测。模型导出之后，假设放在`inference`目录下，则目录结构如下。
``` ```
inference/ inference/
...@@ -174,42 +189,41 @@ inference/ ...@@ -174,42 +189,41 @@ inference/
| |--inference.pdmodel | |--inference.pdmodel
``` ```
<a name="22"></a>
### 2.2 Compile PaddleOCR C++ inference demo ### 2.2 编译PaddleOCR C++预测demo
* The compilation commands are as follows. The addresses of Paddle C++ inference library, opencv and other Dependencies need to be replaced with the actual addresses on your own machines. * 编译命令如下，其中Paddle C++预测库、opencv等其他依赖库的地址需要换成自己机器上的实际地址。
```shell ```shell
sh tools/build.sh sh tools/build.sh
``` ```
Specifically, you should modify the paths in `tools/build.sh`. The related content is as follows. * 具体的，需要修改`tools/build.sh`中环境路径，相关内容如下：
```shell ```shell
OPENCV_DIR=your_opencv_dir OPENCV_DIR=your_opencv_dir
LIB_DIR=your_paddle_inference_dir LIB_DIR=your_paddle_inference_dir
CUDA_LIB_DIR=your_cuda_lib_dir CUDA_LIB_DIR=your_cuda_lib_dir
CUDNN_LIB_DIR=your_cudnn_lib_dir CUDNN_LIB_DIR=/your_cudnn_lib_dir
``` ```
`OPENCV_DIR` is the OpenCV installation path; `LIB_DIR` is the download (`paddle_inference` folder) 其中，`OPENCV_DIR`为opencv编译安装的地址；`LIB_DIR`为下载(`paddle_inference`文件夹)或者编译生成的Paddle预测库地址(`build/paddle_inference_install_dir`文件夹)；`CUDA_LIB_DIR`为cuda库文件地址，在docker中为`/usr/local/cuda/lib64`；`CUDNN_LIB_DIR`为cudnn库文件地址，在docker中为`/usr/lib/x86_64-linux-gnu/`。**注意：以上路径都写绝对路径，不要写相对路径。**
or the generated Paddle inference library path (`build/paddle_inference_install_dir` folder);
`CUDA_LIB_DIR` is the CUDA library file path, in docker; it is `/usr/local/cuda/lib64`; `CUDNN_LIB_DIR` is the cuDNN library file path, in docker it is `/usr/lib/x86_64-linux-gnu/`.
* 编译完成之后，会在`build`文件夹下生成一个名为`ppocr`的可执行文件。
* After the compilation is completed, an executable file named `ppocr` will be generated in the `build` folder. <a name="23"></a>
### 2.3 运行demo
### Run the demo 运行方式：
Execute the built executable file:
```shell ```shell
./build/ppocr [--param1] [--param2] [...] ./build/ppocr [--param1] [--param2] [...]
``` ```
具体命令如下：
Specifically, ##### 1. 检测+分类+识别：
##### 1. det+cls+rec：
```shell ```shell
./build/ppocr --det_model_dir=inference/det_db \ ./build/ppocr --det_model_dir=inference/det_db \
--rec_model_dir=inference/rec_rcnn \ --rec_model_dir=inference/rec_rcnn \
...@@ -221,7 +235,7 @@ Specifically, ...@@ -221,7 +235,7 @@ Specifically,
--cls=true \ --cls=true \
``` ```
##### 2. det+rec： ##### 2. 检测+识别：
```shell ```shell
./build/ppocr --det_model_dir=inference/det_db \ ./build/ppocr --det_model_dir=inference/det_db \
--rec_model_dir=inference/rec_rcnn \ --rec_model_dir=inference/rec_rcnn \
...@@ -232,7 +246,7 @@ Specifically, ...@@ -232,7 +246,7 @@ Specifically,
--cls=false \ --cls=false \
``` ```
##### 3. det ##### 3. 检测：
```shell ```shell
./build/ppocr --det_model_dir=inference/det_db \ ./build/ppocr --det_model_dir=inference/det_db \
--image_dir=../../doc/imgs/12.jpg \ --image_dir=../../doc/imgs/12.jpg \
...@@ -240,7 +254,7 @@ Specifically, ...@@ -240,7 +254,7 @@ Specifically,
--rec=false --rec=false
``` ```
##### 4. cls+rec： ##### 4. 分类+识别：
```shell ```shell
./build/ppocr --rec_model_dir=inference/rec_rcnn \ ./build/ppocr --rec_model_dir=inference/rec_rcnn \
--cls_model_dir=inference/cls \ --cls_model_dir=inference/cls \
...@@ -251,7 +265,7 @@ Specifically, ...@@ -251,7 +265,7 @@ Specifically,
--cls=true \ --cls=true \
``` ```
##### 5. rec ##### 5. 识别：
```shell ```shell
./build/ppocr --rec_model_dir=inference/rec_rcnn \ ./build/ppocr --rec_model_dir=inference/rec_rcnn \
--image_dir=../../doc/imgs_words/ch/word_1.jpg \ --image_dir=../../doc/imgs_words/ch/word_1.jpg \
...@@ -261,7 +275,7 @@ Specifically, ...@@ -261,7 +275,7 @@ Specifically,
--cls=false \ --cls=false \
``` ```
##### 6. cls ##### 6. 分类：
```shell ```shell
./build/ppocr --cls_model_dir=inference/cls \ ./build/ppocr --cls_model_dir=inference/cls \
--cls_model_dir=inference/cls \ --cls_model_dir=inference/cls \
...@@ -272,62 +286,61 @@ Specifically, ...@@ -272,62 +286,61 @@ Specifically,
--cls=true \ --cls=true \
``` ```
More parameters are as follows, 更多支持的可调节参数解释如下：
- Common parameters
|parameter|data type|default|meaning| - 通用参数
| --- | --- | --- | --- |
|use_gpu|bool|false|Whether to use GPU|
|gpu_id|int|0|GPU id when use_gpu is true|
|gpu_mem|int|4000|GPU memory requested|
|cpu_math_library_num_threads|int|10|Number of threads when using CPU inference. When machine cores is enough, the large the value, the faster the inference speed|
|enable_mkldnn|bool|true|Whether to use mkdlnn library|
|output|str|./output|Path where visualization results are saved|
|参数名称|类型|默认参数|意义|
| :---: | :---: | :---: | :---: |
|use_gpu|bool|false|是否使用GPU|
|gpu_id|int|0|GPU id，使用GPU时有效|
|gpu_mem|int|4000|申请的GPU内存|
|cpu_math_library_num_threads|int|10|CPU预测时的线程数，在机器核数充足的情况下，该值越大，预测速度越快|
|enable_mkldnn|bool|true|是否使用mkldnn库|
|output|str|./output|可视化结果保存的路径|
- forward - 前向相关
|parameter|data type|default|meaning| |参数名称|类型|默认参数|意义|
| :---: | :---: | :---: | :---: | | :---: | :---: | :---: | :---: |
|det|bool|true|前向是否执行文字检测| |det|bool|true|前向是否执行文字检测|
|rec|bool|true|前向是否执行文字识别| |rec|bool|true|前向是否执行文字识别|
|cls|bool|false|前向是否执行文字方向分类| |cls|bool|false|前向是否执行文字方向分类|
- Detection related parameters - 检测模型相关
|parameter|data type|default|meaning| |参数名称|类型|默认参数|意义|
| --- | --- | --- | --- | | :---: | :---: | :---: | :---: |
|det_model_dir|string|-|Address of detection inference model| |det_model_dir|string|-|检测模型inference model地址|
|max_side_len|int|960|Limit the maximum image height and width to 960| |max_side_len|int|960|输入图像长宽大于960时，等比例缩放图像，使得图像最长边为960|
|det_db_thresh|float|0.3|Used to filter the binarized image of DB prediction, setting 0.-0.3 has no obvious effect on the result| |det_db_thresh|float|0.3|用于过滤DB预测的二值化图像，设置为0.-0.3对结果影响不明显|
|det_db_box_thresh|float|0.5|DB post-processing filter box threshold, if there is a missing box detected, it can be reduced as appropriate| |det_db_box_thresh|float|0.5|DB后处理过滤box的阈值，如果检测存在漏框情况，可酌情减小|
|det_db_unclip_ratio|float|1.6|Indicates the compactness of the text box, the smaller the value, the closer the text box to the text| |det_db_unclip_ratio|float|1.6|表示文本框的紧致程度，越小则文本框更靠近文本|
|det_db_score_mode|string|slow| slow: use polygon box to calculate bbox score, fast: use rectangle box to calculate. Use rectangular box to calculate faster, and polygonal box more accurate for curved text area.| |det_db_score_mode|string|slow|slow:使用多边形框计算bbox score，fast:使用矩形框计算。矩形框计算速度更快，多边形框对弯曲文本区域计算更准确。|
|visualize|bool|true|Whether to visualize the results，when it is set as true, the prediction results will be saved in the folder specified by the `output` field on an image with the same name as the input image.| |visualize|bool|true|是否对结果进行可视化，为1时，预测结果会保存在`output`字段指定的文件夹下和输入图像同名的图像上。|
- Classifier related parameters - 方向分类器相关
|parameter|data type|default|meaning| |参数名称|类型|默认参数|意义|
| --- | --- | --- | --- | | :---: | :---: | :---: | :---: |
|use_angle_cls|bool|false|Whether to use the direction classifier| |use_angle_cls|bool|false|是否使用方向分类器|
|cls_model_dir|string|-|Address of direction classifier inference model| |cls_model_dir|string|-|方向分类器inference model地址|
|cls_thresh|float|0.9|Score threshold of the direction classifier| |cls_thresh|float|0.9|方向分类器的得分阈值|
|cls_batch_num|int|1|batch size of classifier| |cls_batch_num|int|1|方向分类器batchsize|
- Recognition related parameters - 识别模型相关
|parameter|data type|default|meaning| |参数名称|类型|默认参数|意义|
| --- | --- | --- | --- | | :---: | :---: | :---: | :---: |
|rec_model_dir|string|-|Address of recognition inference model| |rec_model_dir|string|-|识别模型inference model地址|
|rec_char_dict_path|string|../../ppocr/utils/ppocr_keys_v1.txt|dictionary file| |rec_char_dict_path|string|../../ppocr/utils/ppocr_keys_v1.txt|字典文件|
|rec_batch_num|int|6|batch size of recognition| |rec_batch_num|int|6|识别模型batchsize|
* Multi-language inference is also supported in PaddleOCR, you can refer to [recognition tutorial](../../doc/doc_en/recognition_en.md) for more supported languages and models in PaddleOCR. Specifically, if you want to infer using multi-language models, you just need to modify values of `rec_char_dict_path` and `rec_model_dir`.
* PaddleOCR也支持多语言的预测，更多支持的语言和模型可以参考[识别文档](../../doc/doc_ch/recognition.md)中的多语言字典与模型部分，如果希望进行多语言预测，只需将修改`rec_char_dict_path`（字典文件路径）以及`rec_model_dir`（inference模型路径）字段即可。
The detection results will be shown on the screen, which is as follows. 最终屏幕上会输出检测结果如下。
```bash ```bash
predict img: ../../doc/imgs/12.jpg predict img: ../../doc/imgs/12.jpg
...@@ -339,7 +352,6 @@ predict img: ../../doc/imgs/12.jpg ...@@ -339,7 +352,6 @@ predict img: ../../doc/imgs/12.jpg
The detection visualized image saved in ./output//12.jpg The detection visualized image saved in ./output//12.jpg
``` ```
## 3. FAQ ## 3. FAQ
1. Encountered the error `unable to access 'https://github.com/LDOUBLEV/AutoLog.git/': gnutls_handshake() failed: The TLS connection was non-properly terminated.`, change the github address in `deploy/cpp_infer/external-cmake/auto-log.cmake` to the https://gitee.com/Double_V/AutoLog address. 1. 遇到报错 `unable to access 'https://github.com/LDOUBLEV/AutoLog.git/': gnutls_handshake() failed: The TLS connection was non-properly terminated.`， 将 `deploy/cpp_infer/external-cmake/auto-log.cmake` 中的github地址改为 https://gitee.com/Double_V/AutoLog 地址即可。
deploy/lite/readme.md
浏览文件 @ 486aa102
- [端侧部署](#端侧部署) - [Tutorial of PaddleOCR Mobile deployment](#tutorial-of-paddleocr-mobile-deployment)
- [1. 准备环境](#1-准备环境) - [1. Preparation](#1-preparation)
- [运行准备](#运行准备) - [Preparation environment](#preparation-environment)
- [1.1 准备交叉编译环境](#11-准备交叉编译环境) - [1.1 Prepare the cross-compilation environment](#11-prepare-the-cross-compilation-environment)
- [1.2 准备预测库](#12-准备预测库) - [1.2 Prepare Paddle-Lite library](#12-prepare-paddle-lite-library)
- [2 开始运行](#2-开始运行) - [2 Run](#2-run)
- [2.1 模型优化](#21-模型优化) - [2.1 Inference Model Optimization](#21-inference-model-optimization)
- [2.2 与手机联调](#22-与手机联调) - [2.2 Run optimized model on Phone](#22-run-optimized-model-on-phone)
- [注意：](#注意) - [注意：](#注意)
- [FAQ](#faq) - [FAQ](#faq)
# 端侧部署 # Tutorial of PaddleOCR Mobile deployment
本教程将介绍基于[Paddle Lite](https://github.com/PaddlePaddle/Paddle-Lite) 在移动端部署PaddleOCR超轻量中文检测、识别模型的详细步骤。 This tutorial will introduce how to use [Paddle Lite](https://github.com/PaddlePaddle/Paddle-Lite) to deploy PaddleOCR ultra-lightweight Chinese and English detection models on mobile phones.
