+
+
-以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
-- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
+The above command works for Linux or MacOS. For SDK use-pattern in Windows, refer to:
+- [How to use FastDeploy C++ SDK in Windows](../../../../../docs/cn/faq/use_sdk_on_windows.md)
-## FastestDet C++接口
+## FastestDet C++ Interface
-### FastestDet类
+### FastestDet Class
```c++
fastdeploy::vision::detection::FastestDet(
@@ -49,16 +49,16 @@ fastdeploy::vision::detection::FastestDet(
const ModelFormat& model_format = ModelFormat::ONNX)
```
-FastestDet模型加载和初始化，其中model_file为导出的ONNX模型格式。
+FastestDet model loading and initialization, among which model_file is the exported ONNX model format
-**参数**
+**Parameter**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为ONNX格式
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. Only passing an empty string when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. ONNX format by default
-#### Predict函数
+#### Predict Function
> ```c++
> FastestDet::Predict(cv::Mat* im, DetectionResult* result,
@@ -66,22 +66,22 @@ FastestDet模型加载和初始化，其中model_file为导出的ONNX模型格
> float nms_iou_threshold = 0.45)
> ```
>
-> 模型预测接口，输入图像直接输出检测结果。
+> Model prediction interface. Input images and output detection results.
>
-> **参数**
+> **Parameter**
>
-> > * **im**: 输入图像，注意需为HWC，BGR格式
-> > * **result**: 检测结果，包括检测框，各个框的置信度, DetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
-> > * **conf_threshold**: 检测框置信度过滤阈值
-> > * **nms_iou_threshold**: NMS处理过程中iou阈值
+> > * **im**: Input images in HWC or BGR format
+> > * **result**: Detection results, including detection box and confidence of each box. Refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for DetectionResult
+> > * **conf_threshold**: Filtering threshold of detection box confidence
+> > * **nms_iou_threshold**: iou threshold during NMS processing
-### 类成员变量
-#### 预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+### Class Member Variable
+#### Pre-processing Parameter
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
-> > * **size**(vector<int>): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[352, 352]
+> > * **size**(vector<int>): This parameter changes the size of the resize used during preprocessing, containing two integer elements for [width, height] with default value [352, 352]
-- [模型介绍](../../)
-- [Python部署](../python)
-- [视觉模型预测结果](../../../../../docs/api/vision_results/)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+- [Model Description](../../)
+- [Python Deployment](../python)
+- [Vision Model Prediction Results](../../../../../docs/api/vision_results/)
+- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/fastestdet/cpp/README_CN.md b/examples/vision/detection/fastestdet/cpp/README_CN.md
new file mode 100644
index 0000000000..7c940183ef
--- /dev/null
+++ b/examples/vision/detection/fastestdet/cpp/README_CN.md
@@ -0,0 +1,88 @@
+[English](README.md) | 简体中文
+# FastestDet C++部署示例
+
+本目录下提供`infer.cc`快速完成FastestDet在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试
+
+```bash
+mkdir build
+cd build
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-1.0.3.tgz
+tar xvf fastdeploy-linux-x64-1.0.3.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-1.0.3
+make -j
+
+#下载官方转换好的FastestDet模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/FastestDet.onnx
+wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
+
+
+# CPU推理
+./infer_demo FastestDet.onnx 000000014439.jpg 0
+# GPU推理
+./infer_demo FastestDet.onnx 000000014439.jpg 1
+# GPU上TensorRT推理
+./infer_demo FastestDet.onnx 000000014439.jpg 2
+```
+
+运行完成可视化结果如下图所示
+
+
+
+以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
+- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
+
+## FastestDet C++接口
+
+### FastestDet类
+
+```c++
+fastdeploy::vision::detection::FastestDet(
+ const string& model_file,
+ const string& params_file = "",
+ const RuntimeOption& runtime_option = RuntimeOption(),
+ const ModelFormat& model_format = ModelFormat::ONNX)
+```
+
+FastestDet模型加载和初始化，其中model_file为导出的ONNX模型格式。
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为ONNX格式
+
+#### Predict函数
+
+> ```c++
+> FastestDet::Predict(cv::Mat* im, DetectionResult* result,
+> float conf_threshold = 0.65,
+> float nms_iou_threshold = 0.45)
+> ```
+>
+> 模型预测接口，输入图像直接输出检测结果。
+>
+> **参数**
+>
+> > * **im**: 输入图像，注意需为HWC，BGR格式
+> > * **result**: 检测结果，包括检测框，各个框的置信度, DetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > * **conf_threshold**: 检测框置信度过滤阈值
+> > * **nms_iou_threshold**: NMS处理过程中iou阈值
+
+### 类成员变量
+#### 预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> > * **size**(vector<int>): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[352, 352]
+
+- [模型介绍](../../)
+- [Python部署](../python)
+- [视觉模型预测结果](../../../../../docs/api/vision_results/)
+- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/fastestdet/python/README.md b/examples/vision/detection/fastestdet/python/README.md
index 000bf05cc6..492683ec72 100644
--- a/examples/vision/detection/fastestdet/python/README.md
+++ b/examples/vision/detection/fastestdet/python/README.md
@@ -1,74 +1,75 @@
-# FastestDet Python部署示例
+English | [简体中文](README_CN.md)
+# FastestDet Python Deployment Example
-在部署前，需确认以下两个步骤
+Before deployment, two steps require confirmation
-- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. Install FastDeploy Python whl package. Refer to [FastDeploy Python Installation](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-本目录下提供`infer.py`快速完成FastestDet在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+This directory provides examples that `infer.py` fast finishes the deployment of FastestDet on CPU/GPU and GPU accelerated by TensorRT. The script is as follows
```bash
-#下载部署示例代码
+# Download the example code for deployment
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision/detection/fastestdet/python/
-#下载fastestdet模型文件和测试图片
+# Download fastestdet model files and test images
wget https://bj.bcebos.com/paddlehub/fastdeploy/FastestDet.onnx
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
-# CPU推理
+# CPU inference
python infer.py --model FastestDet.onnx --image 000000014439.jpg --device cpu
-# GPU推理
+# GPU inference
python infer.py --model FastestDet.onnx --image 000000014439.jpg --device gpu
-# GPU上使用TensorRT推理
+# TensorRT inference on GPU
python infer.py --model FastestDet.onnx --image 000000014439.jpg --device gpu --use_trt True
```
-运行完成可视化结果如下图所示
+The visualized result after running is as follows
-## FastestDet Python接口
+## FastestDet Python Interface
```python
fastdeploy.vision.detection.FastestDet(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
```
-FastestDet模型加载和初始化，其中model_file为导出的ONNX模型格式
+FastestDet model loading and initialization, among which model_file is the exported ONNX model format
-**参数**
+**Parameter**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为ONNX
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. No need to set when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. ONNX format by default
-### predict函数
+### predict function
> ```python
> FastestDet.predict(image_data)
> ```
>
-> 模型预测接口，输入图像直接输出检测结果。
+> Model prediction interface. Input images and output detection results.
>
-> **参数**
+> **Parameter**
>
-> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
+> > * **image_data**(np.ndarray): Input data in HWC or BGR format
-> **返回**
+> **Return**
>
-> > 返回`fastdeploy.vision.DetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > Return `fastdeploy.vision.DetectionResult` structure. Refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for its structure
-### 类成员属性
-#### 预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+### Class Member Property
+#### Pre-processing Parameter
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
-> > * **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[352, 352]
+> > * **size**(list[int]): This parameter changes the size of the resize used during preprocessing, containing two integer elements for [width, height] with default value [352, 352]
-## 其它文档
+## Other Documents
-- [FastestDet 模型介绍](..)
-- [FastestDet C++部署](../cpp)
-- [模型预测结果说明](../../../../../docs/api/vision_results/)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+- [FastestDet Model Description](..)
+- [FastestDet C++ Deployment](../cpp)
+- [Model Prediction Results](../../../../../docs/api/vision_results/)
+- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/fastestdet/python/README_CN.md b/examples/vision/detection/fastestdet/python/README_CN.md
new file mode 100644
index 0000000000..dce8e469fb
--- /dev/null
+++ b/examples/vision/detection/fastestdet/python/README_CN.md
@@ -0,0 +1,75 @@
+[English](README.md) | 简体中文
+# FastestDet Python部署示例
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+本目录下提供`infer.py`快速完成FastestDet在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+
+```bash
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd examples/vision/detection/fastestdet/python/
+
+#下载fastestdet模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/FastestDet.onnx
+wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
+
+# CPU推理
+python infer.py --model FastestDet.onnx --image 000000014439.jpg --device cpu
+# GPU推理
+python infer.py --model FastestDet.onnx --image 000000014439.jpg --device gpu
+# GPU上使用TensorRT推理
+python infer.py --model FastestDet.onnx --image 000000014439.jpg --device gpu --use_trt True
+```
+
+运行完成可视化结果如下图所示
+
+
+
+## FastestDet Python接口
+
+```python
+fastdeploy.vision.detection.FastestDet(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
+```
+
+FastestDet模型加载和初始化，其中model_file为导出的ONNX模型格式
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为ONNX
+
+### predict函数
+
+> ```python
+> FastestDet.predict(image_data)
+> ```
+>
+> 模型预测接口，输入图像直接输出检测结果。
+>
+> **参数**
+>
+> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
+
+> **返回**
+>
+> > 返回`fastdeploy.vision.DetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+
+### 类成员属性
+#### 预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> > * **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[352, 352]
+
+
+## 其它文档
+
+- [FastestDet 模型介绍](..)
+- [FastestDet C++部署](../cpp)
+- [模型预测结果说明](../../../../../docs/api/vision_results/)
+- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/nanodet_plus/README.md b/examples/vision/detection/nanodet_plus/README.md
index 883164a3a0..bc5b31f756 100644
--- a/examples/vision/detection/nanodet_plus/README.md
+++ b/examples/vision/detection/nanodet_plus/README.md
@@ -1,26 +1,27 @@
-# NanoDetPlus准备部署模型
+English | [简体中文](README_CN.md)
+# NanoDetPlus Ready-to-deploy Model
-- NanoDetPlus部署实现来自[NanoDetPlus](https://github.com/RangiLyu/nanodet/tree/v1.0.0-alpha-1) 的代码，基于coco的[预训练模型](https://github.com/RangiLyu/nanodet/releases/tag/v1.0.0-alpha-1)。
+- NanoDetPlus deployment is based on the code of [NanoDetPlus](https://github.com/RangiLyu/nanodet/tree/v1.0.0-alpha-1) and coco's [Pre-trained Model](https://github.com/RangiLyu/nanodet/releases/tag/v1.0.0-alpha-1).
- - （1）[官方库](https://github.com/RangiLyu/nanodet/releases/tag/v1.0.0-alpha-1)提供的*.onnx可直接进行部署；
- - （2）开发者自己训练的模型，导出ONNX模型后，参考[详细部署文档](#详细部署文档)完成部署。
+ - （1）The *.onnx provided by [official repository](https://github.com/RangiLyu/nanodet/releases/tag/v1.0.0-alpha-1) can directly conduct the deployment；
+ - （2）Models trained by developers should export ONNX models. Please refer to [Detailed Deployment Documents](#详细部署文档) for deployment.
-## 下载预训练ONNX模型
+## Download Pre-trained ONNX Model
-为了方便开发者的测试，下面提供了NanoDetPlus导出的各系列模型，开发者可直接下载使用。（下表中模型的精度来源于源官方库）
-| 模型 | 大小 | 精度 |
+For developers' testing, models exported by NanoDetPlus are provided below. Developers can download them directly. (The model accuracy in the following table is derived from the source official repository)
+| Model | Size | Accuracy |
|:---------------------------------------------------------------- |:----- |:----- |
| [NanoDetPlus_320](https://bj.bcebos.com/paddlehub/fastdeploy/nanodet-plus-m_320.onnx ) | 4.6MB | 27.0% |
| [NanoDetPlus_320_sim](https://bj.bcebos.com/paddlehub/fastdeploy/nanodet-plus-m_320-sim.onnx) | 4.6MB | 27.0% |
-## 详细部署文档
+## Detailed Deployment Documents
-- [Python部署](python)
-- [C++部署](cpp)
+- [Python Deployment](python)
+- [C++ Deployment](cpp)
-## 版本说明
+## Release Note
-- 本版本文档和代码基于[NanoDetPlus v1.0.0-alpha-1](https://github.com/RangiLyu/nanodet/tree/v1.0.0-alpha-1) 编写
+- Document and code are based on [NanoDetPlus v1.0.0-alpha-1](https://github.com/RangiLyu/nanodet/tree/v1.0.0-alpha-1)
diff --git a/examples/vision/detection/nanodet_plus/README_CN.md b/examples/vision/detection/nanodet_plus/README_CN.md
new file mode 100644
index 0000000000..acc87b05e3
--- /dev/null
+++ b/examples/vision/detection/nanodet_plus/README_CN.md
@@ -0,0 +1,27 @@
+[English](README.md) | 简体中文
+# NanoDetPlus准备部署模型
+
+
+- NanoDetPlus部署实现来自[NanoDetPlus](https://github.com/RangiLyu/nanodet/tree/v1.0.0-alpha-1) 的代码，基于coco的[预训练模型](https://github.com/RangiLyu/nanodet/releases/tag/v1.0.0-alpha-1)。
+
+ - （1）[官方库](https://github.com/RangiLyu/nanodet/releases/tag/v1.0.0-alpha-1)提供的*.onnx可直接进行部署；
+ - （2）开发者自己训练的模型，导出ONNX模型后，参考[详细部署文档](#详细部署文档)完成部署。
+
+## 下载预训练ONNX模型
+
+为了方便开发者的测试，下面提供了NanoDetPlus导出的各系列模型，开发者可直接下载使用。（下表中模型的精度来源于源官方库）
+| 模型 | 大小 | 精度 |
+|:---------------------------------------------------------------- |:----- |:----- |
+| [NanoDetPlus_320](https://bj.bcebos.com/paddlehub/fastdeploy/nanodet-plus-m_320.onnx ) | 4.6MB | 27.0% |
+| [NanoDetPlus_320_sim](https://bj.bcebos.com/paddlehub/fastdeploy/nanodet-plus-m_320-sim.onnx) | 4.6MB | 27.0% |
+
+
+## 详细部署文档
+
+- [Python部署](python)
+- [C++部署](cpp)
+
+
+## 版本说明
+
+- 本版本文档和代码基于[NanoDetPlus v1.0.0-alpha-1](https://github.com/RangiLyu/nanodet/tree/v1.0.0-alpha-1) 编写
diff --git a/examples/vision/detection/nanodet_plus/cpp/README.md b/examples/vision/detection/nanodet_plus/cpp/README.md
index bf980355d4..8ef4b6a97e 100644
--- a/examples/vision/detection/nanodet_plus/cpp/README.md
+++ b/examples/vision/detection/nanodet_plus/cpp/README.md
@@ -1,46 +1,47 @@
-# NanoDetPlus C++部署示例
+English | [简体中文](README_CN.md)
+# NanoDetPlus C++ Deployment Example
-本目录下提供`infer.cc`快速完成NanoDetPlus在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+This directory provides examples that `infer.cc` fast finishes the deployment of NanoDetPlus on CPU/GPU and GPU accelerated by TensorRT.
-在部署前，需确认以下两个步骤
+Before deployment, two steps require confirmation
-- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. Download the precompiled deployment library and samples code according to your development environment. Refer to [FastDeploy Precompiled Library](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试，支持此模型需保证FastDeploy版本0.7.0以上(x.x.x>=0.7.0)
+Taking the CPU inference on Linux as an example, the compilation test can be completed by executing the following command in this directory. FastDeploy version 0.7.0 or above (x.x.x>=0.7.0) is required to support this model.
```bash
mkdir build
cd build
-# 下载FastDeploy预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
+# Download the FastDeploy precompiled library. Users can choose your appropriate version in the `FastDeploy Precompiled Library` mentioned above
wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz
tar xvf fastdeploy-linux-x64-x.x.x.tgz
cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x
make -j
-#下载官方转换好的NanoDetPlus模型文件和测试图片
+# Download the official converted NanoDetPlus model files and test images
wget https://bj.bcebos.com/paddlehub/fastdeploy/nanodet-plus-m_320.onnx
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
-# CPU推理
+# CPU inference
./infer_demo nanodet-plus-m_320.onnx 000000014439.jpg 0
-# GPU推理
+# GPU inference
./infer_demo nanodet-plus-m_320.onnx 000000014439.jpg 1
-# GPU上TensorRT推理
+# TensorRT inference on GPU
./infer_demo nanodet-plus-m_320.onnx 000000014439.jpg 2
```
-运行完成可视化结果如下图所示
+The visualized result after running is as follows
-以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
-- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
+The above command works for Linux or MacOS. For SDK use-pattern in Windows, refer to:
+- [How to use FastDeploy C++ SDK in Windows](../../../../../docs/cn/faq/use_sdk_on_windows.md)
-## NanoDetPlus C++接口
+## NanoDetPlus C++ Interface
-### NanoDetPlus类
+### NanoDetPlus Class
```c++
fastdeploy::vision::detection::NanoDetPlus(
@@ -50,16 +51,16 @@ fastdeploy::vision::detection::NanoDetPlus(
const ModelFormat& model_format = ModelFormat::ONNX)
```
-NanoDetPlus模型加载和初始化，其中model_file为导出的ONNX模型格式。
+NanoDetPlus model loading and initialization, among which model_file is the exported ONNX model format
-**参数**
+**Parameter**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为ONNX格式
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. Merely passing an empty string when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. ONNX format by default
-#### Predict函数
+#### Predict Function
> ```c++
> NanoDetPlus::Predict(cv::Mat* im, DetectionResult* result,
@@ -67,27 +68,27 @@ NanoDetPlus模型加载和初始化，其中model_file为导出的ONNX模型格
> float nms_iou_threshold = 0.5)
> ```
>
-> 模型预测接口，输入图像直接输出检测结果。
+> Model prediction interface. Input images and output detection results.
>
-> **参数**
+> **Parameter**
>
-> > * **im**: 输入图像，注意需为HWC，BGR格式
-> > * **result**: 检测结果，包括检测框，各个框的置信度, DetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
-> > * **conf_threshold**: 检测框置信度过滤阈值
-> > * **nms_iou_threshold**: NMS处理过程中iou阈值
-
-### 类成员变量
-
-#### 预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
-
-> > * **size**(vector<int>): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[320, 320]
-> > * **padding_value**(vector<float>): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[0, 0, 0]
-> > * **keep_ratio**(bool): 通过此参数指定resize时是否保持宽高比例不变，默认是fasle.
-> > * **reg_max**(int): GFL回归中的reg_max参数，默认是7.
-> > * **downsample_strides**(vector<int>): 通过此参数可以修改生成anchor的特征图的下采样倍数, 包含三个整型元素, 分别表示默认的生成anchor的下采样倍数, 默认值为[8, 16, 32, 64]
-
-- [模型介绍](../../)
-- [Python部署](../python)
-- [视觉模型预测结果](../../../../../docs/api/vision_results/)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+> > * **im**: Input images in HWC or BGR format
+> > * **result**: Detection results, including detection box and confidence of each box. Refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for DetectionResult
+> > * **conf_threshold**: Filtering threshold of detection box confidence
+> > * **nms_iou_threshold**: iou threshold during NMS processing
+
+### Class Member Variable
+
+#### Pre-processing Parameter
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
+
+> > * **size**(vector<int>): This parameter changes the size of the resize used during preprocessing, containing two integer elements for [width, height] with default value [320, 320]
+> > * **padding_value**(vector<float>): This parameter is used to change the padding value of images during resize, containing three floating-point elements that represent the value of three channels. Default value [0, 0, 0]
+> > * **keep_ratio**(bool): Whether to keep the aspect ratio unchanged during resize. Default fasle
+> > * **reg_max**(int): The reg_max parameter in GFL regression. Default 7
+> > * **downsample_strides**(vector<int>): This parameter is used to change the down-sampling multiple of the feature map that generates anchor, containing three integer elements that represent the default down-sampling multiple for generating anchor. Default value [8, 16, 32, 64]
+
+- [Model Description](../../)
+- [Python Deployment](../python)
+- [Vision Model Prediction Results](../../../../../docs/api/vision_results/)
+- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/nanodet_plus/cpp/README_CN.md b/examples/vision/detection/nanodet_plus/cpp/README_CN.md
new file mode 100644
index 0000000000..b8210fb175
--- /dev/null
+++ b/examples/vision/detection/nanodet_plus/cpp/README_CN.md
@@ -0,0 +1,94 @@
+[English](README.md) | 简体中文
+# NanoDetPlus C++部署示例
+
+本目录下提供`infer.cc`快速完成NanoDetPlus在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试，支持此模型需保证FastDeploy版本0.7.0以上(x.x.x>=0.7.0)
+
+```bash
+mkdir build
+cd build
+# 下载FastDeploy预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz
+tar xvf fastdeploy-linux-x64-x.x.x.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x
+make -j
+
+#下载官方转换好的NanoDetPlus模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/nanodet-plus-m_320.onnx
+wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
+
+
+# CPU推理
+./infer_demo nanodet-plus-m_320.onnx 000000014439.jpg 0
+# GPU推理
+./infer_demo nanodet-plus-m_320.onnx 000000014439.jpg 1
+# GPU上TensorRT推理
+./infer_demo nanodet-plus-m_320.onnx 000000014439.jpg 2
+```
+
+运行完成可视化结果如下图所示
+
+
+
+以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
+- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
+
+## NanoDetPlus C++接口
+
+### NanoDetPlus类
+
+```c++
+fastdeploy::vision::detection::NanoDetPlus(
+ const string& model_file,
+ const string& params_file = "",
+ const RuntimeOption& runtime_option = RuntimeOption(),
+ const ModelFormat& model_format = ModelFormat::ONNX)
+```
+
+NanoDetPlus模型加载和初始化，其中model_file为导出的ONNX模型格式。
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为ONNX格式
+
+#### Predict函数
+
+> ```c++
+> NanoDetPlus::Predict(cv::Mat* im, DetectionResult* result,
+> float conf_threshold = 0.25,
+> float nms_iou_threshold = 0.5)
+> ```
+>
+> 模型预测接口，输入图像直接输出检测结果。
+>
+> **参数**
+>
+> > * **im**: 输入图像，注意需为HWC，BGR格式
+> > * **result**: 检测结果，包括检测框，各个框的置信度, DetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > * **conf_threshold**: 检测框置信度过滤阈值
+> > * **nms_iou_threshold**: NMS处理过程中iou阈值
+
+### 类成员变量
+
+#### 预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> > * **size**(vector<int>): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[320, 320]
+> > * **padding_value**(vector<float>): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[0, 0, 0]
+> > * **keep_ratio**(bool): 通过此参数指定resize时是否保持宽高比例不变，默认是fasle.
+> > * **reg_max**(int): GFL回归中的reg_max参数，默认是7.
+> > * **downsample_strides**(vector<int>): 通过此参数可以修改生成anchor的特征图的下采样倍数, 包含三个整型元素, 分别表示默认的生成anchor的下采样倍数, 默认值为[8, 16, 32, 64]
+
+- [模型介绍](../../)
+- [Python部署](../python)
+- [视觉模型预测结果](../../../../../docs/api/vision_results/)
+- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/nanodet_plus/python/README.md b/examples/vision/detection/nanodet_plus/python/README.md
index a89e15d1b1..2995cb2977 100644
--- a/examples/vision/detection/nanodet_plus/python/README.md
+++ b/examples/vision/detection/nanodet_plus/python/README.md
@@ -1,81 +1,81 @@
-# NanoDetPlus Python部署示例
+English | [简体中文](README_CN.md)
+# NanoDetPlus Python Deployment Example
-在部署前，需确认以下两个步骤
+Before deployment, two steps require confirmation
-- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-
-本目录下提供`infer.py`快速完成NanoDetPlus在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. Install FastDeploy Python whl package. Refer to [FastDeploy Python Installation](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+This directory provides examples that `infer.py` fast finishes the deployment of NanoDetPlus on CPU/GPU and GPU accelerated by TensorRT. The script is as follows
```bash
-#下载部署示例代码
+# Download the example code for deployment
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision/detection/nanodet_plus/python/
-#下载NanoDetPlus模型文件和测试图片
+# Download NanoDetPlus model files and test images
wget https://bj.bcebos.com/paddlehub/fastdeploy/nanodet-plus-m_320.onnx
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
-# CPU推理
+# CPU inference
python infer.py --model nanodet-plus-m_320.onnx --image 000000014439.jpg --device cpu
-# GPU推理
+# GPU inference
python infer.py --model nanodet-plus-m_320.onnx --image 000000014439.jpg --device gpu
-# GPU上使用TensorRT推理
+# TensorRT inference on GPU
python infer.py --model nanodet-plus-m_320.onnx --image 000000014439.jpg --device gpu --use_trt True
```
-运行完成可视化结果如下图所示
+The visualized result after running is as follows
-## NanoDetPlus Python接口
+## NanoDetPlus Python Interface
```python
fastdeploy.vision.detection.NanoDetPlus(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
```
-NanoDetPlus模型加载和初始化，其中model_file为导出的ONNX模型格式
+NanoDetPlus model loading and initialization, among which model_file is the exported ONNX model format
-**参数**
+**Parameter**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为ONNX
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. No need to set when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. ONNX format by default
-### predict函数
+### predict function
> ```python
> NanoDetPlus.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
> ```
>
-> 模型预测结口，输入图像直接输出检测结果。
+> Model prediction interface. Input images and output detection results.
>
-> **参数**
+> **Parameter**
>
-> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
-> > * **conf_threshold**(float): 检测框置信度过滤阈值
-> > * **nms_iou_threshold**(float): NMS处理过程中iou阈值
+> > * **image_data**(np.ndarray): Input data in HWC or BGR format
+> > * **conf_threshold**(float): Filtering threshold of detection box confidence
+> > * **nms_iou_threshold**(float): iou threshold during NMS processing
-> **返回**
+> **Return**
>
-> > 返回`fastdeploy.vision.DetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > Return `fastdeploy.vision.DetectionResult` structure. Refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for its description.
-### 类成员属性
-#### 预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+### Class Member Property
+#### Pre-processing Parameter
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
-> > * **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[320, 320]
-> > * **padding_value**(list[float]): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[0, 0, 0]
-> > * **keep_ratio**(bool): 通过此参数指定resize时是否保持宽高比例不变，默认是fasle.
-> > * **reg_max**(int): GFL回归中的reg_max参数，默认是7.
-> > * **downsample_strides**(list[int]): 通过此参数可以修改生成anchor的特征图的下采样倍数, 包含四个整型元素, 分别表示默认的生成anchor的下采样倍数, 默认值为[8, 16, 32, 64]
+> > * **size**(list[int]): This parameter changes the size of the resize used during preprocessing, containing two integer elements for [width, height] with default value [320, 320]
+> > * **padding_value**(list[float]): This parameter is used to change the padding value of images during resize, containing three floating-point elements that represent the value of three channels. Default value [0, 0, 0]
+> > * **keep_ratio**(bool): Whether to keep the aspect ratio unchanged during resize. Default false
+> > * **reg_max**(int): The reg_max parameter in GFL regression. Default 7.
+> > * **downsample_strides**(list[int]): This parameter is used to change the down-sampling multiple of the feature map that generates anchor, containing four integer elements that represent the default down-sampling multiple for generating anchor. Default [8, 16, 32, 64]
-## 其它文档
+## Other Documents
-- [NanoDetPlus 模型介绍](..)
-- [NanoDetPlus C++部署](../cpp)
-- [模型预测结果说明](../../../../../docs/api/vision_results/)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+- [NanoDetPlus Model Description](..)
+- [NanoDetPlus C++ Deployment](../cpp)
+- [Model Prediction Results](../../../../../docs/api/vision_results/)
+- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/nanodet_plus/python/README_CN.md b/examples/vision/detection/nanodet_plus/python/README_CN.md
new file mode 100644
index 0000000000..63e5a14824
--- /dev/null
+++ b/examples/vision/detection/nanodet_plus/python/README_CN.md
@@ -0,0 +1,82 @@
+[English](README.md) | 简体中文
+# NanoDetPlus Python部署示例
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+本目录下提供`infer.py`快速完成NanoDetPlus在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+
+```bash
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd examples/vision/detection/nanodet_plus/python/
+
+#下载NanoDetPlus模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/nanodet-plus-m_320.onnx
+wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
+
+# CPU推理
+python infer.py --model nanodet-plus-m_320.onnx --image 000000014439.jpg --device cpu
+# GPU推理
+python infer.py --model nanodet-plus-m_320.onnx --image 000000014439.jpg --device gpu
+# GPU上使用TensorRT推理
+python infer.py --model nanodet-plus-m_320.onnx --image 000000014439.jpg --device gpu --use_trt True
+```
+
+运行完成可视化结果如下图所示
+
+
+
+## NanoDetPlus Python接口
+
+```python
+fastdeploy.vision.detection.NanoDetPlus(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
+```
+
+NanoDetPlus模型加载和初始化，其中model_file为导出的ONNX模型格式
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为ONNX
+
+### predict函数
+
+> ```python
+> NanoDetPlus.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
+> ```
+>
+> 模型预测结口，输入图像直接输出检测结果。
+>
+> **参数**
+>
+> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
+> > * **conf_threshold**(float): 检测框置信度过滤阈值
+> > * **nms_iou_threshold**(float): NMS处理过程中iou阈值
+
+> **返回**
+>
+> > 返回`fastdeploy.vision.DetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+
+### 类成员属性
+#### 预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> > * **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[320, 320]
+> > * **padding_value**(list[float]): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[0, 0, 0]
+> > * **keep_ratio**(bool): 通过此参数指定resize时是否保持宽高比例不变，默认是fasle.
+> > * **reg_max**(int): GFL回归中的reg_max参数，默认是7.
+> > * **downsample_strides**(list[int]): 通过此参数可以修改生成anchor的特征图的下采样倍数, 包含四个整型元素, 分别表示默认的生成anchor的下采样倍数, 默认值为[8, 16, 32, 64]
+
+
+
+## 其它文档
+
+- [NanoDetPlus 模型介绍](..)