Paddle Lite是飞桨轻量化推理引擎，为手机、IOT端提供高效推理能力，并广泛整合跨平台硬件，为端侧部署及应用落地问题提供轻量化的部署方案。 paddle-lite is a lightweight inference engine for PaddlePaddle. It provides efficient inference capabilities for mobile phones and IoT, and extensively integrates cross-platform hardware to provide lightweight deployment solutions for end-side deployment issues.
## 1. Preparation
## 1. 准备环境 ### Preparation environment
### 运行准备 - Computer (for Compiling Paddle Lite)
- 电脑（编译Paddle Lite） - Mobile phone (arm7 or arm8)
- 安卓手机（armv7或armv8）
### 1.1 准备交叉编译环境 ### 1.1 Prepare the cross-compilation environment
交叉编译环境用于编译 Paddle Lite 和 PaddleOCR 的C++ demo。 The cross-compilation environment is used to compile C++ demos of Paddle Lite and PaddleOCR.
支持多种开发环境，不同开发环境的编译流程请参考对应文档。 Supports multiple development environments.
For the compilation process of different development environments, please refer to the corresponding documents.
1. [Docker](https://paddle-lite.readthedocs.io/zh/latest/source_compile/compile_env.html#docker) 1. [Docker](https://paddle-lite.readthedocs.io/zh/latest/source_compile/compile_env.html#docker)
2. [Linux](https://paddle-lite.readthedocs.io/zh/latest/source_compile/compile_env.html#linux) 2. [Linux](https://paddle-lite.readthedocs.io/zh/latest/source_compile/compile_env.html#linux)
3. [MAC OS](https://paddle-lite.readthedocs.io/zh/latest/source_compile/compile_env.html#mac-os) 3. [MAC OS](https://paddle-lite.readthedocs.io/zh/latest/source_compile/compile_env.html#mac-os)
### 1.2 准备预测库 ### 1.2 Prepare Paddle-Lite library
预测库有两种获取方式： There are two ways to obtain the Paddle-Lite library：
- 1. 直接下载，预测库下载链接如下： - 1. Download directly, the download link of the Paddle-Lite library is as follows：
| 平台 | 预测库下载链接 | | Platform | Paddle-Lite library download link |
|---|---| |---|---|
|Android|[arm7](https://github.com/PaddlePaddle/Paddle-Lite/releases/download/v2.10/inference_lite_lib.android.armv7.gcc.c++_shared.with_extra.with_cv.tar.gz) / [arm8](https://github.com/PaddlePaddle/Paddle-Lite/releases/download/v2.10/inference_lite_lib.android.armv8.gcc.c++_shared.with_extra.with_cv.tar.gz)| |Android|[arm7](https://github.com/PaddlePaddle/Paddle-Lite/releases/download/v2.10/inference_lite_lib.android.armv7.gcc.c++_shared.with_extra.with_cv.tar.gz) / [arm8](https://github.com/PaddlePaddle/Paddle-Lite/releases/download/v2.10/inference_lite_lib.android.armv8.gcc.c++_shared.with_extra.with_cv.tar.gz)|
|IOS|[arm7](https://github.com/PaddlePaddle/Paddle-Lite/releases/download/v2.10/inference_lite_lib.ios.armv7.with_cv.with_extra.with_log.tiny_publish.tar.gz) / [arm8](https://github.com/PaddlePaddle/Paddle-Lite/releases/download/v2.10/inference_lite_lib.ios.armv8.with_cv.with_extra.with_log.tiny_publish.tar.gz)| |IOS|[arm7](https://github.com/PaddlePaddle/Paddle-Lite/releases/download/v2.10/inference_lite_lib.ios.armv7.with_cv.with_extra.with_log.tiny_publish.tar.gz) / [arm8](https://github.com/PaddlePaddle/Paddle-Lite/releases/download/v2.10/inference_lite_lib.ios.armv8.with_cv.with_extra.with_log.tiny_publish.tar.gz)|
注：1. 上述预测库为PaddleLite 2.10分支编译得到，有关PaddleLite 2.10 详细信息可参考 [链接](https://github.com/PaddlePaddle/Paddle-Lite/releases/tag/v2.10) 。 Note: 1. The above Paddle-Lite library is compiled from the Paddle-Lite 2.10 branch. For more information about Paddle-Lite 2.10, please refer to [link](https://github.com/PaddlePaddle/Paddle-Lite/releases/tag/v2.10).
- 2. [推荐]编译Paddle-Lite得到预测库，Paddle-Lite的编译方式如下： - 2. [Recommended] Compile Paddle-Lite to get the prediction library. The compilation method of Paddle-Lite is as follows：
``` ```
git clone https://github.com/PaddlePaddle/Paddle-Lite.git git clone https://github.com/PaddlePaddle/Paddle-Lite.git
cd Paddle-Lite cd Paddle-Lite
# 切换到Paddle-Lite release/v2.10 稳定分支 # Switch to Paddle-Lite release/v2.10 stable branch
git checkout release/v2.10 git checkout release/v2.10
./lite/tools/build_android.sh --arch=armv8 --with_cv=ON --with_extra=ON ./lite/tools/build_android.sh --arch=armv8 --with_cv=ON --with_extra=ON
``` ```
注意：编译Paddle-Lite获得预测库时，需要打开`--with_cv=ON --with_extra=ON`两个选项，`--arch`表示`arm`版本，这里指定为armv8， Note: When compiling Paddle-Lite to obtain the Paddle-Lite library, you need to turn on the two options `--with_cv=ON --with_extra=ON`, `--arch` means the `arm` version, here is designated as armv8,
更多编译命令
介绍请参考 [链接](https://paddle-lite.readthedocs.io/zh/release-v2.10_a/source_compile/linux_x86_compile_android.html) 。 More compilation commands refer to the introduction [link](https://paddle-lite.readthedocs.io/zh/release-v2.10_a/source_compile/linux_x86_compile_android.html) 。
After directly downloading the Paddle-Lite library and decompressing it, you can get the `inference_lite_lib.android.armv8/` folder, and the Paddle-Lite library obtained by compiling Paddle-Lite is located
`Paddle-Lite/build.lite.android.armv8.gcc/inference_lite_lib.android.armv8/` folder.
直接下载预测库并解压后，可以得到`inference_lite_lib.android.armv8/`文件夹，通过编译Paddle-Lite得到的预测库位于 The structure of the prediction library is as follows:
`Paddle-Lite/build.lite.android.armv8.gcc/inference_lite_lib.android.armv8/`文件夹下。
预测库的文件目录如下：
``` ```
inference_lite_lib.android.armv8/ inference_lite_lib.android.armv8/
|-- cxx C++ 预测库和头文件 |-- cxx C++ prebuild library
| |-- include C++ 头文件 | |-- include C++
| | |-- paddle_api.h | | |-- paddle_api.h
| | |-- paddle_image_preprocess.h | | |-- paddle_image_preprocess.h
| | |-- paddle_lite_factory_helper.h | | |-- paddle_lite_factory_helper.h
...@@ -69,219 +72,215 @@ inference_lite_lib.android.armv8/ ...@@ -69,219 +72,215 @@ inference_lite_lib.android.armv8/
| | |-- paddle_use_kernels.h | | |-- paddle_use_kernels.h
| | |-- paddle_use_ops.h | | |-- paddle_use_ops.h
| | `-- paddle_use_passes.h | | `-- paddle_use_passes.h
| `-- lib C++预测库 | `-- lib C++ library
| |-- libpaddle_api_light_bundled.a C++静态库 | |-- libpaddle_api_light_bundled.a C++ static library
| `-- libpaddle_light_api_shared.so C++动态库 | `-- libpaddle_light_api_shared.so C++ dynamic library
|-- java Java预测库 |-- java Java library
| |-- jar | |-- jar
| | `-- PaddlePredictor.jar | | `-- PaddlePredictor.jar
| |-- so | |-- so
| | `-- libpaddle_lite_jni.so | | `-- libpaddle_lite_jni.so
| `-- src | `-- src
|-- demo C++和Java示例代码 |-- demo C++ and Java demo
| |-- cxx C++ 预测库demo | |-- cxx C++ demo
| `-- java Java 预测库demo | `-- java Java demo
``` ```
## 2 开始运行 ## 2 Run
### 2.1 模型优化 ### 2.1 Inference Model Optimization
Paddle-Lite 提供了多种策略来自动优化原始的模型，其中包括量化、子图融合、混合调度、Kernel优选等方法，使用Paddle-lite的opt工具可以自动 Paddle Lite provides a variety of strategies to automatically optimize the original training model, including quantization, sub-graph fusion, hybrid scheduling, Kernel optimization and so on. In order to make the optimization process more convenient and easy to use, Paddle Lite provide opt tools to automatically complete the optimization steps and output a lightweight, optimal executable model.
对inference模型进行优化，优化后的模型更轻量，模型运行速度更快。
如果已经准备好了 `.nb` 结尾的模型文件，可以跳过此步骤。 If you have prepared the model file ending in .nb, you can skip this step.
下述表格中也提供了一系列中文移动端模型： The following table also provides a series of models that can be deployed on mobile phones to recognize Chinese. You can directly download the optimized model.
|模型版本|模型简介|模型大小|检测模型|文本方向分类模型|识别模型|Paddle-Lite版本| |Version|Introduction|Model size|Detection model|Text Direction model|Recognition model|Paddle-Lite branch|
|---|---|---|---|---|---|---| |---|---|---|---|---|---|---|
|PP-OCRv2|蒸馏版超轻量中文OCR移动端模型|11M|[下载地址](https://paddleocr.bj.bcebos.com/PP-OCRv2/lite/ch_PP-OCRv2_det_infer_opt.nb)|[下载地址](https://paddleocr.bj.bcebos.com/PP-OCRv2/lite/ch_ppocr_mobile_v2.0_cls_infer_opt.nb)|[下载地址](https://paddleocr.bj.bcebos.com/PP-OCRv2/lite/ch_PP-OCRv2_rec_infer_opt.nb)|v2.10| |PP-OCRv2|extra-lightweight chinese OCR optimized model|11M|[download link](https://paddleocr.bj.bcebos.com/PP-OCRv2/lite/ch_PP-OCRv2_det_infer_opt.nb)|[download link](https://paddleocr.bj.bcebos.com/PP-OCRv2/lite/ch_ppocr_mobile_v2.0_cls_infer_opt.nb)|[download link](https://paddleocr.bj.bcebos.com/PP-OCRv2/lite/ch_PP-OCRv2_rec_infer_opt.nb)|v2.10|
|PP-OCRv2(slim)|蒸馏版超轻量中文OCR移动端模型|4.6M|[下载地址](https://paddleocr.bj.bcebos.com/PP-OCRv2/lite/ch_PP-OCRv2_det_slim_opt.nb)|[下载地址](https://paddleocr.bj.bcebos.com/PP-OCRv2/lite/ch_ppocr_mobile_v2.0_cls_slim_opt.nb)|[下载地址](https://paddleocr.bj.bcebos.com/PP-OCRv2/lite/ch_PP-OCRv2_rec_slim_opt.nb)|v2.10| |PP-OCRv2(slim)|extra-lightweight chinese OCR optimized model|4.6M|[download link](https://paddleocr.bj.bcebos.com/PP-OCRv2/lite/ch_PP-OCRv2_det_slim_opt.nb)|[download link](https://paddleocr.bj.bcebos.com/PP-OCRv2/lite/ch_ppocr_mobile_v2.0_cls_slim_opt.nb)|[download link](https://paddleocr.bj.bcebos.com/PP-OCRv2/lite/ch_PP-OCRv2_rec_slim_opt.nb)|v2.10|
如果直接使用上述表格中的模型进行部署，可略过下述步骤，直接阅读 [2.2节](#2.2与手机联调)。 If you directly use the model in the above table for deployment, you can skip the following steps and directly read [Section 2.2](#2.2-Run-optimized-model-on-Phone).
如果要部署的模型不在上述表格中，则需要按照如下步骤获得优化后的模型。 If the model to be deployed is not in the above table, you need to follow the steps below to obtain the optimized model.
模型优化需要Paddle-Lite的opt可执行文件，可以通过编译Paddle-Lite源码获得，编译步骤如下： The `opt` tool can be obtained by compiling Paddle Lite.
``` ```
# 如果准备环境时已经clone了Paddle-Lite，则不用重新clone Paddle-Lite
git clone https://github.com/PaddlePaddle/Paddle-Lite.git git clone https://github.com/PaddlePaddle/Paddle-Lite.git
cd Paddle-Lite cd Paddle-Lite
git checkout release/v2.10 git checkout release/v2.10
# 启动编译
./lite/tools/build.sh build_optimize_tool ./lite/tools/build.sh build_optimize_tool
``` ```
编译完成后，opt文件位于`build.opt/lite/api/`下，可通过如下方式查看opt的运行选项和使用方式； After the compilation is complete, the opt file is located under build.opt/lite/api/, You can view the operating options and usage of opt in the following ways:
``` ```
cd build.opt/lite/api/ cd build.opt/lite/api/
./opt ./opt
``` ```
|选项|说明| |Options|Description|
|---|---| |---|---|
|--model_dir|待优化的PaddlePaddle模型（非combined形式）的路径| |--model_dir|The path of the PaddlePaddle model to be optimized (non-combined form)|
|--model_file|待优化的PaddlePaddle模型（combined形式）的网络结构文件路径| |--model_file|The network structure file path of the PaddlePaddle model (combined form) to be optimized|
|--param_file|待优化的PaddlePaddle模型（combined形式）的权重文件路径| |--param_file|The weight file path of the PaddlePaddle model (combined form) to be optimized|
|--optimize_out_type|输出模型类型，目前支持两种类型：protobuf和naive_buffer，其中naive_buffer是一种更轻量级的序列化/反序列化实现。若您需要在mobile端执行模型预测，请将此选项设置为naive_buffer。默认为protobuf| |--optimize_out_type|Output model type, currently supports two types: protobuf and naive_buffer, among which naive_buffer is a more lightweight serialization/deserialization implementation. If you need to perform model prediction on the mobile side, please set this option to naive_buffer. The default is protobuf|
|--optimize_out|优化模型的输出路径| |--optimize_out|The output path of the optimized model|
|--valid_targets|指定模型可执行的backend，默认为arm。目前可支持x86、arm、opencl、npu、xpu，可以同时指定多个backend(以空格分隔)，Model Optimize Tool将会自动选择最佳方式。如果需要支持华为NPU（Kirin 810/990 Soc搭载的达芬奇架构NPU），应当设置为npu, arm| |--valid_targets|The executable backend of the model, the default is arm. Currently it supports x86, arm, opencl, npu, xpu, multiple backends can be specified at the same time (separated by spaces), and Model Optimize Tool will automatically select the best method. If you need to support Huawei NPU (DaVinci architecture NPU equipped with Kirin 810/990 Soc), it should be set to npu, arm|
|--record_tailoring_info|当使用 根据模型裁剪库文件 功能时，则设置该选项为true，以记录优化后模型含有的kernel和OP信息，默认为false| |--record_tailoring_info|When using the function of cutting library files according to the model, set this option to true to record the kernel and OP information contained in the optimized model. The default is false|
`--model_dir`适用于待优化的模型是非combined方式，PaddleOCR的inference模型是combined方式，即模型结构和模型参数使用单独一个文件存储。 `--model_dir` is suitable for the non-combined mode of the model to be optimized, and the inference model of PaddleOCR is the combined mode, that is, the model structure and model parameters are stored in a single file.
下面以PaddleOCR的超轻量中文模型为例，介绍使用编译好的opt文件完成inference模型到Paddle-Lite优化模型的转换。 The following takes the ultra-lightweight Chinese model of PaddleOCR as an example to introduce the use of the compiled opt file to complete the conversion of the inference model to the Paddle-Lite optimized model
``` ```
# 【推荐】 下载 PP-OCRv2版本的中英文 inference模型 # 【[Recommendation] Download the Chinese and English inference model of PP-OCRv2
wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_slim_quant_infer.tar && tar xf ch_PP-OCRv2_det_slim_quant_infer.tar wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_slim_quant_infer.tar && tar xf ch_PP-OCRv2_det_slim_quant_infer.tar
wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_slim_quant_infer.tar && tar xf ch_PP-OCRv2_rec_slim_quant_infer.tar wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_slim_quant_infer.tar && tar xf ch_PP-OCRv2_rec_slim_quant_infer.tar
wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_cls_slim_infer.tar && tar xf ch_ppocr_mobile_v2.0_cls_slim_infer.tar wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_cls_slim_infer.tar && tar xf ch_ppocr_mobile_v2.0_cls_slim_infer.tar
# 转换检测模型 # Convert detection model
./opt --model_file=./ch_PP-OCRv2_det_slim_quant_infer/inference.pdmodel --param_file=./ch_PP-OCRv2_det_slim_quant_infer/inference.pdiparams --optimize_out=./ch_PP-OCRv2_det_slim_opt --valid_targets=arm --optimize_out_type=naive_buffer ./opt --model_file=./ch_PP-OCRv2_det_slim_quant_infer/inference.pdmodel --param_file=./ch_PP-OCRv2_det_slim_quant_infer/inference.pdiparams --optimize_out=./ch_PP-OCRv2_det_slim_opt --valid_targets=arm --optimize_out_type=naive_buffer
# 转换识别模型 # Convert recognition model
./opt --model_file=./ch_PP-OCRv2_rec_slim_quant_infer/inference.pdmodel --param_file=./ch_PP-OCRv2_rec_slim_quant_infer/inference.pdiparams --optimize_out=./ch_PP-OCRv2_rec_slim_opt --valid_targets=arm --optimize_out_type=naive_buffer ./opt --model_file=./ch_PP-OCRv2_rec_slim_quant_infer/inference.pdmodel --param_file=./ch_PP-OCRv2_rec_slim_quant_infer/inference.pdiparams --optimize_out=./ch_PP-OCRv2_rec_slim_opt --valid_targets=arm --optimize_out_type=naive_buffer
# 转换方向分类器模型 # Convert angle classifier model
./opt --model_file=./ch_ppocr_mobile_v2.0_cls_slim_infer/inference.pdmodel --param_file=./ch_ppocr_mobile_v2.0_cls_slim_infer/inference.pdiparams --optimize_out=./ch_ppocr_mobile_v2.0_cls_slim_opt --valid_targets=arm --optimize_out_type=naive_buffer ./opt --model_file=./ch_ppocr_mobile_v2.0_cls_slim_infer/inference.pdmodel --param_file=./ch_ppocr_mobile_v2.0_cls_slim_infer/inference.pdiparams --optimize_out=./ch_ppocr_mobile_v2.0_cls_slim_opt --valid_targets=arm --optimize_out_type=naive_buffer
``` ```
转换成功后，inference模型目录下会多出`.nb`结尾的文件，即是转换成功的模型文件。 After the conversion is successful, there will be more files ending with `.nb` in the inference model directory, which is the successfully converted model file.
注意：使用paddle-lite部署时，需要使用opt工具优化后的模型。 opt 工具的输入模型是paddle保存的inference模型
<a name="2.2与手机联调"></a> <a name="2.2-Run-optimized-model-on-Phone"></a>
### 2.2 与手机联调 ### 2.2 Run optimized model on Phone
首先需要进行一些准备工作。 Some preparatory work is required first.
1. 准备一台arm8的安卓手机，如果编译的预测库和opt文件是armv7，则需要arm7的手机，并修改Makefile中`ARM_ABI = arm7`。 1. Prepare an Android phone with arm8. If the compiled prediction library and opt file are armv7, you need an arm7 phone and modify ARM_ABI = arm7 in the Makefile.
2. 打开手机的USB调试选项，选择文件传输模式，连接电脑。 2. Make sure the phone is connected to the computer, open the USB debugging option of the phone, and select the file transfer mode.
3. 电脑上安装adb工具，用于调试。 adb安装方式如下： 3. Install the adb tool on the computer.
3.1. MAC电脑安装ADB: 3.1. Install ADB for MAC:
``` ```
brew cask install android-platform-tools brew cask install android-platform-tools
``` ```
3.2. Linux安装ADB 3.2. Install ADB for Linux
``` ```
sudo apt update sudo apt update
sudo apt install -y wget adb sudo apt install -y wget adb
``` ```
3.3. Window安装ADB 3.3. Install ADB for windows
win上安装需要去谷歌的安卓平台下载adb软件包进行安装：[链接](https://developer.android.com/studio) To install on win, you need to go to Google's Android platform to download the adb package for installation：[link](https://developer.android.com/studio)
打开终端，手机连接电脑，在终端中输入 Verify whether adb is installed successfully
``` ```
adb devices adb devices
``` ```
如果有device输出，则表示安装成功。 If there is device output, it means the installation is successful。
``` ```
List of devices attached List of devices attached
744be294 device 744be294 device
``` ```
4. 准备优化后的模型、预测库文件、测试图像和使用的字典文件。 4. Prepare optimized models, prediction library files, test images and dictionary files used.
``` ```
git clone https://github.com/PaddlePaddle/PaddleOCR.git git clone https://github.com/PaddlePaddle/PaddleOCR.git
cd PaddleOCR/deploy/lite/ cd PaddleOCR/deploy/lite/
# 运行prepare.sh，准备预测库文件、测试图像和使用的字典文件，并放置在预测库中的demo/cxx/ocr文件夹下 # run prepare.sh
sh prepare.sh /{lite prediction library path}/inference_lite_lib.android.armv8 sh prepare.sh /{lite prediction library path}/inference_lite_lib.android.armv8
# 进入OCR demo的工作目录 #
cd /{lite prediction library path}/inference_lite_lib.android.armv8/ cd /{lite prediction library path}/inference_lite_lib.android.armv8/
cd demo/cxx/ocr/ cd demo/cxx/ocr/
# 将C++预测动态库so文件复制到debug文件夹中 # copy paddle-lite C++ .so file to debug/ directory
cp ../../../cxx/lib/libpaddle_light_api_shared.so ./debug/
cd inference_lite_lib.android.armv8/demo/cxx/ocr/
cp ../../../cxx/lib/libpaddle_light_api_shared.so ./debug/ cp ../../../cxx/lib/libpaddle_light_api_shared.so ./debug/
``` ```
准备测试图像，以`PaddleOCR/doc/imgs/11.jpg`为例，将测试的图像复制到`demo/cxx/ocr/debug/`文件夹下。 Prepare the test image, taking PaddleOCR/doc/imgs/11.jpg as an example, copy the image file to the demo/cxx/ocr/debug/ folder. Prepare the model files optimized by the lite opt tool, ch_det_mv3_db_opt.nb, ch_rec_mv3_crnn_opt.nb, and place them under the demo/cxx/ocr/debug/ folder.
准备lite opt工具优化后的模型文件，比如使用`ch_PP-OCRv2_det_slim_opt.ch_PP-OCRv2_rec_slim_rec.nb, ch_ppocr_mobile_v2.0_cls_slim_opt.nb`，模型文件放置在`demo/cxx/ocr/debug/`文件夹下。
执行完成后，ocr文件夹下将有如下文件格式： The structure of the OCR demo is as follows after the above command is executed:
``` ```
demo/cxx/ocr/ demo/cxx/ocr/
|-- debug/ |-- debug/
| |--ch_PP-OCRv2_det_slim_opt.nb 优化后的检测模型文件 | |--ch_PP-OCRv2_det_slim_opt.nb Detection model
| |--ch_PP-OCRv2_rec_slim_opt.nb 优化后的识别模型文件 | |--ch_PP-OCRv2_rec_slim_opt.nb Recognition model
| |--ch_ppocr_mobile_v2.0_cls_slim_opt.nb 优化后的文字方向分类器模型文件 | |--ch_ppocr_mobile_v2.0_cls_slim_opt.nb Text direction classification model
| |--11.jpg 待测试图像 | |--11.jpg Image for OCR
| |--ppocr_keys_v1.txt 中文字典文件 | |--ppocr_keys_v1.txt Dictionary file
| |--libpaddle_light_api_shared.so C++预测库文件 | |--libpaddle_light_api_shared.so C++ .so file
| |--config.txt 超参数配置 | |--config.txt Config file
|-- config.txt 超参数配置 |-- config.txt Config file
|-- cls_process.cc 方向分类器的预处理和后处理文件 |-- cls_process.cc Pre-processing and post-processing files for the angle classifier
|-- cls_process.h |-- cls_process.h
|-- crnn_process.cc 识别模型CRNN的预处理和后处理文件 |-- crnn_process.cc Pre-processing and post-processing files for the CRNN model
|-- crnn_process.h |-- crnn_process.h
|-- db_post_process.cc 检测模型DB的后处理文件 |-- db_post_process.cc Pre-processing and post-processing files for the DB model
|-- db_post_process.h |-- db_post_process.h
|-- Makefile 编译文件 |-- Makefile
|-- ocr_db_crnn.cc C++预测源文件 |-- ocr_db_crnn.cc C++ main code
``` ```
#### 注意： #### 注意：
1. ppocr_keys_v1.txt是中文字典文件，如果使用的 nb 模型是英文数字或其他语言的模型，需要更换为对应语言的字典。 1. `ppocr_keys_v1.txt` is a Chinese dictionary file. If the nb model is used for English recognition or other language recognition, dictionary file should be replaced with a dictionary of the corresponding language. PaddleOCR provides a variety of dictionaries under ppocr/utils/, including:
PaddleOCR 在ppocr/utils/下存放了多种字典，包括：
``` ```
dict/french_dict.txt # 法语字典 dict/french_dict.txt # french
dict/german_dict.txt # 德语字典 dict/german_dict.txt # german
ic15_dict.txt # 英文字典 ic15_dict.txt # english
dict/japan_dict.txt # 日语字典 dict/japan_dict.txt # japan
dict/korean_dict.txt # 韩语字典 dict/korean_dict.txt # korean
ppocr_keys_v1.txt # 中文字典 ppocr_keys_v1.txt # chinese
...