+- [NanoDetPlus C++部署](../cpp)
+- [模型预测结果说明](../../../../../docs/api/vision_results/)
+- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/paddledetection/README.md b/examples/vision/detection/paddledetection/README.md
index 11b616ba90..0fdcd24b95 100644
--- a/examples/vision/detection/paddledetection/README.md
+++ b/examples/vision/detection/paddledetection/README.md
@@ -1,65 +1,56 @@
-# PaddleDetection模型部署
+English | [简体中文](README_CN.md)
+# PaddleDetection Model Deployment
-## 模型版本说明
+## Model Description
- [PaddleDetection Release/2.4](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4)
-## 支持模型列表
+## List of Supported Models
-目前FastDeploy支持如下模型的部署
+Now FastDeploy supports the deployment of the following models
-- [PP-YOLOE(含PP-YOLOE+)系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/ppyoloe)
-- [PicoDet系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/picodet)
-- [PP-YOLO系列模型(含v2)](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/ppyolo)
-- [YOLOv3系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/yolov3)
-- [YOLOX系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/yolox)
-- [FasterRCNN系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/faster_rcnn)
-- [MaskRCNN系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/mask_rcnn)
-- [SSD系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/ssd)
-- [YOLOv5系列模型](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5)
-- [YOLOv6系列模型](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov6)
-- [YOLOv7系列模型](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov7)
-- [RTMDet系列模型](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/rtmdet)
-- [CascadeRCNN系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/cascade_rcnn)
-- [PSSDet系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/rcnn_enhance)
-- [RetinaNet系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/retinanet)
-- [PPYOLOESOD系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/smalldet)
-- [FCOS系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/fcos)
-- [TTFNet系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/ttfnet)
-- [TOOD系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/tood)
-- [GFL系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/gfl)
+- [PP-YOLOE(including PP-YOLOE+) models](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/ppyoloe)
+- [PicoDet models](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/picodet)
+- [PP-YOLO models(including v2)](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/ppyolo)
+- [YOLOv3 models](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/yolov3)
+- [YOLOX models](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/yolox)
+- [FasterRCNN models](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/faster_rcnn)
+- [MaskRCNN models](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/mask_rcnn)
+- [SSD models](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/ssd)
+- [YOLOv5 models](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5)
+- [YOLOv6 models](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov6)
+- [YOLOv7 models](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov7)
+- [RTMDet models](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/rtmdet)
+## Export Deployment Model
-## 导出部署模型
+Before deployment, PaddleDetection needs to be exported into the deployment model. Refer to [Export Models](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.4/deploy/EXPORT_MODEL.md) for more details.
-在部署前，需要先将PaddleDetection导出成部署模型，导出步骤参考文档[导出模型](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.4/deploy/EXPORT_MODEL.md)
+**Attention**
+- Do not perform NMS removal when exporting the model
+- If you are running a native TensorRT backend (not a Paddle Inference backend), do not add the --trt parameter
+- Do not add the parameter `fuse_normalize=True` when exporting the model
-**注意**
-- 在导出模型时不要进行NMS的去除操作，正常导出即可
-- 如果用于跑原生TensorRT后端（非Paddle Inference后端），不要添加--trt参数
-- 导出模型时，不要添加`fuse_normalize=True`参数
+## Download Pre-trained Model
-## 下载预训练模型
+For developers' testing, models exported by PaddleDetection are provided below. Developers can download them directly.
-为了方便开发者的测试，下面提供了PaddleDetection导出的各系列模型，开发者可直接下载使用。
+The accuracy metric is from model descriptions in PaddleDetection. Refer to them for details.
-其中精度指标来源于PaddleDetection中对各模型的介绍，详情各参考PaddleDetection中的说明。
-
-
-| 模型 | 参数大小 | 精度 | 备注 |
+| Model | Parameter Size | Accuracy | Note |
|:---------------------------------------------------------------- |:----- |:----- | :------ |
| [picodet_l_320_coco_lcnet](https://bj.bcebos.com/paddlehub/fastdeploy/picodet_l_320_coco_lcnet.tgz) |23MB | Box AP 42.6% |
| [ppyoloe_crn_l_300e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/ppyoloe_crn_l_300e_coco.tgz) |200MB | Box AP 51.4% |
| [ppyoloe_plus_crn_m_80e_coco](https://bj.bcebos.com/fastdeploy/models/ppyoloe_plus_crn_m_80e_coco.tgz) |83.3MB | Box AP 49.8% |
-| [ppyolo_r50vd_dcn_1x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/ppyolo_r50vd_dcn_1x_coco.tgz) | 180MB | Box AP 44.8% | 暂不支持TensorRT |
-| [ppyolov2_r101vd_dcn_365e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/ppyolov2_r101vd_dcn_365e_coco.tgz) | 282MB | Box AP 49.7% | 暂不支持TensorRT |
+| [ppyolo_r50vd_dcn_1x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/ppyolo_r50vd_dcn_1x_coco.tgz) | 180MB | Box AP 44.8% | TensorRT not supported yet |
+| [ppyolov2_r101vd_dcn_365e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/ppyolov2_r101vd_dcn_365e_coco.tgz) | 282MB | Box AP 49.7% | TensorRT not supported yet |
| [yolov3_darknet53_270e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/yolov3_darknet53_270e_coco.tgz) |237MB | Box AP 39.1% | |
| [yolox_s_300e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/yolox_s_300e_coco.tgz) | 35MB | Box AP 40.4% | |
-| [faster_rcnn_r50_vd_fpn_2x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/faster_rcnn_r50_vd_fpn_2x_coco.tgz) | 160MB | Box AP 40.8%| 暂不支持TensorRT |
-| [mask_rcnn_r50_1x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/mask_rcnn_r50_1x_coco.tgz) | 128M | Box AP 37.4%, Mask AP 32.8%| 暂不支持TensorRT、ORT |
-| [ssd_mobilenet_v1_300_120e_voc](https://bj.bcebos.com/paddlehub/fastdeploy/ssd_mobilenet_v1_300_120e_voc.tgz) | 24.9M | Box AP 73.8%| 暂不支持TensorRT、ORT |
-| [ssd_vgg16_300_240e_voc](https://bj.bcebos.com/paddlehub/fastdeploy/ssd_vgg16_300_240e_voc.tgz) | 106.5M | Box AP 77.8%| 暂不支持TensorRT、ORT |
-| [ssdlite_mobilenet_v1_300_coco](https://bj.bcebos.com/paddlehub/fastdeploy/ssdlite_mobilenet_v1_300_coco.tgz) | 29.1M | | 暂不支持TensorRT、ORT |
+| [faster_rcnn_r50_vd_fpn_2x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/faster_rcnn_r50_vd_fpn_2x_coco.tgz) | 160MB | Box AP 40.8%| TensorRT not supported yet |
+| [mask_rcnn_r50_1x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/mask_rcnn_r50_1x_coco.tgz) | 128M | Box AP 37.4%, Mask AP 32.8%| TensorRT、ORT not supported yet |
+| [ssd_mobilenet_v1_300_120e_voc](https://bj.bcebos.com/paddlehub/fastdeploy/ssd_mobilenet_v1_300_120e_voc.tgz) | 24.9M | Box AP 73.8%| TensorRT、ORT not supported yet |
+| [ssd_vgg16_300_240e_voc](https://bj.bcebos.com/paddlehub/fastdeploy/ssd_vgg16_300_240e_voc.tgz) | 106.5M | Box AP 77.8%| TensorRT、ORT not supported yet |
+| [ssdlite_mobilenet_v1_300_coco](https://bj.bcebos.com/paddlehub/fastdeploy/ssdlite_mobilenet_v1_300_coco.tgz) | 29.1M | | TensorRT、ORT not supported yet|
| [rtmdet_l_300e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/rtmdet_l_300e_coco.tgz) | 224M | Box AP 51.2%| |
| [rtmdet_s_300e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/rtmdet_s_300e_coco.tgz) | 42M | Box AP 44.5%| |
| [yolov5_l_300e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5_l_300e_coco.tgz) | 183M | Box AP 48.9%| |
@@ -68,18 +59,8 @@
| [yolov6_s_400e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6_s_400e_coco.tgz) | 68M | Box AP 43.4%| |
| [yolov7_l_300e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_l_300e_coco.tgz) | 145M | Box AP 51.0%| |
| [yolov7_x_300e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_x_300e_coco.tgz) | 277M | Box AP 53.0%| |
-| [cascade_rcnn_r50_fpn_1x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/cascade_rcnn_r50_fpn_1x_coco.tgz) | 271M | Box AP 41.1%| 暂不支持TensorRT、ORT |
-| [cascade_rcnn_r50_vd_fpn_ssld_2x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/cascade_rcnn_r50_vd_fpn_ssld_2x_coco.tgz) | 271M | Box AP 45.0%| 暂不支持TensorRT、ORT |
-| [faster_rcnn_enhance_3x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/faster_rcnn_enhance_3x_coco.tgz) | 119M | Box AP 41.5%| 暂不支持TensorRT、ORT |
-| [fcos_r50_fpn_1x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/fcos_r50_fpn_1x_coco.tgz) | 129M | Box AP 39.6%| 暂不支持TensorRT |
-| [gfl_r50_fpn_1x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/gfl_r50_fpn_1x_coco.tgz) | 128M | Box AP 41.0%| 暂不支持TensorRT |
-| [ppyoloe_crn_l_80e_sliced_visdrone_640_025](https://bj.bcebos.com/paddlehub/fastdeploy/ppyoloe_crn_l_80e_sliced_visdrone_640_025.tgz) | 200M | Box AP 31.9%| |
-| [retinanet_r101_fpn_2x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/retinanet_r101_fpn_2x_coco.tgz) | 210M | Box AP 40.6%| 暂不支持TensorRT、ORT |
-| [retinanet_r50_fpn_1x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/retinanet_r50_fpn_1x_coco.tgz) | 136M | Box AP 37.5%| 暂不支持TensorRT、ORT |
-| [tood_r50_fpn_1x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/tood_r50_fpn_1x_coco.tgz) | 130M | Box AP 42.5%| 暂不支持TensorRT、ORT |
-| [ttfnet_darknet53_1x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/ttfnet_darknet53_1x_coco.tgz) | 178M | Box AP 33.5%| 暂不支持TensorRT、ORT |
-## 详细部署文档
+## Detailed Deployment Documents
-- [Python部署](python)
-- [C++部署](cpp)
+- [Python Deployment](python)
+- [C++ Deployment](cpp)
diff --git a/examples/vision/detection/paddledetection/README_CN.md b/examples/vision/detection/paddledetection/README_CN.md
new file mode 100644
index 0000000000..f7e78091a0
--- /dev/null
+++ b/examples/vision/detection/paddledetection/README_CN.md
@@ -0,0 +1,86 @@
+[English](README.md) | 简体中文
+# PaddleDetection模型部署
+
+## 模型版本说明
+
+- [PaddleDetection Release/2.4](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4)
+
+## 支持模型列表
+
+目前FastDeploy支持如下模型的部署
+
+- [PP-YOLOE(含PP-YOLOE+)系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/ppyoloe)
+- [PicoDet系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/picodet)
+- [PP-YOLO系列模型(含v2)](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/ppyolo)
+- [YOLOv3系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/yolov3)
+- [YOLOX系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/yolox)
+- [FasterRCNN系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/faster_rcnn)
+- [MaskRCNN系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/mask_rcnn)
+- [SSD系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/ssd)
+- [YOLOv5系列模型](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5)
+- [YOLOv6系列模型](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov6)
+- [YOLOv7系列模型](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov7)
+- [RTMDet系列模型](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/rtmdet)
+- [CascadeRCNN系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/cascade_rcnn)
+- [PSSDet系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/rcnn_enhance)
+- [RetinaNet系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/retinanet)
+- [PPYOLOESOD系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/smalldet)
+- [FCOS系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/fcos)
+- [TTFNet系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/ttfnet)
+- [TOOD系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/tood)
+- [GFL系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/gfl)
+
+
+## 导出部署模型
+
+在部署前，需要先将PaddleDetection导出成部署模型，导出步骤参考文档[导出模型](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.4/deploy/EXPORT_MODEL.md)
+
+**注意**
+- 在导出模型时不要进行NMS的去除操作，正常导出即可
+- 如果用于跑原生TensorRT后端（非Paddle Inference后端），不要添加--trt参数
+- 导出模型时，不要添加`fuse_normalize=True`参数
+
+## 下载预训练模型
+
+为了方便开发者的测试，下面提供了PaddleDetection导出的各系列模型，开发者可直接下载使用。
+
+其中精度指标来源于PaddleDetection中对各模型的介绍，详情各参考PaddleDetection中的说明。
+
+
+| 模型 | 参数大小 | 精度 | 备注 |
+|:---------------------------------------------------------------- |:----- |:----- | :------ |
+| [picodet_l_320_coco_lcnet](https://bj.bcebos.com/paddlehub/fastdeploy/picodet_l_320_coco_lcnet.tgz) |23MB | Box AP 42.6% |
+| [ppyoloe_crn_l_300e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/ppyoloe_crn_l_300e_coco.tgz) |200MB | Box AP 51.4% |
+| [ppyoloe_plus_crn_m_80e_coco](https://bj.bcebos.com/fastdeploy/models/ppyoloe_plus_crn_m_80e_coco.tgz) |83.3MB | Box AP 49.8% |
+| [ppyolo_r50vd_dcn_1x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/ppyolo_r50vd_dcn_1x_coco.tgz) | 180MB | Box AP 44.8% | 暂不支持TensorRT |
+| [ppyolov2_r101vd_dcn_365e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/ppyolov2_r101vd_dcn_365e_coco.tgz) | 282MB | Box AP 49.7% | 暂不支持TensorRT |
+| [yolov3_darknet53_270e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/yolov3_darknet53_270e_coco.tgz) |237MB | Box AP 39.1% | |
+| [yolox_s_300e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/yolox_s_300e_coco.tgz) | 35MB | Box AP 40.4% | |
+| [faster_rcnn_r50_vd_fpn_2x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/faster_rcnn_r50_vd_fpn_2x_coco.tgz) | 160MB | Box AP 40.8%| 暂不支持TensorRT |
+| [mask_rcnn_r50_1x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/mask_rcnn_r50_1x_coco.tgz) | 128M | Box AP 37.4%, Mask AP 32.8%| 暂不支持TensorRT、ORT |
+| [ssd_mobilenet_v1_300_120e_voc](https://bj.bcebos.com/paddlehub/fastdeploy/ssd_mobilenet_v1_300_120e_voc.tgz) | 24.9M | Box AP 73.8%| 暂不支持TensorRT、ORT |
+| [ssd_vgg16_300_240e_voc](https://bj.bcebos.com/paddlehub/fastdeploy/ssd_vgg16_300_240e_voc.tgz) | 106.5M | Box AP 77.8%| 暂不支持TensorRT、ORT |
+| [ssdlite_mobilenet_v1_300_coco](https://bj.bcebos.com/paddlehub/fastdeploy/ssdlite_mobilenet_v1_300_coco.tgz) | 29.1M | | 暂不支持TensorRT、ORT |
+| [rtmdet_l_300e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/rtmdet_l_300e_coco.tgz) | 224M | Box AP 51.2%| |
+| [rtmdet_s_300e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/rtmdet_s_300e_coco.tgz) | 42M | Box AP 44.5%| |
+| [yolov5_l_300e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5_l_300e_coco.tgz) | 183M | Box AP 48.9%| |
+| [yolov5_s_300e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5_s_300e_coco.tgz) | 31M | Box AP 37.6%| |
+| [yolov6_l_300e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6_l_300e_coco.tgz) | 229M | Box AP 51.0%| |
+| [yolov6_s_400e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6_s_400e_coco.tgz) | 68M | Box AP 43.4%| |
+| [yolov7_l_300e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_l_300e_coco.tgz) | 145M | Box AP 51.0%| |
+| [yolov7_x_300e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_x_300e_coco.tgz) | 277M | Box AP 53.0%| |
+| [cascade_rcnn_r50_fpn_1x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/cascade_rcnn_r50_fpn_1x_coco.tgz) | 271M | Box AP 41.1%| 暂不支持TensorRT、ORT |
+| [cascade_rcnn_r50_vd_fpn_ssld_2x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/cascade_rcnn_r50_vd_fpn_ssld_2x_coco.tgz) | 271M | Box AP 45.0%| 暂不支持TensorRT、ORT |
+| [faster_rcnn_enhance_3x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/faster_rcnn_enhance_3x_coco.tgz) | 119M | Box AP 41.5%| 暂不支持TensorRT、ORT |
+| [fcos_r50_fpn_1x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/fcos_r50_fpn_1x_coco.tgz) | 129M | Box AP 39.6%| 暂不支持TensorRT |
+| [gfl_r50_fpn_1x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/gfl_r50_fpn_1x_coco.tgz) | 128M | Box AP 41.0%| 暂不支持TensorRT |
+| [ppyoloe_crn_l_80e_sliced_visdrone_640_025](https://bj.bcebos.com/paddlehub/fastdeploy/ppyoloe_crn_l_80e_sliced_visdrone_640_025.tgz) | 200M | Box AP 31.9%| |
+| [retinanet_r101_fpn_2x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/retinanet_r101_fpn_2x_coco.tgz) | 210M | Box AP 40.6%| 暂不支持TensorRT、ORT |
+| [retinanet_r50_fpn_1x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/retinanet_r50_fpn_1x_coco.tgz) | 136M | Box AP 37.5%| 暂不支持TensorRT、ORT |
+| [tood_r50_fpn_1x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/tood_r50_fpn_1x_coco.tgz) | 130M | Box AP 42.5%| 暂不支持TensorRT、ORT |
+| [ttfnet_darknet53_1x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/ttfnet_darknet53_1x_coco.tgz) | 178M | Box AP 33.5%| 暂不支持TensorRT、ORT |
+
+## 详细部署文档
+
+- [Python部署](python)
+- [C++部署](cpp)
diff --git a/examples/vision/detection/paddledetection/a311d/README.md b/examples/vision/detection/paddledetection/a311d/README.md
index 0619e788a3..916a41cf97 100755
--- a/examples/vision/detection/paddledetection/a311d/README.md
+++ b/examples/vision/detection/paddledetection/a311d/README.md
@@ -1,11 +1,12 @@
-# PP-YOLOE 量化模型在 A311D 上的部署
-目前 FastDeploy 已经支持基于 Paddle Lite 部署 PP-YOLOE 量化模型到 A311D 上。
+English | [简体中文](README_CN.md)
+# Deploy PP-YOLOE Quantification Model on A311D
+Now FastDeploy supports the deployment of PP-YOLOE quantification model to A311D on Paddle Lite.
-模型的量化和量化模型的下载请参考：[模型量化](../quantize/README.md)
+For model quantification and download, refer to [Model Quantification](../quantize/README.md)
-## 详细部署文档
+## Detailed Deployment Tutorials
-在 A311D 上只支持 C++ 的部署。
+Only C++ deployment is supported on A311D
-- [C++部署](cpp)
+- [C++ deployment](cpp)
diff --git a/examples/vision/detection/paddledetection/a311d/README_CN.md b/examples/vision/detection/paddledetection/a311d/README_CN.md
new file mode 100644
index 0000000000..2bb531e531
--- /dev/null
+++ b/examples/vision/detection/paddledetection/a311d/README_CN.md
@@ -0,0 +1,12 @@
+[English](README.md) | 简体中文
+# PP-YOLOE 量化模型在 A311D 上的部署
+目前 FastDeploy 已经支持基于 Paddle Lite 部署 PP-YOLOE 量化模型到 A311D 上。
+
+模型的量化和量化模型的下载请参考：[模型量化](../quantize/README.md)
+
+
+## 详细部署文档
+
+在 A311D 上只支持 C++ 的部署。
+
+- [C++部署](cpp)
diff --git a/examples/vision/detection/paddledetection/android/README.md b/examples/vision/detection/paddledetection/android/README.md
index 3669bc2a43..311a6b06e9 100644
--- a/examples/vision/detection/paddledetection/android/README.md
+++ b/examples/vision/detection/paddledetection/android/README.md
@@ -1,87 +1,88 @@
-# 目标检测 PicoDet Android Demo 使用文档
+English | [简体中文](README_CN.md)
+# Target Detection PicoDet Android Demo Tutorial
-在 Android 上实现实时的目标检测功能，此 Demo 有很好的的易用性和开放性，如在 Demo 中跑自己训练好的模型等。
+Real-time target detection on Android. This Demo is simple to use for everyone. For example, you can run your own trained model in the Demo.
-## 环境准备
+## Prepare the Environment
-1. 在本地环境安装好 Android Studio 工具，详细安装方法请见[Android Stuido 官网](https://developer.android.com/studio)。
-2. 准备一部 Android 手机，并开启 USB 调试模式。开启方法: `手机设置 -> 查找开发者选项 -> 打开开发者选项和 USB 调试模式`
+1. Install Android Studio in your local environment. Refer to [Android Studio Official Website](https://developer.android.com/studio) for detailed tutorial.
+2. Prepare an Android phone and turn on the USB debug mode: `Settings -> Find developer options -> Open developer options and USB debug mode`
-## 部署步骤
+## Deployment Steps
-1. 目标检测 PicoDet Demo 位于 `fastdeploy/examples/vision/detection/paddledetection/android` 目录
-2. 用 Android Studio 打开 paddledetection/android 工程
-3. 手机连接电脑，打开 USB 调试和文件传输模式，并在 Android Studio 上连接自己的手机设备（手机需要开启允许从 USB 安装软件权限）
+1. The target detection PicoDet Demo is located in the `fastdeploy/examples/vision/detection/paddledetection/android` directory
+2. Open paddledetection/android project with Android Studio
+3. Connect the phone to the computer, turn on USB debug mode and file transfer mode, and connect your phone to Android Studio (allow the phone to install software from USB)
| 
| 
|
-### PicoDet Java API 说明
-- 模型初始化 API: 模型初始化API包含两种方式，方式一是通过构造函数直接初始化；方式二是，通过调用init函数，在合适的程序节点进行初始化。PicoDet初始化参数说明如下：
- - modelFile: String, paddle格式的模型文件路径，如 model.pdmodel
- - paramFile: String, paddle格式的参数文件路径，如 model.pdiparams
- - configFile: String, 模型推理的预处理配置文件，如 infer_cfg.yml
- - labelFile: String, 可选参数，表示label标签文件所在路径，用于可视化，如 coco_label_list.txt，每一行包含一个label
- - option: RuntimeOption，可选参数，模型初始化option。如果不传入该参数则会使用默认的运行时选项。
+### PicoDet Java API Description
+- Model initialized API: The initialized API contains two ways: Firstly, initialize directly through the constructor. Secondly, initialize at the appropriate program node by calling the init function. PicoDet initialization parameters are as follows.
+ - modelFile: String. Model file path in paddle format, such as model.pdmodel
+ - paramFile: String. Parameter file path in paddle format, such as model.pdiparams
+ - configFile: String. Preprocessing file for model inference, such as infer_cfg.yml
+ - labelFile: String. This optional parameter indicates the path of the label file and is used for visualization, such as coco_label_list.txt, each line containing one label
+ - option: RuntimeOption. Optional parameter for model initialization. Default runtime options if not passing the parameter.
```java
-// 构造函数: constructor w/o label file
-public PicoDet(); // 空构造函数，之后可以调用init初始化
+// Constructor: constructor w/o label file
+public PicoDet(); // An empty constructor, which can be initialized by calling init
public PicoDet(String modelFile, String paramsFile, String configFile);
public PicoDet(String modelFile, String paramsFile, String configFile, String labelFile);
public PicoDet(String modelFile, String paramsFile, String configFile, RuntimeOption option);
public PicoDet(String modelFile, String paramsFile, String configFile, String labelFile, RuntimeOption option);
-// 手动调用init初始化: call init manually w/o label file
+// Call init manually for initialization: call init manually w/o label file
public boolean init(String modelFile, String paramsFile, String configFile, RuntimeOption option);
public boolean init(String modelFile, String paramsFile, String configFile, String labelFile, RuntimeOption option);
```
-- 模型预测 API：模型预测API包含直接预测的API以及带可视化功能的API。直接预测是指，不保存图片以及不渲染结果到Bitmap上，仅预测推理结果。预测并且可视化是指，预测结果以及可视化，并将可视化后的图片保存到指定的途径，以及将可视化结果渲染在Bitmap(目前支持ARGB8888格式的Bitmap), 后续可将该Bitmap在camera中进行显示。
+- Model Prediction API: The Model Prediction API contains an API for direct prediction and an API for visualization. In direct prediction, we do not save the image and render the result on Bitmap. Instead, we merely predict the inference result. For prediction and visualization, the results are both predicted and visualized, the visualized images are saved to the specified path, and the visualized results are rendered in Bitmap (Now Bitmap in ARGB8888 format is supported). Afterward, the Bitmap can be displayed on the camera.
```java
-// 直接预测：不保存图片以及不渲染结果到Bitmap上
+// Direct prediction: No image saving and no result rendering to Bitmap
public DetectionResult predict(Bitmap ARGB8888Bitmap)；
-// 预测并且可视化：预测结果以及可视化，并将可视化后的图片保存到指定的途径，以及将可视化结果渲染在Bitmap上
+// Prediction and visualization: Predict and visualize the results, save the visualized image to the specified path, and render the visualized results on Bitmap
public DetectionResult predict(Bitmap ARGB8888Bitmap, String savedImagePath, float scoreThreshold);
-public DetectionResult predict(Bitmap ARGB8888Bitmap, boolean rendering, float scoreThreshold); // 只渲染 不保存图片
+public DetectionResult predict(Bitmap ARGB8888Bitmap, boolean rendering, float scoreThreshold); // Render without saving images
```
-- 模型资源释放 API：调用 release() API 可以释放模型资源，返回true表示释放成功，false表示失败；调用 initialized() 可以判断模型是否初始化成功，true表示初始化成功，false表示失败。
+- Model resource release API: Call release() API to release model resources. Return true for successful release and false for failure; call initialized() to determine whether the model was initialized successfully, with true indicating successful initialization and false indicating failure.
```java
-public boolean release(); // 释放native资源
-public boolean initialized(); // 检查是否初始化成功
+public boolean release(); // Release native resources
+public boolean initialized(); // Check if the initialization is successful
```
-- RuntimeOption设置说明
+- RuntimeOption settings
```java
-public void enableLiteFp16(); // 开启fp16精度推理
-public void disableLiteFP16(); // 关闭fp16精度推理
-public void setCpuThreadNum(int threadNum); // 设置线程数
-public void setLitePowerMode(LitePowerMode mode); // 设置能耗模式
-public void setLitePowerMode(String modeStr); // 通过字符串形式设置能耗模式
+public void enableLiteFp16(); // Enable fp16 accuracy inference
+public void disableLiteFP16(); // Disable fp16 accuracy inference
+public void setCpuThreadNum(int threadNum); // Set thread numbers
+public void setLitePowerMode(LitePowerMode mode); // Set power mode
+public void setLitePowerMode(String modeStr); // Set power mode through character string
```
-- 模型结果DetectionResult说明
+- Model DetectionResult
```java
public class DetectionResult {
- public float[][] mBoxes; // [n,4] 检测框 (x1,y1,x2,y2)
- public float[] mScores; // [n] 每个检测框得分(置信度，概率值)
- public int[] mLabelIds; // [n] 分类ID
- public boolean initialized(); // 检测结果是否有效
+ public float[][] mBoxes; // [n,4] Detection box (x1,y1,x2,y2)
+ public float[] mScores; // [n] Score (confidence, probability)
+ public int[] mLabelIds; // [n] Classification ID
+ public boolean initialized(); // Whether the result is valid
}
```
-其他参考：C++/Python对应的DetectionResult说明: [api/vision_results/detection_result.md](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/api/vision_results/detection_result.md)
+Refer to [api/vision_results/detection_result.md](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/api/vision_results/detection_result.md) for C++/Python DetectionResult
-- 模型调用示例1：使用构造函数以及默认的RuntimeOption
+- Model Calling Example 1: Using Constructor and the default RuntimeOption
```java
import java.nio.ByteBuffer;
import android.graphics.Bitmap;
@@ -90,63 +91,63 @@ import android.opengl.GLES20;
import com.baidu.paddle.fastdeploy.vision.DetectionResult;
import com.baidu.paddle.fastdeploy.vision.detection.PicoDet;
-// 初始化模型
+// Initialize the model
PicoDet model = new PicoDet("picodet_s_320_coco_lcnet/model.pdmodel",
"picodet_s_320_coco_lcnet/model.pdiparams",
"picodet_s_320_coco_lcnet/infer_cfg.yml");
-// 读取图片: 以下仅为读取Bitmap的伪代码
+// Read the image: The following is merely the pseudo code to read Bitmap
ByteBuffer pixelBuffer = ByteBuffer.allocate(width * height * 4);
GLES20.glReadPixels(0, 0, width, height, GLES20.GL_RGBA, GLES20.GL_UNSIGNED_BYTE, pixelBuffer);
Bitmap ARGB8888ImageBitmap = Bitmap.createBitmap(width, height, Bitmap.Config.ARGB_8888);
ARGB8888ImageBitmap.copyPixelsFromBuffer(pixelBuffer);
-// 模型推理
+// Model inference
DetectionResult result = model.predict(ARGB8888ImageBitmap);
-// 释放模型资源
+// Release model resources
model.release();
```
-- 模型调用示例2: 在合适的程序节点，手动调用init，并自定义RuntimeOption
+- Model calling example 2: Manually call init at the appropriate program node and self-define RuntimeOption
```java
-// import 同上 ...
+// import is as the above...
import com.baidu.paddle.fastdeploy.RuntimeOption;
import com.baidu.paddle.fastdeploy.LitePowerMode;
import com.baidu.paddle.fastdeploy.vision.DetectionResult;
import com.baidu.paddle.fastdeploy.vision.detection.PicoDet;
-// 新建空模型
+// Create an empty model
PicoDet model = new PicoDet();
-// 模型路径
+// Model path
String modelFile = "picodet_s_320_coco_lcnet/model.pdmodel";
String paramFile = "picodet_s_320_coco_lcnet/model.pdiparams";
String configFile = "picodet_s_320_coco_lcnet/infer_cfg.yml";
-// 指定RuntimeOption
+// Specify RuntimeOption
RuntimeOption option = new RuntimeOption();
option.setCpuThreadNum(2);
option.setLitePowerMode(LitePowerMode.LITE_POWER_HIGH);
option.enableLiteFp16();
-// 使用init函数初始化
+// Use init function for initialization
model.init(modelFile, paramFile, configFile, option);
-// Bitmap读取、模型预测、资源释放 同上 ...
+// Bitmap reading, model prediction, and resource release are as above...
```
-更详细的用法请参考 [DetectionMainActivity](./app/src/main/java/com/baidu/paddle/fastdeploy/app/examples/detection/DetectionMainActivity.java) 中的用法
+Refer to [DetectionMainActivity](./app/src/main/java/com/baidu/paddle/fastdeploy/app/examples/detection/DetectionMainActivity.java) for more information.
-## 替换 FastDeploy SDK和模型
-替换FastDeploy预测库和模型的步骤非常简单。预测库所在的位置为 `app/libs/fastdeploy-android-sdk-xxx.aar`，其中 `xxx` 表示当前您使用的预测库版本号。模型所在的位置为，`app/src/main/assets/models/picodet_s_320_coco_lcnet`。
-- 替换FastDeploy Android SDK: 下载或编译最新的FastDeploy Android SDK，解压缩后放在 `app/libs` 目录下；详细配置文档可参考:
- - [在 Android 中使用 FastDeploy Java SDK](../../../../../java/android/)
+## Replace FastDeploy SDK and Models
+It’s simple to replace the FastDeploy prediction library and models. The prediction library is located at `app/libs/fastdeploy-android-sdk-xxx.aar`, where `xxx` represents the version of your prediction library. The models are located at `app/src/main/assets/models/picodet_s_320_coco_lcnet`.