``` ```
2. `config.txt` 包含了检测器、分类器的超参数，如下： 2. `config.txt` of the detector and classifier, as shown below:
``` ```
max_side_len 960 # 输入图像长宽大于960时，等比例缩放图像，使得图像最长边为960 max_side_len 960 # Limit the maximum image height and width to 960
det_db_thresh 0.3 # 用于过滤DB预测的二值化图像，设置为0.-0.3对结果影响不明显 det_db_thresh 0.3 # Used to filter the binarized image of DB prediction, setting 0.-0.3 has no obvious effect on the result
det_db_box_thresh 0.5 # DB后处理过滤box的阈值，如果检测存在漏框情况，可酌情减小 det_db_box_thresh 0.5 # DDB post-processing filter box threshold, if there is a missing box detected, it can be reduced as appropriate
det_db_unclip_ratio 1.6 # 表示文本框的紧致程度，越小则文本框更靠近文本 det_db_unclip_ratio 1.6 # Indicates the compactness of the text box, the smaller the value, the closer the text box to the text
use_direction_classify 0 # 是否使用方向分类器，0表示不使用，1表示使用 use_direction_classify 0 # Whether to use the direction classifier, 0 means not to use, 1 means to use
``` ```
5. 启动调试 5. Run Model on phone
上述步骤完成后就可以使用adb将文件push到手机上运行，步骤如下： After the above steps are completed, you can use adb to push the file to the phone to run, the steps are as follows:
``` ```
# 执行编译，得到可执行文件ocr_db_crnn, 第一次执行此命令会下载opencv等依赖库，下载完成后，需要再执行一次 # Execute the compilation and get the executable file ocr_db_crnn
# The first execution of this command will download dependent libraries such as opencv. After the download is complete, you need to execute it again
make -j make -j
# Move the compiled executable file to the debug folder
# 将编译的可执行文件移动到debug文件夹中
mv ocr_db_crnn ./debug/ mv ocr_db_crnn ./debug/
# 将debug文件夹push到手机上 # Push the debug folder to the phone
adb push debug /data/local/tmp/ adb push debug /data/local/tmp/
adb shell adb shell
cd /data/local/tmp/debug cd /data/local/tmp/debug
export LD_LIBRARY_PATH=${PWD}:$LD_LIBRARY_PATH export LD_LIBRARY_PATH=${PWD}:$LD_LIBRARY_PATH
# 开始使用，ocr_db_crnn可执行文件的使用方式为: # The use of ocr_db_crnn is:
# ./ocr_db_crnn 检测模型文件 方向分类器模型文件 识别模型文件 测试图像路径 字典文件路径 # ./ocr_db_crnn Detection model file Orientation classifier model file Recognition model file Test image path Dictionary file path
./ocr_db_crnn ch_PP-OCRv2_det_slim_opt.nb ch_PP-OCRv2_rec_slim_opt.nb ch_ppocr_mobile_v2.0_cls_slim_opt.nb ./11.jpg ppocr_keys_v1.txt ./ocr_db_crnn ch_PP-OCRv2_det_slim_opt.nb ch_PP-OCRv2_rec_slim_opt.nb ch_ppocr_mobile_v2.0_cls_opt.nb ./11.jpg ppocr_keys_v1.txt
``` ```
如果对代码做了修改，则需要重新编译并push到手机上。 If you modify the code, you need to recompile and push to the phone.
运行效果如下： The outputs are as follows:
<div align="center"> <div align="center">
<img src="imgs/lite_demo.png" width="600"> <img src="imgs/lite_demo.png" width="600">
</div> </div>
## FAQ ## FAQ
Q1：如果想更换模型怎么办，需要重新按照流程走一遍吗？
A1：如果已经走通了上述步骤，更换模型只需要替换 .nb 模型文件即可，同时要注意更新字典 Q1: What if I want to change the model, do I need to run it again according to the process?
A1: If you have performed the above steps, you only need to replace the .nb model file to complete the model replacement.
Q2：换一个图测试怎么做？ Q2: How to test with another picture?
A2：替换debug下的.jpg测试图像为你想要测试的图像，adb push 到手机上即可 A2: Replace the .jpg test image under ./debug with the image you want to test, and run adb push to push new image to the phone.
Q3：如何封装到手机APP中？ Q3: How to package it into the mobile APP?
A3：此demo旨在提供能在手机上运行OCR的核心算法部分，PaddleOCR/deploy/android_demo是将这个demo封装到手机app的示例，供参考 A3: This demo aims to provide the core algorithm part that can run OCR on mobile phones. Further, PaddleOCR/deploy/android_demo is an example of encapsulating this demo into a mobile app for reference.
deploy/lite/readme_ch.md 0 → 100644
浏览文件 @ 486aa102
- [端侧部署](#端侧部署)
- [1. 准备环境](#1-准备环境)
- [运行准备](#运行准备)
- [1.1 准备交叉编译环境](#11-准备交叉编译环境)
- [1.2 准备预测库](#12-准备预测库)
- [2 开始运行](#2-开始运行)
- [2.1 模型优化](#21-模型优化)
- [2.2 与手机联调](#22-与手机联调)
- [注意：](#注意)
- [FAQ](#faq)
# 端侧部署
本教程将介绍基于[Paddle Lite](https://github.com/PaddlePaddle/Paddle-Lite) 在移动端部署PaddleOCR超轻量中文检测、识别模型的详细步骤。
Paddle Lite是飞桨轻量化推理引擎，为手机、IOT端提供高效推理能力，并广泛整合跨平台硬件，为端侧部署及应用落地问题提供轻量化的部署方案。
## 1. 准备环境
### 运行准备
- 电脑（编译Paddle Lite）
- 安卓手机（armv7或armv8）
### 1.1 准备交叉编译环境
交叉编译环境用于编译 Paddle Lite 和 PaddleOCR 的C++ demo。
支持多种开发环境，不同开发环境的编译流程请参考对应文档。
1. [Docker](https://paddle-lite.readthedocs.io/zh/latest/source_compile/compile_env.html#docker)
2. [Linux](https://paddle-lite.readthedocs.io/zh/latest/source_compile/compile_env.html#linux)
3. [MAC OS](https://paddle-lite.readthedocs.io/zh/latest/source_compile/compile_env.html#mac-os)
### 1.2 准备预测库
预测库有两种获取方式：
- 1. 直接下载，预测库下载链接如下：
| 平台 | 预测库下载链接 |
|---|---|
|Android|[arm7](https://github.com/PaddlePaddle/Paddle-Lite/releases/download/v2.10/inference_lite_lib.android.armv7.gcc.c++_shared.with_extra.with_cv.tar.gz) / [arm8](https://github.com/PaddlePaddle/Paddle-Lite/releases/download/v2.10/inference_lite_lib.android.armv8.gcc.c++_shared.with_extra.with_cv.tar.gz)|
|IOS|[arm7](https://github.com/PaddlePaddle/Paddle-Lite/releases/download/v2.10/inference_lite_lib.ios.armv7.with_cv.with_extra.with_log.tiny_publish.tar.gz) / [arm8](https://github.com/PaddlePaddle/Paddle-Lite/releases/download/v2.10/inference_lite_lib.ios.armv8.with_cv.with_extra.with_log.tiny_publish.tar.gz)|
注：1. 上述预测库为PaddleLite 2.10分支编译得到，有关PaddleLite 2.10 详细信息可参考 [链接](https://github.com/PaddlePaddle/Paddle-Lite/releases/tag/v2.10) 。
- 2. [推荐]编译Paddle-Lite得到预测库，Paddle-Lite的编译方式如下：
```
git clone https://github.com/PaddlePaddle/Paddle-Lite.git
cd Paddle-Lite
# 切换到Paddle-Lite release/v2.10 稳定分支
git checkout release/v2.10
./lite/tools/build_android.sh --arch=armv8 --with_cv=ON --with_extra=ON
```
注意：编译Paddle-Lite获得预测库时，需要打开`--with_cv=ON --with_extra=ON`两个选项，`--arch`表示`arm`版本，这里指定为armv8，
更多编译命令
介绍请参考 [链接](https://paddle-lite.readthedocs.io/zh/release-v2.10_a/source_compile/linux_x86_compile_android.html) 。
直接下载预测库并解压后，可以得到`inference_lite_lib.android.armv8/`文件夹，通过编译Paddle-Lite得到的预测库位于
`Paddle-Lite/build.lite.android.armv8.gcc/inference_lite_lib.android.armv8/`文件夹下。
预测库的文件目录如下：
```
inference_lite_lib.android.armv8/
|-- cxx C++ 预测库和头文件
| |-- include C++ 头文件
| | |-- paddle_api.h
| | |-- paddle_image_preprocess.h
| | |-- paddle_lite_factory_helper.h
| | |-- paddle_place.h
| | |-- paddle_use_kernels.h
| | |-- paddle_use_ops.h
| | `-- paddle_use_passes.h
| `-- lib C++预测库
| |-- libpaddle_api_light_bundled.a C++静态库
| `-- libpaddle_light_api_shared.so C++动态库
|-- java Java预测库
| |-- jar
| | `-- PaddlePredictor.jar
| |-- so
| | `-- libpaddle_lite_jni.so
| `-- src
|-- demo C++和Java示例代码
| |-- cxx C++ 预测库demo
| `-- java Java 预测库demo
```
## 2 开始运行
### 2.1 模型优化
Paddle-Lite 提供了多种策略来自动优化原始的模型，其中包括量化、子图融合、混合调度、Kernel优选等方法，使用Paddle-lite的opt工具可以自动
对inference模型进行优化，优化后的模型更轻量，模型运行速度更快。
如果已经准备好了 `.nb` 结尾的模型文件，可以跳过此步骤。
下述表格中也提供了一系列中文移动端模型：
|模型版本|模型简介|模型大小|检测模型|文本方向分类模型|识别模型|Paddle-Lite版本|
|---|---|---|---|---|---|---|
|PP-OCRv2|蒸馏版超轻量中文OCR移动端模型|11M|[下载地址](https://paddleocr.bj.bcebos.com/PP-OCRv2/lite/ch_PP-OCRv2_det_infer_opt.nb)|[下载地址](https://paddleocr.bj.bcebos.com/PP-OCRv2/lite/ch_ppocr_mobile_v2.0_cls_infer_opt.nb)|[下载地址](https://paddleocr.bj.bcebos.com/PP-OCRv2/lite/ch_PP-OCRv2_rec_infer_opt.nb)|v2.10|
|PP-OCRv2(slim)|蒸馏版超轻量中文OCR移动端模型|4.6M|[下载地址](https://paddleocr.bj.bcebos.com/PP-OCRv2/lite/ch_PP-OCRv2_det_slim_opt.nb)|[下载地址](https://paddleocr.bj.bcebos.com/PP-OCRv2/lite/ch_ppocr_mobile_v2.0_cls_slim_opt.nb)|[下载地址](https://paddleocr.bj.bcebos.com/PP-OCRv2/lite/ch_PP-OCRv2_rec_slim_opt.nb)|v2.10|
如果直接使用上述表格中的模型进行部署，可略过下述步骤，直接阅读 [2.2节](#2.2与手机联调)。
如果要部署的模型不在上述表格中，则需要按照如下步骤获得优化后的模型。
模型优化需要Paddle-Lite的opt可执行文件，可以通过编译Paddle-Lite源码获得，编译步骤如下：
```
# 如果准备环境时已经clone了Paddle-Lite，则不用重新clone Paddle-Lite
git clone https://github.com/PaddlePaddle/Paddle-Lite.git
cd Paddle-Lite
git checkout release/v2.10
# 启动编译
./lite/tools/build.sh build_optimize_tool
```
编译完成后，opt文件位于`build.opt/lite/api/`下，可通过如下方式查看opt的运行选项和使用方式；
```
cd build.opt/lite/api/
./opt
```
|选项|说明|
|---|---|
|--model_dir|待优化的PaddlePaddle模型（非combined形式）的路径|
|--model_file|待优化的PaddlePaddle模型（combined形式）的网络结构文件路径|
|--param_file|待优化的PaddlePaddle模型（combined形式）的权重文件路径|
|--optimize_out_type|输出模型类型，目前支持两种类型：protobuf和naive_buffer，其中naive_buffer是一种更轻量级的序列化/反序列化实现。若您需要在mobile端执行模型预测，请将此选项设置为naive_buffer。默认为protobuf|
|--optimize_out|优化模型的输出路径|
|--valid_targets|指定模型可执行的backend，默认为arm。目前可支持x86、arm、opencl、npu、xpu，可以同时指定多个backend(以空格分隔)，Model Optimize Tool将会自动选择最佳方式。如果需要支持华为NPU（Kirin 810/990 Soc搭载的达芬奇架构NPU），应当设置为npu, arm|
|--record_tailoring_info|当使用 根据模型裁剪库文件 功能时，则设置该选项为true，以记录优化后模型含有的kernel和OP信息，默认为false|
`--model_dir`适用于待优化的模型是非combined方式，PaddleOCR的inference模型是combined方式，即模型结构和模型参数使用单独一个文件存储。
下面以PaddleOCR的超轻量中文模型为例，介绍使用编译好的opt文件完成inference模型到Paddle-Lite优化模型的转换。
```
# 【推荐】 下载 PP-OCRv2版本的中英文 inference模型
wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_slim_quant_infer.tar && tar xf ch_PP-OCRv2_det_slim_quant_infer.tar
wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_slim_quant_infer.tar && tar xf ch_PP-OCRv2_rec_slim_quant_infer.tar
wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_cls_slim_infer.tar && tar xf ch_ppocr_mobile_v2.0_cls_slim_infer.tar
# 转换检测模型
./opt --model_file=./ch_PP-OCRv2_det_slim_quant_infer/inference.pdmodel --param_file=./ch_PP-OCRv2_det_slim_quant_infer/inference.pdiparams --optimize_out=./ch_PP-OCRv2_det_slim_opt --valid_targets=arm --optimize_out_type=naive_buffer
# 转换识别模型
./opt --model_file=./ch_PP-OCRv2_rec_slim_quant_infer/inference.pdmodel --param_file=./ch_PP-OCRv2_rec_slim_quant_infer/inference.pdiparams --optimize_out=./ch_PP-OCRv2_rec_slim_opt --valid_targets=arm --optimize_out_type=naive_buffer
# 转换方向分类器模型
./opt --model_file=./ch_ppocr_mobile_v2.0_cls_slim_infer/inference.pdmodel --param_file=./ch_ppocr_mobile_v2.0_cls_slim_infer/inference.pdiparams --optimize_out=./ch_ppocr_mobile_v2.0_cls_slim_opt --valid_targets=arm --optimize_out_type=naive_buffer
```
转换成功后，inference模型目录下会多出`.nb`结尾的文件，即是转换成功的模型文件。
注意：使用paddle-lite部署时，需要使用opt工具优化后的模型。 opt 工具的输入模型是paddle保存的inference模型
<a name="2.2与手机联调"></a>
### 2.2 与手机联调
首先需要进行一些准备工作。
1. 准备一台arm8的安卓手机，如果编译的预测库和opt文件是armv7，则需要arm7的手机，并修改Makefile中`ARM_ABI = arm7`。
2. 打开手机的USB调试选项，选择文件传输模式，连接电脑。
3. 电脑上安装adb工具，用于调试。 adb安装方式如下：
3.1. MAC电脑安装ADB:
```
brew cask install android-platform-tools
```
3.2. Linux安装ADB
```
sudo apt update
sudo apt install -y wget adb
```
3.3. Window安装ADB
win上安装需要去谷歌的安卓平台下载adb软件包进行安装：[链接](https://developer.android.com/studio)
打开终端，手机连接电脑，在终端中输入
```
adb devices
```
如果有device输出，则表示安装成功。
```
List of devices attached
744be294 device
```
4. 准备优化后的模型、预测库文件、测试图像和使用的字典文件。
```
git clone https://github.com/PaddlePaddle/PaddleOCR.git
cd PaddleOCR/deploy/lite/
# 运行prepare.sh，准备预测库文件、测试图像和使用的字典文件，并放置在预测库中的demo/cxx/ocr文件夹下
sh prepare.sh /{lite prediction library path}/inference_lite_lib.android.armv8
# 进入OCR demo的工作目录
cd /{lite prediction library path}/inference_lite_lib.android.armv8/
cd demo/cxx/ocr/
# 将C++预测动态库so文件复制到debug文件夹中
cp ../../../cxx/lib/libpaddle_light_api_shared.so ./debug/
```
准备测试图像，以`PaddleOCR/doc/imgs/11.jpg`为例，将测试的图像复制到`demo/cxx/ocr/debug/`文件夹下。
准备lite opt工具优化后的模型文件，比如使用`ch_PP-OCRv2_det_slim_opt.ch_PP-OCRv2_rec_slim_rec.nb, ch_ppocr_mobile_v2.0_cls_slim_opt.nb`，模型文件放置在`demo/cxx/ocr/debug/`文件夹下。
执行完成后，ocr文件夹下将有如下文件格式：
```
demo/cxx/ocr/
|-- debug/
| |--ch_PP-OCRv2_det_slim_opt.nb 优化后的检测模型文件
| |--ch_PP-OCRv2_rec_slim_opt.nb 优化后的识别模型文件
| |--ch_ppocr_mobile_v2.0_cls_slim_opt.nb 优化后的文字方向分类器模型文件
| |--11.jpg 待测试图像
| |--ppocr_keys_v1.txt 中文字典文件
| |--libpaddle_light_api_shared.so C++预测库文件
| |--config.txt 超参数配置
|-- config.txt 超参数配置
|-- cls_process.cc 方向分类器的预处理和后处理文件
|-- cls_process.h
|-- crnn_process.cc 识别模型CRNN的预处理和后处理文件
|-- crnn_process.h
|-- db_post_process.cc 检测模型DB的后处理文件
|-- db_post_process.h
|-- Makefile 编译文件
|-- ocr_db_crnn.cc C++预测源文件
```
#### 注意：
1. ppocr_keys_v1.txt是中文字典文件，如果使用的 nb 模型是英文数字或其他语言的模型，需要更换为对应语言的字典。
PaddleOCR 在ppocr/utils/下存放了多种字典，包括：
```
dict/french_dict.txt # 法语字典
dict/german_dict.txt # 德语字典
ic15_dict.txt # 英文字典
dict/japan_dict.txt # 日语字典
dict/korean_dict.txt # 韩语字典
ppocr_keys_v1.txt # 中文字典
...