+- Replace the FastDeploy Android SDK: Download or compile the latest FastDeploy Android SDK, unzip and place it in the `app/libs` directory; For detailed configuration, refer to
+ - [FastDeploy Java SDK in Android](../../../../../java/android/)
-- 替换PicoDet模型的步骤：
- - 将您的PicoDet模型放在 `app/src/main/assets/models` 目录下；
- - 修改 `app/src/main/res/values/strings.xml` 中模型路径的默认值，如：
+- Steps to replace PicoDet models:
+ - Put your PicoDet model in `app/src/main/assets/models`;
+ - Modify the default value of the model path in `app/src/main/res/values/strings.xml`. For example:
```xml
-
+
+
+
| | |
+
+
+### PicoDet Java API 说明
+- 模型初始化 API: 模型初始化API包含两种方式，方式一是通过构造函数直接初始化；方式二是，通过调用init函数，在合适的程序节点进行初始化。PicoDet初始化参数说明如下：
+ - modelFile: String, paddle格式的模型文件路径，如 model.pdmodel
+ - paramFile: String, paddle格式的参数文件路径，如 model.pdiparams
+ - configFile: String, 模型推理的预处理配置文件，如 infer_cfg.yml
+ - labelFile: String, 可选参数，表示label标签文件所在路径，用于可视化，如 coco_label_list.txt，每一行包含一个label
+ - option: RuntimeOption，可选参数，模型初始化option。如果不传入该参数则会使用默认的运行时选项。
+
+```java
+// 构造函数: constructor w/o label file
+public PicoDet(); // 空构造函数，之后可以调用init初始化
+public PicoDet(String modelFile, String paramsFile, String configFile);
+public PicoDet(String modelFile, String paramsFile, String configFile, String labelFile);
+public PicoDet(String modelFile, String paramsFile, String configFile, RuntimeOption option);
+public PicoDet(String modelFile, String paramsFile, String configFile, String labelFile, RuntimeOption option);
+// 手动调用init初始化: call init manually w/o label file
+public boolean init(String modelFile, String paramsFile, String configFile, RuntimeOption option);
+public boolean init(String modelFile, String paramsFile, String configFile, String labelFile, RuntimeOption option);
+```
+- 模型预测 API：模型预测API包含直接预测的API以及带可视化功能的API。直接预测是指，不保存图片以及不渲染结果到Bitmap上，仅预测推理结果。预测并且可视化是指，预测结果以及可视化，并将可视化后的图片保存到指定的途径，以及将可视化结果渲染在Bitmap(目前支持ARGB8888格式的Bitmap), 后续可将该Bitmap在camera中进行显示。
+```java
+// 直接预测：不保存图片以及不渲染结果到Bitmap上
+public DetectionResult predict(Bitmap ARGB8888Bitmap)；
+// 预测并且可视化：预测结果以及可视化，并将可视化后的图片保存到指定的途径，以及将可视化结果渲染在Bitmap上
+public DetectionResult predict(Bitmap ARGB8888Bitmap, String savedImagePath, float scoreThreshold);
+public DetectionResult predict(Bitmap ARGB8888Bitmap, boolean rendering, float scoreThreshold); // 只渲染 不保存图片
+```
+- 模型资源释放 API：调用 release() API 可以释放模型资源，返回true表示释放成功，false表示失败；调用 initialized() 可以判断模型是否初始化成功，true表示初始化成功，false表示失败。
+```java
+public boolean release(); // 释放native资源
+public boolean initialized(); // 检查是否初始化成功
+```
+
+- RuntimeOption设置说明
+```java
+public void enableLiteFp16(); // 开启fp16精度推理
+public void disableLiteFP16(); // 关闭fp16精度推理
+public void setCpuThreadNum(int threadNum); // 设置线程数
+public void setLitePowerMode(LitePowerMode mode); // 设置能耗模式
+public void setLitePowerMode(String modeStr); // 通过字符串形式设置能耗模式
+```
+
+- 模型结果DetectionResult说明
+```java
+public class DetectionResult {
+ public float[][] mBoxes; // [n,4] 检测框 (x1,y1,x2,y2)
+ public float[] mScores; // [n] 每个检测框得分(置信度，概率值)
+ public int[] mLabelIds; // [n] 分类ID
+ public boolean initialized(); // 检测结果是否有效
+}
+```
+其他参考：C++/Python对应的DetectionResult说明: [api/vision_results/detection_result.md](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/api/vision_results/detection_result.md)
+
+- 模型调用示例1：使用构造函数以及默认的RuntimeOption
+```java
+import java.nio.ByteBuffer;
+import android.graphics.Bitmap;
+import android.opengl.GLES20;
+
+import com.baidu.paddle.fastdeploy.vision.DetectionResult;
+import com.baidu.paddle.fastdeploy.vision.detection.PicoDet;
+
+// 初始化模型
+PicoDet model = new PicoDet("picodet_s_320_coco_lcnet/model.pdmodel",
+ "picodet_s_320_coco_lcnet/model.pdiparams",
+ "picodet_s_320_coco_lcnet/infer_cfg.yml");
+
+// 读取图片: 以下仅为读取Bitmap的伪代码
+ByteBuffer pixelBuffer = ByteBuffer.allocate(width * height * 4);
+GLES20.glReadPixels(0, 0, width, height, GLES20.GL_RGBA, GLES20.GL_UNSIGNED_BYTE, pixelBuffer);
+Bitmap ARGB8888ImageBitmap = Bitmap.createBitmap(width, height, Bitmap.Config.ARGB_8888);
+ARGB8888ImageBitmap.copyPixelsFromBuffer(pixelBuffer);
+
+// 模型推理
+DetectionResult result = model.predict(ARGB8888ImageBitmap);
+
+// 释放模型资源
+model.release();
+```
+
+- 模型调用示例2: 在合适的程序节点，手动调用init，并自定义RuntimeOption
+```java
+// import 同上 ...
+import com.baidu.paddle.fastdeploy.RuntimeOption;
+import com.baidu.paddle.fastdeploy.LitePowerMode;
+import com.baidu.paddle.fastdeploy.vision.DetectionResult;
+import com.baidu.paddle.fastdeploy.vision.detection.PicoDet;
+// 新建空模型
+PicoDet model = new PicoDet();
+// 模型路径
+String modelFile = "picodet_s_320_coco_lcnet/model.pdmodel";
+String paramFile = "picodet_s_320_coco_lcnet/model.pdiparams";
+String configFile = "picodet_s_320_coco_lcnet/infer_cfg.yml";
+// 指定RuntimeOption
+RuntimeOption option = new RuntimeOption();
+option.setCpuThreadNum(2);
+option.setLitePowerMode(LitePowerMode.LITE_POWER_HIGH);
+option.enableLiteFp16();
+// 使用init函数初始化
+model.init(modelFile, paramFile, configFile, option);
+// Bitmap读取、模型预测、资源释放 同上 ...
+```
+更详细的用法请参考 [DetectionMainActivity](./app/src/main/java/com/baidu/paddle/fastdeploy/app/examples/detection/DetectionMainActivity.java) 中的用法
+
+## 替换 FastDeploy SDK和模型
+替换FastDeploy预测库和模型的步骤非常简单。预测库所在的位置为 `app/libs/fastdeploy-android-sdk-xxx.aar`，其中 `xxx` 表示当前您使用的预测库版本号。模型所在的位置为，`app/src/main/assets/models/picodet_s_320_coco_lcnet`。
+- 替换FastDeploy Android SDK: 下载或编译最新的FastDeploy Android SDK，解压缩后放在 `app/libs` 目录下；详细配置文档可参考:
+ - [在 Android 中使用 FastDeploy Java SDK](../../../../../java/android/)
+
+- 替换PicoDet模型的步骤：
+ - 将您的PicoDet模型放在 `app/src/main/assets/models` 目录下；
+ - 修改 `app/src/main/res/values/strings.xml` 中模型路径的默认值，如：
+```xml
+
+
+
-以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
-- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
+The above command works for Linux or MacOS. For SDK use-pattern in Windows, refer to:
+- [How to use FastDeploy C++ SDK in Windows](../../../../../docs/cn/faq/use_sdk_on_windows.md)
-## ScaledYOLOv4 C++接口
+## ScaledYOLOv4 C++ Interface
-### ScaledYOLOv4类
+### ScaledYOLOv4 Class
```c++
fastdeploy::vision::detection::ScaledYOLOv4(
@@ -50,16 +51,16 @@ fastdeploy::vision::detection::ScaledYOLOv4(
const ModelFormat& model_format = ModelFormat::ONNX)
```
-ScaledYOLOv4模型加载和初始化，其中model_file为导出的ONNX模型格式。
+ScaledYOLOv4 model loading and initialization, among which model_file is the exported ONNX model format
-**参数**
+**Parameter**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为ONNX格式
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. Merely passing an empty string when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. ONNX format by default
-#### Predict函数
+#### Predict Parameter
> ```c++
> ScaledYOLOv4::Predict(cv::Mat* im, DetectionResult* result,
@@ -67,26 +68,26 @@ ScaledYOLOv4模型加载和初始化，其中model_file为导出的ONNX模型格
> float nms_iou_threshold = 0.5)
> ```
>
-> 模型预测接口，输入图像直接输出检测结果。
+> Model prediction interface. Input images and output detection results.
>
-> **参数**
+> **Parameter**
>
-> > * **im**: 输入图像，注意需为HWC，BGR格式
-> > * **result**: 检测结果，包括检测框，各个框的置信度, DetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
-> > * **conf_threshold**: 检测框置信度过滤阈值
-> > * **nms_iou_threshold**: NMS处理过程中iou阈值
-
-### 类成员变量
-#### 预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
-
-> > * **size**(vector<int>): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
-> > * **padding_value**(vector<float>): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
-> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=ture` 表示不使用填充的方式，默认值为`is_no_pad=false`
-> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=false`
-> > * **stride**(int): 配合`stris_mini_pad`成员变量使用, 默认值为`stride=32`
-
-- [模型介绍](../../)
-- [Python部署](../python)
-- [视觉模型预测结果](../../../../../docs/api/vision_results/)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+> > * **im**: Input images in HWC or BGR format
+> > * **result**: Detection results, including detection box and confidence of each box. Refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for DetectionResult
+> > * **conf_threshold**: Filtering threshold of detection box confidence
+> > * **nms_iou_threshold**: iou threshold during NMS processing
+
+### Class Member Variable
+#### Pre-processing Parameter
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
+
+> > * **size**(vector<int>): This parameter changes the size of the resize used during preprocessing, containing two integer elements for [width, height] with default value [640, 640]
+> > * **padding_value**(vector<float>): This parameter is used to change the padding value of images during resize, containing three floating-point elements that represent the value of three channels. Default value [114, 114, 114]
+> > * **is_no_pad**(bool): Specify whether to resize the image through padding or not. `is_no_pad=ture` represents no paddling. Default `is_no_pad=false`
+> > * **is_mini_pad**(bool): This parameter sets the width and height of the image after resize to the value nearest to the `size` member variable and to the point where the padded pixel size is divisible by the `stride` member variable. Default `is_mini_pad=false`
+> > * **stride**(int): Used with the `stris_mini_pad` member variable. Default `stride=32`
+
+- [Model Description](../../)
+- [Python Deployment](../python)
+- [Vision Model Prediction Results](../../../../../docs/api/vision_results/)
+- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/scaledyolov4/cpp/README_CN.md b/examples/vision/detection/scaledyolov4/cpp/README_CN.md
new file mode 100644
index 0000000000..53fbc412db
--- /dev/null
+++ b/examples/vision/detection/scaledyolov4/cpp/README_CN.md
@@ -0,0 +1,93 @@
+[English](README.md) | 简体中文
+# ScaledYOLOv4 C++部署示例
+
+本目录下提供`infer.cc`快速完成ScaledYOLOv4在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试，支持此模型需保证FastDeploy版本0.7.0以上(x.x.x>=0.7.0)
+
+```bash
+mkdir build
+cd build
+# 下载FastDeploy预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz
+tar xvf fastdeploy-linux-x64-x.x.x.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x
+make -j
+
+#下载官方转换好的ScaledYOLOv4模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/scaled_yolov4-p5.onnx
+wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
+
+
+# CPU推理
+./infer_demo scaled_yolov4-p5.onnx 000000014439.jpg 0
+# GPU推理
+./infer_demo scaled_yolov4-p5.onnx 000000014439.jpg 1
+# GPU上TensorRT推理
+./infer_demo scaled_yolov4-p5.onnx 000000014439.jpg 2
+```
+
+运行完成可视化结果如下图所示
+
+
+
+以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
+- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
+
+## ScaledYOLOv4 C++接口
+
+### ScaledYOLOv4类
+
+```c++
+fastdeploy::vision::detection::ScaledYOLOv4(
+ const string& model_file,
+ const string& params_file = "",
+ const RuntimeOption& runtime_option = RuntimeOption(),
+ const ModelFormat& model_format = ModelFormat::ONNX)
+```
+
+ScaledYOLOv4模型加载和初始化，其中model_file为导出的ONNX模型格式。
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为ONNX格式
+
+#### Predict函数
+
+> ```c++
+> ScaledYOLOv4::Predict(cv::Mat* im, DetectionResult* result,
+> float conf_threshold = 0.25,
+> float nms_iou_threshold = 0.5)
+> ```
+>
+> 模型预测接口，输入图像直接输出检测结果。
+>
+> **参数**
+>
+> > * **im**: 输入图像，注意需为HWC，BGR格式
+> > * **result**: 检测结果，包括检测框，各个框的置信度, DetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > * **conf_threshold**: 检测框置信度过滤阈值
+> > * **nms_iou_threshold**: NMS处理过程中iou阈值
+
+### 类成员变量
+#### 预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> > * **size**(vector<int>): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
+> > * **padding_value**(vector<float>): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
+> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=ture` 表示不使用填充的方式，默认值为`is_no_pad=false`
+> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=false`
+> > * **stride**(int): 配合`stris_mini_pad`成员变量使用, 默认值为`stride=32`
+
+- [模型介绍](../../)
+- [Python部署](../python)
+- [视觉模型预测结果](../../../../../docs/api/vision_results/)
+- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/scaledyolov4/python/README.md b/examples/vision/detection/scaledyolov4/python/README.md
index cb89fdb729..ff67320e39 100644
--- a/examples/vision/detection/scaledyolov4/python/README.md
+++ b/examples/vision/detection/scaledyolov4/python/README.md
@@ -1,84 +1,82 @@
-# ScaledYOLOv4 Python部署示例
+English | [简体中文](README_CN.md)
+# ScaledYOLOv4 Python Deployment Example
-在部署前，需确认以下两个步骤
+Before deployment, two steps require confirmation
-- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-
-本目录下提供`infer.py`快速完成ScaledYOLOv4在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. Install FastDeploy Python whl package. Refer to [FastDeploy Python Installation](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+This directory provides examples that `infer.py` fast finishes the deployment of ScaledYOLOv4 on CPU/GPU and GPU accelerated by TensorRT. The script is as follows
```bash
-#下载部署示例代码
+# Download the example code for deployment
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision/detection/scaledyolov4/python/
-#下载scaledyolov4模型文件和测试图片
+# Download scaledyolov4 model files and test images
wget https://bj.bcebos.com/paddlehub/fastdeploy/scaled_yolov4-p5.onnx
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
-# CPU推理
+# CPU inference
python infer.py --model scaled_yolov4-p5.onnx --image 000000014439.jpg --device cpu
-# GPU推理
+# GPU inference
python infer.py --model scaled_yolov4-p5.onnx --image 000000014439.jpg --device gpu
-# GPU上使用TensorRT推理
+# TensorRT inference on GPU
python infer.py --model scaled_yolov4-p5.onnx --image 000000014439.jpg --device gpu --use_trt True
```
-运行完成可视化结果如下图所示
+The visualized result after running is as follows
-## ScaledYOLOv4 Python接口
+## ScaledYOLOv4 Python Interface
```python
fastdeploy.vision.detection.ScaledYOLOv4(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
```
-ScaledYOLOv4模型加载和初始化，其中model_file为导出的ONNX模型格式
+ScaledYOLOv4 model loading and initialization, among which model_file is the exported ONNX model format
-**参数**
+**Parameter**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为ONNX
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. No need to set when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. ONNX format by default
-### predict函数
+### predict function
> ```python
> ScaledYOLOv4.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
> ```
>
-> 模型预测结口，输入图像直接输出检测结果。
+> Model prediction interface. Input images and output detection results.
>
-> **参数**
+> **Parameter**
>
-> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
-> > * **conf_threshold**(float): 检测框置信度过滤阈值
-> > * **nms_iou_threshold**(float): NMS处理过程中iou阈值
+> > * **image_data**(np.ndarray): Input data in HWC or BGR format
+> > * **conf_threshold**(float): Filtering threshold of detection box confidence
+> > * **nms_iou_threshold**(float): iou threshold during NMS processing
-> **返回**
+> **Return**
>
-> > 返回`fastdeploy.vision.DetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > Return `fastdeploy.vision.DetectionResult` structure. Refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for its description.
-### 类成员属性
-#### 预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+### Class Member Property
-#### 预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+#### Pre-processing Parameter
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
-> > * **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
-> > * **padding_value**(list[float]): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
-> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=True` 表示不使用填充的方式，默认值为`is_no_pad=False`
-> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=False`
-> > * **stride**(int): 配合`stris_mini_padide`成员变量使用, 默认值为`stride=32`
+> > * **size**(list[int]): This parameter changes the size of the resize used during preprocessing, containing two integer elements for [width, height] with default value [640, 640]
+> > * **padding_value**(list[float]): This parameter is used to change the padding value of images during resize, containing three floating-point elements that represent the value of three channels. Default value [114, 114, 114]
+> > * **is_no_pad**(bool): Specify whether to resize the image through padding. `is_no_pad=True` represents no paddling. Default `is_no_pad=False`
+> > * **is_mini_pad**(bool): This parameter sets the width and height of the image after resize to the value nearest to the `size` member variable and to the point where the padded pixel size is divisible by the `stride` member variable. Default `is_mini_pad=False`
+> > * **stride**(int): Used with the `stris_mini_padide` member variable. Default `stride=32`
-## 其它文档
+## Other Documents
-- [ScaledYOLOv4 模型介绍](..)
-- [ScaledYOLOv4 C++部署](../cpp)
-- [模型预测结果说明](../../../../../docs/api/vision_results/)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+- [ScaledYOLOv4 Model Description](..)
+- [ScaledYOLOv4 C++ Deployment](../cpp)
+- [Model Prediction Results](../../../../../docs/api/vision_results/)
+- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/scaledyolov4/python/README_CN.md b/examples/vision/detection/scaledyolov4/python/README_CN.md
new file mode 100644
index 0000000000..2cc4ec0efa
--- /dev/null
+++ b/examples/vision/detection/scaledyolov4/python/README_CN.md
@@ -0,0 +1,85 @@
+[English](README.md) | 简体中文
+# ScaledYOLOv4 Python部署示例
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+本目录下提供`infer.py`快速完成ScaledYOLOv4在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+
+```bash
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd examples/vision/detection/scaledyolov4/python/
+
+#下载scaledyolov4模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/scaled_yolov4-p5.onnx
+wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
+
+# CPU推理
+python infer.py --model scaled_yolov4-p5.onnx --image 000000014439.jpg --device cpu
+# GPU推理
+python infer.py --model scaled_yolov4-p5.onnx --image 000000014439.jpg --device gpu
+# GPU上使用TensorRT推理
+python infer.py --model scaled_yolov4-p5.onnx --image 000000014439.jpg --device gpu --use_trt True
+```
+
+运行完成可视化结果如下图所示
+
+
+
+## ScaledYOLOv4 Python接口
+
+```python
+fastdeploy.vision.detection.ScaledYOLOv4(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
+```
+
+ScaledYOLOv4模型加载和初始化，其中model_file为导出的ONNX模型格式
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为ONNX
+
+### predict函数
+
+> ```python
+> ScaledYOLOv4.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
+> ```
+>
+> 模型预测结口，输入图像直接输出检测结果。
+>
+> **参数**
+>
+> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
+> > * **conf_threshold**(float): 检测框置信度过滤阈值
+> > * **nms_iou_threshold**(float): NMS处理过程中iou阈值
+
+> **返回**
+>
+> > 返回`fastdeploy.vision.DetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+
+### 类成员属性
+#### 预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+#### 预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> > * **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
+> > * **padding_value**(list[float]): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
+> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=True` 表示不使用填充的方式，默认值为`is_no_pad=False`
+> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=False`
+> > * **stride**(int): 配合`stris_mini_padide`成员变量使用, 默认值为`stride=32`
+
+
+
+## 其它文档
+
+- [ScaledYOLOv4 模型介绍](..)
+- [ScaledYOLOv4 C++部署](../cpp)
+- [模型预测结果说明](../../../../../docs/api/vision_results/)
+- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/yolor/README.md b/examples/vision/detection/yolor/README.md
index c9749a0886..f3b966b8b2 100644
--- a/examples/vision/detection/yolor/README.md
+++ b/examples/vision/detection/yolor/README.md
@@ -1,46 +1,47 @@
-# YOLOR准备部署模型
+English | [简体中文](README_CN.md)
+# YOLOR Ready-to-deploy Model
-- YOLOR部署实现来自[YOLOR](https://github.com/WongKinYiu/yolor/releases/tag/weights)的代码，和[基于COCO的预训练模型](https://github.com/WongKinYiu/yolor/releases/tag/weights)。
+- The YOLOR deployment is based on the code of [YOLOR](https://github.com/WongKinYiu/yolor/releases/tag/weights) and [Pre-trained Model Based on COCO](https://github.com/WongKinYiu/yolor/releases/tag/weights).
- - （1）[官方库](https://github.com/WongKinYiu/yolor/releases/tag/weights)提供的*.pt通过[导出ONNX模型](#导出ONNX模型)操作后，可进行部署，*.pose模型不支持部署；
- - （2）自己数据训练的YOLOR模型，按照[导出ONNX模型](#%E5%AF%BC%E5%87%BAONNX%E6%A8%A1%E5%9E%8B)操作后，参考[详细部署文档](#详细部署文档)完成部署。
+ - （1）The *.pt provided by [Official Repository](https://github.com/WongKinYiu/yolor/releases/tag/weights) should [Export the ONNX Model](#导出ONNX模型) to complete the deployment. The *.pose model’s deployment is not supported；
+ - （2）The ScaledYOLOv4 model trained by personal data should [Export the ONNX Model](#%E5%AF%BC%E5%87%BAONNX%E6%A8%A1%E5%9E%8B). Please refer to [Detailed Deployment Documents](#详细部署文档) to complete the deployment.
-## 导出ONNX模型
+## Export the ONNX Model
- 访问[YOLOR](https://github.com/WongKinYiu/yolor)官方github库，按照指引下载安装，下载`yolor.pt` 模型，利用 `models/export.py` 得到`onnx`格式文件。如果您导出的`onnx`模型出现精度不达标或者是数据维度的问题，可以参考[yolor#32](https://github.com/WongKinYiu/yolor/issues/32)的解决办法
+ Visit the official [YOLOR](https://github.com/WongKinYiu/yolor) github repository, follow the guidelines to download the `yolor.pt` model, and employ `models/export.py` to get the file in `onnx` format. If the exported `onnx` model has a substandard accuracy or other problems about data dimension, you can refer to [yolor#32](https://github.com/WongKinYiu/yolor/issues/32) for the solution.
```bash
- #下载yolor模型文件
+ # Download yolor model file
wget https://github.com/WongKinYiu/yolor/releases/download/weights/yolor-d6-paper-570.pt
- # 导出onnx格式文件
+ # Export the file in onnx format
python models/export.py --weights PATH/TO/yolor-xx-xx-xx.pt --img-size 640
```
-## 下载预训练ONNX模型
+## Download Pre-trained ONNX Model
-为了方便开发者的测试，下面提供了YOLOR导出的各系列模型，开发者可直接下载使用。（下表中模型的精度来源于源官方库）
-| 模型 | 大小 | 精度 | 备注 |
+For developers' testing, models exported by YOLOR are provided below. Developers can download them directly. (The accuracy in the following table is derived from the source official repository)
+| Model | Size | Accuracy | Note |
|:---------------------------------------------------------------- |:----- |:----- |:----- |
-| [YOLOR-P6-1280](https://bj.bcebos.com/paddlehub/fastdeploy/yolor-p6-paper-541-1280-1280.onnx) | 143MB | 54.1% | 此模型文件来源于[YOLOR](https://github.com/WongKinYiu/yolor)，GPL-3.0 License |
-| [YOLOR-W6-1280](https://bj.bcebos.com/paddlehub/fastdeploy/yolor-w6-paper-555-1280-1280.onnx) | 305MB | 55.5% | 此模型文件来源于[YOLOR](https://github.com/WongKinYiu/yolor)，GPL-3.0 License |
-| [YOLOR-E6-1280](https://bj.bcebos.com/paddlehub/fastdeploy/yolor-e6-paper-564-1280-1280.onnx ) | 443MB | 56.4% | 此模型文件来源于[YOLOR](https://github.com/WongKinYiu/yolor)，GPL-3.0 License |
-| [YOLOR-D6-1280](https://bj.bcebos.com/paddlehub/fastdeploy/yolor-d6-paper-570-1280-1280.onnx) | 580MB | 57.0% | 此模型文件来源于[YOLOR](https://github.com/WongKinYiu/yolor)，GPL-3.0 License |
-| [YOLOR-D6-1280](https://bj.bcebos.com/paddlehub/fastdeploy/yolor-d6-paper-573-1280-1280.onnx) | 580MB | 57.3% | 此模型文件来源于[YOLOR](https://github.com/WongKinYiu/yolor)，GPL-3.0 License |
-| [YOLOR-P6](https://bj.bcebos.com/paddlehub/fastdeploy/yolor-p6-paper-541-640-640.onnx) | 143MB | - | 此模型文件来源于[YOLOR](https://github.com/WongKinYiu/yolor)，GPL-3.0 License |
-| [YOLOR-W6](https://bj.bcebos.com/paddlehub/fastdeploy/yolor-w6-paper-555-640-640.onnx) | 305MB | - | 此模型文件来源于[YOLOR](https://github.com/WongKinYiu/yolor)，GPL-3.0 License |
-| [YOLOR-E6](https://bj.bcebos.com/paddlehub/fastdeploy/yolor-e6-paper-564-640-640.onnx ) | 443MB | - | 此模型文件来源于[YOLOR](https://github.com/WongKinYiu/yolor)，GPL-3.0 License |
-| [YOLOR-D6](https://bj.bcebos.com/paddlehub/fastdeploy/yolor-d6-paper-570-640-640.onnx) | 580MB | - | 此模型文件来源于[YOLOR](https://github.com/WongKinYiu/yolor)，GPL-3.0 License |
-| [YOLOR-D6](https://bj.bcebos.com/paddlehub/fastdeploy/yolor-d6-paper-573-640-640.onnx) | 580MB | - | 此模型文件来源于[YOLOR](https://github.com/WongKinYiu/yolor)，GPL-3.0 License |
+| [YOLOR-P6-1280](https://bj.bcebos.com/paddlehub/fastdeploy/yolor-p6-paper-541-1280-1280.onnx) | 143MB | 54.1% | This model file is sourced from [YOLOR](https://github.com/WongKinYiu/yolor)，GPL-3.0 License |
+| [YOLOR-W6-1280](https://bj.bcebos.com/paddlehub/fastdeploy/yolor-w6-paper-555-1280-1280.onnx) | 305MB | 55.5% | This model file is sourced from [YOLOR](https://github.com/WongKinYiu/yolor)，GPL-3.0 License |
+| [YOLOR-E6-1280](https://bj.bcebos.com/paddlehub/fastdeploy/yolor-e6-paper-564-1280-1280.onnx ) | 443MB | 56.4% | This model file is sourced from [YOLOR](https://github.com/WongKinYiu/yolor)，GPL-3.0 License |
+| [YOLOR-D6-1280](https://bj.bcebos.com/paddlehub/fastdeploy/yolor-d6-paper-570-1280-1280.onnx) | 580MB | 57.0% | This model file is sourced from [YOLOR](https://github.com/WongKinYiu/yolor)，GPL-3.0 License |
+| [YOLOR-D6-1280](https://bj.bcebos.com/paddlehub/fastdeploy/yolor-d6-paper-573-1280-1280.onnx) | 580MB | 57.3% | This model file is sourced from [YOLOR](https://github.com/WongKinYiu/yolor)，GPL-3.0 License |
+| [YOLOR-P6](https://bj.bcebos.com/paddlehub/fastdeploy/yolor-p6-paper-541-640-640.onnx) | 143MB | - | This model file is sourced from [YOLOR](https://github.com/WongKinYiu/yolor)，GPL-3.0 License |
+| [YOLOR-W6](https://bj.bcebos.com/paddlehub/fastdeploy/yolor-w6-paper-555-640-640.onnx) | 305MB | - | This model file is sourced from [YOLOR](https://github.com/WongKinYiu/yolor)，GPL-3.0 License |
+| [YOLOR-E6](https://bj.bcebos.com/paddlehub/fastdeploy/yolor-e6-paper-564-640-640.onnx ) | 443MB | - | This model file is sourced from [YOLOR](https://github.com/WongKinYiu/yolor)，GPL-3.0 License |
+| [YOLOR-D6](https://bj.bcebos.com/paddlehub/fastdeploy/yolor-d6-paper-570-640-640.onnx) | 580MB | - | This model file is sourced from [YOLOR](https://github.com/WongKinYiu/yolor)，GPL-3.0 License |
+| [YOLOR-D6](https://bj.bcebos.com/paddlehub/fastdeploy/yolor-d6-paper-573-640-640.onnx) | 580MB | - | This model file is sourced from [YOLOR](https://github.com/WongKinYiu/yolor)，GPL-3.0 License |
-## 详细部署文档
+## Detailed Deployment Documents
-- [Python部署](python)
-- [C++部署](cpp)
+- [Python Deployment](python)
+- [C++ Deployment](cpp)
-## 版本说明
+## Release Note
-- 本版本文档和代码基于[YOLOR weights](https://github.com/WongKinYiu/yolor/releases/tag/weights) 编写
+- Document and code are based on [YOLOR weights](https://github.com/WongKinYiu/yolor/releases/tag/weights)
diff --git a/examples/vision/detection/yolor/README_CN.md b/examples/vision/detection/yolor/README_CN.md
new file mode 100644
index 0000000000..7e487057a5
--- /dev/null
+++ b/examples/vision/detection/yolor/README_CN.md
@@ -0,0 +1,48 @@
+[English](README.md) | 简体中文
+# YOLOR准备部署模型
+
+- YOLOR部署实现来自[YOLOR](https://github.com/WongKinYiu/yolor/releases/tag/weights)的代码，和[基于COCO的预训练模型](https://github.com/WongKinYiu/yolor/releases/tag/weights)。
+
+ - （1）[官方库](https://github.com/WongKinYiu/yolor/releases/tag/weights)提供的*.pt通过[导出ONNX模型](#导出ONNX模型)操作后，可进行部署，*.pose模型不支持部署；
+ - （2）自己数据训练的YOLOR模型，按照[导出ONNX模型](#%E5%AF%BC%E5%87%BAONNX%E6%A8%A1%E5%9E%8B)操作后，参考[详细部署文档](#详细部署文档)完成部署。
+
+
+## 导出ONNX模型
+
+
+ 访问[YOLOR](https://github.com/WongKinYiu/yolor)官方github库，按照指引下载安装，下载`yolor.pt` 模型，利用 `models/export.py` 得到`onnx`格式文件。如果您导出的`onnx`模型出现精度不达标或者是数据维度的问题，可以参考[yolor#32](https://github.com/WongKinYiu/yolor/issues/32)的解决办法
+
+ ```bash
+ #下载yolor模型文件
+ wget https://github.com/WongKinYiu/yolor/releases/download/weights/yolor-d6-paper-570.pt
+
+ # 导出onnx格式文件
+ python models/export.py --weights PATH/TO/yolor-xx-xx-xx.pt --img-size 640
+ ```
+
+## 下载预训练ONNX模型
+
+为了方便开发者的测试，下面提供了YOLOR导出的各系列模型，开发者可直接下载使用。（下表中模型的精度来源于源官方库）
+| 模型 | 大小 | 精度 | 备注 |
+|:---------------------------------------------------------------- |:----- |:----- |:----- |
+| [YOLOR-P6-1280](https://bj.bcebos.com/paddlehub/fastdeploy/yolor-p6-paper-541-1280-1280.onnx) | 143MB | 54.1% | 此模型文件来源于[YOLOR](https://github.com/WongKinYiu/yolor)，GPL-3.0 License |
+| [YOLOR-W6-1280](https://bj.bcebos.com/paddlehub/fastdeploy/yolor-w6-paper-555-1280-1280.onnx) | 305MB | 55.5% | 此模型文件来源于[YOLOR](https://github.com/WongKinYiu/yolor)，GPL-3.0 License |
+| [YOLOR-E6-1280](https://bj.bcebos.com/paddlehub/fastdeploy/yolor-e6-paper-564-1280-1280.onnx ) | 443MB | 56.4% | 此模型文件来源于[YOLOR](https://github.com/WongKinYiu/yolor)，GPL-3.0 License |
+| [YOLOR-D6-1280](https://bj.bcebos.com/paddlehub/fastdeploy/yolor-d6-paper-570-1280-1280.onnx) | 580MB | 57.0% | 此模型文件来源于[YOLOR](https://github.com/WongKinYiu/yolor)，GPL-3.0 License |
+| [YOLOR-D6-1280](https://bj.bcebos.com/paddlehub/fastdeploy/yolor-d6-paper-573-1280-1280.onnx) | 580MB | 57.3% | 此模型文件来源于[YOLOR](https://github.com/WongKinYiu/yolor)，GPL-3.0 License |
+| [YOLOR-P6](https://bj.bcebos.com/paddlehub/fastdeploy/yolor-p6-paper-541-640-640.onnx) | 143MB | - | 此模型文件来源于[YOLOR](https://github.com/WongKinYiu/yolor)，GPL-3.0 License |
+| [YOLOR-W6](https://bj.bcebos.com/paddlehub/fastdeploy/yolor-w6-paper-555-640-640.onnx) | 305MB | - | 此模型文件来源于[YOLOR](https://github.com/WongKinYiu/yolor)，GPL-3.0 License |
+| [YOLOR-E6](https://bj.bcebos.com/paddlehub/fastdeploy/yolor-e6-paper-564-640-640.onnx ) | 443MB | - | 此模型文件来源于[YOLOR](https://github.com/WongKinYiu/yolor)，GPL-3.0 License |
+| [YOLOR-D6](https://bj.bcebos.com/paddlehub/fastdeploy/yolor-d6-paper-570-640-640.onnx) | 580MB | - | 此模型文件来源于[YOLOR](https://github.com/WongKinYiu/yolor)，GPL-3.0 License |
+| [YOLOR-D6](https://bj.bcebos.com/paddlehub/fastdeploy/yolor-d6-paper-573-640-640.onnx) | 580MB | - | 此模型文件来源于[YOLOR](https://github.com/WongKinYiu/yolor)，GPL-3.0 License |
+
+
+## 详细部署文档
+
+- [Python部署](python)
+- [C++部署](cpp)
+
+## 版本说明
+
+- 本版本文档和代码基于[YOLOR weights](https://github.com/WongKinYiu/yolor/releases/tag/weights) 编写
+
diff --git a/examples/vision/detection/yolor/cpp/README.md b/examples/vision/detection/yolor/cpp/README.md
index 89bccb487d..d410fecb61 100644
--- a/examples/vision/detection/yolor/cpp/README.md
+++ b/examples/vision/detection/yolor/cpp/README.md
@@ -1,46 +1,47 @@
-# YOLOR C++部署示例
+English | [简体中文](README_CN.md)
+# YOLOR C++ Deployment Example
-本目录下提供`infer.cc`快速完成YOLOR在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+This directory provides examples that `infer.cc` fast finishes the deployment of YOLOR on CPU/GPU and GPU accelerated by TensorRT.
-在部署前，需确认以下两个步骤
+Before deployment, two steps require confirmation
-- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. Download the precompiled deployment library and samples code according to your development environment. Refer to [FastDeploy Precompiled Library](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试，支持此模型需保证FastDeploy版本0.7.0以上(x.x.x>=0.7.0)
+Taking the CPU inference on Linux as an example, the compilation test can be completed by executing the following command in this directory. FastDeploy version 0.7.0 or above (x.x.x>=0.7.0) is required to support this model.
```bash
mkdir build
cd build
-# 下载FastDeploy预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
+# Download the FastDeploy precompiled library. Users can choose your appropriate version in the `FastDeploy Precompiled Library` mentioned above
wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz
tar xvf fastdeploy-linux-x64-x.x.x.tgz
cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x
make -j
-#下载官方转换好的YOLOR模型文件和测试图片
+# Download the official converted YOLOR model files and test images
wget https://bj.bcebos.com/paddlehub/fastdeploy/yolor-p6-paper-541-640-640.onnx
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
-# CPU推理
+# CPU inference
./infer_demo yolor-p6-paper-541-640-640.onnx 000000014439.jpg 0
-# GPU推理
+# GPU inference
./infer_demo yolor-p6-paper-541-640-640.onnx 000000014439.jpg 1
-# GPU上TensorRT推理
+# TensorRT inference on GPU
./infer_demo yolor-p6-paper-541-640-640.onnx 000000014439.jpg 2
```
-运行完成可视化结果如下图所示
+The visualized result after running is as follows
-以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
-- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
+The above command works for Linux or MacOS. For SDK use-pattern in Windows, refer to:
+- [How to use FastDeploy C++ SDK in Windows](../../../../../docs/cn/faq/use_sdk_on_windows.md)
-## YOLOR C++接口
+## YOLOR C++ Interface
-### YOLOR类
+### YOLOR Class
```c++
fastdeploy::vision::detection::YOLOR(
@@ -50,16 +51,16 @@ fastdeploy::vision::detection::YOLOR(
const ModelFormat& model_format = ModelFormat::ONNX)
```
-YOLOR模型加载和初始化，其中model_file为导出的ONNX模型格式。
+YOLOR model loading and initialization, among which model_file is the exported ONNX model format
-**参数**
+**Parameter**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为ONNX格式
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. Merely passing an empty string when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. ONNX format by default
-#### Predict函数
+#### Predict Function
> ```c++
> YOLOR::Predict(cv::Mat* im, DetectionResult* result,
@@ -67,26 +68,26 @@ YOLOR模型加载和初始化，其中model_file为导出的ONNX模型格式。
> float nms_iou_threshold = 0.5)
> ```
>
-> 模型预测接口，输入图像直接输出检测结果。
+> Model prediction interface. Input images and output detection results.
>
-> **参数**
+> **Parameter**
>
-> > * **im**: 输入图像，注意需为HWC，BGR格式
-> > * **result**: 检测结果，包括检测框，各个框的置信度, DetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
-> > * **conf_threshold**: 检测框置信度过滤阈值
-> > * **nms_iou_threshold**: NMS处理过程中iou阈值
-
-### 类成员变量
-#### 预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
-
-> > * **size**(vector<int>): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
-> > * **padding_value**(vector<float>): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
-> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=ture` 表示不使用填充的方式，默认值为`is_no_pad=false`
-> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=false`
-> > * **stride**(int): 配合`stris_mini_pad`成员变量使用, 默认值为`stride=32`
-
-- [模型介绍](../../)
-- [Python部署](../python)
-- [视觉模型预测结果](../../../../../docs/api/vision_results/)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+> > * **im**: Input images in HWC or BGR format
+> > * **result**: Detection results, including detection box and confidence of each box. Refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for DetectionResult
+> > * **conf_threshold**: Filtering threshold of detection box confidence
+> > * **nms_iou_threshold**: iou threshold during NMS processing
+
+### Class Member Variable
+#### Pre-processing Parameter
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
+
+> > * **size**(vector<int>): This parameter changes the size of the resize used during preprocessing, containing two integer elements for [width, height] with default value [640, 640]
+> > * **padding_value**(vector<float>): This parameter is used to change the padding value of images during resize, containing three floating-point elements that represent the value of three channels. Default value [114, 114, 114]
+> > * **is_no_pad**(bool): Specify whether to resize the image through padding. `is_no_pad=ture` represents no paddling. Default `is_no_pad=false`
+> > * **is_mini_pad**(bool): This parameter sets the width and height of the image after resize to the value nearest to the `size` member variable and to the point where the padded pixel size is divisible by the `stride` member variable. Default `is_mini_pad=false`
+> > * **stride**(int): Used with the `stris_mini_pad` member variable. Default `stride=32`
+
+- [Model Description](../../)
+- [Python Deployment](../python)
+- [Vision Model Prediction Results](../../../../../docs/api/vision_results/)
+- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/yolor/cpp/README_CN.md b/examples/vision/detection/yolor/cpp/README_CN.md
new file mode 100644
index 0000000000..a2f7b10064
--- /dev/null
+++ b/examples/vision/detection/yolor/cpp/README_CN.md
@@ -0,0 +1,93 @@
+[English](README.md) | 简体中文
+# YOLOR C++部署示例
+
+本目录下提供`infer.cc`快速完成YOLOR在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试，支持此模型需保证FastDeploy版本0.7.0以上(x.x.x>=0.7.0)
+
+```bash
+mkdir build
+cd build
+# 下载FastDeploy预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz
+tar xvf fastdeploy-linux-x64-x.x.x.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x
+make -j
+
+#下载官方转换好的YOLOR模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/yolor-p6-paper-541-640-640.onnx
+wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
+
+
+# CPU推理
+./infer_demo yolor-p6-paper-541-640-640.onnx 000000014439.jpg 0
+# GPU推理
+./infer_demo yolor-p6-paper-541-640-640.onnx 000000014439.jpg 1
+# GPU上TensorRT推理
+./infer_demo yolor-p6-paper-541-640-640.onnx 000000014439.jpg 2
+```
+
+运行完成可视化结果如下图所示
+
+
+
+以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
+- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
+
+## YOLOR C++接口
+
+### YOLOR类
+
+```c++
+fastdeploy::vision::detection::YOLOR(
+ const string& model_file,
+ const string& params_file = "",
+ const RuntimeOption& runtime_option = RuntimeOption(),
+ const ModelFormat& model_format = ModelFormat::ONNX)
+```
+
+YOLOR模型加载和初始化，其中model_file为导出的ONNX模型格式。
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为ONNX格式
+
+#### Predict函数
+
+> ```c++
+> YOLOR::Predict(cv::Mat* im, DetectionResult* result,
+> float conf_threshold = 0.25,
+> float nms_iou_threshold = 0.5)
+> ```
+>
+> 模型预测接口，输入图像直接输出检测结果。
+>
+> **参数**
+>
+> > * **im**: 输入图像，注意需为HWC，BGR格式
+> > * **result**: 检测结果，包括检测框，各个框的置信度, DetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > * **conf_threshold**: 检测框置信度过滤阈值
+> > * **nms_iou_threshold**: NMS处理过程中iou阈值
+
+### 类成员变量
+#### 预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> > * **size**(vector<int>): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
+> > * **padding_value**(vector<float>): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
+> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=ture` 表示不使用填充的方式，默认值为`is_no_pad=false`
+> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=false`
+> > * **stride**(int): 配合`stris_mini_pad`成员变量使用, 默认值为`stride=32`
+
+- [模型介绍](../../)
+- [Python部署](../python)
+- [视觉模型预测结果](../../../../../docs/api/vision_results/)
+- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/yolor/python/README.md b/examples/vision/detection/yolor/python/README.md
index ed433c0745..68e423742a 100644
--- a/examples/vision/detection/yolor/python/README.md
+++ b/examples/vision/detection/yolor/python/README.md
@@ -1,81 +1,81 @@
-# YOLOR Python部署示例
+English | [简体中文](README_CN.md)
+# YOLOR Python Deployment Example
-在部署前，需确认以下两个步骤
+Before deployment, two steps require confirmation
-- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-
-本目录下提供`infer.py`快速完成YOLOR在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. Install FastDeploy Python whl package. Refer to [FastDeploy Python Installation](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+This directory provides examples that `infer.py` ast finishes the deployment of YOLOR on CPU/GPU and GPU accelerated by TensorRT. The script is as follows
```bash
-#下载部署示例代码
+# Download the example code for deployment
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision/detection/yolor/python/
-#下载YOLOR模型文件和测试图片
+# Download YOLOR model files and test images
wget https://bj.bcebos.com/paddlehub/fastdeploy/yolor-p6-paper-541-640-640.onnx
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
-# CPU推理
+# CPU inference
python infer.py --model yolor-p6-paper-541-640-640.onnx --image 000000014439.jpg --device cpu
-# GPU推理
+# GPU inference
python infer.py --model yolor-p6-paper-541-640-640.onnx --image 000000014439.jpg --device gpu
-# GPU上使用TensorRT推理
+# TensorRT inference on GPU
python infer.py --model yolor-p6-paper-541-640-640.onnx --image 000000014439.jpg --device gpu --use_trt True
```
-运行完成可视化结果如下图所示
+The visualized result after running is as follows
-## YOLOR Python接口
+## YOLOR Python Interface
```python
fastdeploy.vision.detection.YOLOR(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
```
-YOLOR模型加载和初始化，其中model_file为导出的ONNX模型格式
+YOLOR model loading and initialization, among which model_file is the exported ONNX model format
-**参数**
+**Parameter**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为ONNX
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. No need to set when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. ONNX format by default
-### predict函数
+### predict function
> ```python
> YOLOR.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
> ```
>
-> 模型预测结口，输入图像直接输出检测结果。
+> Model prediction interface. Input images and output detection results.
>
-> **参数**
+> **Parameter**
>
-> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
-> > * **conf_threshold**(float): 检测框置信度过滤阈值
-> > * **nms_iou_threshold**(float): NMS处理过程中iou阈值
+> > * **image_data**(np.ndarray): Input data in HWC or BGR format
+> > * **conf_threshold**(float): Filtering threshold of detection box confidence
+> > * **nms_iou_threshold**(float): iou threshold during NMS processing
-> **返回**
+> **Return**
>
-> > 返回`fastdeploy.vision.DetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > Return `fastdeploy.vision.DetectionResult` structure. Refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for its description.
-### 类成员属性
-#### 预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+### Class Member Property
+#### Pre-processing Parameter
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
-> > * **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
-> > * **padding_value**(list[float]): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
-> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=True` 表示不使用填充的方式，默认值为`is_no_pad=False`
-> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=False`
-> > * **stride**(int): 配合`stris_mini_padide`成员变量使用, 默认值为`stride=32`
+> > * **size**(list[int]): This parameter changes the size of the resize used during preprocessing, containing two integer elements for [width, height] with default value [640, 640]
+> > * **padding_value**(list[float]): This parameter is used to change the padding value of images during resize, containing three floating-point elements that represent the value of three channels. Default value [114, 114, 114]
+> > * **is_no_pad**(bool): Specify whether to resize the image through padding. `is_no_pad=True` represents no paddling. Default `is_no_pad=False`
+> > * **is_mini_pad**(bool): This parameter sets the width and height of the image after resize to the value nearest to the `size` member variable and to the point where the padded pixel size is divisible by the `stride` member variable. Default `is_mini_pad=False`
+> > * **stride**(int): Used with the `stris_mini_padide` member variable. Default `stride=32`
-## 其它文档
+## Other Documents
-- [YOLOR 模型介绍](..)
-- [YOLOR C++部署](../cpp)
-- [模型预测结果说明](../../../../../docs/api/vision_results/)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+- [YOLOR Model Description](..)
+- [YOLOR C++ Deployment](../cpp)
+- [Model Prediction Results](../../../../../docs/api/vision_results/)
+- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/yolor/python/README_CN.md b/examples/vision/detection/yolor/python/README_CN.md
new file mode 100644
index 0000000000..0fa1cb294d
--- /dev/null
+++ b/examples/vision/detection/yolor/python/README_CN.md
@@ -0,0 +1,82 @@
+[English](README.md) | 简体中文
+# YOLOR Python部署示例
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+本目录下提供`infer.py`快速完成YOLOR在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+
+```bash
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd examples/vision/detection/yolor/python/
+
+#下载YOLOR模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/yolor-p6-paper-541-640-640.onnx
+wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
+
+# CPU推理
+python infer.py --model yolor-p6-paper-541-640-640.onnx --image 000000014439.jpg --device cpu
+# GPU推理
+python infer.py --model yolor-p6-paper-541-640-640.onnx --image 000000014439.jpg --device gpu
+# GPU上使用TensorRT推理
+python infer.py --model yolor-p6-paper-541-640-640.onnx --image 000000014439.jpg --device gpu --use_trt True
+```
+
+运行完成可视化结果如下图所示
+
+
+
+## YOLOR Python接口
+
+```python
+fastdeploy.vision.detection.YOLOR(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
+```
+
+YOLOR模型加载和初始化，其中model_file为导出的ONNX模型格式
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为ONNX
+
+### predict函数
+
+> ```python
+> YOLOR.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
+> ```
+>
+> 模型预测结口，输入图像直接输出检测结果。
+>
+> **参数**
+>
+> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
+> > * **conf_threshold**(float): 检测框置信度过滤阈值
+> > * **nms_iou_threshold**(float): NMS处理过程中iou阈值
+
+> **返回**
+>
+> > 返回`fastdeploy.vision.DetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+
+### 类成员属性
+#### 预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> > * **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
+> > * **padding_value**(list[float]): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
+> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=True` 表示不使用填充的方式，默认值为`is_no_pad=False`
+> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=False`
+> > * **stride**(int): 配合`stris_mini_padide`成员变量使用, 默认值为`stride=32`
+
+
+
+## 其它文档
+
+- [YOLOR 模型介绍](..)
+- [YOLOR C++部署](../cpp)
+- [模型预测结果说明](../../../../../docs/api/vision_results/)
+- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/yolov5/README.md b/examples/vision/detection/yolov5/README.md
index 5ffe3f046a..918b7d2537 100644
--- a/examples/vision/detection/yolov5/README.md
+++ b/examples/vision/detection/yolov5/README.md
@@ -1,28 +1,30 @@
-# YOLOv5准备部署模型
+English | [简体中文](README_CN.md)
-- YOLOv5 v7.0部署模型实现来自[YOLOv5](https://github.com/ultralytics/yolov5/tree/v7.0),和[基于COCO的预训练模型](https://github.com/ultralytics/yolov5/releases/tag/v7.0)
- - （1）[官方库](https://github.com/ultralytics/yolov5/releases/tag/v7.0)提供的*.onnx可直接进行部署；
- - （2）开发者基于自己数据训练的YOLOv5 v7.0模型，可使用[YOLOv5](https://github.com/ultralytics/yolov5)中的`export.py`导出ONNX文件后，完成部署。
+# YOLOv5 Ready-to-deploy Model
+- The deployment of the YOLOv5 v7.0 model is based on [YOLOv5](https://github.com/ultralytics/yolov5/tree/v7.0) and [Pre-trained Model Based on COCO](https://github.com/ultralytics/yolov5/releases/tag/v7.0)
+ - （1）The *.onnx provided by [Official Repository](https://github.com/ultralytics/yolov5/releases/tag/v7.0) can be deployed directly；
+ - （2）The YOLOv5 v7.0 model trained by personal data should employ `export.py` in [YOLOv5](https://github.com/ultralytics/yolov5) to export the ONNX files for deployment.
-## 下载预训练ONNX模型
-为了方便开发者的测试，下面提供了YOLOv5导出的各系列模型，开发者可直接下载使用。（下表中模型的精度来源于源官方库）
-| 模型 | 大小 | 精度 | 备注 |
+## Download Pre-trained ONNX Model
+
+For developers' testing, models exported by YOLOv5 are provided below. Developers can download them directly. (The accuracy in the following table is derived from the source official repository)
+| Model | Size | Accuracy | Note |
|:---------------------------------------------------------------- |:----- |:----- |:---- |
-| [YOLOv5n](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5n.onnx) | 7.6MB | 28.0% | 此模型文件来源于[YOLOv5](https://github.com/ultralytics/yolov5)，GPL-3.0 License |
-| [YOLOv5s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s.onnx) | 28MB | 37.4% | 此模型文件来源于[YOLOv5](https://github.com/ultralytics/yolov5)，GPL-3.0 License |
-| [YOLOv5m](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5m.onnx) | 82MB | 45.4% | 此模型文件来源于[YOLOv5](https://github.com/ultralytics/yolov5)，GPL-3.0 License |
-| [YOLOv5l](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5l.onnx) | 178MB | 49.0% | 此模型文件来源于[YOLOv5](https://github.com/ultralytics/yolov5)，GPL-3.0 License |
-| [YOLOv5x](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5x.onnx) | 332MB | 50.7% | 此模型文件来源于[YOLOv5](https://github.com/ultralytics/yolov5)，GPL-3.0 License |
+| [YOLOv5n](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5n.onnx) | 7.6MB | 28.0% | This model file is sourced from [YOLOv5](https://github.com/ultralytics/yolov5)，GPL-3.0 License |
+| [YOLOv5s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s.onnx) | 28MB | 37.4% | This model file is sourced from [YOLOv5](https://github.com/ultralytics/yolov5)，GPL-3.0 License |
+| [YOLOv5m](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5m.onnx) | 82MB | 45.4% | This model file is sourced from [YOLOv5](https://github.com/ultralytics/yolov5)，GPL-3.0 License |
+| [YOLOv5l](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5l.onnx) | 178MB | 49.0% | This model file is sourced from [YOLOv5](https://github.com/ultralytics/yolov5)，GPL-3.0 License |
+| [YOLOv5x](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5x.onnx) | 332MB | 50.7% | This model file is sourced from [YOLOv5](https://github.com/ultralytics/yolov5)，GPL-3.0 License |
-## 详细部署文档
+## Detailed Deployment Documents
-- [Python部署](python)
-- [C++部署](cpp)
-- [服务化部署](serving)
+- [Python Deployment](python)
+- [C++ Deployment](cpp)
+- [Serving Deployment](serving)
-## 版本说明
+## Release Note
-- 本版本文档和代码基于[YOLOv5 v7.0](https://github.com/ultralytics/yolov5/tree/v7.0) 编写
+- Document and code are based on [YOLOv5 v7.0](https://github.com/ultralytics/yolov5/tree/v7.0)
diff --git a/examples/vision/detection/yolov5/README_CN.md b/examples/vision/detection/yolov5/README_CN.md
new file mode 100644
index 0000000000..591c359ee2
--- /dev/null
+++ b/examples/vision/detection/yolov5/README_CN.md
@@ -0,0 +1,29 @@
+[English](README.md) | 简体中文
+# YOLOv5准备部署模型
+
+- YOLOv5 v7.0部署模型实现来自[YOLOv5](https://github.com/ultralytics/yolov5/tree/v7.0),和[基于COCO的预训练模型](https://github.com/ultralytics/yolov5/releases/tag/v7.0)
+ - （1）[官方库](https://github.com/ultralytics/yolov5/releases/tag/v7.0)提供的*.onnx可直接进行部署；
+ - （2）开发者基于自己数据训练的YOLOv5 v7.0模型，可使用[YOLOv5](https://github.com/ultralytics/yolov5)中的`export.py`导出ONNX文件后，完成部署。
+
+
+## 下载预训练ONNX模型
+
+为了方便开发者的测试，下面提供了YOLOv5导出的各系列模型，开发者可直接下载使用。（下表中模型的精度来源于源官方库）
+| 模型 | 大小 | 精度 | 备注 |
+|:---------------------------------------------------------------- |:----- |:----- |:---- |
+| [YOLOv5n](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5n.onnx) | 7.6MB | 28.0% | 此模型文件来源于[YOLOv5](https://github.com/ultralytics/yolov5)，GPL-3.0 License |
+| [YOLOv5s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s.onnx) | 28MB | 37.4% | 此模型文件来源于[YOLOv5](https://github.com/ultralytics/yolov5)，GPL-3.0 License |
+| [YOLOv5m](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5m.onnx) | 82MB | 45.4% | 此模型文件来源于[YOLOv5](https://github.com/ultralytics/yolov5)，GPL-3.0 License |
+| [YOLOv5l](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5l.onnx) | 178MB | 49.0% | 此模型文件来源于[YOLOv5](https://github.com/ultralytics/yolov5)，GPL-3.0 License |
+| [YOLOv5x](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5x.onnx) | 332MB | 50.7% | 此模型文件来源于[YOLOv5](https://github.com/ultralytics/yolov5)，GPL-3.0 License |
+
+
+## 详细部署文档
+
+- [Python部署](python)
+- [C++部署](cpp)
+- [服务化部署](serving)
+
+## 版本说明
+
+- 本版本文档和代码基于[YOLOv5 v7.0](https://github.com/ultralytics/yolov5/tree/v7.0) 编写
diff --git a/examples/vision/detection/yolov5/a311d/README.md b/examples/vision/detection/yolov5/a311d/README.md
index 2f8451c60e..47917fbb0a 100755
--- a/examples/vision/detection/yolov5/a311d/README.md
+++ b/examples/vision/detection/yolov5/a311d/README.md
@@ -1,8 +1,12 @@
-# YOLOv5 量化模型在 A311D 上的部署
-目前 FastDeploy 已经支持基于 Paddle Lite 部署 [YOLOv5](https://github.com/ultralytics/yolov5/releases/tag/v6.1) 量化模型到 A311D 上。
+English | [简体中文](README_CN.md)
+# Deploy YOLOv5 Quantification Model on A311D
+Now FastDeploy supports the deployment of YOLOv5 quantification model to A311D based on Paddle Lite.
-## 详细部署文档
+For model quantification and download, refer to [Model Quantification](../quantize/README.md)
-在 A311D 上只支持 C++ 的部署。
-- [C++部署](cpp)
+## Detailed Deployment Tutorials
+
+Only C++ deployment is supported on A311D.
+
+- [C++ Deployment](cpp)
diff --git a/examples/vision/detection/yolov5/a311d/README_CN.md b/examples/vision/detection/yolov5/a311d/README_CN.md
new file mode 100644
index 0000000000..767518b56e
--- /dev/null
+++ b/examples/vision/detection/yolov5/a311d/README_CN.md
@@ -0,0 +1,9 @@
+[English](README.md) | 简体中文
+# YOLOv5 量化模型在 A311D 上的部署
+目前 FastDeploy 已经支持基于 Paddle Lite 部署 [YOLOv5](https://github.com/ultralytics/yolov5/releases/tag/v6.1) 量化模型到 A311D 上。
+
+## 详细部署文档
+
+在 A311D 上只支持 C++ 的部署。
+
+- [C++部署](cpp)
diff --git a/examples/vision/detection/yolov5/cpp/README.md b/examples/vision/detection/yolov5/cpp/README.md
index c70d0d1188..39e105cd9e 100755
--- a/examples/vision/detection/yolov5/cpp/README.md
+++ b/examples/vision/detection/yolov5/cpp/README.md
@@ -1,66 +1,61 @@
-# YOLOv5 C++部署示例
+English | [简体中文](README_CN.md)
+# YOLOv5 C++ Deployment Example
-本目录下提供`infer.cc`快速完成YOLOv5在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+This directory provides examples that `infer.cc` fast finishes the deployment of YOLOv5 on CPU/GPU and GPU accelerated by TensorRT.
+Before deployment, two steps require confirmation
-在部署前，需确认以下两个步骤
+- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. Download the precompiled deployment library and samples code according to your development environment. Refer to [FastDeployPrecompiled Library](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-
-以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试，支持此模型需保证FastDeploy版本0.7.0以上(x.x.x>=0.7.0)
+Taking the CPU inference on Linux as an example, the compilation test can be completed by executing the following command in this directory. FastDeploy version 0.7.0 or above (x.x.x>=0.7.0) is required to support this model.
```bash
mkdir build
cd build
-# 下载 FastDeploy 预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
+# Download the FastDeploy precompiled library. Users can choose your appropriate version in the `FastDeploy Precompiled Library` mentioned above
wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz
tar xvf fastdeploy-linux-x64-x.x.x.tgz
cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x
make -j
-#下载官方转换好的 yolov5 Paddle 模型文件和测试图片
+# Download the official converted yolov5 Paddle model files and test images
wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s_infer.tar
tar -xvf yolov5s_infer.tar
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
-# CPU推理
+# CPU inference
./infer_paddle_demo yolov5s_infer 000000014439.jpg 0
-# GPU推理
+# GPU inference
./infer_paddle_demo yolov5s_infer 000000014439.jpg 1
-# GPU上TensorRT推理
+# TensorRT inference on GPU
./infer_paddle_demo yolov5s_infer 000000014439.jpg 2
-# 昆仑芯XPU推理
+# KunlunXin XPU inference
./infer_paddle_demo yolov5s_infer 000000014439.jpg 3
-# 华为昇腾推理
-./infer_paddle_demo yolov5s_infer 000000014439.jpg 4
```
-上述的模型为 Paddle 模型的推理，如果想要做 ONNX 模型的推理，可以按照如下步骤：
+The above steps apply to the inference of Paddle models. If you want to conduct the inference of ONNX models, follow these steps:
```bash
-# 1. 下载官方转换好的 yolov5 ONNX 模型文件和测试图片
+# 1. Download the official converted yolov5 ONNX model files and test images
wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s.onnx
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
-# CPU推理
+# CPU inference
./infer_demo yolov5s.onnx 000000014439.jpg 0
-# GPU推理
+# GPU inference
./infer_demo yolov5s.onnx 000000014439.jpg 1
-# GPU上TensorRT推理
+# TensorRT inference on GPU
./infer_demo yolov5s.onnx 000000014439.jpg 2
```
-运行完成可视化结果如下图所示
+The visualized result after running is as follows
-以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
-- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
-
-如果用户使用华为昇腾NPU部署, 请参考以下方式在部署前初始化部署环境:
-- [如何使用华为昇腾NPU部署](../../../../../docs/cn/faq/use_sdk_on_ascend.md)
+The above command works for Linux or MacOS. For SDK use-pattern in Windows, refer to:
+- [How to use FastDeploy C++ SDK in Windows](../../../../../docs/cn/faq/use_sdk_on_windows.md)
-## YOLOv5 C++接口
+## YOLOv5 C++ Interface
-### YOLOv5类
+### YOLOv5 Class
```c++
fastdeploy::vision::detection::YOLOv5(
@@ -70,16 +65,16 @@ fastdeploy::vision::detection::YOLOv5(
const ModelFormat& model_format = ModelFormat::ONNX)
```
-YOLOv5模型加载和初始化，其中model_file为导出的ONNX模型格式。
+YOLOv5 model loading and initialization, among which model_file is the exported ONNX model format
-**参数**
+**Parameter**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为ONNX格式
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. Merely passing an empty string when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. ONNX format by default
-#### Predict函数
+#### Predict Function
> ```c++
> YOLOv5::Predict(cv::Mat* im, DetectionResult* result,
@@ -87,26 +82,26 @@ YOLOv5模型加载和初始化，其中model_file为导出的ONNX模型格式。
> float nms_iou_threshold = 0.5)
> ```
>
-> 模型预测接口，输入图像直接输出检测结果。
+> Model prediction interface. Input images and output detection results.