```
2. `config.txt` 包含了检测器、分类器的超参数，如下：
```
max_side_len 960 # 输入图像长宽大于960时，等比例缩放图像，使得图像最长边为960
det_db_thresh 0.3 # 用于过滤DB预测的二值化图像，设置为0.-0.3对结果影响不明显
det_db_box_thresh 0.5 # DB后处理过滤box的阈值，如果检测存在漏框情况，可酌情减小
det_db_unclip_ratio 1.6 # 表示文本框的紧致程度，越小则文本框更靠近文本
use_direction_classify 0 # 是否使用方向分类器，0表示不使用，1表示使用
```
5. 启动调试
上述步骤完成后就可以使用adb将文件push到手机上运行，步骤如下：
```
# 执行编译，得到可执行文件ocr_db_crnn, 第一次执行此命令会下载opencv等依赖库，下载完成后，需要再执行一次
make -j
# 将编译的可执行文件移动到debug文件夹中
mv ocr_db_crnn ./debug/
# 将debug文件夹push到手机上
adb push debug /data/local/tmp/
adb shell
cd /data/local/tmp/debug
export LD_LIBRARY_PATH=${PWD}:$LD_LIBRARY_PATH
# 开始使用，ocr_db_crnn可执行文件的使用方式为:
# ./ocr_db_crnn 检测模型文件 方向分类器模型文件 识别模型文件 测试图像路径 字典文件路径
./ocr_db_crnn ch_PP-OCRv2_det_slim_opt.nb ch_PP-OCRv2_rec_slim_opt.nb ch_ppocr_mobile_v2.0_cls_slim_opt.nb ./11.jpg ppocr_keys_v1.txt
```
如果对代码做了修改，则需要重新编译并push到手机上。
运行效果如下：
<div align="center">
<img src="imgs/lite_demo.png" width="600">
</div>
## FAQ
Q1：如果想更换模型怎么办，需要重新按照流程走一遍吗？
A1：如果已经走通了上述步骤，更换模型只需要替换 .nb 模型文件即可，同时要注意更新字典
Q2：换一个图测试怎么做？
A2：替换debug下的.jpg测试图像为你想要测试的图像，adb push 到手机上即可
Q3：如何封装到手机APP中？
A3：此demo旨在提供能在手机上运行OCR的核心算法部分，PaddleOCR/deploy/android_demo是将这个demo封装到手机app的示例，供参考
deploy/lite/readme_en.md 已删除 100644 → 0
浏览文件 @ 52b7dee0
- [Tutorial of PaddleOCR Mobile deployment](#tutorial-of-paddleocr-mobile-deployment)
- [1. Preparation](#1-preparation)
- [Preparation environment](#preparation-environment)
- [1.1 Prepare the cross-compilation environment](#11-prepare-the-cross-compilation-environment)
- [1.2 Prepare Paddle-Lite library](#12-prepare-paddle-lite-library)
- [2 Run](#2-run)
- [2.1 Inference Model Optimization](#21-inference-model-optimization)
- [2.2 Run optimized model on Phone](#22-run-optimized-model-on-phone)
- [注意：](#注意)
- [FAQ](#faq)
# Tutorial of PaddleOCR Mobile deployment
This tutorial will introduce how to use [Paddle Lite](https://github.com/PaddlePaddle/Paddle-Lite) to deploy PaddleOCR ultra-lightweight Chinese and English detection models on mobile phones.
paddle-lite is a lightweight inference engine for PaddlePaddle. It provides efficient inference capabilities for mobile phones and IoT, and extensively integrates cross-platform hardware to provide lightweight deployment solutions for end-side deployment issues.
## 1. Preparation
### Preparation environment
- Computer (for Compiling Paddle Lite)
- Mobile phone (arm7 or arm8)
### 1.1 Prepare the cross-compilation environment
The cross-compilation environment is used to compile C++ demos of Paddle Lite and PaddleOCR.
Supports multiple development environments.
For the compilation process of different development environments, please refer to the corresponding documents.
1. [Docker](https://paddle-lite.readthedocs.io/zh/latest/source_compile/compile_env.html#docker)
2. [Linux](https://paddle-lite.readthedocs.io/zh/latest/source_compile/compile_env.html#linux)
3. [MAC OS](https://paddle-lite.readthedocs.io/zh/latest/source_compile/compile_env.html#mac-os)
### 1.2 Prepare Paddle-Lite library
There are two ways to obtain the Paddle-Lite library：
- 1. Download directly, the download link of the Paddle-Lite library is as follows：
| Platform | Paddle-Lite library download link |
|---|---|
|Android|[arm7](https://github.com/PaddlePaddle/Paddle-Lite/releases/download/v2.10/inference_lite_lib.android.armv7.gcc.c++_shared.with_extra.with_cv.tar.gz) / [arm8](https://github.com/PaddlePaddle/Paddle-Lite/releases/download/v2.10/inference_lite_lib.android.armv8.gcc.c++_shared.with_extra.with_cv.tar.gz)|
|IOS|[arm7](https://github.com/PaddlePaddle/Paddle-Lite/releases/download/v2.10/inference_lite_lib.ios.armv7.with_cv.with_extra.with_log.tiny_publish.tar.gz) / [arm8](https://github.com/PaddlePaddle/Paddle-Lite/releases/download/v2.10/inference_lite_lib.ios.armv8.with_cv.with_extra.with_log.tiny_publish.tar.gz)|
Note: 1. The above Paddle-Lite library is compiled from the Paddle-Lite 2.10 branch. For more information about Paddle-Lite 2.10, please refer to [link](https://github.com/PaddlePaddle/Paddle-Lite/releases/tag/v2.10).
- 2. [Recommended] Compile Paddle-Lite to get the prediction library. The compilation method of Paddle-Lite is as follows：
```
git clone https://github.com/PaddlePaddle/Paddle-Lite.git
cd Paddle-Lite
# Switch to Paddle-Lite release/v2.10 stable branch
git checkout release/v2.10
./lite/tools/build_android.sh --arch=armv8 --with_cv=ON --with_extra=ON
```
Note: When compiling Paddle-Lite to obtain the Paddle-Lite library, you need to turn on the two options `--with_cv=ON --with_extra=ON`, `--arch` means the `arm` version, here is designated as armv8,
More compilation commands refer to the introduction [link](https://paddle-lite.readthedocs.io/zh/release-v2.10_a/source_compile/linux_x86_compile_android.html) 。
After directly downloading the Paddle-Lite library and decompressing it, you can get the `inference_lite_lib.android.armv8/` folder, and the Paddle-Lite library obtained by compiling Paddle-Lite is located
`Paddle-Lite/build.lite.android.armv8.gcc/inference_lite_lib.android.armv8/` folder.
The structure of the prediction library is as follows:
```
inference_lite_lib.android.armv8/
|-- cxx C++ prebuild library
| |-- include C++
| | |-- paddle_api.h
| | |-- paddle_image_preprocess.h
| | |-- paddle_lite_factory_helper.h
| | |-- paddle_place.h
| | |-- paddle_use_kernels.h
| | |-- paddle_use_ops.h
| | `-- paddle_use_passes.h
| `-- lib C++ library
| |-- libpaddle_api_light_bundled.a C++ static library
| `-- libpaddle_light_api_shared.so C++ dynamic library
|-- java Java library
| |-- jar
| | `-- PaddlePredictor.jar
| |-- so
| | `-- libpaddle_lite_jni.so
| `-- src
|-- demo C++ and Java demo
| |-- cxx C++ demo
| `-- java Java demo
```
## 2 Run
### 2.1 Inference Model Optimization
Paddle Lite provides a variety of strategies to automatically optimize the original training model, including quantization, sub-graph fusion, hybrid scheduling, Kernel optimization and so on. In order to make the optimization process more convenient and easy to use, Paddle Lite provide opt tools to automatically complete the optimization steps and output a lightweight, optimal executable model.
If you have prepared the model file ending in .nb, you can skip this step.
The following table also provides a series of models that can be deployed on mobile phones to recognize Chinese. You can directly download the optimized model.
|Version|Introduction|Model size|Detection model|Text Direction model|Recognition model|Paddle-Lite branch|
|---|---|---|---|---|---|---|
|PP-OCRv2|extra-lightweight chinese OCR optimized model|11M|[download link](https://paddleocr.bj.bcebos.com/PP-OCRv2/lite/ch_PP-OCRv2_det_infer_opt.nb)|[download link](https://paddleocr.bj.bcebos.com/PP-OCRv2/lite/ch_ppocr_mobile_v2.0_cls_infer_opt.nb)|[download link](https://paddleocr.bj.bcebos.com/PP-OCRv2/lite/ch_PP-OCRv2_rec_infer_opt.nb)|v2.10|
|PP-OCRv2(slim)|extra-lightweight chinese OCR optimized model|4.6M|[download link](https://paddleocr.bj.bcebos.com/PP-OCRv2/lite/ch_PP-OCRv2_det_slim_opt.nb)|[download link](https://paddleocr.bj.bcebos.com/PP-OCRv2/lite/ch_ppocr_mobile_v2.0_cls_slim_opt.nb)|[download link](https://paddleocr.bj.bcebos.com/PP-OCRv2/lite/ch_PP-OCRv2_rec_slim_opt.nb)|v2.10|
If you directly use the model in the above table for deployment, you can skip the following steps and directly read [Section 2.2](#2.2-Run-optimized-model-on-Phone).
If the model to be deployed is not in the above table, you need to follow the steps below to obtain the optimized model.
The `opt` tool can be obtained by compiling Paddle Lite.