>
-> **参数**
+> **Parameter**
>
-> > * **im**: 输入图像，注意需为HWC，BGR格式
-> > * **result**: 检测结果，包括检测框，各个框的置信度, DetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
-> > * **conf_threshold**: 检测框置信度过滤阈值
-> > * **nms_iou_threshold**: NMS处理过程中iou阈值
-
-### 类成员变量
-#### 预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
-
-> > * **size**(vector<int>): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
-> > * **padding_value**(vector<float>): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
-> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=ture` 表示不使用填充的方式，默认值为`is_no_pad=false`
-> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=false`
-> > * **stride**(int): 配合`stris_mini_pad`成员变量使用, 默认值为`stride=32`
-
-- [模型介绍](../../)
-- [Python部署](../python)
-- [视觉模型预测结果](../../../../../docs/api/vision_results/)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+> > * **im**: Input images in HWC or BGR format
+> > * **result**: Detection results, including detection box and confidence of each box. Refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for DetectionResult
+> > * **conf_threshold**: Filtering threshold of detection box confidence
+> > * **nms_iou_threshold**: iou threshold during NMS processing
+
+### Class Member Variable
+#### Pre-processing Parameter
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
+
+> > * **size**(vector<int>): This parameter changes the size of the resize used during preprocessing, containing two integer elements for [width, height] with default value [640, 640]
+> > * **padding_value**(vector<float>): This parameter is used to change the padding value of images during resize, containing three floating-point elements that represent the value of three channels. Default value [114, 114, 114]
+> > * **is_no_pad**(bool): Specify whether to resize the image through padding. `is_no_pad=ture` represents no paddling. Default `is_no_pad=false`
+> > * **is_mini_pad**(bool): This parameter sets the width and height of the image after resize to the value nearest to the `size` member variable and to the point where the padded pixel size is divisible by the `stride` member variable. Default `is_mini_pad=false`
+> > * **stride**(int): Used with the `stris_mini_pad` member variable. Default `stride=32`
+
+- [Model Description](../../)
+- [Python Deployment](../python)
+- [Vision Model Prediction Results](../../../../../docs/api/vision_results/)
+- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/yolov5/cpp/README_CN.md b/examples/vision/detection/yolov5/cpp/README_CN.md
new file mode 100644
index 0000000000..d8499ec231
--- /dev/null
+++ b/examples/vision/detection/yolov5/cpp/README_CN.md
@@ -0,0 +1,113 @@
+[English](README.md) | 简体中文
+# YOLOv5 C++部署示例
+
+本目录下提供`infer.cc`快速完成YOLOv5在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试，支持此模型需保证FastDeploy版本0.7.0以上(x.x.x>=0.7.0)
+
+```bash
+mkdir build
+cd build
+# 下载 FastDeploy 预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz
+tar xvf fastdeploy-linux-x64-x.x.x.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x
+make -j
+#下载官方转换好的 yolov5 Paddle 模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s_infer.tar
+tar -xvf yolov5s_infer.tar
+wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
+
+
+# CPU推理
+./infer_paddle_demo yolov5s_infer 000000014439.jpg 0
+# GPU推理
+./infer_paddle_demo yolov5s_infer 000000014439.jpg 1
+# GPU上TensorRT推理
+./infer_paddle_demo yolov5s_infer 000000014439.jpg 2
+# 昆仑芯XPU推理
+./infer_paddle_demo yolov5s_infer 000000014439.jpg 3
+# 华为昇腾推理
+./infer_paddle_demo yolov5s_infer 000000014439.jpg 4
+```
+
+上述的模型为 Paddle 模型的推理，如果想要做 ONNX 模型的推理，可以按照如下步骤：
+```bash
+# 1. 下载官方转换好的 yolov5 ONNX 模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s.onnx
+wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
+
+# CPU推理
+./infer_demo yolov5s.onnx 000000014439.jpg 0
+# GPU推理
+./infer_demo yolov5s.onnx 000000014439.jpg 1
+# GPU上TensorRT推理
+./infer_demo yolov5s.onnx 000000014439.jpg 2
+```
+运行完成可视化结果如下图所示
+
+
+
+以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
+- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
+
+如果用户使用华为昇腾NPU部署, 请参考以下方式在部署前初始化部署环境:
+- [如何使用华为昇腾NPU部署](../../../../../docs/cn/faq/use_sdk_on_ascend.md)
+
+## YOLOv5 C++接口
+
+### YOLOv5类
+
+```c++
+fastdeploy::vision::detection::YOLOv5(
+ const string& model_file,
+ const string& params_file = "",
+ const RuntimeOption& runtime_option = RuntimeOption(),
+ const ModelFormat& model_format = ModelFormat::ONNX)
+```
+
+YOLOv5模型加载和初始化，其中model_file为导出的ONNX模型格式。
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为ONNX格式
+
+#### Predict函数
+
+> ```c++
+> YOLOv5::Predict(cv::Mat* im, DetectionResult* result,
+> float conf_threshold = 0.25,
+> float nms_iou_threshold = 0.5)
+> ```
+>
+> 模型预测接口，输入图像直接输出检测结果。
+>
+> **参数**
+>
+> > * **im**: 输入图像，注意需为HWC，BGR格式
+> > * **result**: 检测结果，包括检测框，各个框的置信度, DetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > * **conf_threshold**: 检测框置信度过滤阈值
+> > * **nms_iou_threshold**: NMS处理过程中iou阈值
+
+### 类成员变量
+#### 预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> > * **size**(vector<int>): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
+> > * **padding_value**(vector<float>): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
+> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=ture` 表示不使用填充的方式，默认值为`is_no_pad=false`
+> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=false`
+> > * **stride**(int): 配合`stris_mini_pad`成员变量使用, 默认值为`stride=32`
+
+- [模型介绍](../../)
+- [Python部署](../python)
+- [视觉模型预测结果](../../../../../docs/api/vision_results/)
+- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/yolov5/python/README.md b/examples/vision/detection/yolov5/python/README.md
index de93ef0ecb..b1c56a0541 100755
--- a/examples/vision/detection/yolov5/python/README.md
+++ b/examples/vision/detection/yolov5/python/README.md
@@ -1,86 +1,85 @@
-# YOLOv5 Python部署示例
+English | [简体中文](README_CN.md)
+# YOLOv5 Python Deployment Example
-在部署前，需确认以下两个步骤
+Before deployment, two steps require confirmation
-- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. Install FastDeploy Python whl package. Refer to [FastDeploy Python Installation](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-本目录下提供`infer.py`快速完成YOLOv5在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+This directory provides examples that `infer.py` fast finishes the deployment of YOLOv5 on CPU/GPU and GPU accelerated by TensorRT. The script is as follows
```bash
-#下载部署示例代码
+# Download the example code for deployment
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision/detection/yolov5/python/
-#下载yolov5模型文件和测试图片
+# Download yolov5 model files and test images
wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s_infer.tar
tar -xf yolov5s_infer.tar
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
-# CPU推理
+# CPU inference
python infer.py --model yolov5s_infer --image 000000014439.jpg --device cpu
-# GPU推理
+# GPU inference
python infer.py --model yolov5s_infer --image 000000014439.jpg --device gpu
-# GPU上使用TensorRT推理
+# TensorRT inference on GPU
python infer.py --model yolov5s_infer --image 000000014439.jpg --device gpu --use_trt True
-# 昆仑芯XPU推理
+# KunlunXin XPU inference
python infer.py --model yolov5s_infer --image 000000014439.jpg --device kunlunxin
-# 华为昇腾推理
-python infer.py --model yolov5s_infer --image 000000014439.jpg --device ascend
```
-运行完成可视化结果如下图所示
+The visualized result after running is as follows
-## YOLOv5 Python接口
+## YOLOv5 Python Interface
```python
fastdeploy.vision.detection.YOLOv5(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
```
-YOLOv5模型加载和初始化，其中model_file为导出的ONNX模型格式
+YOLOv5 model loading and initialization, among which model_file is the exported ONNX model format
-**参数**
+**Parameter**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为ONNX
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. No need to set when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. ONNX format by default
-### predict函数
+### predict function
> ```python
> YOLOv5.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
> ```
>
-> 模型预测结口，输入图像直接输出检测结果。
+> Model prediction interface. Input images and output detection results.
>
-> **参数**
+> **Parameter**
>
-> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
-> > * **conf_threshold**(float): 检测框置信度过滤阈值
-> > * **nms_iou_threshold**(float): NMS处理过程中iou阈值
+> > * **image_data**(np.ndarray): Input data in HWC or BGR format
+> > * **conf_threshold**(float): Filtering threshold of detection box confidence
+> > * **nms_iou_threshold**(float): iou threshold during NMS processing
-> **返回**
+> **Return**
>
-> > 返回`fastdeploy.vision.DetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > Return `fastdeploy.vision.DetectionResult` structure. Refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for its description.
-### 类成员属性
-#### 预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+### Class Member Property
+#### Pre-processing Parameter
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
-> > * **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
-> > * **padding_value**(list[float]): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
-> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=True` 表示不使用填充的方式，默认值为`is_no_pad=False`
-> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=False`
-> > * **stride**(int): 配合`stris_mini_padide`成员变量使用, 默认值为`stride=32`
+> > * **size**(list[int]): This parameter changes the size of the resize used during preprocessing, containing two integer elements for [width, height] with default value [640, 640]
+> > * **padding_value**(list[float]): This parameter is used to change the padding value of images during resize, containing three floating-point elements that represent the value of three channels. Default value [114, 114, 114]
+> > * **is_no_pad**(bool): Specify whether to resize the image through padding. `is_no_pad=True` represents no paddling. Default `is_no_pad=False`
+> > * **is_mini_pad**(bool): This parameter sets the width and height of the image after resize to the value nearest to the `size` member variable and to the point where the padded pixel size is divisible by the `stride` member variable. Default `is_mini_pad=False`
+> > * **stride**(int): Used with the `stris_mini_padide` member variable. Default `stride=32`
-## 其它文档
+## Other Documents
-- [YOLOv5 模型介绍](..)
-- [YOLOv5 C++部署](../cpp)
-- [模型预测结果说明](../../../../../docs/api/vision_results/)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+- [YOLOv5 Model Description](..)
+- [YOLOv5 C++ Deployment](../cpp)
+- [Model Prediction Results](../../../../../docs/api/vision_results/)
+- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/yolov5/python/README_CN.md b/examples/vision/detection/yolov5/python/README_CN.md
new file mode 100644
index 0000000000..e575472ce4
--- /dev/null
+++ b/examples/vision/detection/yolov5/python/README_CN.md
@@ -0,0 +1,87 @@
+[English](README.md) | 简体中文
+# YOLOv5 Python部署示例
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+本目录下提供`infer.py`快速完成YOLOv5在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+
+```bash
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd examples/vision/detection/yolov5/python/
+
+#下载yolov5模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s_infer.tar
+tar -xf yolov5s_infer.tar
+wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
+
+# CPU推理
+python infer.py --model yolov5s_infer --image 000000014439.jpg --device cpu
+# GPU推理
+python infer.py --model yolov5s_infer --image 000000014439.jpg --device gpu
+# GPU上使用TensorRT推理
+python infer.py --model yolov5s_infer --image 000000014439.jpg --device gpu --use_trt True
+# 昆仑芯XPU推理
+python infer.py --model yolov5s_infer --image 000000014439.jpg --device kunlunxin
+# 华为昇腾推理
+python infer.py --model yolov5s_infer --image 000000014439.jpg --device ascend
+```
+
+运行完成可视化结果如下图所示
+
+
+
+## YOLOv5 Python接口
+
+```python
+fastdeploy.vision.detection.YOLOv5(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
+```
+
+YOLOv5模型加载和初始化，其中model_file为导出的ONNX模型格式
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为ONNX
+
+### predict函数
+
+> ```python
+> YOLOv5.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
+> ```
+>
+> 模型预测结口，输入图像直接输出检测结果。
+>
+> **参数**
+>
+> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
+> > * **conf_threshold**(float): 检测框置信度过滤阈值
+> > * **nms_iou_threshold**(float): NMS处理过程中iou阈值
+
+> **返回**
+>
+> > 返回`fastdeploy.vision.DetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+
+### 类成员属性
+#### 预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> > * **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
+> > * **padding_value**(list[float]): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
+> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=True` 表示不使用填充的方式，默认值为`is_no_pad=False`
+> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=False`
+> > * **stride**(int): 配合`stris_mini_padide`成员变量使用, 默认值为`stride=32`
+
+
+
+## 其它文档
+
+- [YOLOv5 模型介绍](..)
+- [YOLOv5 C++部署](../cpp)
+- [模型预测结果说明](../../../../../docs/api/vision_results/)
+- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/yolov5/quantize/README.md b/examples/vision/detection/yolov5/quantize/README.md
index aa0a8d5431..4d97b7578c 100755
--- a/examples/vision/detection/yolov5/quantize/README.md
+++ b/examples/vision/detection/yolov5/quantize/README.md
@@ -1,44 +1,30 @@
-# YOLOv5量化模型部署
-FastDeploy已支持部署量化模型,并提供一键模型自动化压缩的工具.
-用户可以使用一键模型自动化压缩工具,自行对模型量化后部署, 也可以直接下载FastDeploy提供的量化模型进行部署.
-
-## FastDeploy一键模型自动化压缩工具
-FastDeploy 提供了一键模型自动化压缩工具, 能够简单地通过输入一个配置文件, 对模型进行量化.
-详细教程请见: [一键模型自动化压缩工具](../../../../../tools/common_tools/auto_compression/)
-
-## 下载量化完成的YOLOv5s模型
-用户也可以直接下载下表中的量化模型进行部署.(点击模型名字即可下载)
-
-Benchmark表格说明:
-- Runtime时延为模型在各种Runtime上的推理时延,包含CPU->GPU数据拷贝,GPU推理,GPU->CPU数据拷贝时间. 不包含模型各自的前后处理时间.
-- 端到端时延为模型在实际推理场景中的时延, 包含模型的前后处理.
-- 所测时延均为推理1000次后求得的平均值, 单位是毫秒.
-- INT8 + FP16 为在推理INT8量化模型的同时, 给Runtime 开启FP16推理选项
-- INT8 + FP16 + PM, 为在推理INT8量化模型和开启FP16的同时, 开启使用Pinned Memory的选项,可加速GPU->CPU数据拷贝的速度
-- 最大加速比, 为FP32时延除以INT8推理的最快时延,得到最大加速比.
-- 策略为量化蒸馏训练时, 采用少量无标签数据集训练得到量化模型, 并在全量验证集上验证精度, INT8精度并不代表最高的INT8精度.
-- CPU为Intel(R) Xeon(R) Gold 6271C, 所有测试中固定CPU线程数为1. GPU为Tesla T4, TensorRT版本8.4.15.
-
-
-#### Runtime Benchmark
-| 模型 |推理后端 |部署硬件 | FP32 Runtime时延 | INT8 Runtime时延 | INT8 + FP16 Runtime时延 | INT8+FP16+PM Runtime时延 | 最大加速比 | FP32 mAP | INT8 mAP | 量化方式 |
-| ------------------- | -----------------|-----------| -------- |-------- |-------- | --------- |-------- |----- |----- |----- |
-| [YOLOv5s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s_quant.tar) | TensorRT | GPU | 7.87 | 4.51 | 4.31 | 3.17 | 2.48 | 37.6 | 36.7 | 量化蒸馏训练 |
-| [YOLOv5s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s_quant.tar) | Paddle-TensorRT | GPU | 7.99 | None | 4.46 | 3.31 | 2.41 | 37.6 | 36.8 | 量化蒸馏训练 |
-| [YOLOv5s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s_quant.tar) | ONNX Runtime | CPU | 176.41 | 91.90 | None | None | 1.90 | 37.6 | 33.1 |量化蒸馏训练 |
-| [YOLOv5s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s_quant.tar) | Paddle Inference| CPU | 213.73 | 130.19 | None | None | 1.64 |37.6 | 35.2 | 量化蒸馏训练 |
-
-#### 端到端 Benchmark
-| 模型 |推理后端 |部署硬件 | FP32 End2End时延 | INT8 End2End时延 | INT8 + FP16 End2End时延 | INT8+FP16+PM End2End时延 | 最大加速比 | FP32 mAP | INT8 mAP | 量化方式 |
-| ------------------- | -----------------|-----------| -------- |-------- |-------- | --------- |-------- |----- |----- |----- |
-| [YOLOv5s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s_quant.tar) | TensorRT | GPU | 24.61 | 21.20 | 20.78 | 20.94 | 1.18 | 37.6 | 36.7 | 量化蒸馏训练 |
-| [YOLOv5s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s_quant.tar) | Paddle-TensorRT | GPU | 23.53 | None | 21.98 | 19.84 | 1.28 | 37.6 | 36.8 | 量化蒸馏训练 |
-| [YOLOv5s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s_quant.tar) | ONNX Runtime | CPU | 197.323 | 110.99 | None | None | 1.78 | 37.6 | 33.1 |量化蒸馏训练 |
-| [YOLOv5s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s_quant.tar) | Paddle Inference| CPU | 235.73 | 144.82 | None | None | 1.63 |37.6 | 35.2 | 量化蒸馏训练 |
-
-
-
-## 详细部署文档
-
-- [Python部署](python)
-- [C++部署](cpp)
+English | [简体中文](README_CN.md)
+# YOLOv5 Quantized Model Deployment
+
+FastDeploy supports the deployment of quantized models and provides a one-click model quantization tool.
+Users can use the one-click model quantization tool to quantize and deploy the models themselves or download the quantized models provided by FastDeploy directly for deployment.
+
+## FastDeploy One-Click Model Quantization Tool
+
+FastDeploy provides a one-click quantization tool that allows users to quantize a model simply with a configuration file.
+For a detailed tutorial, please refer to: [One-Click Model Quantization Tool](../../../../../tools/common_tools/auto_compression/)
+
+## Download Quantized YOLOv5s Model
+
+Users can also directly download the quantized models in the table below for deployment.
+
+| Model | Inference Backend | Hardware | FP32 Inference Time Delay | INT8 Inference Time Delay | Acceleration ratio | FP32 mAP | INT8 mAP | Method |
+| ----------------------------------------------------------------------- | ----------------- | -------- | ------------------------- | -------------------------- | ------------------ | -------- | -------- | ------------------------------- |
+| [YOLOv5s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s_quant.tar) | TensorRT | GPU | 8.79 | 5.17 | 1.70 | 37.6 | 36.6 | Quantized distillation training |
+| [YOLOv5s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s_quant.tar) | Paddle Inference | CPU | 217.05 | 133.31 | 1.63 | 37.6 | 36.8 | Quantized distillation training |
+
+The data in the above table shows the end-to-end inference performance of FastDeploy deployment before and after model quantization.
+
+- The test images are from COCO val2017.
+- The inference time delay is the inference latency on different Runtime in milliseconds.
+- CPU is Intel(R) Xeon(R) Gold 6271C, GPU is Tesla T4, TensorRT version 8.4.15, and the fixed CPU thread is 1 for all tests.
+
+## More Detailed Tutorials
+
+- [Python Deployment](python)
+- [C++ Deployment](cpp)
diff --git a/examples/vision/detection/yolov5/quantize/README_CN.md b/examples/vision/detection/yolov5/quantize/README_CN.md
new file mode 100755
index 0000000000..dc85b1e329
--- /dev/null
+++ b/examples/vision/detection/yolov5/quantize/README_CN.md
@@ -0,0 +1,45 @@
+[English](README.md) | 简体中文
+# YOLOv5量化模型部署
+FastDeploy已支持部署量化模型,并提供一键模型自动化压缩的工具.
+用户可以使用一键模型自动化压缩工具,自行对模型量化后部署, 也可以直接下载FastDeploy提供的量化模型进行部署.
+
+## FastDeploy一键模型自动化压缩工具
+FastDeploy 提供了一键模型自动化压缩工具, 能够简单地通过输入一个配置文件, 对模型进行量化.
+详细教程请见: [一键模型自动化压缩工具](../../../../../tools/common_tools/auto_compression/)
+
+## 下载量化完成的YOLOv5s模型
+用户也可以直接下载下表中的量化模型进行部署.(点击模型名字即可下载)
+
+Benchmark表格说明:
+- Runtime时延为模型在各种Runtime上的推理时延,包含CPU->GPU数据拷贝,GPU推理,GPU->CPU数据拷贝时间. 不包含模型各自的前后处理时间.
+- 端到端时延为模型在实际推理场景中的时延, 包含模型的前后处理.
+- 所测时延均为推理1000次后求得的平均值, 单位是毫秒.
+- INT8 + FP16 为在推理INT8量化模型的同时, 给Runtime 开启FP16推理选项
+- INT8 + FP16 + PM, 为在推理INT8量化模型和开启FP16的同时, 开启使用Pinned Memory的选项,可加速GPU->CPU数据拷贝的速度
+- 最大加速比, 为FP32时延除以INT8推理的最快时延,得到最大加速比.
+- 策略为量化蒸馏训练时, 采用少量无标签数据集训练得到量化模型, 并在全量验证集上验证精度, INT8精度并不代表最高的INT8精度.
+- CPU为Intel(R) Xeon(R) Gold 6271C, 所有测试中固定CPU线程数为1. GPU为Tesla T4, TensorRT版本8.4.15.
+
+
+#### Runtime Benchmark
+| 模型 |推理后端 |部署硬件 | FP32 Runtime时延 | INT8 Runtime时延 | INT8 + FP16 Runtime时延 | INT8+FP16+PM Runtime时延 | 最大加速比 | FP32 mAP | INT8 mAP | 量化方式 |
+| ------------------- | -----------------|-----------| -------- |-------- |-------- | --------- |-------- |----- |----- |----- |
+| [YOLOv5s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s_quant.tar) | TensorRT | GPU | 7.87 | 4.51 | 4.31 | 3.17 | 2.48 | 37.6 | 36.7 | 量化蒸馏训练 |
+| [YOLOv5s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s_quant.tar) | Paddle-TensorRT | GPU | 7.99 | None | 4.46 | 3.31 | 2.41 | 37.6 | 36.8 | 量化蒸馏训练 |
+| [YOLOv5s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s_quant.tar) | ONNX Runtime | CPU | 176.41 | 91.90 | None | None | 1.90 | 37.6 | 33.1 |量化蒸馏训练 |
+| [YOLOv5s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s_quant.tar) | Paddle Inference| CPU | 213.73 | 130.19 | None | None | 1.64 |37.6 | 35.2 | 量化蒸馏训练 |
+
+#### 端到端 Benchmark
+| 模型 |推理后端 |部署硬件 | FP32 End2End时延 | INT8 End2End时延 | INT8 + FP16 End2End时延 | INT8+FP16+PM End2End时延 | 最大加速比 | FP32 mAP | INT8 mAP | 量化方式 |
+| ------------------- | -----------------|-----------| -------- |-------- |-------- | --------- |-------- |----- |----- |----- |
+| [YOLOv5s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s_quant.tar) | TensorRT | GPU | 24.61 | 21.20 | 20.78 | 20.94 | 1.18 | 37.6 | 36.7 | 量化蒸馏训练 |
+| [YOLOv5s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s_quant.tar) | Paddle-TensorRT | GPU | 23.53 | None | 21.98 | 19.84 | 1.28 | 37.6 | 36.8 | 量化蒸馏训练 |
+| [YOLOv5s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s_quant.tar) | ONNX Runtime | CPU | 197.323 | 110.99 | None | None | 1.78 | 37.6 | 33.1 |量化蒸馏训练 |
+| [YOLOv5s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s_quant.tar) | Paddle Inference| CPU | 235.73 | 144.82 | None | None | 1.63 |37.6 | 35.2 | 量化蒸馏训练 |
+
+
+
+## 详细部署文档
+
+- [Python部署](python)
+- [C++部署](cpp)
diff --git a/examples/vision/detection/yolov5/quantize/README_EN.md b/examples/vision/detection/yolov5/quantize/README_EN.md
deleted file mode 100755
index d897710f98..0000000000
--- a/examples/vision/detection/yolov5/quantize/README_EN.md
+++ /dev/null
@@ -1,29 +0,0 @@
-# YOLOv5 Quantized Model Deployment
-
-FastDeploy supports the deployment of quantized models and provides a one-click model quantization tool.
-Users can use the one-click model quantization tool to quantize and deploy the models themselves or download the quantized models provided by FastDeploy directly for deployment.
-
-## FastDeploy One-Click Model Quantization Tool
-
-FastDeploy provides a one-click quantization tool that allows users to quantize a model simply with a configuration file.
-For a detailed tutorial, please refer to: [One-Click Model Quantization Tool](../../../../../tools/common_tools/auto_compression/)
-
-## Download Quantized YOLOv5s Model
-
-Users can also directly download the quantized models in the table below for deployment.
-
-| Model | Inference Backend | Hardware | FP32 Inference Time Delay | INT8 Inference Time Delay | Acceleration ratio | FP32 mAP | INT8 mAP | Method |
-| ----------------------------------------------------------------------- | ----------------- | -------- | ------------------------- | -------------------------- | ------------------ | -------- | -------- | ------------------------------- |
-| [YOLOv5s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s_quant.tar) | TensorRT | GPU | 8.79 | 5.17 | 1.70 | 37.6 | 36.6 | Quantized distillation training |
-| [YOLOv5s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s_quant.tar) | Paddle Inference | CPU | 217.05 | 133.31 | 1.63 | 37.6 | 36.8 | Quantized distillation training |
-
-The data in the above table shows the end-to-end inference performance of FastDeploy deployment before and after model quantization.
-
-- The test images are from COCO val2017.
-- The inference time delay is the inference latency on different Runtime in milliseconds.
-- CPU is Intel(R) Xeon(R) Gold 6271C, GPU is Tesla T4, TensorRT version 8.4.15, and the fixed CPU thread is 1 for all tests.
-
-## More Detailed Tutorials
-
-- [Python Deployment](python)
-- [C++ Deployment](cpp)
diff --git a/examples/vision/detection/yolov5/rv1126/README.md b/examples/vision/detection/yolov5/rv1126/README.md
index 5bac651e20..736b963dce 100755
--- a/examples/vision/detection/yolov5/rv1126/README.md
+++ b/examples/vision/detection/yolov5/rv1126/README.md
@@ -1,8 +1,12 @@
-# YOLOv5 量化模型在 RV1126 上的部署
-目前 FastDeploy 已经支持基于 Paddle Lite 部署 [YOLOv5](https://github.com/ultralytics/yolov5/releases/tag/v6.1) 量化模型到 RV1126 上。
+English | [简体中文](README_CN.md)
+# Deploy YOLOv5 Quantification Model on RV1126
+Now FastDeploy supports the deployment of YOLOv5 quantification model to RV1126 based on Paddle Lite.
-## 详细部署文档
+For model quantification and download, refer to [Model Quantification](../quantize/README.md)
-在 RV1126 上只支持 C++ 的部署。
-- [C++部署](cpp)
+## Detailed Deployment Tutorials
+
+Only C++ deployment is supported on RV1126.
+
+- [C++ Deployment](cpp)
diff --git a/examples/vision/detection/yolov5/rv1126/README_CN.md b/examples/vision/detection/yolov5/rv1126/README_CN.md
new file mode 100644
index 0000000000..11a1afc7df
--- /dev/null
+++ b/examples/vision/detection/yolov5/rv1126/README_CN.md
@@ -0,0 +1,9 @@
+[English](README.md) | 简体中文
+# YOLOv5 量化模型在 RV1126 上的部署
+目前 FastDeploy 已经支持基于 Paddle Lite 部署 [YOLOv5](https://github.com/ultralytics/yolov5/releases/tag/v6.1) 量化模型到 RV1126 上。
+
+## 详细部署文档
+
+在 RV1126 上只支持 C++ 的部署。
+
+- [C++部署](cpp)
diff --git a/examples/vision/detection/yolov5/serving/README.md b/examples/vision/detection/yolov5/serving/README.md
index 8ad6218496..50500fa398 100644
--- a/examples/vision/detection/yolov5/serving/README.md
+++ b/examples/vision/detection/yolov5/serving/README.md
@@ -1,38 +1,27 @@
-# YOLOv5 服务化部署示例
+English | [简体中文](README_CN.md)
+# YOLOv5 Serving Deployment Demo
-在服务化部署前，需确认
-
-- 1. 服务化镜像的软硬件环境要求和镜像拉取命令请参考[FastDeploy服务化部署](../../../../../serving/README_CN.md)
-
-
-## 启动服务
+## Launch Serving
```bash
-#下载部署示例代码
-git clone https://github.com/PaddlePaddle/FastDeploy.git
-cd FastDeploy/examples/vision/detection/yolov5/serving/
-
-#下载yolov5模型文件
+#Download yolov5 model file
wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s.onnx
-# 将模型放入 models/runtime/1目录下, 并重命名为model.onnx
-mv yolov5s.onnx models/runtime/1/model.onnx
+# Save the model under models/infer/1 and rename it as model.onnx
+mv yolov5s.onnx models/infer/1/
-# 拉取fastdeploy镜像(x.y.z为镜像版本号，需参照serving文档替换为数字)
-# GPU镜像
-docker pull registry.baidubce.com/paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10
-# CPU镜像
-docker pull registry.baidubce.com/paddlepaddle/fastdeploy:x.y.z-cpu-only-21.10
+# Pull fastdeploy image, x.y.z is FastDeploy version, example 1.0.0.
+docker pull paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10
-# 运行容器.容器名字为 fd_serving, 并挂载当前目录为容器的 /yolov5_serving 目录
-nvidia-docker run -it --net=host --name fd_serving -v `pwd`/:/yolov5_serving registry.baidubce.com/paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10 bash
+# Run the docker. The docker name is fd_serving, and the current directory is mounted as the docker's /yolov5_serving directory
+nvidia-docker run -it --net=host --name fd_serving -v `pwd`/:/yolov5_serving paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10 bash
-# 启动服务(不设置CUDA_VISIBLE_DEVICES环境变量，会拥有所有GPU卡的调度权限)
-CUDA_VISIBLE_DEVICES=0 fastdeployserver --model-repository=/yolov5_serving/models --backend-config=python,shm-default-byte-size=10485760
+# Start the service (Without setting the CUDA_VISIBLE_DEVICES environment variable, it will have scheduling privileges for all GPU cards)
+CUDA_VISIBLE_DEVICES=0 fastdeployserver --model-repository=models --backend-config=python,shm-default-byte-size=10485760
```
->> **注意**: 当出现"Address already in use", 请使用`--grpc-port`指定端口号来启动服务，同时更改yolov5_grpc_client.py中的请求端口号
-服务启动成功后， 会有以下输出:
+Output the following contents if serving is launched
+
```
......
I0928 04:51:15.784517 206 grpc_server.cc:4117] Started GRPCInferenceService at 0.0.0.0:8001
@@ -40,27 +29,30 @@ I0928 04:51:15.785177 206 http_server.cc:2815] Started HTTPService at 0.0.0.0:80
I0928 04:51:15.826578 206 http_server.cc:167] Started Metrics Service at 0.0.0.0:8002
```
+## Client Requests
-## 客户端请求
+Execute the following command in the physical machine to send a grpc request and output the result
-在物理机器中执行以下命令，发送grpc请求并输出结果
```
-#下载测试图片
+#Download test images
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
-#安装客户端依赖
-python3 -m pip install tritonclient[all]
+#Installing client-side dependencies
+python3 -m pip install tritonclient\[all\]
-# 发送请求
+# Send requests
python3 yolov5_grpc_client.py
```
-发送请求成功后，会返回json格式的检测结果并打印输出:
+When the request is sent successfully, the results are returned in json format and printed out:
+
```
output_name: detction_result
{'boxes': [[268.48028564453125, 81.05305480957031, 298.69476318359375, 169.43902587890625], [104.73116302490234, 45.66197204589844, 127.58382415771484, 93.44938659667969], [378.9093933105469, 39.75013732910156, 395.6086120605469, 84.24342346191406], [158.552978515625, 80.36149597167969, 199.18576049804688, 168.18191528320312], [414.37530517578125, 90.94805908203125, 506.3218994140625, 280.40521240234375], [364.00341796875, 56.608917236328125, 381.97857666015625, 115.96823120117188], [351.7251281738281, 42.635345458984375, 366.9103088378906, 98.04837036132812], [505.8882751464844, 114.36674499511719, 593.1248779296875, 275.99530029296875], [327.7086181640625, 38.36369323730469, 346.84991455078125, 80.89302062988281], [583.493408203125, 114.53289794921875, 612.3546142578125, 175.87353515625], [186.4706573486328, 44.941375732421875, 199.6645050048828, 61.037628173828125], [169.6158905029297, 48.01460266113281, 178.1415557861328, 60.88859558105469], [25.81019401550293, 117.19969177246094, 59.88878631591797, 152.85012817382812], [352.1452941894531, 46.71272277832031, 381.9460754394531, 106.75212097167969], [1.875, 150.734375, 37.96875, 173.78125], [464.65728759765625, 15.901412963867188, 472.512939453125, 34.11640930175781], [64.625, 135.171875, 84.5, 154.40625], [57.8125, 151.234375, 103.0, 174.15625], [165.890625, 88.609375, 527.90625, 339.953125], [101.40625, 152.5625, 118.890625, 169.140625]], 'scores': [0.8965693116188049, 0.8695310950279236, 0.8684297800064087, 0.8429877758026123, 0.8358422517776489, 0.8151364326477051, 0.8089362382888794, 0.801361083984375, 0.7947245836257935, 0.7606497406959534, 0.6325908303260803, 0.6139386892318726, 0.5906146764755249, 0.505328893661499, 0.40457233786582947, 0.3460320234298706, 0.33283042907714844, 0.3325657248497009, 0.2594234347343445, 0.25389009714126587], 'label_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 24, 0, 24, 24, 33, 24], 'masks': [], 'contain_masks': False}
```
-## 配置修改
+## Modify Configs
+
+
-当前默认配置在CPU上运行ONNXRuntime引擎， 如果要在GPU或其他推理引擎上运行。 需要修改`models/runtime/config.pbtxt`中配置，详情请参考[配置文档](../../../../../serving/docs/zh_CN/model_configuration.md)
+The default is to run ONNXRuntime on CPU. If developers need to run it on GPU or other inference engines, please see the [Configs File](../../../../../serving/docs/zh_CN/model_configuration.md) to modify the configs in `models/runtime/config.pbtxt`.
diff --git a/examples/vision/detection/yolov5/serving/README_EN.md b/examples/vision/detection/yolov5/serving/README_CN.md
similarity index 56%
rename from examples/vision/detection/yolov5/serving/README_EN.md
rename to examples/vision/detection/yolov5/serving/README_CN.md
index 46deb29f1c..4fc0b3800e 100644
--- a/examples/vision/detection/yolov5/serving/README_EN.md
+++ b/examples/vision/detection/yolov5/serving/README_CN.md
@@ -1,26 +1,39 @@
-# YOLOv5 Serving Deployment Demo
+[English](README.md) | 简体中文
+# YOLOv5 服务化部署示例
-## Launch Serving
+在服务化部署前，需确认
+
+- 1. 服务化镜像的软硬件环境要求和镜像拉取命令请参考[FastDeploy服务化部署](../../../../../serving/README_CN.md)
+
+
+## 启动服务
```bash
-#Download yolov5 model file
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd FastDeploy/examples/vision/detection/yolov5/serving/
+
+#下载yolov5模型文件
wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s.onnx
-# Save the model under models/infer/1 and rename it as model.onnx
-mv yolov5s.onnx models/infer/1/
+# 将模型放入 models/runtime/1目录下, 并重命名为model.onnx
+mv yolov5s.onnx models/runtime/1/model.onnx
-# Pull fastdeploy image, x.y.z is FastDeploy version, example 1.0.0.
-docker pull paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10
+# 拉取fastdeploy镜像(x.y.z为镜像版本号，需参照serving文档替换为数字)
+# GPU镜像
+docker pull registry.baidubce.com/paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10
+# CPU镜像
+docker pull registry.baidubce.com/paddlepaddle/fastdeploy:x.y.z-cpu-only-21.10
-# Run the docker. The docker name is fd_serving, and the current directory is mounted as the docker's /yolov5_serving directory
-nvidia-docker run -it --net=host --name fd_serving -v `pwd`/:/yolov5_serving paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10 bash
+# 运行容器.容器名字为 fd_serving, 并挂载当前目录为容器的 /yolov5_serving 目录
+nvidia-docker run -it --net=host --name fd_serving -v `pwd`/:/yolov5_serving registry.baidubce.com/paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10 bash
-# Start the service (Without setting the CUDA_VISIBLE_DEVICES environment variable, it will have scheduling privileges for all GPU cards)
-CUDA_VISIBLE_DEVICES=0 fastdeployserver --model-repository=models --backend-config=python,shm-default-byte-size=10485760
+# 启动服务(不设置CUDA_VISIBLE_DEVICES环境变量，会拥有所有GPU卡的调度权限)
+CUDA_VISIBLE_DEVICES=0 fastdeployserver --model-repository=/yolov5_serving/models --backend-config=python,shm-default-byte-size=10485760
```
+>> **注意**: 当出现"Address already in use", 请使用`--grpc-port`指定端口号来启动服务，同时更改yolov5_grpc_client.py中的请求端口号
-Output the following contents if serving is launched
-
+服务启动成功后， 会有以下输出:
```
......
I0928 04:51:15.784517 206 grpc_server.cc:4117] Started GRPCInferenceService at 0.0.0.0:8001
@@ -28,30 +41,27 @@ I0928 04:51:15.785177 206 http_server.cc:2815] Started HTTPService at 0.0.0.0:80
I0928 04:51:15.826578 206 http_server.cc:167] Started Metrics Service at 0.0.0.0:8002
```
-## Client Requests
-Execute the following command in the physical machine to send a grpc request and output the result
+## 客户端请求
+在物理机器中执行以下命令，发送grpc请求并输出结果
```
-#Download test images
+#下载测试图片
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
-#Installing client-side dependencies
-python3 -m pip install tritonclient\[all\]
+#安装客户端依赖
+python3 -m pip install tritonclient[all]
-# Send requests
+# 发送请求
python3 yolov5_grpc_client.py
```
-When the request is sent successfully, the results are returned in json format and printed out:
-
+发送请求成功后，会返回json格式的检测结果并打印输出:
```
output_name: detction_result
{'boxes': [[268.48028564453125, 81.05305480957031, 298.69476318359375, 169.43902587890625], [104.73116302490234, 45.66197204589844, 127.58382415771484, 93.44938659667969], [378.9093933105469, 39.75013732910156, 395.6086120605469, 84.24342346191406], [158.552978515625, 80.36149597167969, 199.18576049804688, 168.18191528320312], [414.37530517578125, 90.94805908203125, 506.3218994140625, 280.40521240234375], [364.00341796875, 56.608917236328125, 381.97857666015625, 115.96823120117188], [351.7251281738281, 42.635345458984375, 366.9103088378906, 98.04837036132812], [505.8882751464844, 114.36674499511719, 593.1248779296875, 275.99530029296875], [327.7086181640625, 38.36369323730469, 346.84991455078125, 80.89302062988281], [583.493408203125, 114.53289794921875, 612.3546142578125, 175.87353515625], [186.4706573486328, 44.941375732421875, 199.6645050048828, 61.037628173828125], [169.6158905029297, 48.01460266113281, 178.1415557861328, 60.88859558105469], [25.81019401550293, 117.19969177246094, 59.88878631591797, 152.85012817382812], [352.1452941894531, 46.71272277832031, 381.9460754394531, 106.75212097167969], [1.875, 150.734375, 37.96875, 173.78125], [464.65728759765625, 15.901412963867188, 472.512939453125, 34.11640930175781], [64.625, 135.171875, 84.5, 154.40625], [57.8125, 151.234375, 103.0, 174.15625], [165.890625, 88.609375, 527.90625, 339.953125], [101.40625, 152.5625, 118.890625, 169.140625]], 'scores': [0.8965693116188049, 0.8695310950279236, 0.8684297800064087, 0.8429877758026123, 0.8358422517776489, 0.8151364326477051, 0.8089362382888794, 0.801361083984375, 0.7947245836257935, 0.7606497406959534, 0.6325908303260803, 0.6139386892318726, 0.5906146764755249, 0.505328893661499, 0.40457233786582947, 0.3460320234298706, 0.33283042907714844, 0.3325657248497009, 0.2594234347343445, 0.25389009714126587], 'label_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 24, 0, 24, 24, 33, 24], 'masks': [], 'contain_masks': False}
```
-## Modify Configs
-
-
+## 配置修改
-The default is to run ONNXRuntime on CPU. If developers need to run it on GPU or other inference engines, please see the [Configs File](../../../../../serving/docs/zh_CN/model_configuration.md) to modify the configs in `models/runtime/config.pbtxt`.
+当前默认配置在CPU上运行ONNXRuntime引擎， 如果要在GPU或其他推理引擎上运行。 需要修改`models/runtime/config.pbtxt`中配置，详情请参考[配置文档](../../../../../serving/docs/zh_CN/model_configuration.md)
diff --git a/examples/vision/detection/yolov5lite/README.md b/examples/vision/detection/yolov5lite/README.md
index 0429758b84..aa4343a3d7 100644
--- a/examples/vision/detection/yolov5lite/README.md
+++ b/examples/vision/detection/yolov5lite/README.md
@@ -1,71 +1,72 @@
-# YOLOv5Lite准备部署模型
+English | [简体中文](README_CN.md)
+# YOLOv5Lite Ready-to-deploy Model
-- YOLOv5Lite部署实现来自[YOLOv5-Lite](https://github.com/ppogg/YOLOv5-Lite/releases/tag/v1.4)
-代码，和[基于COCO的预训练模型](https://github.com/ppogg/YOLOv5-Lite/releases/tag/v1.4)。
+- The YOLOv5Lite Deployment is based on the code of [YOLOv5-Lite](https://github.com/ppogg/YOLOv5-Lite/releases/tag/v1.4)
+and [Pre-trained Model Based on COCO](https://github.com/ppogg/YOLOv5-Lite/releases/tag/v1.4)。
- - （1）[官方库](https://github.com/ppogg/YOLOv5-Lite/releases/tag/v1.4)提供的*.pt通过[导出ONNX模型](#导出ONNX模型)操作后，可进行部署；
- - （2）自己数据训练的YOLOv5Lite模型，按照[导出ONNX模型](#%E5%AF%BC%E5%87%BAONNX%E6%A8%A1%E5%9E%8B)操作后，参考[详细部署文档](#详细部署文档)完成部署。
+ - （1）The *.pt provided by [Official Repository](https://github.com/ppogg/YOLOv5-Lite/releases/tag/v1.4) should [Export the ONNX Model](#导出ONNX模型)to complete the deployment；
+ - （2）The YOLOv5Lite model trained by personal data should [Export the ONNX Model](#%E5%AF%BC%E5%87%BAONNX%E6%A8%A1%E5%9E%8B). Refer to [Detailed Deployment Documents](#详细部署文档) to complete the deployment.
-## 导出ONNX模型
+## Export the ONNX Model
-- 自动获取
- 访问[YOLOv5Lite](https://github.com/ppogg/YOLOv5-Lite)
-官方github库，按照指引下载安装，下载`yolov5-lite-xx.onnx` 模型(Tips：官方提供的ONNX文件目前是没有decode模块的)
+- Auto-acquisition
+ Visit official [YOLOv5Lite](https://github.com/ppogg/YOLOv5-Lite)
+github repository, follow the guidelines to download the `yolov5-lite-xx.onnx` model(Tips: The official ONNX files are currently provided without the decode module)
```bash
- #下载yolov5-lite模型文件(.onnx)
+ # Download yolov5-lite model files(.onnx)
Download from https://drive.google.com/file/d/1bJByk9eoS6pv8Z3N4bcLRCV3i7uk24aU/view
- 官方Repo也支持百度云下载
+ Official Repo also supports Baidu cloud download
```
-- 手动获取
+- Manual Acquisition
- 访问[YOLOv5Lite](https://github.com/ppogg/YOLOv5-Lite)
-官方github库，按照指引下载安装，下载`yolov5-lite-xx.pt` 模型，利用 `export.py` 得到`onnx`格式文件。
+ Visit official [YOLOv5Lite](https://github.com/ppogg/YOLOv5-Lite)
+github repository, follow the guidelines to download the `yolov5-lite-xx.pt` model, and employ `export.py` to get files in `onnx` format.
- - 导出含有decode模块的ONNX文件
+ - Export ONNX files with the decode module
- 首先需要参考[YOLOv5-Lite#189](https://github.com/ppogg/YOLOv5-Lite/pull/189)的解决办法，修改代码。
+ First refer to [YOLOv5-Lite#189](https://github.com/ppogg/YOLOv5-Lite/pull/189) to modify the code.
```bash
- #下载yolov5-lite模型文件(.pt)
+ # Download yolov5-lite model files(.pt)
Download from https://drive.google.com/file/d/1oftzqOREGqDCerf7DtD5BZp9YWELlkMe/view
- 官方Repo也支持百度云下载
+ Official Repo also supports Baidu cloud download
- # 导出onnx格式文件
+ # Export files in onnx format
python export.py --grid --dynamic --concat --weights PATH/TO/yolov5-lite-xx.pt
```
- - 导出无decode模块的ONNX文件(不需要修改代码)
+ - Export ONNX files without the docode module(No code changes are required)
```bash
- #下载yolov5-lite模型文件
+ # Download yolov5-lite model files
Download from https://drive.google.com/file/d/1oftzqOREGqDCerf7DtD5BZp9YWELlkMe/view
- 官方Repo也支持百度云下载
+ Official Repo also supports Baidu cloud download
- # 导出onnx格式文件
+ # Export files in onnx format
python export.py --grid --dynamic --weights PATH/TO/yolov5-lite-xx.pt
```
-## 下载预训练ONNX模型
+## Download Pre-trained ONNX Model
-为了方便开发者的测试，下面提供了YOLOv5Lite导出的各系列模型，开发者可直接下载使用。（下表中模型的精度来源于源官方库）
-| 模型 | 大小 | 精度 | 备注 |
+For developers' testing, models exported by YOLOv5Lite are provided below. Developers can download them directly. (The accuracy in the following table is derived from the source official repository)
+| Model | Size | Accuracy | Note |
|:---------------------------------------------------------------- |:----- |:----- |:----- |
-| [YOLOv5Lite-e](https://bj.bcebos.com/paddlehub/fastdeploy/v5Lite-e-sim-320.onnx) | 3.1MB | 35.1% | 此模型文件来源于[YOLOv5-Lite](https://github.com/ppogg/YOLOv5-Lite)，GPL-3.0 License ｜
-| [YOLOv5Lite-s](https://bj.bcebos.com/paddlehub/fastdeploy/v5Lite-s-sim-416.onnx) | 6.3MB | 42.0% | 此模型文件来源于[YOLOv5-Lite](https://github.com/ppogg/YOLOv5-Lite)，GPL-3.0 License |
-| [YOLOv5Lite-c](https://bj.bcebos.com/paddlehub/fastdeploy/v5Lite-c-sim-512.onnx) | 18MB | 50.9% | 此模型文件来源于[YOLOv5-Lite](https://github.com/ppogg/YOLOv5-Lite)，GPL-3.0 License |
-| [YOLOv5Lite-g](https://bj.bcebos.com/paddlehub/fastdeploy/v5Lite-g-sim-640.onnx) | 21MB | 57.6% | 此模型文件来源于[YOLOv5-Lite](https://github.com/ppogg/YOLOv5-Lite)，GPL-3.0 License |
+| [YOLOv5Lite-e](https://bj.bcebos.com/paddlehub/fastdeploy/v5Lite-e-sim-320.onnx) | 3.1MB | 35.1% | This model file is sourced from [YOLOv5-Lite](https://github.com/ppogg/YOLOv5-Lite)，GPL-3.0 License |
+| [YOLOv5Lite-s](https://bj.bcebos.com/paddlehub/fastdeploy/v5Lite-s-sim-416.onnx) | 6.3MB | 42.0% | This model file is sourced from [YOLOv5-Lite](https://github.com/ppogg/YOLOv5-Lite)，GPL-3.0 License |
+| [YOLOv5Lite-c](https://bj.bcebos.com/paddlehub/fastdeploy/v5Lite-c-sim-512.onnx) | 18MB | 50.9% | This model file is sourced from[YOLOv5-Lite](https://github.com/ppogg/YOLOv5-Lite)，GPL-3.0 License |
+| [YOLOv5Lite-g](https://bj.bcebos.com/paddlehub/fastdeploy/v5Lite-g-sim-640.onnx) | 21MB | 57.6% | This model file is sourced from [YOLOv5-Lite](https://github.com/ppogg/YOLOv5-Lite)，GPL-3.0 License |
-## 详细部署文档
+## Detailed Deployment Documents
-- [Python部署](python)
-- [C++部署](cpp)
+- [Python Deployment](python)
+- [C++ Deployment](cpp)
-## 版本说明
+## Release Note
-- 本版本文档和代码基于[YOLOv5-Lite v1.4](https://github.com/ppogg/YOLOv5-Lite/releases/tag/v1.4) 编写
+- Document and code are based on [YOLOv5-Lite v1.4](https://github.com/ppogg/YOLOv5-Lite/releases/tag/v1.4)
diff --git a/examples/vision/detection/yolov5lite/README_CN.md b/examples/vision/detection/yolov5lite/README_CN.md
new file mode 100644
index 0000000000..c69c2d9920
--- /dev/null
+++ b/examples/vision/detection/yolov5lite/README_CN.md
@@ -0,0 +1,72 @@
+[English](README.md) | 简体中文
+# YOLOv5Lite准备部署模型
+
+- YOLOv5Lite部署实现来自[YOLOv5-Lite](https://github.com/ppogg/YOLOv5-Lite/releases/tag/v1.4)
+代码，和[基于COCO的预训练模型](https://github.com/ppogg/YOLOv5-Lite/releases/tag/v1.4)。
+
+ - （1）[官方库](https://github.com/ppogg/YOLOv5-Lite/releases/tag/v1.4)提供的*.pt通过[导出ONNX模型](#导出ONNX模型)操作后，可进行部署；
+ - （2）自己数据训练的YOLOv5Lite模型，按照[导出ONNX模型](#%E5%AF%BC%E5%87%BAONNX%E6%A8%A1%E5%9E%8B)操作后，参考[详细部署文档](#详细部署文档)完成部署。
+
+
+## 导出ONNX模型
+
+- 自动获取
+ 访问[YOLOv5Lite](https://github.com/ppogg/YOLOv5-Lite)
+官方github库，按照指引下载安装，下载`yolov5-lite-xx.onnx` 模型(Tips：官方提供的ONNX文件目前是没有decode模块的)
+ ```bash
+ #下载yolov5-lite模型文件(.onnx)
+ Download from https://drive.google.com/file/d/1bJByk9eoS6pv8Z3N4bcLRCV3i7uk24aU/view
+ 官方Repo也支持百度云下载
+ ```
+
+- 手动获取
+
+ 访问[YOLOv5Lite](https://github.com/ppogg/YOLOv5-Lite)
+官方github库，按照指引下载安装，下载`yolov5-lite-xx.pt` 模型，利用 `export.py` 得到`onnx`格式文件。
+
+ - 导出含有decode模块的ONNX文件
+
+ 首先需要参考[YOLOv5-Lite#189](https://github.com/ppogg/YOLOv5-Lite/pull/189)的解决办法，修改代码。
+
+ ```bash
+ #下载yolov5-lite模型文件(.pt)
+ Download from https://drive.google.com/file/d/1oftzqOREGqDCerf7DtD5BZp9YWELlkMe/view
+ 官方Repo也支持百度云下载
+
+ # 导出onnx格式文件
+ python export.py --grid --dynamic --concat --weights PATH/TO/yolov5-lite-xx.pt
+
+
+ ```
+ - 导出无decode模块的ONNX文件(不需要修改代码)
+
+ ```bash
+ #下载yolov5-lite模型文件
+ Download from https://drive.google.com/file/d/1oftzqOREGqDCerf7DtD5BZp9YWELlkMe/view
+ 官方Repo也支持百度云下载
+
+ # 导出onnx格式文件
+ python export.py --grid --dynamic --weights PATH/TO/yolov5-lite-xx.pt
+
+ ```
+
+## 下载预训练ONNX模型
+
+为了方便开发者的测试，下面提供了YOLOv5Lite导出的各系列模型，开发者可直接下载使用。（下表中模型的精度来源于源官方库）
+| 模型 | 大小 | 精度 | 备注 |
+|:---------------------------------------------------------------- |:----- |:----- |:----- |
+| [YOLOv5Lite-e](https://bj.bcebos.com/paddlehub/fastdeploy/v5Lite-e-sim-320.onnx) | 3.1MB | 35.1% | 此模型文件来源于[YOLOv5-Lite](https://github.com/ppogg/YOLOv5-Lite)，GPL-3.0 License |
+| [YOLOv5Lite-s](https://bj.bcebos.com/paddlehub/fastdeploy/v5Lite-s-sim-416.onnx) | 6.3MB | 42.0% | 此模型文件来源于[YOLOv5-Lite](https://github.com/ppogg/YOLOv5-Lite)，GPL-3.0 License |
+| [YOLOv5Lite-c](https://bj.bcebos.com/paddlehub/fastdeploy/v5Lite-c-sim-512.onnx) | 18MB | 50.9% | 此模型文件来源于[YOLOv5-Lite](https://github.com/ppogg/YOLOv5-Lite)，GPL-3.0 License |
+| [YOLOv5Lite-g](https://bj.bcebos.com/paddlehub/fastdeploy/v5Lite-g-sim-640.onnx) | 21MB | 57.6% | 此模型文件来源于[YOLOv5-Lite](https://github.com/ppogg/YOLOv5-Lite)，GPL-3.0 License |
+
+
+## 详细部署文档
+
+- [Python部署](python)
+- [C++部署](cpp)
+
+
+## 版本说明
+
+- 本版本文档和代码基于[YOLOv5-Lite v1.4](https://github.com/ppogg/YOLOv5-Lite/releases/tag/v1.4) 编写
diff --git a/examples/vision/detection/yolov5lite/cpp/README.md b/examples/vision/detection/yolov5lite/cpp/README.md
index 43ec415807..7edbc3b739 100644
--- a/examples/vision/detection/yolov5lite/cpp/README.md
+++ b/examples/vision/detection/yolov5lite/cpp/README.md
@@ -1,46 +1,47 @@
-# YOLOv5Lite C++部署示例
+English | [简体中文](README_CN.md)
+# YOLOv5Lite C++ Deployment Example
-本目录下提供`infer.cc`快速完成YOLOv5Lite在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+This directory provides examples that `infer.cc` fast finishes the deployment of YOLOv5Lite on CPU/GPU and GPU accelerated by TensorRT.
-在部署前，需确认以下两个步骤
+Before deployment, two steps require confirmation
-- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. Download the precompiled deployment library and samples code according to your development environment. Refer to [FastDeploy Precompiled Library](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试，支持此模型需保证FastDeploy版本0.7.0以上(x.x.x>=0.7.0)
+Taking the CPU inference on Linux as an example, the compilation test can be completed by executing the following command in this directory. FastDeploy version 0.7.0 or above (x.x.x>=0.7.0) is required to support this model.
```bash
mkdir build
cd build
-# 下载FastDeploy预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
+# Download the FastDeploy precompiled library. Users can choose your appropriate version in the `FastDeploy Precompiled Library` mentioned above
wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz
tar xvf fastdeploy-linux-x64-x.x.x.tgz
cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x
make -j
-#下载官方转换好的YOLOv5Lite模型文件和测试图片
+# Download the official converted YOLOv5Lite model files and test images
wget https://bj.bcebos.com/paddlehub/fastdeploy/v5Lite-g-sim-640.onnx
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
-# CPU推理
+# CPU inference
./infer_demo v5Lite-g-sim-640.onnx 000000014439.jpg 0
-# GPU推理
+# GPU inference
./infer_demo v5Lite-g-sim-640.onnx 000000014439.jpg 1
-# GPU上TensorRT推理
+# TensorRT inference on GPU
./infer_demo v5Lite-g-sim-640.onnx 000000014439.jpg 2
```
-运行完成可视化结果如下图所示
+The visualized result after running is as follows
-以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
-- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
+The above command works for Linux or MacOS. For SDK use-pattern in Windows, refer to:
+- [How to use FastDeploy C++ SDK in Windows](../../../../../docs/cn/faq/use_sdk_on_windows.md)
-## YOLOv5Lite C++接口
+## YOLOv5Lite C++ Interface
-### YOLOv5Lite类
+### YOLOv5Lite Class
```c++
fastdeploy::vision::detection::YOLOv5Lite(
@@ -50,16 +51,16 @@ fastdeploy::vision::detection::YOLOv5Lite(
const ModelFormat& model_format = ModelFormat::ONNX)
```
-YOLOv5Lite模型加载和初始化，其中model_file为导出的ONNX模型格式。
+YOLOv5Lite model loading and initialization, among which model_file is the exported ONNX model format
-**参数**
+**Parameter**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为ONNX格式
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. Merely passing an empty string when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. ONNX format by default
-#### Predict函数
+#### Predict Function
> ```c++
> YOLOv5Lite::Predict(cv::Mat* im, DetectionResult* result,
@@ -67,26 +68,26 @@ YOLOv5Lite模型加载和初始化，其中model_file为导出的ONNX模型格
> float nms_iou_threshold = 0.5)
> ```
>
-> 模型预测接口，输入图像直接输出检测结果。
+> Model prediction interface. Input images and output detection results.
>
-> **参数**
+> **Parameter**
>
-> > * **im**: 输入图像，注意需为HWC，BGR格式
-> > * **result**: 检测结果，包括检测框，各个框的置信度, DetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
-> > * **conf_threshold**: 检测框置信度过滤阈值
-> > * **nms_iou_threshold**: NMS处理过程中iou阈值
-
-### 类成员变量
-#### 预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
-
-> > * **size**(vector<int>): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
-> > * **padding_value**(vector<float>): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
-> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=ture` 表示不使用填充的方式，默认值为`is_no_pad=false`
-> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=false`
-> > * **stride**(int): 配合`stris_mini_pad`成员变量使用, 默认值为`stride=32`
-
-- [模型介绍](../../)
-- [Python部署](../python)
-- [视觉模型预测结果](../../../../../docs/api/vision_results/)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+> > * **im**: Input images in HWC or BGR format
+> > * **result**: Detection results, including detection box and confidence of each box. Refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/)
+> > * **conf_threshold**: Filtering threshold of detection box confidence
+> > * **nms_iou_threshold**: iou threshold during NMS processing
+
+### Class Member Variable
+#### Pre-processing Parameter
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
+
+> > * **size**(vector<int>): This parameter changes the size of the resize used during preprocessing, containing two integer elements for [width, height] with default value [640, 640]
+> > * **padding_value**(vector<float>): This parameter is used to change the padding value of images during resize, containing three floating-point elements that represent the value of three channels. Default value [114, 114, 114]
+> > * **is_no_pad**(bool): Specify whether to resize the image through padding. `is_no_pad=ture` represents no paddling. Default `is_no_pad=false`
+> > * **is_mini_pad**(bool): This parameter sets the width and height of the image after resize to the value nearest to the `size` member variable and to the point where the padded pixel size is divisible by the `stride` member variable. Default `is_mini_pad=false`
+> > * **stride**(int): Used with the `stris_mini_pad` member variable. Default `stride=32`
+
+- [Model Description](../../)
+- [Python Deployment](../python)
+- [Vision Model Prediction Results](../../../../../docs/api/vision_results/)
+- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/yolov5lite/cpp/README_CN.md b/examples/vision/detection/yolov5lite/cpp/README_CN.md
new file mode 100644
index 0000000000..46b918f5c8
--- /dev/null
+++ b/examples/vision/detection/yolov5lite/cpp/README_CN.md
@@ -0,0 +1,93 @@
+[English](README.md) | 简体中文
+# YOLOv5Lite C++部署示例
+
+本目录下提供`infer.cc`快速完成YOLOv5Lite在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试，支持此模型需保证FastDeploy版本0.7.0以上(x.x.x>=0.7.0)
+
+```bash
+mkdir build
+cd build
+# 下载FastDeploy预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz
+tar xvf fastdeploy-linux-x64-x.x.x.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x
+make -j
+
+#下载官方转换好的YOLOv5Lite模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/v5Lite-g-sim-640.onnx
+wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
+
+
+# CPU推理
+./infer_demo v5Lite-g-sim-640.onnx 000000014439.jpg 0
+# GPU推理
+./infer_demo v5Lite-g-sim-640.onnx 000000014439.jpg 1
+# GPU上TensorRT推理
+./infer_demo v5Lite-g-sim-640.onnx 000000014439.jpg 2
+```
+
+运行完成可视化结果如下图所示
+
+
+
+以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
+- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
+
+## YOLOv5Lite C++接口
+
+### YOLOv5Lite类
+
+```c++
+fastdeploy::vision::detection::YOLOv5Lite(
+ const string& model_file,
+ const string& params_file = "",
+ const RuntimeOption& runtime_option = RuntimeOption(),
+ const ModelFormat& model_format = ModelFormat::ONNX)
+```
+
+YOLOv5Lite模型加载和初始化，其中model_file为导出的ONNX模型格式。
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为ONNX格式
+
+#### Predict函数
+
+> ```c++
+> YOLOv5Lite::Predict(cv::Mat* im, DetectionResult* result,
+> float conf_threshold = 0.25,
+> float nms_iou_threshold = 0.5)
+> ```
+>
+> 模型预测接口，输入图像直接输出检测结果。
+>
+> **参数**
+>
+> > * **im**: 输入图像，注意需为HWC，BGR格式
+> > * **result**: 检测结果，包括检测框，各个框的置信度, DetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > * **conf_threshold**: 检测框置信度过滤阈值
+> > * **nms_iou_threshold**: NMS处理过程中iou阈值
+
+### 类成员变量
+#### 预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> > * **size**(vector<int>): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
+> > * **padding_value**(vector<float>): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
+> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=ture` 表示不使用填充的方式，默认值为`is_no_pad=false`
+> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=false`
+> > * **stride**(int): 配合`stris_mini_pad`成员变量使用, 默认值为`stride=32`
+
+- [模型介绍](../../)
+- [Python部署](../python)
+- [视觉模型预测结果](../../../../../docs/api/vision_results/)
+- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/yolov5lite/python/README.md b/examples/vision/detection/yolov5lite/python/README.md
index ebf8fba944..55a05e1273 100644
--- a/examples/vision/detection/yolov5lite/python/README.md
+++ b/examples/vision/detection/yolov5lite/python/README.md
@@ -1,81 +1,82 @@
-# YOLOv5Lite Python部署示例
+English | [简体中文](README_CN.md)
+# YOLOv5Lite Python Deployment Example
-在部署前，需确认以下两个步骤
+Before deployment, two steps require confirmation
-- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. Install FastDeploy Python whl package. Refer to [FastDeploy Python Installation](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-本目录下提供`infer.py`快速完成YOLOv5Lite在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+This directory provides examples that `infer.py` fast finishes the deployment of YOLOv5Lite on CPU/GPU and GPU accelerated by TensorRT. The script is as follows
```bash
-#下载部署示例代码
+# Download the example code for deployment
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision/detection/yolov5lite/python/
-#下载YOLOv5Lite模型文件和测试图片
+# Download YOLOv5Lite model files and test images
wget https://bj.bcebos.com/paddlehub/fastdeploy/v5Lite-g-sim-640.onnx
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
-# CPU推理
+# CPU inference
python infer.py --model v5Lite-g-sim-640.onnx --image 000000014439.jpg --device cpu
-# GPU推理
+# GPU inference
python infer.py --model v5Lite-g-sim-640.onnx --image 000000014439.jpg --device gpu
-# GPU上使用TensorRT推理
+# TensorRT inference on GPU
python infer.py --model v5Lite-g-sim-640.onnx --image 000000014439.jpg --device gpu --use_trt True
```
-运行完成可视化结果如下图所示
+The visualized result after running is as follows
-## YOLOv5Lite Python接口
+## YOLOv5Lite Python Interface
```python
fastdeploy.vision.detection.YOLOv5Lite(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
```
-YOLOv5Lite模型加载和初始化，其中model_file为导出的ONNX模型格式
+YOLOv5Lite model loading and initialization, among which model_file is the exported ONNX model format
-**参数**
+**Parameter**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为ONNX
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. No need to set when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. ONNX format by default
-### predict函数
+### predict function
> ```python
> YOLOv5Lite.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
> ```
>
-> 模型预测结口，输入图像直接输出检测结果。
+> Model prediction interface. Input images and output detection results.