```
git clone https://github.com/PaddlePaddle/Paddle-Lite.git
cd Paddle-Lite
git checkout release/v2.10
./lite/tools/build.sh build_optimize_tool
```
After the compilation is complete, the opt file is located under build.opt/lite/api/, You can view the operating options and usage of opt in the following ways:
```
cd build.opt/lite/api/
./opt
```
|Options|Description|
|---|---|
|--model_dir|The path of the PaddlePaddle model to be optimized (non-combined form)|
|--model_file|The network structure file path of the PaddlePaddle model (combined form) to be optimized|
|--param_file|The weight file path of the PaddlePaddle model (combined form) to be optimized|
|--optimize_out_type|Output model type, currently supports two types: protobuf and naive_buffer, among which naive_buffer is a more lightweight serialization/deserialization implementation. If you need to perform model prediction on the mobile side, please set this option to naive_buffer. The default is protobuf|
|--optimize_out|The output path of the optimized model|
|--valid_targets|The executable backend of the model, the default is arm. Currently it supports x86, arm, opencl, npu, xpu, multiple backends can be specified at the same time (separated by spaces), and Model Optimize Tool will automatically select the best method. If you need to support Huawei NPU (DaVinci architecture NPU equipped with Kirin 810/990 Soc), it should be set to npu, arm|
|--record_tailoring_info|When using the function of cutting library files according to the model, set this option to true to record the kernel and OP information contained in the optimized model. The default is false|
`--model_dir` is suitable for the non-combined mode of the model to be optimized, and the inference model of PaddleOCR is the combined mode, that is, the model structure and model parameters are stored in a single file.
The following takes the ultra-lightweight Chinese model of PaddleOCR as an example to introduce the use of the compiled opt file to complete the conversion of the inference model to the Paddle-Lite optimized model
```
# 【[Recommendation] Download the Chinese and English inference model of PP-OCRv2
wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_slim_quant_infer.tar && tar xf ch_PP-OCRv2_det_slim_quant_infer.tar
wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_slim_quant_infer.tar && tar xf ch_PP-OCRv2_rec_slim_quant_infer.tar
wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_cls_slim_infer.tar && tar xf ch_ppocr_mobile_v2.0_cls_slim_infer.tar
# Convert detection model
./opt --model_file=./ch_PP-OCRv2_det_slim_quant_infer/inference.pdmodel --param_file=./ch_PP-OCRv2_det_slim_quant_infer/inference.pdiparams --optimize_out=./ch_PP-OCRv2_det_slim_opt --valid_targets=arm --optimize_out_type=naive_buffer
# Convert recognition model
./opt --model_file=./ch_PP-OCRv2_rec_slim_quant_infer/inference.pdmodel --param_file=./ch_PP-OCRv2_rec_slim_quant_infer/inference.pdiparams --optimize_out=./ch_PP-OCRv2_rec_slim_opt --valid_targets=arm --optimize_out_type=naive_buffer
# Convert angle classifier model
./opt --model_file=./ch_ppocr_mobile_v2.0_cls_slim_infer/inference.pdmodel --param_file=./ch_ppocr_mobile_v2.0_cls_slim_infer/inference.pdiparams --optimize_out=./ch_ppocr_mobile_v2.0_cls_slim_opt --valid_targets=arm --optimize_out_type=naive_buffer
```
After the conversion is successful, there will be more files ending with `.nb` in the inference model directory, which is the successfully converted model file.
<a name="2.2-Run-optimized-model-on-Phone"></a>
### 2.2 Run optimized model on Phone
Some preparatory work is required first.
1. Prepare an Android phone with arm8. If the compiled prediction library and opt file are armv7, you need an arm7 phone and modify ARM_ABI = arm7 in the Makefile.
2. Make sure the phone is connected to the computer, open the USB debugging option of the phone, and select the file transfer mode.
3. Install the adb tool on the computer.
3.1. Install ADB for MAC:
```
brew cask install android-platform-tools
```
3.2. Install ADB for Linux
```
sudo apt update
sudo apt install -y wget adb
```
3.3. Install ADB for windows
To install on win, you need to go to Google's Android platform to download the adb package for installation：[link](https://developer.android.com/studio)
Verify whether adb is installed successfully
```
adb devices
```
If there is device output, it means the installation is successful。
```
List of devices attached
744be294 device
```
4. Prepare optimized models, prediction library files, test images and dictionary files used.
```
git clone https://github.com/PaddlePaddle/PaddleOCR.git
cd PaddleOCR/deploy/lite/
# run prepare.sh
sh prepare.sh /{lite prediction library path}/inference_lite_lib.android.armv8
#
cd /{lite prediction library path}/inference_lite_lib.android.armv8/
cd demo/cxx/ocr/
# copy paddle-lite C++ .so file to debug/ directory
cp ../../../cxx/lib/libpaddle_light_api_shared.so ./debug/
cd inference_lite_lib.android.armv8/demo/cxx/ocr/
cp ../../../cxx/lib/libpaddle_light_api_shared.so ./debug/
```
Prepare the test image, taking PaddleOCR/doc/imgs/11.jpg as an example, copy the image file to the demo/cxx/ocr/debug/ folder. Prepare the model files optimized by the lite opt tool, ch_det_mv3_db_opt.nb, ch_rec_mv3_crnn_opt.nb, and place them under the demo/cxx/ocr/debug/ folder.
The structure of the OCR demo is as follows after the above command is executed:
```
demo/cxx/ocr/
|-- debug/
| |--ch_PP-OCRv2_det_slim_opt.nb Detection model
| |--ch_PP-OCRv2_rec_slim_opt.nb Recognition model
| |--ch_ppocr_mobile_v2.0_cls_slim_opt.nb Text direction classification model
| |--11.jpg Image for OCR
| |--ppocr_keys_v1.txt Dictionary file
| |--libpaddle_light_api_shared.so C++ .so file
| |--config.txt Config file
|-- config.txt Config file
|-- cls_process.cc Pre-processing and post-processing files for the angle classifier
|-- cls_process.h
|-- crnn_process.cc Pre-processing and post-processing files for the CRNN model
|-- crnn_process.h
|-- db_post_process.cc Pre-processing and post-processing files for the DB model
|-- db_post_process.h
|-- Makefile
|-- ocr_db_crnn.cc C++ main code
```
#### 注意：
1. `ppocr_keys_v1.txt` is a Chinese dictionary file. If the nb model is used for English recognition or other language recognition, dictionary file should be replaced with a dictionary of the corresponding language. PaddleOCR provides a variety of dictionaries under ppocr/utils/, including:
```
dict/french_dict.txt # french
dict/german_dict.txt # german
ic15_dict.txt # english
dict/japan_dict.txt # japan
dict/korean_dict.txt # korean
ppocr_keys_v1.txt # chinese
```
2. `config.txt` of the detector and classifier, as shown below:
```
max_side_len 960 # Limit the maximum image height and width to 960
det_db_thresh 0.3 # Used to filter the binarized image of DB prediction, setting 0.-0.3 has no obvious effect on the result
det_db_box_thresh 0.5 # DDB post-processing filter box threshold, if there is a missing box detected, it can be reduced as appropriate
det_db_unclip_ratio 1.6 # Indicates the compactness of the text box, the smaller the value, the closer the text box to the text
use_direction_classify 0 # Whether to use the direction classifier, 0 means not to use, 1 means to use
```
5. Run Model on phone
After the above steps are completed, you can use adb to push the file to the phone to run, the steps are as follows:
```
# Execute the compilation and get the executable file ocr_db_crnn
# The first execution of this command will download dependent libraries such as opencv. After the download is complete, you need to execute it again
make -j
# Move the compiled executable file to the debug folder
mv ocr_db_crnn ./debug/
# Push the debug folder to the phone
adb push debug /data/local/tmp/
adb shell
cd /data/local/tmp/debug
export LD_LIBRARY_PATH=${PWD}:$LD_LIBRARY_PATH
# The use of ocr_db_crnn is:
# ./ocr_db_crnn Detection model file Orientation classifier model file Recognition model file Test image path Dictionary file path
./ocr_db_crnn ch_PP-OCRv2_det_slim_opt.nb ch_PP-OCRv2_rec_slim_opt.nb ch_ppocr_mobile_v2.0_cls_opt.nb ./11.jpg ppocr_keys_v1.txt
```
If you modify the code, you need to recompile and push to the phone.
The outputs are as follows:
<div align="center">
<img src="imgs/lite_demo.png" width="600">
</div>
## FAQ
Q1: What if I want to change the model, do I need to run it again according to the process?
A1: If you have performed the above steps, you only need to replace the .nb model file to complete the model replacement.
Q2: How to test with another picture?
A2: Replace the .jpg test image under ./debug with the image you want to test, and run adb push to push new image to the phone.
Q3: How to package it into the mobile APP?
A3: This demo aims to provide the core algorithm part that can run OCR on mobile phones. Further, PaddleOCR/deploy/android_demo is an example of encapsulating this demo into a mobile app for reference.
deploy/paddle2onnx/readme_ch.md 0 → 100644
浏览文件 @ 486aa102
# Paddle2ONNX模型转化与预测
本章节介绍 PaddleOCR 模型如何转化为 ONNX 模型，并基于 ONNXRuntime 引擎预测。
## 1. 环境准备
需要准备 PaddleOCR、Paddle2ONNX 模型转化环境，和 ONNXRuntime 预测环境
### PaddleOCR
克隆PaddleOCR的仓库，使用release/2.4分支，并进行安装，由于PaddleOCR仓库比较大，git clone速度比较慢，所以本教程已下载
```
git clone -b release/2.4 https://github.com/PaddlePaddle/PaddleOCR.git
cd PaddleOCR && python3.7 setup.py install
```
### Paddle2ONNX
Paddle2ONNX 支持将 PaddlePaddle 模型格式转化到 ONNX 模型格式，算子目前稳定支持导出 ONNX Opset 9~11，部分Paddle算子支持更低的ONNX Opset转换。
更多细节可参考 [Paddle2ONNX](https://github.com/PaddlePaddle/Paddle2ONNX/blob/develop/README_zh.md)
- 安装 Paddle2ONNX
```
python3.7 -m pip install paddle2onnx
```
- 安装 ONNXRuntime
```
# 建议安装 1.9.0 版本，可根据环境更换版本号
python3.7 -m pip install onnxruntime==1.9.0
```
## 2. 模型转换
- Paddle 模型下载
有两种方式获取Paddle静态图模型：在 [model_list](../../doc/doc_ch/models_list.md) 中下载PaddleOCR提供的预测模型；
参考[模型导出说明](../../doc/doc_ch/inference.md#训练模型转inference模型)把训练好的权重转为 inference_model。
以 ppocr 中文检测、识别、分类模型为例：
```
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar
cd ./inference && tar xf ch_PP-OCRv2_det_infer.tar && cd ..
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar
cd ./inference && tar xf ch_PP-OCRv2_rec_infer.tar && cd ..
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar
cd ./inference && tar xf ch_ppocr_mobile_v2.0_cls_infer.tar && cd ..