>
-> **参数**
+> **Parameter**
>
-> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
-> > * **conf_threshold**(float): 检测框置信度过滤阈值
-> > * **nms_iou_threshold**(float): NMS处理过程中iou阈值
+> > * **image_data**(np.ndarray): Input data in HWC or BGR format
+> > * **conf_threshold**(float): Filtering threshold of detection box confidence
+> > * **nms_iou_threshold**(float): iou threshold during NMS processing
-> **返回**
+> **Return**
>
-> > 返回`fastdeploy.vision.DetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > Return `fastdeploy.vision.DetectionResult` structure. Refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for its description.
-### 类成员属性
-#### 预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+### Class Member Property
+#### Pre-processing Parameter
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
-> > * **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
-> > * **padding_value**(list[float]): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
-> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=True` 表示不使用填充的方式，默认值为`is_no_pad=False`
-> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=False`
-> > * **stride**(int): 配合`stris_mini_padide`成员变量使用, 默认值为`stride=32`
+> > * **size**(list[int]): This parameter changes the size of the resize used during preprocessing, containing two integer elements for [width, height] with default value [640, 640]
+> > * **padding_value**(list[float]): This parameter is used to change the padding value of images during resize, containing three floating-point elements that represent the value of three channels. Default value [114, 114, 114]
+> > * **is_no_pad**(bool): Specify whether to resize the image through padding. `is_no_pad=True` represents no paddling. Default `is_no_pad=False`
+> > * **is_mini_pad**(bool): This parameter sets the width and height of the image after resize to the value nearest to the `size` member variable and to the point where the padded pixel size is divisible by the `stride` member variable. Default `is_mini_pad=False`
+> > * **stride**(int): Used with the `stris_mini_padide` member variable. Default `stride=32`
-## 其它文档
+## Other Documents
-- [YOLOv5Lite 模型介绍](..)
-- [YOLOv5Lite C++部署](../cpp)
-- [模型预测结果说明](../../../../../docs/api/vision_results/)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+- [YOLOv5Lite Model Description](..)
+- [YOLOv5Lite C++ Deployment](../cpp)
+- [Model Prediction Results](../../../../../docs/api/vision_results/)
+- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/yolov5lite/python/README_CN.md b/examples/vision/detection/yolov5lite/python/README_CN.md
new file mode 100644
index 0000000000..87f5e8bcdf
--- /dev/null
+++ b/examples/vision/detection/yolov5lite/python/README_CN.md
@@ -0,0 +1,82 @@
+[English](README.md) | 简体中文
+# YOLOv5Lite Python部署示例
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+本目录下提供`infer.py`快速完成YOLOv5Lite在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+
+```bash
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd examples/vision/detection/yolov5lite/python/
+
+#下载YOLOv5Lite模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/v5Lite-g-sim-640.onnx
+wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
+
+# CPU推理
+python infer.py --model v5Lite-g-sim-640.onnx --image 000000014439.jpg --device cpu
+# GPU推理
+python infer.py --model v5Lite-g-sim-640.onnx --image 000000014439.jpg --device gpu
+# GPU上使用TensorRT推理
+python infer.py --model v5Lite-g-sim-640.onnx --image 000000014439.jpg --device gpu --use_trt True
+```
+
+运行完成可视化结果如下图所示
+
+
+
+## YOLOv5Lite Python接口
+
+```python
+fastdeploy.vision.detection.YOLOv5Lite(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
+```
+
+YOLOv5Lite模型加载和初始化，其中model_file为导出的ONNX模型格式
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为ONNX
+
+### predict函数
+
+> ```python
+> YOLOv5Lite.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
+> ```
+>
+> 模型预测结口，输入图像直接输出检测结果。
+>
+> **参数**
+>
+> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
+> > * **conf_threshold**(float): 检测框置信度过滤阈值
+> > * **nms_iou_threshold**(float): NMS处理过程中iou阈值
+
+> **返回**
+>
+> > 返回`fastdeploy.vision.DetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+
+### 类成员属性
+#### 预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> > * **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
+> > * **padding_value**(list[float]): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
+> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=True` 表示不使用填充的方式，默认值为`is_no_pad=False`
+> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=False`
+> > * **stride**(int): 配合`stris_mini_padide`成员变量使用, 默认值为`stride=32`
+
+
+
+## 其它文档
+
+- [YOLOv5Lite 模型介绍](..)
+- [YOLOv5Lite C++部署](../cpp)
+- [模型预测结果说明](../../../../../docs/api/vision_results/)
+- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/yolov6/README.md b/examples/vision/detection/yolov6/README.md
index d31622a8b3..6a63dc07e0 100644
--- a/examples/vision/detection/yolov6/README.md
+++ b/examples/vision/detection/yolov6/README.md
@@ -1,30 +1,33 @@
-# YOLOv6准备部署模型
+English | [简体中文](README_CN.md)
+# YOLOv6 Ready-to-deploy Model
-- YOLOv6 部署实现来自[YOLOv6](https://github.com/meituan/YOLOv6/releases/tag/0.1.0)，和[基于coco的预训练模型](https://github.com/meituan/YOLOv6/releases/tag/0.1.0)。
- - （1）[官方库](https://github.com/meituan/YOLOv6/releases/tag/0.1.0)提供的*.onnx可直接进行部署；
- - （2）开发者自己训练的模型，导出ONNX模型后，参考[详细部署文档](#详细部署文档)完成部署。
+- The YOLOv6 deployment is based on [YOLOv6](https://github.com/meituan/YOLOv6/releases/tag/0.1.0) and [Pre-trained Model Based on COCO](https://github.com/meituan/YOLOv6/releases/tag/0.1.0).
+ - （1）The *.onnx provided by [Official Repository](https://github.com/meituan/YOLOv6/releases/tag/0.1.0) can directly conduct deployemnt；
+ - （2）Personal models trained by developers should export the ONNX model. Refer to [Detailed Deployment Documents](#详细部署文档) to complete the deployment.
-## 下载预训练ONNX模型
-为了方便开发者的测试，下面提供了YOLOv6导出的各系列模型，开发者可直接下载使用。（下表中模型的精度来源于源官方库）
-| 模型 | 大小 | 精度 | 备注 |
+## Download Pre-trained ONNX Model
+
+For developers' testing, models exported by YOLOv6 are provided below. Developers can download them directly. (The accuracy in the following table is derived from the source official repository)
+| Model | Size | Accuracy | Note |
|:---------------------------------------------------------------- |:----- |:----- |:----- |
-| [YOLOv6s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s.onnx) | 66MB | 43.1% | 此模型文件来源于[YOLOv6](https://github.com/meituan/YOLOv6)，GPL-3.0 License |
-| [YOLOv6s_640](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s-640x640.onnx) | 66MB | 43.1% | 此模型文件来源于[YOLOv6](https://github.com/meituan/YOLOv6)，GPL-3.0 License |
-| [YOLOv6t](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6t.onnx) | 58MB | 41.3% | 此模型文件来源于[YOLOv6](https://github.com/meituan/YOLOv6)，GPL-3.0 License |
-| [YOLOv6n](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6n.onnx) | 17MB | 35.0% | 此模型文件来源于[YOLOv6](https://github.com/meituan/YOLOv6)，GPL-3.0 License |
+| [YOLOv6s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s.onnx) | 66MB | 43.1% | This model file is sourced from [YOLOv6](https://github.com/meituan/YOLOv6)，GPL-3.0 License |
+| [YOLOv6s_640](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s-640x640.onnx) | 66MB | 43.1% | This model file is sourced from [YOLOv6](https://github.com/meituan/YOLOv6)，GPL-3.0 License |
+| [YOLOv6t](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6t.onnx) | 58MB | 41.3% | This model file is sourced from [YOLOv6](https://github.com/meituan/YOLOv6)，GPL-3.0 License |
+| [YOLOv6n](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6n.onnx) | 17MB | 35.0% | This model file is sourced from [YOLOv6](https://github.com/meituan/YOLOv6)，GPL-3.0 License |
+
-## 详细部署文档
+## Detailed Deployment Documents
-- [Python部署](python)
-- [C++部署](cpp)
+- [Python Deployment](python)
+- [C++ Deployement](cpp)
-## 版本说明
+## Release Note
-- 本版本文档和代码基于[YOLOv6 0.1.0版本](https://github.com/meituan/YOLOv6/releases/tag/0.1.0) 编写
+- Document and code are based on [YOLOv6 0.1.0 version](https://github.com/meituan/YOLOv6/releases/tag/0.1.0)
diff --git a/examples/vision/detection/yolov6/README_CN.md b/examples/vision/detection/yolov6/README_CN.md
new file mode 100644
index 0000000000..6324969196
--- /dev/null
+++ b/examples/vision/detection/yolov6/README_CN.md
@@ -0,0 +1,31 @@
+[English](README.md) | 简体中文
+# YOLOv6准备部署模型
+
+
+- YOLOv6 部署实现来自[YOLOv6](https://github.com/meituan/YOLOv6/releases/tag/0.1.0)，和[基于coco的预训练模型](https://github.com/meituan/YOLOv6/releases/tag/0.1.0)。
+
+ - （1）[官方库](https://github.com/meituan/YOLOv6/releases/tag/0.1.0)提供的*.onnx可直接进行部署；
+ - （2）开发者自己训练的模型，导出ONNX模型后，参考[详细部署文档](#详细部署文档)完成部署。
+
+
+
+## 下载预训练ONNX模型
+
+为了方便开发者的测试，下面提供了YOLOv6导出的各系列模型，开发者可直接下载使用。（下表中模型的精度来源于源官方库）
+| 模型 | 大小 | 精度 | 备注 |
+|:---------------------------------------------------------------- |:----- |:----- |:----- |
+| [YOLOv6s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s.onnx) | 66MB | 43.1% | 此模型文件来源于[YOLOv6](https://github.com/meituan/YOLOv6)，GPL-3.0 License |
+| [YOLOv6s_640](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s-640x640.onnx) | 66MB | 43.1% | 此模型文件来源于[YOLOv6](https://github.com/meituan/YOLOv6)，GPL-3.0 License |
+| [YOLOv6t](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6t.onnx) | 58MB | 41.3% | 此模型文件来源于[YOLOv6](https://github.com/meituan/YOLOv6)，GPL-3.0 License |
+| [YOLOv6n](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6n.onnx) | 17MB | 35.0% | 此模型文件来源于[YOLOv6](https://github.com/meituan/YOLOv6)，GPL-3.0 License |
+
+
+## 详细部署文档
+
+- [Python部署](python)
+- [C++部署](cpp)
+
+
+## 版本说明
+
+- 本版本文档和代码基于[YOLOv6 0.1.0版本](https://github.com/meituan/YOLOv6/releases/tag/0.1.0) 编写
diff --git a/examples/vision/detection/yolov6/cpp/README.md b/examples/vision/detection/yolov6/cpp/README.md
index eceb5bc46f..75633dfead 100755
--- a/examples/vision/detection/yolov6/cpp/README.md
+++ b/examples/vision/detection/yolov6/cpp/README.md
@@ -1,66 +1,67 @@
-# YOLOv6 C++部署示例
+English | [简体中文](README_CN.md)
+# YOLOv6 C++ Deployment Example
-本目录下提供`infer.cc`快速完成YOLOv6在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+This directory provides examples that `infer.cc` fast finishes the deployment of YOLOv6 on CPU/GPU and GPU accelerated by TensorRT.
-在部署前，需确认以下两个步骤
+Before deployment, two steps require confirmation
-- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. Download the precompiled deployment library and samples code according to your development environment. Refer to [FastDeploy Precompiled Library](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试，支持此模型需保证FastDeploy版本0.7.0以上(x.x.x>=0.7.0)
+Taking the CPU inference on Linux as an example, the compilation test can be completed by executing the following command in this directory. FastDeploy version 0.7.0 or above (x.x.x>=0.7.0) is required to support this model.
```bash
mkdir build
cd build
-# 下载FastDeploy预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
+# Download the FastDeploy precompiled library. Users can choose your appropriate version in the `FastDeploy Precompiled Library` mentioned above
wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz
tar xvf fastdeploy-linux-x64-x.x.x.tgz
cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x
make -j
-#下载Paddle模型文件和测试图片
+# Download Paddle model files and test images
wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s_infer.tar
tar -xf yolov6s_infer.tar
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
-# CPU推理
+# CPU inference
./infer_paddle_demo yolov6s_infer 000000014439.jpg 0
-# GPU推理
+# GPU inference
./infer_paddle_demo yolov6s_infer 000000014439.jpg 1
-# 昆仑芯XPU推理
+# KunlunXin XPU inference
./infer_paddle_demo yolov6s_infer 000000014439.jpg 2
-# 华为昇腾推理
+# HUAWEI Ascend inference
./infer_paddle_demo yolov6s_infer 000000014439.jpg 3
```
-如果用户使用华为昇腾NPU部署, 请参考以下方式在部署前初始化部署环境:
-- [如何使用华为昇腾NPU部署](../../../../../docs/cn/faq/use_sdk_on_ascend.md)
+If you use HUAWEI Ascend NPU deployment, refer to the following document to initialize deployment environment:
+- [How to use HUAWEI Ascend NPU deployment](../../../../../docs/cn/faq/use_sdk_on_ascend.md)
-如果想要验证ONNX模型的推理，可以参考如下命令：
+If you want to verify the inference of ONNX models, refer to the following commands:
```bash
-#下载官方转换好的YOLOv6 ONNX模型文件和测试图片
+# Download the official converted YOLOv6 ONNX model files and test images
wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s.onnx
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
-# CPU推理
+# CPU inference
./infer_demo yolov6s.onnx 000000014439.jpg 0
-# GPU推理
+# GPU inference
./infer_demo yolov6s.onnx 000000014439.jpg 1
-# GPU上TensorRT推理
+# TensorRT inference on GPU
./infer_demo yolov6s.onnx 000000014439.jpg 2
```
-运行完成可视化结果如下图所示
+The visualized result after running is as follows
-以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
-- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
+The above command works for Linux or MacOS. For SDK use-pattern in Windows, refer to:
+- [How to use FastDeploy C++ SDK in Windows](../../../../../docs/cn/faq/use_sdk_on_windows.md)
-## YOLOv6 C++接口
+## YOLOv6 C++ Interface
-### YOLOv6类
+### YOLOv6 Class
```c++
fastdeploy::vision::detection::YOLOv6(
@@ -70,16 +71,16 @@ fastdeploy::vision::detection::YOLOv6(
const ModelFormat& model_format = ModelFormat::ONNX)
```
-YOLOv6模型加载和初始化，其中model_file为导出的ONNX模型格式。
+YOLOv6 model loading and initialization, among which model_file is the exported ONNX model format
-**参数**
+**Parameter**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为ONNX格式
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. Merely passing an empty string when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. ONNX format by default
-#### Predict函数
+#### Predict Function
> ```c++
> YOLOv6::Predict(cv::Mat* im, DetectionResult* result,
@@ -87,26 +88,26 @@ YOLOv6模型加载和初始化，其中model_file为导出的ONNX模型格式。
> float nms_iou_threshold = 0.5)
> ```
>
-> 模型预测接口，输入图像直接输出检测结果。
+> Model prediction interface. Input images and output detection results.
>
-> **参数**
+> **Parameter**
>
-> > * **im**: 输入图像，注意需为HWC，BGR格式
-> > * **result**: 检测结果，包括检测框，各个框的置信度, DetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
-> > * **conf_threshold**: 检测框置信度过滤阈值
-> > * **nms_iou_threshold**: NMS处理过程中iou阈值
-
-### 类成员变量
-#### 预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
-
-> > * **size**(vector<int>): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
-> > * **padding_value**(vector<float>): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
-> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=ture` 表示不使用填充的方式，默认值为`is_no_pad=false`
-> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=false`
-> > * **stride**(int): 配合`is_mini_pad`成员变量使用, 默认值为`stride=32`
-
-- [模型介绍](../../)
-- [Python部署](../python)
-- [视觉模型预测结果](../../../../../docs/api/vision_results/)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+> > * **im**: Input images in HWC or BGR format
+> > * **result**: Detection results, including detection box and confidence of each box. Refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for DetectionResult
+> > * **conf_threshold**: Filtering threshold of detection box confidence
+> > * **nms_iou_threshold**: iou threshold during NMS processing
+
+### Class Member Variable
+#### Pre-processing Parameter
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
+
+> > * **size**(vector<int>): This parameter changes the size of the resize used during preprocessing, containing two integer elements for [width, height] with default value [640, 640]
+> > * **padding_value**(vector<float>): This parameter is used to change the padding value of images during resize, containing three floating-point elements that represent the value of three channels. Default value [114, 114, 114]
+> > * **is_no_pad**(bool): Specify whether to resize the image through padding. `is_no_pad=ture` represents no paddling. Default `is_no_pad=false`
+> > * **is_mini_pad**(bool): This parameter sets the width and height of the image after resize to the value nearest to the `size` member variable and to the point where the padded pixel size is divisible by the `stride` member variable. Default `is_mini_pad=false`
+> > * **stride**(int): Used with the `is_mini_pad` member variable. Default `stride=32`
+
+- [Model Description](../../)
+- [Python Deployment](../python)
+- [Vision Model Prediction Results](../../../../../docs/api/vision_results/)
+- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/yolov6/cpp/README_CN.md b/examples/vision/detection/yolov6/cpp/README_CN.md
new file mode 100644
index 0000000000..901977676a
--- /dev/null
+++ b/examples/vision/detection/yolov6/cpp/README_CN.md
@@ -0,0 +1,113 @@
+[English](README.md) | 简体中文
+# YOLOv6 C++部署示例
+
+本目录下提供`infer.cc`快速完成YOLOv6在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试，支持此模型需保证FastDeploy版本0.7.0以上(x.x.x>=0.7.0)
+
+```bash
+mkdir build
+cd build
+# 下载FastDeploy预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz
+tar xvf fastdeploy-linux-x64-x.x.x.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x
+make -j
+
+#下载Paddle模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s_infer.tar
+tar -xf yolov6s_infer.tar
+wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
+
+# CPU推理
+./infer_paddle_demo yolov6s_infer 000000014439.jpg 0
+# GPU推理
+./infer_paddle_demo yolov6s_infer 000000014439.jpg 1
+# 昆仑芯XPU推理
+./infer_paddle_demo yolov6s_infer 000000014439.jpg 2
+# 华为昇腾推理
+./infer_paddle_demo yolov6s_infer 000000014439.jpg 3
+```
+
+如果用户使用华为昇腾NPU部署, 请参考以下方式在部署前初始化部署环境:
+- [如何使用华为昇腾NPU部署](../../../../../docs/cn/faq/use_sdk_on_ascend.md)
+
+
+如果想要验证ONNX模型的推理，可以参考如下命令：
+```bash
+#下载官方转换好的YOLOv6 ONNX模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s.onnx
+wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
+
+# CPU推理
+./infer_demo yolov6s.onnx 000000014439.jpg 0
+# GPU推理
+./infer_demo yolov6s.onnx 000000014439.jpg 1
+# GPU上TensorRT推理
+./infer_demo yolov6s.onnx 000000014439.jpg 2
+```
+
+运行完成可视化结果如下图所示
+
+
+
+以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
+- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
+
+## YOLOv6 C++接口
+
+### YOLOv6类
+
+```c++
+fastdeploy::vision::detection::YOLOv6(
+ const string& model_file,
+ const string& params_file = "",
+ const RuntimeOption& runtime_option = RuntimeOption(),
+ const ModelFormat& model_format = ModelFormat::ONNX)
+```
+
+YOLOv6模型加载和初始化，其中model_file为导出的ONNX模型格式。
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为ONNX格式
+
+#### Predict函数
+
+> ```c++
+> YOLOv6::Predict(cv::Mat* im, DetectionResult* result,
+> float conf_threshold = 0.25,
+> float nms_iou_threshold = 0.5)
+> ```
+>
+> 模型预测接口，输入图像直接输出检测结果。
+>
+> **参数**
+>
+> > * **im**: 输入图像，注意需为HWC，BGR格式
+> > * **result**: 检测结果，包括检测框，各个框的置信度, DetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > * **conf_threshold**: 检测框置信度过滤阈值
+> > * **nms_iou_threshold**: NMS处理过程中iou阈值
+
+### 类成员变量
+#### 预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> > * **size**(vector<int>): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
+> > * **padding_value**(vector<float>): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
+> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=ture` 表示不使用填充的方式，默认值为`is_no_pad=false`
+> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=false`
+> > * **stride**(int): 配合`is_mini_pad`成员变量使用, 默认值为`stride=32`
+
+- [模型介绍](../../)
+- [Python部署](../python)
+- [视觉模型预测结果](../../../../../docs/api/vision_results/)
+- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/yolov6/python/README.md b/examples/vision/detection/yolov6/python/README.md
index 37a06fd5ce..82d6ce4abd 100755
--- a/examples/vision/detection/yolov6/python/README.md
+++ b/examples/vision/detection/yolov6/python/README.md
@@ -1,14 +1,15 @@
-# YOLOv6 Python部署示例
+English | [简体中文](README_CN.md)
+# YOLOv6 Python Deployment Example
-在部署前，需确认以下两个步骤
+Before deployment, two steps require confirmation
-- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 1. Software and hardware should meet the requirements. Please refer to [FastDeployEnvironment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. Install FastDeploy Python whl package. Refer to [FastDeploy Python Installation](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-本目录下提供`infer.py`快速完成YOLOv6在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+This directory provides examples that `infer.py` fast finishes the deployment of YOLOv6 on CPU/GPU and GPU accelerated by TensorRT. The script is as follows
```bash
-#下载部署示例代码
+# Download the example code for deployment
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision/detection/yolov6/python/
@@ -16,82 +17,80 @@ wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s_infer.tar
tar -xf yolov6s_infer.tar
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
-# CPU推理
+# CPU inference
python infer_paddle_model.py --model yolov6s_infer --image 000000014439.jpg --device cpu
-# GPU推理
+# GPU inference
python infer_paddle_model.py --model yolov6s_infer --image 000000014439.jpg --device gpu
-# 昆仑芯XPU推理
+# KunlunXin XPU inference
python infer_paddle_model.py --model yolov6s_infer --image 000000014439.jpg --device kunlunxin
-# 华为昇腾推理
-python infer_paddle_model.py --model yolov6s_infer --image 000000014439.jpg --device ascend
```
-如果想要验证ONNX模型的推理，可以参考如下命令：
+If you want to verify the inference of ONNX models, refer to the following command:
```bash
-#下载YOLOv6模型文件和测试图片
+# Download YOLOv6 model files and test images
wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s.onnx
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
-# CPU推理
+# CPU inference
python infer.py --model yolov6s.onnx --image 000000014439.jpg --device cpu
-# GPU推理
+# GPU inference
python infer.py --model yolov6s.onnx --image 000000014439.jpg --device gpu
-# GPU上使用TensorRT推理
+# TensorRT inference on GPU
python infer.py --model yolov6s.onnx --image 000000014439.jpg --device gpu --use_trt True
```
-运行完成可视化结果如下图所示
+The visualized result after running is as follows
-## YOLOv6 Python接口
+## YOLOv6 Python Interface
```python
fastdeploy.vision.detection.YOLOv6(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
```
-YOLOv6模型加载和初始化，其中model_file为导出的ONNX模型格式
+YOLOv6 model loading and initialization, among which model_file is the exported ONNX model format
-**参数**
+**Parameter**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为ONNX
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. No need to set when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. ONNX format by default
-### predict函数
+### predict function
> ```python
> YOLOv6.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
> ```
>
-> 模型预测结口，输入图像直接输出检测结果。
+> Model prediction interface. Input images and output detection results.
>
-> **参数**
+> **Parameter**
>
-> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
-> > * **conf_threshold**(float): 检测框置信度过滤阈值
-> > * **nms_iou_threshold**(float): NMS处理过程中iou阈值
+> > * **image_data**(np.ndarray): Input data in HWC or BGR format
+> > * **conf_threshold**(float): Filtering threshold of detection box confidence
+> > * **nms_iou_threshold**(float): iou threshold during NMS processing
-> **返回**
+> **Return**
>
-> > 返回`fastdeploy.vision.DetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > Return `fastdeploy.vision.DetectionResult` structure. Refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for its description.
-### 类成员属性
-#### 预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+### Class Member Property
+#### Pre-processing Parameter
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
-> > * **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
-> > * **padding_value**(list[float]): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
-> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=True` 表示不使用填充的方式，默认值为`is_no_pad=False`
-> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=False`
-> > * **stride**(int): 配合`is_mini_padide`成员变量使用, 默认值为`stride=32`
+> > * **size**(list[int]): This parameter changes the size of the resize used during preprocessing, containing two integer elements for [width, height] with default value [640, 640]
+> > * **padding_value**(list[float]): This parameter is used to change the padding value of images during resize, containing three floating-point elements that represent the value of three channels. Default value [114, 114, 114]
+> > * **is_no_pad**(bool): Specify whether to resize the image through padding. `is_no_pad=True` represents no paddling. Default `is_no_pad=False`
+> > * **is_mini_pad**(bool): This parameter sets the width and height of the image after resize to the value nearest to the `size` member variable and to the point where the padded pixel size is divisible by the `stride` member variable. Default `is_mini_pad=False`
+> > * **stride**(int): Used with the `is_mini_padide` member variable. Default `stride=32`
-## 其它文档
+## Other Documents
-- [YOLOv6 模型介绍](..)
-- [YOLOv6 C++部署](../cpp)
-- [模型预测结果说明](../../../../../docs/api/vision_results/)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+- [YOLOv6 Model Description](..)
+- [YOLOv6 C++ Deployment](../cpp)
+- [Model Prediction Results](../../../../../docs/api/vision_results/)
+- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/yolov6/python/README_CN.md b/examples/vision/detection/yolov6/python/README_CN.md
new file mode 100644
index 0000000000..0f9f91b625
--- /dev/null
+++ b/examples/vision/detection/yolov6/python/README_CN.md
@@ -0,0 +1,98 @@
+[English](README.md) | 简体中文
+# YOLOv6 Python部署示例
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+本目录下提供`infer.py`快速完成YOLOv6在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+
+```bash
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd examples/vision/detection/yolov6/python/
+
+wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s_infer.tar
+tar -xf yolov6s_infer.tar
+wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
+
+# CPU推理
+python infer_paddle_model.py --model yolov6s_infer --image 000000014439.jpg --device cpu
+# GPU推理
+python infer_paddle_model.py --model yolov6s_infer --image 000000014439.jpg --device gpu
+# 昆仑芯XPU推理
+python infer_paddle_model.py --model yolov6s_infer --image 000000014439.jpg --device kunlunxin
+# 华为昇腾推理
+python infer_paddle_model.py --model yolov6s_infer --image 000000014439.jpg --device ascend
+```
+如果想要验证ONNX模型的推理，可以参考如下命令：
+```bash
+#下载YOLOv6模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s.onnx
+wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
+
+# CPU推理
+python infer.py --model yolov6s.onnx --image 000000014439.jpg --device cpu
+# GPU推理
+python infer.py --model yolov6s.onnx --image 000000014439.jpg --device gpu
+# GPU上使用TensorRT推理
+python infer.py --model yolov6s.onnx --image 000000014439.jpg --device gpu --use_trt True
+```
+
+运行完成可视化结果如下图所示
+
+
+
+## YOLOv6 Python接口
+
+```python
+fastdeploy.vision.detection.YOLOv6(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
+```
+
+YOLOv6模型加载和初始化，其中model_file为导出的ONNX模型格式
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为ONNX
+
+### predict函数
+
+> ```python
+> YOLOv6.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
+> ```
+>
+> 模型预测结口，输入图像直接输出检测结果。
+>
+> **参数**
+>
+> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
+> > * **conf_threshold**(float): 检测框置信度过滤阈值
+> > * **nms_iou_threshold**(float): NMS处理过程中iou阈值
+
+> **返回**
+>
+> > 返回`fastdeploy.vision.DetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+
+### 类成员属性
+#### 预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+
+> > * **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
+> > * **padding_value**(list[float]): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
+> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=True` 表示不使用填充的方式，默认值为`is_no_pad=False`
+> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=False`
+> > * **stride**(int): 配合`is_mini_padide`成员变量使用, 默认值为`stride=32`
+
+
+
+## 其它文档
+
+- [YOLOv6 模型介绍](..)