```
- 模型转换
使用 Paddle2ONNX 将Paddle静态图模型转换为ONNX模型格式：
```
paddle2onnx --model_dir ./inference/ch_PP-OCRv2_det_infer \
--model_filename inference.pdmodel \
--params_filename inference.pdiparams \
--save_file ./inference/det_onnx/model.onnx \
--opset_version 10 \
--input_shape_dict="{'x':[-1,3,-1,-1]}" \
--enable_onnx_checker True
paddle2onnx --model_dir ./inference/ch_PP-OCRv2_rec_infer \
--model_filename inference.pdmodel \
--params_filename inference.pdiparams \
--save_file ./inference/rec_onnx/model.onnx \
--opset_version 10 \
--input_shape_dict="{'x':[-1,3,-1,-1]}" \
--enable_onnx_checker True
paddle2onnx --model_dir ./inference/ch_ppocr_mobile_v2.0_cls_infer \
--model_filename ch_ppocr_mobile_v2.0_cls_infer/inference.pdmodel \
--params_filename ch_ppocr_mobile_v2.0_cls_infer/inference.pdiparams \
--save_file ./inferencecls_onnx/model.onnx \
--opset_version 10 \
--input_shape_dict="{'x':[-1,3,-1,-1]}" \
--enable_onnx_checker True
```
执行完毕后，ONNX 模型会被分别保存在 `./inference/det_onnx/`，`./inference/rec_onnx/`，`./inference/cls_onnx/`路径下
* 注意：对于OCR模型，转化过程中必须采用动态shape的形式，即加入选项--input_shape_dict="{'x': [-1, 3, -1, -1]}"，否则预测结果可能与直接使用Paddle预测有细微不同。
另外，以下几个模型暂不支持转换为 ONNX 模型：
NRTR、SAR、RARE、SRN
## 3. 推理预测
以中文OCR模型为例，使用 ONNXRuntime 预测可执行如下命令：
```
python3.7 tools/infer/predict_system.py --use_gpu=False --use_onnx=True \
--det_model_dir=./inference/det_onnx/model.onnx \
--rec_model_dir=./inference/rec_onnx/model.onnx \
--cls_model_dir=./inference/cls_onnx/model.onnx \
--image_dir=./deploy/lite/imgs/lite_demo.png
```
以中文OCR模型为例，使用 Paddle Inference 预测可执行如下命令：
```
python3.7 tools/infer/predict_system.py --use_gpu=False \
--cls_model_dir=./inference/ch_ppocr_mobile_v2.0_cls_infer \
--rec_model_dir=./inference/ch_PP-OCRv2_rec_infer \
--det_model_dir=./inference/ch_PP-OCRv2_det_infer \
--image_dir=./deploy/lite/imgs/lite_demo.png
```
执行命令后在终端会打印出预测的识别信息，并在 `./inference_results/` 下保存可视化结果。
ONNXRuntime 执行效果：
<div align="center">
<img src="./images/lite_demo_onnx.png" width=800">
</div>
Paddle Inference 执行效果：
<div align="center">
<img src="./images/lite_demo_paddle.png" width=800">
</div>
使用 ONNXRuntime 预测，终端输出：
```
[2022/02/22 17:48:27] root DEBUG: dt_boxes num : 38, elapse : 0.043187856674194336
[2022/02/22 17:48:27] root DEBUG: rec_res num : 38, elapse : 0.592170000076294
[2022/02/22 17:48:27] root DEBUG: 0 Predict time of ./deploy/lite/imgs/lite_demo.png: 0.642s
[2022/02/22 17:48:27] root DEBUG: The, 0.984
[2022/02/22 17:48:27] root DEBUG: visualized, 0.882
[2022/02/22 17:48:27] root DEBUG: etect18片, 0.720
[2022/02/22 17:48:27] root DEBUG: image saved in./vis.jpg, 0.947
[2022/02/22 17:48:27] root DEBUG: 纯臻营养护发素0.993604, 0.996
[2022/02/22 17:48:27] root DEBUG: 产品信息/参数, 0.922
[2022/02/22 17:48:27] root DEBUG: 0.992728, 0.914
[2022/02/22 17:48:27] root DEBUG: （45元／每公斤，100公斤起订）, 0.926
[2022/02/22 17:48:27] root DEBUG: 0.97417, 0.977
[2022/02/22 17:48:27] root DEBUG: 每瓶22元，1000瓶起订）0.993976, 0.962
[2022/02/22 17:48:27] root DEBUG: 【品牌】：代加工方式/0EMODM, 0.945
[2022/02/22 17:48:27] root DEBUG: 0.985133, 0.980
[2022/02/22 17:48:27] root DEBUG: 【品名】：纯臻营养护发素, 0.921
[2022/02/22 17:48:27] root DEBUG: 0.995007, 0.883
[2022/02/22 17:48:27] root DEBUG: 【产品编号】：YM-X-30110.96899, 0.955
[2022/02/22 17:48:27] root DEBUG: 【净含量】：220ml, 0.943
[2022/02/22 17:48:27] root DEBUG: Q.996577, 0.932
[2022/02/22 17:48:27] root DEBUG: 【适用人群】：适合所有肤质, 0.913
[2022/02/22 17:48:27] root DEBUG: 0.995842, 0.969
[2022/02/22 17:48:27] root DEBUG: 【主要成分】：鲸蜡硬脂醇、燕麦B-葡聚, 0.883
[2022/02/22 17:48:27] root DEBUG: 0.961928, 0.964
[2022/02/22 17:48:27] root DEBUG: 10, 0.812
[2022/02/22 17:48:27] root DEBUG: 糖、椰油酰胺丙基甜菜碱、泛醒, 0.866
[2022/02/22 17:48:27] root DEBUG: 0.925898, 0.943
[2022/02/22 17:48:27] root DEBUG: （成品包材）, 0.974
[2022/02/22 17:48:27] root DEBUG: 0.972573, 0.961
[2022/02/22 17:48:27] root DEBUG: 【主要功能】：可紧致头发磷层，从而达到, 0.936
[2022/02/22 17:48:27] root DEBUG: 0.994448, 0.952
[2022/02/22 17:48:27] root DEBUG: 13, 0.998
[2022/02/22 17:48:27] root DEBUG: 即时持久改善头发光泽的效果，给干燥的头, 0.994
[2022/02/22 17:48:27] root DEBUG: 0.990198, 0.975
[2022/02/22 17:48:27] root DEBUG: 14, 0.977
[2022/02/22 17:48:27] root DEBUG: 发足够的滋养, 0.991
[2022/02/22 17:48:27] root DEBUG: 0.997668, 0.918
[2022/02/22 17:48:27] root DEBUG: 花费了0.457335秒, 0.901
[2022/02/22 17:48:27] root DEBUG: The visualized image saved in ./inference_results/lite_demo.png
[2022/02/22 17:48:27] root INFO: The predict total time is 0.7003889083862305
```
使用 Paddle Inference 预测，终端输出：
```
[2022/02/22 17:47:25] root DEBUG: dt_boxes num : 38, elapse : 0.11791276931762695
[2022/02/22 17:47:27] root DEBUG: rec_res num : 38, elapse : 2.6206860542297363
[2022/02/22 17:47:27] root DEBUG: 0 Predict time of ./deploy/lite/imgs/lite_demo.png: 2.746s
[2022/02/22 17:47:27] root DEBUG: The, 0.984
[2022/02/22 17:47:27] root DEBUG: visualized, 0.882
[2022/02/22 17:47:27] root DEBUG: etect18片, 0.720
[2022/02/22 17:47:27] root DEBUG: image saved in./vis.jpg, 0.947
[2022/02/22 17:47:27] root DEBUG: 纯臻营养护发素0.993604, 0.996
[2022/02/22 17:47:27] root DEBUG: 产品信息/参数, 0.922
[2022/02/22 17:47:27] root DEBUG: 0.992728, 0.914
[2022/02/22 17:47:27] root DEBUG: （45元／每公斤，100公斤起订）, 0.926
[2022/02/22 17:47:27] root DEBUG: 0.97417, 0.977
[2022/02/22 17:47:27] root DEBUG: 每瓶22元，1000瓶起订）0.993976, 0.962
[2022/02/22 17:47:27] root DEBUG: 【品牌】：代加工方式/0EMODM, 0.945
[2022/02/22 17:47:27] root DEBUG: 0.985133, 0.980
[2022/02/22 17:47:27] root DEBUG: 【品名】：纯臻营养护发素, 0.921
[2022/02/22 17:47:27] root DEBUG: 0.995007, 0.883
[2022/02/22 17:47:27] root DEBUG: 【产品编号】：YM-X-30110.96899, 0.955
[2022/02/22 17:47:27] root DEBUG: 【净含量】：220ml, 0.943
[2022/02/22 17:47:27] root DEBUG: Q.996577, 0.932
[2022/02/22 17:47:27] root DEBUG: 【适用人群】：适合所有肤质, 0.913
[2022/02/22 17:47:27] root DEBUG: 0.995842, 0.969
[2022/02/22 17:47:27] root DEBUG: 【主要成分】：鲸蜡硬脂醇、燕麦B-葡聚, 0.883
[2022/02/22 17:47:27] root DEBUG: 0.961928, 0.964
[2022/02/22 17:47:27] root DEBUG: 10, 0.812
[2022/02/22 17:47:27] root DEBUG: 糖、椰油酰胺丙基甜菜碱、泛醒, 0.866
[2022/02/22 17:47:27] root DEBUG: 0.925898, 0.943
[2022/02/22 17:47:27] root DEBUG: （成品包材）, 0.974
[2022/02/22 17:47:27] root DEBUG: 0.972573, 0.961
[2022/02/22 17:47:27] root DEBUG: 【主要功能】：可紧致头发磷层，从而达到, 0.936
[2022/02/22 17:47:27] root DEBUG: 0.994448, 0.952
[2022/02/22 17:47:27] root DEBUG: 13, 0.998
[2022/02/22 17:47:27] root DEBUG: 即时持久改善头发光泽的效果，给干燥的头, 0.994
[2022/02/22 17:47:27] root DEBUG: 0.990198, 0.975
[2022/02/22 17:47:27] root DEBUG: 14, 0.977
[2022/02/22 17:47:27] root DEBUG: 发足够的滋养, 0.991
[2022/02/22 17:47:27] root DEBUG: 0.997668, 0.918
[2022/02/22 17:47:27] root DEBUG: 花费了0.457335秒, 0.901
[2022/02/22 17:47:27] root DEBUG: The visualized image saved in ./inference_results/lite_demo.png
[2022/02/22 17:47:27] root INFO: The predict total time is 2.8338775634765625
```
deploy/paddlejs/README.md 0 → 100644
浏览文件 @ 486aa102
English| [简体中文](README_ch.md)
# Paddle.js
[Paddle.js](https://github.com/PaddlePaddle/Paddle.js) is a web project for Baidu PaddlePaddle, which is an open source deep learning framework running in the browser. Paddle.js can either load a pre-trained model, or transforming a model from paddle-hub with model transforming tools provided by Paddle.js. It could run in every browser with WebGL/WebGPU/WebAssembly supported. It could also run in Baidu Smartprogram and WX miniprogram.
- [Online experience](https://paddlejs.baidu.com/ocr)
- [Tutorial](https://github.com/PaddlePaddle/Paddle.js/blob/release/v2.2.3/packages/paddlejs-models/ocr/README_cn.md)
- Visualization：
<div align="center">
<img src="./paddlejs_demo.gif" width="800">
</div>
\ No newline at end of file
deploy/paddlejs/README_ch.md 0 → 100644
浏览文件 @ 486aa102
[English](README.md) | 简体中文
# Paddle.js 网页前端部署
[Paddle.js](https://github.com/PaddlePaddle/Paddle.js) 是百度 PaddlePaddle 的 web 方向子项目，是一个运行在浏览器中的开源深度学习框架。Paddle.js 可以加载提前训练好的 paddle 模型，通过 Paddle.js 的模型转换工具 paddlejs-converter 变成浏览器友好的模型进行在线推理预测使用。目前，Paddle.js 可以在支持 WebGL/WebGPU/WebAssembly 的浏览器中运行，也可以在百度小程序和微信小程序环境下运行。
- [在线体验](https://paddlejs.baidu.com/ocr)
- [直达教程](https://github.com/PaddlePaddle/Paddle.js/blob/release/v2.2.3/packages/paddlejs-models/ocr/README_cn.md)
- 效果：
<div align="center">
<img src="./paddlejs_demo.gif" width="800">
</div>
\ No newline at end of file
doc/doc_ch/ppocr_introduction.md
浏览文件 @ 486aa102
...@@ -4,11 +4,12 @@ ...@@ -4,11 +4,12 @@
- [1. 简介](#1) - [1. 简介](#1)
- [2. 特性](#2) - [2. 特性](#2)
- [3. 效果展示](#3) - [3. benchmark](#3)
- [4. 使用教程](#4) - [4. 效果展示](#4)
- [4.1 快速体验](#41) - [5. 使用教程](#5)
- [4.2 模型训练、压缩、推理部署](#42) - [5.1 快速体验](#51)
- [5. 模型库](#5) - [5.2 模型训练、压缩、推理部署](#52)
- [6. 模型库](#6)
<a name="1"></a> <a name="1"></a>
...@@ -42,7 +43,13 @@ PP-OCR系统在持续迭代优化，目前已发布PP-OCR和PP-OCRv2两个版本 ...@@ -42,7 +43,13 @@ PP-OCR系统在持续迭代优化，目前已发布PP-OCR和PP-OCRv2两个版本
- 支持多语言识别：韩语、日语、德语、法语等约80种语言 - 支持多语言识别：韩语、日语、德语、法语等约80种语言
<a name="3"></a> <a name="3"></a>
## 3. 效果展示 [more](./visualization.md) ## 3. benchmark
关于PP-OCR系列模型之间的性能对比，请查看[benchmark](./benchmark.md)文档。
<a name="4"></a>
## 4. 效果展示 [more](./visualization.md)
<details open> <details open>
<summary>PP-OCRv2 中文模型</summary> <summary>PP-OCRv2 中文模型</summary>
...@@ -80,23 +87,23 @@ PP-OCR系统在持续迭代优化，目前已发布PP-OCR和PP-OCRv2两个版本 ...@@ -80,23 +87,23 @@ PP-OCR系统在持续迭代优化，目前已发布PP-OCR和PP-OCRv2两个版本
</details> </details>
<a name="4"></a> <a name="5"></a>
## 4. 使用教程 ## 5. 使用教程
<a name="41"></a> <a name="51"></a>
### 4.1 快速体验 ### 5.1 快速体验
- 在线网站体验：超轻量PP-OCR mobile模型体验地址：https://www.paddlepaddle.org.cn/hub/scene/ocr - 在线网站体验：超轻量PP-OCR mobile模型体验地址：https://www.paddlepaddle.org.cn/hub/scene/ocr
- 移动端demo体验：[安装包DEMO下载地址](https://ai.baidu.com/easyedge/app/openSource?from=paddlelite)(基于EasyEdge和Paddle-Lite, 支持iOS和Android系统) - 移动端demo体验：[安装包DEMO下载地址](https://ai.baidu.com/easyedge/app/openSource?from=paddlelite)(基于EasyEdge和Paddle-Lite, 支持iOS和Android系统)
- 一行命令快速使用：[快速开始（中英文/多语言）](./doc/doc_ch/quickstart.md) - 一行命令快速使用：[快速开始（中英文/多语言）](./doc/doc_ch/quickstart.md)
<a name="42"></a> <a name="52"></a>
### 4.2 模型训练、压缩、推理部署 ### 5.2 模型训练、压缩、推理部署
更多教程，包括模型训练、模型压缩、推理部署等，请参考[文档教程](../../README_ch.md#文档教程)。 更多教程，包括模型训练、模型压缩、推理部署等，请参考[文档教程](../../README_ch.md#文档教程)。
<a name="5"></a> <a name="6"></a>
## 5. 模型库 ## 6. 模型库
PP-OCR中英文模型列表如下： PP-OCR中英文模型列表如下：
......
doc/doc_en/algorithm_det_db_en.md
浏览文件 @ 486aa102
# DB
- [1. Introduction](#1)
- [2. Environment](#2)
- [3. Model Training / Evaluation / Prediction](#3)
- [3.1 Training](#3-1)
- [3.2 Evaluation](#3-2)
- [3.3 Prediction](#3-3)
- [4. Inference and Deployment](#4)
- [4.1 Python Inference](#4-1)
- [4.2 C++ Inference](#4-2)
- [4.3 Serving](#4-3)
- [4.4 More](#4-4)
- [5. FAQ](#5)
<a name="1"></a>
## 1. Introduction
\ No newline at end of file
doc/doc_en/algorithm_en.md
浏览文件 @ 486aa102
# Academic Algorithms and Models
PaddleOCR will add cutting-edge OCR algorithms and models continuously. Check out the supported models and tutorials by clicking the following list:
- [text detection algorithms](./algorithm_overview_en.md#11)
- [text recognition algorithms](./algorithm_overview_en.md#12)
- [end-to-end algorithms](./algorithm_overview_en.md#2)
Developers are welcome to contribute more algorithms! Please refer to [add new algorithm](./add_new_algorithm_en.md) guideline.
\ No newline at end of file
doc/doc_en/algorithm_overview_en.md
浏览文件 @ 486aa102
# Two-stage Algorithm # OCR Algorithms
- [1. Algorithm Introduction](#1-algorithm-introduction) - [1. Two-stage Algorithms](#1)
* [1.1 Text Detection Algorithm](#11-text-detection-algorithm) * [1.1 Text Detection Algorithms](#11)
* [1.2 Text Recognition Algorithm](#12-text-recognition-algorithm) * [1.2 Text Recognition Algorithms](#12)
- [2. Training](#2-training) - [2. End-to-end Algorithms](#2)
- [3. Inference](#3-inference)
<a name="Algorithm_introduction"></a>
## 1. Algorithm Introduction This tutorial lists the OCR algorithms supported by PaddleOCR, as well as the models and metrics of each algorithm on **English public datasets**. It is mainly used for algorithm introduction and algorithm performance comparison. For more models on other datasets including Chinese, please refer to [PP-OCR v2.0 models list](./models_list_en.md).
This tutorial lists the text detection algorithms and text recognition algorithms supported by PaddleOCR, as well as the models and metrics of each algorithm on **English public datasets**. It is mainly used for algorithm introduction and algorithm performance comparison. For more models on other datasets including Chinese, please refer to [PP-OCR v2.0 models list](./models_list_en.md). <a name="1"></a>
## 1. Two-stage Algorithms
- [1. Text Detection Algorithm](#TEXTDETECTIONALGORITHM) <a name="11"></a>
- [2. Text Recognition Algorithm](#TEXTRECOGNITIONALGORITHM)
<a name="TEXTDETECTIONALGORITHM"></a> ### 1.1 Text Detection Algorithms
### 1.1 Text Detection Algorithm Supported text detection algorithms (Click the link to get the tutorial):
- [x] [DB](./algorithm_det_db_en.md)
PaddleOCR open source text detection algorithms list: - [x] [EAST](./algorithm_det_east_en.md)
- [x] EAST([paper](https://arxiv.org/abs/1704.03155))[2] - [x] [SAST](./algorithm_det_sast_en.md)
- [x] DB([paper](https://arxiv.org/abs/1911.08947))[1] - [x] [PSENet](./algorithm_det_psenet_en.md)
- [x] SAST([paper](https://arxiv.org/abs/1908.05498))[4] - [x] [FCENet](./algorithm_det_fcenet_en.md)
- [x] PSENet([paper](https://arxiv.org/abs/1903.12473v2)）
On the ICDAR2015 dataset, the text detection result is as follows: On the ICDAR2015 dataset, the text detection result is as follows:
...@@ -48,20 +45,19 @@ On Total-Text dataset, the text detection result is as follows: ...@@ -48,20 +45,19 @@ On Total-Text dataset, the text detection result is as follows:
* [Baidu Drive](https://pan.baidu.com/s/12cPnZcVuV1zn5DOd4mqjVw) (download code: 2bpi). * [Baidu Drive](https://pan.baidu.com/s/12cPnZcVuV1zn5DOd4mqjVw) (download code: 2bpi).
* [Google Drive](https://drive.google.com/drive/folders/1ll2-XEVyCQLpJjawLDiRlvo_i4BqHCJe?usp=sharing) * [Google Drive](https://drive.google.com/drive/folders/1ll2-XEVyCQLpJjawLDiRlvo_i4BqHCJe?usp=sharing)
For the training guide and use of PaddleOCR text detection algorithms, please refer to the document [Text detection model training/evaluation/prediction](./detection_en.md)
<a name="TEXTRECOGNITIONALGORITHM"></a> <a name="12"></a>
### 1.2 Text Recognition Algorithm ### 1.2 Text Recognition Algorithms
PaddleOCR open-source text recognition algorithms list: Supported text recognition algorithms (Click the link to get the tutorial):
- [x] CRNN([paper](https://arxiv.org/abs/1507.05717))[7] - [x] [CRNN](./algorithm_rec_crnn_en.md)
- [x] Rosetta([paper](https://arxiv.org/abs/1910.05085))[10] - [x] [Rosetta](./algorithm_rec_rosetta_en.md)
- [x] STAR-Net([paper](http://www.bmva.org/bmvc/2016/papers/paper043/index.html))[11] - [x] [STAR-Net](./algorithm_rec_starnet_en.md)
- [x] RARE([paper](https://arxiv.org/abs/1603.03915v1))[12] - [x] [RARE](./algorithm_rec_rare_en.md)
- [x] SRN([paper](https://arxiv.org/abs/2003.12294))[5] - [x] [SRN](./algorithm_rec_srn_en.md)
- [x] NRTR([paper](https://arxiv.org/abs/1806.00926v2))[13] - [x] [NRTR](./algorithm_rec_nrtr_en.md)
- [x] SAR([paper](https://arxiv.org/abs/1811.00751v2)) - [x] [SAR](./algorithm_rec_sar_en.md)
- [x] SEED([paper](https://arxiv.org/pdf/2005.10977.pdf)) - [x] [SEED](./algorithm_rec_seed_en.md)
Refer to [DTRB](https://arxiv.org/abs/1904.01906), the training and evaluation result of these above text recognition (using MJSynth and SynthText for training, evaluate on IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE) is as follow: Refer to [DTRB](https://arxiv.org/abs/1904.01906), the training and evaluation result of these above text recognition (using MJSynth and SynthText for training, evaluate on IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE) is as follow:
...@@ -80,12 +76,10 @@ Refer to [DTRB](https://arxiv.org/abs/1904.01906), the training and evaluation r ...@@ -80,12 +76,10 @@ Refer to [DTRB](https://arxiv.org/abs/1904.01906), the training and evaluation r
|SAR|Resnet31| 87.20% | rec_r31_sar | [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.1/rec/rec_r31_sar_train.tar) | |SAR|Resnet31| 87.20% | rec_r31_sar | [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.1/rec/rec_r31_sar_train.tar) |
|SEED|Aster_Resnet| 85.35% | rec_resnet_stn_bilstm_att | [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.1/rec/rec_resnet_stn_bilstm_att.tar) | |SEED|Aster_Resnet| 85.35% | rec_resnet_stn_bilstm_att | [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.1/rec/rec_resnet_stn_bilstm_att.tar) |
Please refer to the document for training guide and use of PaddleOCR
## 2. Training
For the training guide and use of PaddleOCR text detection algorithms, please refer to the document [Text detection model training/evaluation/prediction](./detection_en.md). For text recognition algorithms, please refer to [Text recognition model training/evaluation/prediction](./recognition_en.md) <a name="2"></a>
## 3. Inference ## 2. End-to-end Algorithms
Except for the PP-OCR series models of the above models, the other models only support inference based on the Python engine. For details, please refer to [Inference based on Python prediction engine](./inference_en.md) Supported end-to-end algorithms (Click the link to get the tutorial):
- [x] [PGNet](./algorithm_e2e_pgnet_en.md)
doc/doc_en/ppocr_introduction_en.md
浏览文件 @ 486aa102
English | [简体中文](../doc_ch/ppocr_introduction.md)
# PP-OCR
- [1. Introduction](#1)
- [2. Features](#2)
- [3. Benchmark](#3)
- [4. Visualization](#4)
- [5. Tutorial](#5)
- [5.1 Quick start](#51)
- [5.2 Model training / compression / deployment](#52)
- [6. Model zoo](#6)
<a name="1"></a>
## 1. Introduction
PP-OCR is a self-developed practical ultra-lightweight OCR system, which is slimed and optimized based on the reimplemented [academic algorithms](algorithm_en.md), considering the balance between **accuracy** and **speed**.
PP-OCR is a two-stage OCR system, in which the text detection algorithm is [DB](algorithm_det_db_en.md), and the text recognition algorithm is [CRNN](algorithm_rec_crnn_en.md). Besides, a [text direction classifier](angle_class_en.md) is added between the detection and recognition modules to deal with text in different directions.
PP-OCR pipeline is as follows:
<div align="center">
<img src="../ppocrv2_framework.jpg" width="800">
</div>
PP-OCR system is in continuous optimization. At present, PP-OCR and PP-OCRv2 have been released:
[1] PP-OCR adopts 19 effective strategies from 8 aspects including backbone network selection and adjustment, prediction head design, data augmentation, learning rate transformation strategy, regularization parameter selection, pre-training model use, and automatic model tailoring and quantization to optimize and slim down the models of each module (as shown in the green box above). The final results are an ultra-lightweight Chinese and English OCR model with an overall size of 3.5M and a 2.8M English digital OCR model. For more details, please refer to the PP-OCR technical article (https://arxiv.org/abs/2009.09941).
[2] On the basis of PP-OCR, PP-OCRv2 is further optimized in five aspects. The detection model adopts CML(Collaborative Mutual Learning) knowledge distillation strategy and CopyPaste data expansion strategy. The recognition model adopts LCNet lightweight backbone network, U-DML knowledge distillation strategy and enhanced CTC loss function improvement (as shown in the red box above), which further improves the inference speed and prediction effect. For more details, please refer to the technical report of PP-OCRv2 (https://arxiv.org/abs/2109.03144).
<a name="2"></a>
## 2. Features
- Ultra lightweight PP-OCRv2 series models: detection (3.1M) + direction classifier (1.4M) + recognition 8.5M) = 13.0M
- Ultra lightweight PP-OCR mobile series models: detection (3.0M) + direction classifier (1.4M) + recognition (5.0M) = 9.4M
- General PP-OCR server series models: detection (47.1M) + direction classifier (1.4M) + recognition (94.9M) = 143.4M
- Support Chinese, English, and digit recognition, vertical text recognition, and long text recognition
- Support multi-lingual recognition: about 80 languages like Korean, Japanese, German, French, etc
<a name="3"></a>
## 3. benchmark
For the performance comparison between PP-OCR series models, please check the [benchmark](./benchmark_en.md) documentation.
<a name="4"></a>
## 4. Visualization [more](./visualization.md)
<details open>
<summary>PP-OCRv2 English model</summary>
<div align="center">
<img src="../imgs_results/ch_ppocr_mobile_v2.0/img_12.jpg" width="800">
</div>
</details>
<details open>
<summary>PP-OCRv2 Chinese model</summary>
<div align="center">
<img src="../imgs_results/ch_ppocr_mobile_v2.0/test_add_91.jpg" width="800">
<img src="../imgs_results/ch_ppocr_mobile_v2.0/00018069.jpg" width="800">
</div>
<div align="center">
<img src="../imgs_results/ch_ppocr_mobile_v2.0/00056221.jpg" width="800">
<img src="../imgs_results/ch_ppocr_mobile_v2.0/rotate_00052204.jpg" width="800">
</div>
</details>
<details open>
<summary>PP-OCRv2 Multilingual model</summary>
<div align="center">
<img src="../imgs_results/french_0.jpg" width="800">
<img src="../imgs_results/korean.jpg" width="800">
</div>
</details>
<a name="5"></a>
## 5. Tutorial
<a name="51"></a>
### 5.1 Quick start
- You can also quickly experience the ultra-lightweight OCR : [Online Experience](https://www.paddlepaddle.org.cn/hub/scene/ocr)
- Mobile DEMO experience (based on EasyEdge and Paddle-Lite, supports iOS and Android systems): [Sign in to the website to obtain the QR code for installing the App](https://ai.baidu.com/easyedge/app/openSource?from=paddlelite)
- One line of code quick use: [Quick Start](./quickstart_en.md)
<a name="52"></a>
### 5.2 Model training / compression / deployment
For more tutorials, including model training, model compression, deployment, etc., please refer to [tutorials](../../README.md#Tutorials)。
<a name="6"></a>
## 6. Model zoo
## PP-OCR Series Model List（Update on September 8th）
| Model introduction | Model name | Recommended scene | Detection model | Direction classifier | Recognition model |
| ------------------------------------------------------------ | ---------------------------- | ----------------- | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ |
| Chinese and English ultra-lightweight PP-OCRv2 model（11.6M） | ch_PP-OCRv2_xx |Mobile & Server|[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_distill_train.tar)| [inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_train.tar)|
| Chinese and English ultra-lightweight PP-OCR model (9.4M) | ch_ppocr_mobile_v2.0_xx | Mobile & server |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar)|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_train.tar) |
| Chinese and English general PP-OCR model (143.4M) | ch_ppocr_server_v2.0_xx | Server |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar) |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_train.tar) |
For more model downloads (including multiple languages), please refer to [PP-OCR series model downloads](./models_list_en.md).
For a new language request, please refer to [Guideline for new language_requests](../../README.md#language_requests).
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或