+- [YOLOv6 C++部署](../cpp)
+- [模型预测结果说明](../../../../../docs/api/vision_results/)
+- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/yolov6/quantize/README.md b/examples/vision/detection/yolov6/quantize/README.md
index 57c71cedbf..ce2bbe823e 100755
--- a/examples/vision/detection/yolov6/quantize/README.md
+++ b/examples/vision/detection/yolov6/quantize/README.md
@@ -1,44 +1,30 @@
-# YOLOv6量化模型部署
-FastDeploy已支持部署量化模型,并提供一键模型自动化压缩的工具.
-用户可以使用一键模型自动化压缩工具,自行对模型量化后部署, 也可以直接下载FastDeploy提供的量化模型进行部署.
-
-## FastDeploy一键模型自动化压缩工具
-FastDeploy 提供了一键模型自动化压缩工具, 能够简单地通过输入一个配置文件, 对模型进行量化.
-详细教程请见: [一键模型自动化压缩工具](../../../../../tools/common_tools/auto_compression/)
-## 下载量化完成的YOLOv6s模型
-用户也可以直接下载下表中的量化模型进行部署.(点击模型名字即可下载)
-
-Benchmark表格说明:
-- Runtime时延为模型在各种Runtime上的推理时延,包含CPU->GPU数据拷贝,GPU推理,GPU->CPU数据拷贝时间. 不包含模型各自的前后处理时间.
-- 端到端时延为模型在实际推理场景中的时延, 包含模型的前后处理.
-- 所测时延均为推理1000次后求得的平均值, 单位是毫秒.
-- INT8 + FP16 为在推理INT8量化模型的同时, 给Runtime 开启FP16推理选项
-- INT8 + FP16 + PM, 为在推理INT8量化模型和开启FP16的同时, 开启使用Pinned Memory的选项,可加速GPU->CPU数据拷贝的速度
-- 最大加速比, 为FP32时延除以INT8推理的最快时延,得到最大加速比.
-- 策略为量化蒸馏训练时, 采用少量无标签数据集训练得到量化模型, 并在全量验证集上验证精度, INT8精度并不代表最高的INT8精度.
-- CPU为Intel(R) Xeon(R) Gold 6271C, 所有测试中固定CPU线程数为1. GPU为Tesla T4, TensorRT版本8.4.15.
-
-#### Runtime Benchmark
-| 模型 |推理后端 |部署硬件 | FP32 Runtime时延 | INT8 Runtime时延 | INT8 + FP16 Runtime时延 | INT8+FP16+PM Runtime时延 | 最大加速比 | FP32 mAP | INT8 mAP | 量化方式 |
-| ------------------- | -----------------|-----------| -------- |-------- |-------- | --------- |-------- |----- |----- |----- |
-| [YOLOv6s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s_ptq_model.tar) | TensorRT | GPU | 9.47 | 3.23 | 4.09 |2.81 | 3.37 | 42.5 | 40.7|量化蒸馏训练 |
-| [YOLOv6s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s_ptq_model.tar) | Paddle-TensorRT | GPU | 9.31 | None| 4.17 | 2.95 | 3.16 | 42.5 | 40.7|量化蒸馏训练 |
-| [YOLOv6s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s_ptq_model.tar) | ONNX Runtime | CPU | 334.65 | 126.38 | None | None| 2.65 |42.5| 36.8|量化蒸馏训练 |
-| [YOLOv6s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s_ptq_model.tar) | Paddle Inference | CPU | 352.87 | 123.12 |None | None| 2.87 |42.5| 40.8|量化蒸馏训练 |
-
-
-#### 端到端 Benchmark
-| 模型 |推理后端 |部署硬件 | FP32 End2End时延 | INT8 End2End时延 | INT8 + FP16 End2End时延 | INT8+FP16+PM End2End时延 | 最大加速比 | FP32 mAP | INT8 mAP | 量化方式 |
-| ------------------- | -----------------|-----------| -------- |-------- |-------- | --------- |-------- |----- |----- |----- |
-| [YOLOv6s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s_ptq_model.tar) | TensorRT | GPU | 15.66 | 11.30 | 10.25 |9.59 | 1.63 | 42.5 | 40.7|量化蒸馏训练 |
-| [YOLOv6s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s_ptq_model.tar) | Paddle-TensorRT | GPU | 15.03 | None| 11.36 | 9.32 | 1.61 | 42.5 | 40.7|量化蒸馏训练 |
-| [YOLOv6s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s_ptq_model.tar) | ONNX Runtime | CPU | 348.21 | 126.38 | None | None| 2.82 |42.5| 36.8|量化蒸馏训练 |
-| [YOLOv6s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s_ptq_model.tar) | Paddle Inference | CPU | 352.87 | 121.64 |None | None| 3.04 |42.5| 40.8|量化蒸馏训练 |
-
-
-
-
-## 详细部署文档
-
-- [Python部署](python)
-- [C++部署](cpp)
+English | [简体中文](README_CN.md)
+# YOLOv6 Quantized Model Deployment
+
+FastDeploy supports the deployment of quantized models and provides a one-click model quantization tool.
+Users can use the one-click model quantization tool to quantize and deploy the models themselves or download the quantized models provided by FastDeploy directly for deployment.
+
+## FastDeploy One-Click Model Quantization Tool
+
+FastDeploy provides a one-click quantization tool that allows users to quantize a model simply with a configuration file.
+For detailed tutorial, please refer to : [One-Click Model Quantization Tool](../../../../../tools/common_tools/auto_compression/)
+
+## Download Quantized YOLOv6s Model
+
+Users can also directly download the quantized models in the table below for deployment.
+
+| Model | Inference Backend | Hardware | FP32 Inference Time Delay | INT8 Inference Time Delay | Acceleration ratio | FP32 mAP | INT8 mAP | Method |
+| ----------------------------------------------------------------------- | ----------------- | -------- | -------------------------- | ------------------------- | ------------------ | -------- | -------- | ------------------------------- |
+| [YOLOv6s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s_quant.tar) | TensorRT | GPU | 8.60 | 5.16 | 1.67 | 42.5 | 40.6 | Quantized distillation training |
+| [YOLOv6s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s_quant.tar) | Paddle Inference | CPU | 356.62 | 125.72 | 2.84 | 42.5 | 41.2 | Quantized distillation training |
+
+The data in the above table shows the end-to-end inference performance of FastDeploy deployment before and after model quantization.
+
+- The test images are from COCO val2017.
+- The inference time delay is the inference latency on different Runtimes in milliseconds.
+- CPU is Intel(R) Xeon(R) Gold 6271C, GPU is Tesla T4, TensorRT version 8.4.15, and the fixed CPU thread is 1 for all tests.
+
+## More Detailed Tutorials
+
+- [Python Deployment](python)
+- [C++ Deployment](cpp)
diff --git a/examples/vision/detection/yolov6/quantize/README_CN.md b/examples/vision/detection/yolov6/quantize/README_CN.md
new file mode 100755
index 0000000000..d0b57d82d5
--- /dev/null
+++ b/examples/vision/detection/yolov6/quantize/README_CN.md
@@ -0,0 +1,45 @@
+[English](README.md) | 简体中文
+# YOLOv6量化模型部署
+FastDeploy已支持部署量化模型,并提供一键模型自动化压缩的工具.
+用户可以使用一键模型自动化压缩工具,自行对模型量化后部署, 也可以直接下载FastDeploy提供的量化模型进行部署.
+
+## FastDeploy一键模型自动化压缩工具
+FastDeploy 提供了一键模型自动化压缩工具, 能够简单地通过输入一个配置文件, 对模型进行量化.
+详细教程请见: [一键模型自动化压缩工具](../../../../../tools/common_tools/auto_compression/)
+## 下载量化完成的YOLOv6s模型
+用户也可以直接下载下表中的量化模型进行部署.(点击模型名字即可下载)
+
+Benchmark表格说明:
+- Runtime时延为模型在各种Runtime上的推理时延,包含CPU->GPU数据拷贝,GPU推理,GPU->CPU数据拷贝时间. 不包含模型各自的前后处理时间.
+- 端到端时延为模型在实际推理场景中的时延, 包含模型的前后处理.
+- 所测时延均为推理1000次后求得的平均值, 单位是毫秒.
+- INT8 + FP16 为在推理INT8量化模型的同时, 给Runtime 开启FP16推理选项
+- INT8 + FP16 + PM, 为在推理INT8量化模型和开启FP16的同时, 开启使用Pinned Memory的选项,可加速GPU->CPU数据拷贝的速度
+- 最大加速比, 为FP32时延除以INT8推理的最快时延,得到最大加速比.
+- 策略为量化蒸馏训练时, 采用少量无标签数据集训练得到量化模型, 并在全量验证集上验证精度, INT8精度并不代表最高的INT8精度.
+- CPU为Intel(R) Xeon(R) Gold 6271C, 所有测试中固定CPU线程数为1. GPU为Tesla T4, TensorRT版本8.4.15.
+
+#### Runtime Benchmark
+| 模型 |推理后端 |部署硬件 | FP32 Runtime时延 | INT8 Runtime时延 | INT8 + FP16 Runtime时延 | INT8+FP16+PM Runtime时延 | 最大加速比 | FP32 mAP | INT8 mAP | 量化方式 |
+| ------------------- | -----------------|-----------| -------- |-------- |-------- | --------- |-------- |----- |----- |----- |
+| [YOLOv6s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s_ptq_model.tar) | TensorRT | GPU | 9.47 | 3.23 | 4.09 |2.81 | 3.37 | 42.5 | 40.7|量化蒸馏训练 |
+| [YOLOv6s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s_ptq_model.tar) | Paddle-TensorRT | GPU | 9.31 | None| 4.17 | 2.95 | 3.16 | 42.5 | 40.7|量化蒸馏训练 |
+| [YOLOv6s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s_ptq_model.tar) | ONNX Runtime | CPU | 334.65 | 126.38 | None | None| 2.65 |42.5| 36.8|量化蒸馏训练 |
+| [YOLOv6s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s_ptq_model.tar) | Paddle Inference | CPU | 352.87 | 123.12 |None | None| 2.87 |42.5| 40.8|量化蒸馏训练 |
+
+
+#### 端到端 Benchmark
+| 模型 |推理后端 |部署硬件 | FP32 End2End时延 | INT8 End2End时延 | INT8 + FP16 End2End时延 | INT8+FP16+PM End2End时延 | 最大加速比 | FP32 mAP | INT8 mAP | 量化方式 |
+| ------------------- | -----------------|-----------| -------- |-------- |-------- | --------- |-------- |----- |----- |----- |
+| [YOLOv6s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s_ptq_model.tar) | TensorRT | GPU | 15.66 | 11.30 | 10.25 |9.59 | 1.63 | 42.5 | 40.7|量化蒸馏训练 |
+| [YOLOv6s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s_ptq_model.tar) | Paddle-TensorRT | GPU | 15.03 | None| 11.36 | 9.32 | 1.61 | 42.5 | 40.7|量化蒸馏训练 |
+| [YOLOv6s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s_ptq_model.tar) | ONNX Runtime | CPU | 348.21 | 126.38 | None | None| 2.82 |42.5| 36.8|量化蒸馏训练 |
+| [YOLOv6s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s_ptq_model.tar) | Paddle Inference | CPU | 352.87 | 121.64 |None | None| 3.04 |42.5| 40.8|量化蒸馏训练 |
+
+
+
+
+## 详细部署文档
+
+- [Python部署](python)
+- [C++部署](cpp)
diff --git a/examples/vision/detection/yolov6/quantize/README_EN.md b/examples/vision/detection/yolov6/quantize/README_EN.md
deleted file mode 100755
index 7a13ef7d0e..0000000000
--- a/examples/vision/detection/yolov6/quantize/README_EN.md
+++ /dev/null
@@ -1,29 +0,0 @@
-# YOLOv6 Quantized Model Deployment
-
-FastDeploy supports the deployment of quantized models and provides a one-click model quantization tool.
-Users can use the one-click model quantization tool to quantize and deploy the models themselves or download the quantized models provided by FastDeploy directly for deployment.
-
-## FastDeploy One-Click Model Quantization Tool
-
-FastDeploy provides a one-click quantization tool that allows users to quantize a model simply with a configuration file.
-For detailed tutorial, please refer to : [One-Click Model Quantization Tool](../../../../../tools/common_tools/auto_compression/)
-
-## Download Quantized YOLOv6s Model
-
-Users can also directly download the quantized models in the table below for deployment.
-
-| Model | Inference Backend | Hardware | FP32 Inference Time Delay | INT8 Inference Time Delay | Acceleration ratio | FP32 mAP | INT8 mAP | Method |
-| ----------------------------------------------------------------------- | ----------------- | -------- | -------------------------- | ------------------------- | ------------------ | -------- | -------- | ------------------------------- |
-| [YOLOv6s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s_quant.tar) | TensorRT | GPU | 8.60 | 5.16 | 1.67 | 42.5 | 40.6 | Quantized distillation training |
-| [YOLOv6s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s_quant.tar) | Paddle Inference | CPU | 356.62 | 125.72 | 2.84 | 42.5 | 41.2 | Quantized distillation training |
-
-The data in the above table shows the end-to-end inference performance of FastDeploy deployment before and after model quantization.
-
-- The test images are from COCO val2017.
-- The inference time delay is the inference latency on different Runtimes in milliseconds.
-- CPU is Intel(R) Xeon(R) Gold 6271C, GPU is Tesla T4, TensorRT version 8.4.15, and the fixed CPU thread is 1 for all tests.
-
-## More Detailed Tutorials
-
-- [Python Deployment](python)
-- [C++ Deployment](cpp)
diff --git a/examples/vision/detection/yolov7/README.md b/examples/vision/detection/yolov7/README.md
index d07350fbc5..7a89007a76 100644
--- a/examples/vision/detection/yolov7/README.md
+++ b/examples/vision/detection/yolov7/README.md
@@ -1,48 +1,43 @@
-简体中文 | [English](README_EN.md)
-# YOLOv7准备部署模型
+English | [简体中文](README_CN.md)
-- YOLOv7部署实现来自[YOLOv7](https://github.com/WongKinYiu/yolov7/tree/v0.1)分支代码，和[基于COCO的预训练模型](https://github.com/WongKinYiu/yolov7/releases/tag/v0.1)。
+# YOLOv7 Prepare the model for Deployment
- - （1）[官方库](https://github.com/WongKinYiu/yolov7/releases/tag/v0.1)提供的*.pt通过[导出ONNX模型](#导出ONNX模型)操作后，可进行部署；*.trt和*.pose模型不支持部署；
- - （2）自己数据训练的YOLOv7模型，按照[导出ONNX模型](#%E5%AF%BC%E5%87%BAONNX%E6%A8%A1%E5%9E%8B)操作后，参考[详细部署文档](#详细部署文档)完成部署。
+- YOLOv7 deployment is based on [YOLOv7](https://github.com/WongKinYiu/yolov7/tree/v0.1) branching code, and [COCO Pre-Trained Models](https://github.com/WongKinYiu/yolov7/releases/tag/v0.1).
+ - （1）The *.pt provided by the [Official Library](https://github.com/WongKinYiu/yolov7/releases/tag/v0.1) can be deployed after the [export ONNX model](#export ONNX model) operation; *.trt and *.pose models do not support deployment.
+ - （2）As for YOLOv7 model trained on customized data, please follow the operations guidelines in [Export ONNX model](#Export-ONNX-Model) and then refer to [Detailed Deployment Tutorials](#Detailed-Deployment-Tutorials) to complete the deployment.
-
-
-## 导出ONNX模型
+## Export ONNX Model
```bash
-# 下载yolov7模型文件
+# Download yolov7 model file
wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7.pt
-# 导出onnx格式文件 (Tips: 对应 YOLOv7 release v0.1 代码)
+# Export onnx file (Tips: in accordance with YOLOv7 release v0.1 code)
python models/export.py --grid --dynamic --weights PATH/TO/yolov7.pt
-# 如果您的代码版本中有支持NMS的ONNX文件导出，请使用如下命令导出ONNX文件，并且参考`yolov7end2end_ort` 或 `yolov7end2end_trt`示例使用
+# If your code supports exporting ONNX files with NMS, please use the following command to export ONNX files, then refer to the example of `yolov7end2end_ort` or `yolov7end2end_ort`
python models/export.py --grid --dynamic --end2end --weights PATH/TO/yolov7.pt
-
-
```
-## 下载预训练ONNX模型
-
-为了方便开发者的测试，下面提供了YOLOv7导出的各系列模型，开发者可直接下载使用。（下表中模型的精度来源于源官方库）
-| 模型 | 大小 | 精度 | 备注 |
-|:---------------------------------------------------------------- |:----- |:----- | :----- |
-| [YOLOv7](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7.onnx) | 141MB | 51.4% | 此模型文件来源于[YOLOv7](https://github.com/WongKinYiu/yolov7)，GPL-3.0 License |
-| [YOLOv7x](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7x.onnx) | 273MB | 53.1% | 此模型文件来源于[YOLOv7](https://github.com/WongKinYiu/yolov7)，GPL-3.0 License |
-| [YOLOv7-w6](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-w6.onnx) | 269MB | 54.9% | 此模型文件来源于[YOLOv7](https://github.com/WongKinYiu/yolov7)，GPL-3.0 License |
-| [YOLOv7-e6](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-e6.onnx) | 372MB | 56.0% | 此模型文件来源于[YOLOv7](https://github.com/WongKinYiu/yolov7)，GPL-3.0 License |
-| [YOLOv7-d6](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-d6.onnx) | 511MB | 56.6% | 此模型文件来源于[YOLOv7](https://github.com/WongKinYiu/yolov7)，GPL-3.0 License |
-| [YOLOv7-e6e](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-e6e.onnx) | 579MB | 56.8% | 此模型文件来源于[YOLOv7](https://github.com/WongKinYiu/yolov7)，GPL-3.0 License |
+## Download the pre-trained ONNX model
+To facilitate testing for developers, we provide below the models exported by YOLOv7, which developers can download and use directly. (The accuracy of the models in the table is sourced from the official library)
-## 详细部署文档
+| Model | Size | Accuracy | Note |
+| ------------------------------------------------------------------------ | ----- | -------- | -------- |
+| [YOLOv7](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7.onnx) | 141MB | 51.4% | This model file comes from [YOLOv7](https://github.com/WongKinYiu/yolov7), GPL-3.0 License |
+| [YOLOv7x](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7x.onnx) | 273MB | 53.1% | This model file comes from [YOLOv7](https://github.com/WongKinYiu/yolov7), GPL-3.0 License |
+| [YOLOv7-w6](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-w6.onnx) | 269MB | 54.9% | This model file comes from [YOLOv7](https://github.com/WongKinYiu/yolov7), GPL-3.0 License |
+| [YOLOv7-e6](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-e6.onnx) | 372MB | 56.0% | This model file comes from [YOLOv7](https://github.com/WongKinYiu/yolov7), GPL-3.0 License |
+| [YOLOv7-d6](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-d6.onnx) | 511MB | 56.6% | This model file comes from [YOLOv7](https://github.com/WongKinYiu/yolov7), GPL-3.0 License |
+| [YOLOv7-e6e](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-e6e.onnx) | 579MB | 56.8% | This model file comes from [YOLOv7](https://github.com/WongKinYiu/yolov7), GPL-3.0 License |
-- [Python部署](python)
-- [C++部署](cpp)
+## Detailed Deployment Tutorials
+- [Python Deployment](python)
+- [C++ Deployment](cpp)
-## 版本说明
+## Version
-- 本版本文档和代码基于[YOLOv7 0.1](https://github.com/WongKinYiu/yolov7/tree/v0.1) 编写
+- This tutorial and related code are written based on [YOLOv7 0.1](https://github.com/WongKinYiu/yolov7/tree/v0.1)
diff --git a/examples/vision/detection/yolov7/README_CN.md b/examples/vision/detection/yolov7/README_CN.md
new file mode 100644
index 0000000000..3d7a911f4d
--- /dev/null
+++ b/examples/vision/detection/yolov7/README_CN.md
@@ -0,0 +1,48 @@
+[English](README.md) | 简体中文
+# YOLOv7准备部署模型
+
+- YOLOv7部署实现来自[YOLOv7](https://github.com/WongKinYiu/yolov7/tree/v0.1)分支代码，和[基于COCO的预训练模型](https://github.com/WongKinYiu/yolov7/releases/tag/v0.1)。
+
+ - （1）[官方库](https://github.com/WongKinYiu/yolov7/releases/tag/v0.1)提供的*.pt通过[导出ONNX模型](#导出ONNX模型)操作后，可进行部署；*.trt和*.pose模型不支持部署；
+ - （2）自己数据训练的YOLOv7模型，按照[导出ONNX模型](#%E5%AF%BC%E5%87%BAONNX%E6%A8%A1%E5%9E%8B)操作后，参考[详细部署文档](#详细部署文档)完成部署。
+
+
+
+
+## 导出ONNX模型
+
+```bash
+# 下载yolov7模型文件
+wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7.pt
+
+# 导出onnx格式文件 (Tips: 对应 YOLOv7 release v0.1 代码)
+python models/export.py --grid --dynamic --weights PATH/TO/yolov7.pt
+
+# 如果您的代码版本中有支持NMS的ONNX文件导出，请使用如下命令导出ONNX文件，并且参考`yolov7end2end_ort` 或 `yolov7end2end_trt`示例使用
+python models/export.py --grid --dynamic --end2end --weights PATH/TO/yolov7.pt
+
+
+```
+
+## 下载预训练ONNX模型
+
+为了方便开发者的测试，下面提供了YOLOv7导出的各系列模型，开发者可直接下载使用。（下表中模型的精度来源于源官方库）
+| 模型 | 大小 | 精度 | 备注 |
+|:---------------------------------------------------------------- |:----- |:----- | :----- |
+| [YOLOv7](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7.onnx) | 141MB | 51.4% | 此模型文件来源于[YOLOv7](https://github.com/WongKinYiu/yolov7)，GPL-3.0 License |
+| [YOLOv7x](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7x.onnx) | 273MB | 53.1% | 此模型文件来源于[YOLOv7](https://github.com/WongKinYiu/yolov7)，GPL-3.0 License |
+| [YOLOv7-w6](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-w6.onnx) | 269MB | 54.9% | 此模型文件来源于[YOLOv7](https://github.com/WongKinYiu/yolov7)，GPL-3.0 License |
+| [YOLOv7-e6](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-e6.onnx) | 372MB | 56.0% | 此模型文件来源于[YOLOv7](https://github.com/WongKinYiu/yolov7)，GPL-3.0 License |
+| [YOLOv7-d6](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-d6.onnx) | 511MB | 56.6% | 此模型文件来源于[YOLOv7](https://github.com/WongKinYiu/yolov7)，GPL-3.0 License |
+| [YOLOv7-e6e](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-e6e.onnx) | 579MB | 56.8% | 此模型文件来源于[YOLOv7](https://github.com/WongKinYiu/yolov7)，GPL-3.0 License |
+
+
+## 详细部署文档
+
+- [Python部署](python)
+- [C++部署](cpp)
+
+
+## 版本说明
+
+- 本版本文档和代码基于[YOLOv7 0.1](https://github.com/WongKinYiu/yolov7/tree/v0.1) 编写
diff --git a/examples/vision/detection/yolov7/README_EN.md b/examples/vision/detection/yolov7/README_EN.md
deleted file mode 100644
index 04001beb7b..0000000000
--- a/examples/vision/detection/yolov7/README_EN.md
+++ /dev/null
@@ -1,43 +0,0 @@
-[简体中文](README.md) | English
-
-# YOLOv7 Prepare the model for Deployment
-
-- YOLOv7 deployment is based on [YOLOv7](https://github.com/WongKinYiu/yolov7/tree/v0.1) branching code, and [COCO Pre-Trained Models](https://github.com/WongKinYiu/yolov7/releases/tag/v0.1).
-
- - （1）The *.pt provided by the [Official Library](https://github.com/WongKinYiu/yolov7/releases/tag/v0.1) can be deployed after the [export ONNX model](#export ONNX model) operation; *.trt and *.pose models do not support deployment.
- - （2）As for YOLOv7 model trained on customized data, please follow the operations guidelines in [Export ONNX model](#Export-ONNX-Model) and then refer to [Detailed Deployment Tutorials](#Detailed-Deployment-Tutorials) to complete the deployment.
-
-## Export ONNX Model
-
-```bash
-# Download yolov7 model file
-wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7.pt
-
-# Export onnx file (Tips: in accordance with YOLOv7 release v0.1 code)
-python models/export.py --grid --dynamic --weights PATH/TO/yolov7.pt
-
-# If your code supports exporting ONNX files with NMS, please use the following command to export ONNX files, then refer to the example of `yolov7end2end_ort` or `yolov7end2end_ort`
-python models/export.py --grid --dynamic --end2end --weights PATH/TO/yolov7.pt
-```
-
-## Download the pre-trained ONNX model
-
-To facilitate testing for developers, we provide below the models exported by YOLOv7, which developers can download and use directly. (The accuracy of the models in the table is sourced from the official library)
-
-| Model | Size | Accuracy | Note |
-| ------------------------------------------------------------------------ | ----- | -------- | -------- |
-| [YOLOv7](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7.onnx) | 141MB | 51.4% | This model file comes from [YOLOv7](https://github.com/WongKinYiu/yolov7), GPL-3.0 License |
-| [YOLOv7x](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7x.onnx) | 273MB | 53.1% | This model file comes from [YOLOv7](https://github.com/WongKinYiu/yolov7), GPL-3.0 License |
-| [YOLOv7-w6](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-w6.onnx) | 269MB | 54.9% | This model file comes from [YOLOv7](https://github.com/WongKinYiu/yolov7), GPL-3.0 License |
-| [YOLOv7-e6](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-e6.onnx) | 372MB | 56.0% | This model file comes from [YOLOv7](https://github.com/WongKinYiu/yolov7), GPL-3.0 License |
-| [YOLOv7-d6](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-d6.onnx) | 511MB | 56.6% | This model file comes from [YOLOv7](https://github.com/WongKinYiu/yolov7), GPL-3.0 License |
-| [YOLOv7-e6e](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-e6e.onnx) | 579MB | 56.8% | This model file comes from [YOLOv7](https://github.com/WongKinYiu/yolov7), GPL-3.0 License |
-
-## Detailed Deployment Tutorials
-
-- [Python Deployment](python)
-- [C++ Deployment](cpp)
-
-## Version
-
-- This tutorial and related code are written based on [YOLOv7 0.1](https://github.com/WongKinYiu/yolov7/tree/v0.1)
diff --git a/examples/vision/detection/yolov7/cpp/README.md b/examples/vision/detection/yolov7/cpp/README.md
index 5308f7ddbe..ab5e086074 100755
--- a/examples/vision/detection/yolov7/cpp/README.md
+++ b/examples/vision/detection/yolov7/cpp/README.md
@@ -1,18 +1,19 @@
-# YOLOv7 C++部署示例
+English | [简体中文](README_CN.md)
+# YOLOv7 C++ Deployment Example
-本目录下提供`infer.cc`快速完成YOLOv7在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+This directory provides examples that `infer.cc` fast finishes the deployment of YOLOv7 on CPU/GPU and GPU accelerated by TensorRT.
-在部署前，需确认以下两个步骤
+Before deployment, two steps require confirmation
-- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. Download the precompiled deployment library and samples code according to your development environment. Refer to [FastDeploy Precompiled Library](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试，支持此模型需保证FastDeploy版本0.7.0以上(x.x.x>=0.7.0)
+Taking the CPU inference on Linux as an example, the compilation test can be completed by executing the following command in this directory. FastDeploy version 0.7.0 or above (x.x.x>=0.7.0) is required to support this model.
```bash
mkdir build
cd build
-# 下载FastDeploy预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
+# Download the FastDeploy precompiled library. Users can choose your appropriate version in the `FastDeploy Precompiled Library` mentioned above
wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz
tar xvf fastdeploy-linux-x64-x.x.x.tgz
cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x
@@ -22,44 +23,38 @@ wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_infer.tar
tar -xf yolov7_infer.tar
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
-# CPU推理
+# CPU inference
./infer_paddle_model_demo yolov7_infer 000000014439.jpg 0
-# GPU推理
+# GPU inference
./infer_paddle_model_demo yolov7_infer 000000014439.jpg 1
-# 昆仑芯XPU推理
+# KunlunXin XPU inference
./infer_paddle_model_demo yolov7_infer 000000014439.jpg 2
-# 华为昇腾推理
-./infer_paddle_model_demo yolov7_infer 000000014439.jpg 3
```
-
-如果用户使用华为昇腾NPU部署, 请参考以下方式在部署前初始化部署环境:
-- [如何使用华为昇腾NPU部署](../../../../../docs/cn/faq/use_sdk_on_ascend.md)
-
-如果想要验证ONNX模型的推理，可以参考如下命令：
+If you want to verify the inference of ONNX models, refer to the following command:
```bash
-#下载官方转换好的yolov7 ONNX模型文件和测试图片
+# Download the official converted yolov7 ONNX model files and test images
wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov7.onnx
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
-# CPU推理
+# CPU inference
./infer_demo yolov7.onnx 000000014439.jpg 0
-# GPU推理
+# GPU inference
./infer_demo yolov7.onnx 000000014439.jpg 1
-# GPU上TensorRT推理
+# TensorRT inference on GPU
./infer_demo yolov7.onnx 000000014439.jpg 2
```
-运行完成可视化结果如下图所示
+The visualized result after running is as follows
-以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
-- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
+The above command works for Linux or MacOS. For SDK use-pattern in Windows, refer to:
+- [How to use FastDeploy C++ SDK in Windows](../../../../../docs/cn/faq/use_sdk_on_windows.md)
-## YOLOv7 C++接口
+## YOLOv7 C++ Interface
-### YOLOv7类
+### YOLOv7 Class
```c++
fastdeploy::vision::detection::YOLOv7(
@@ -69,16 +64,16 @@ fastdeploy::vision::detection::YOLOv7(
const ModelFormat& model_format = ModelFormat::ONNX)
```
-YOLOv7模型加载和初始化，其中model_file为导出的ONNX模型格式。
+YOLOv7 model loading and initialization, among which model_file is the exported ONNX model format
-**参数**
+**Parameter**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为ONNX格式
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. Merely passing an empty string when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. ONNX format by default
-#### Predict函数
+#### Predict Function
> ```c++
> YOLOv7::Predict(cv::Mat* im, DetectionResult* result,
@@ -86,26 +81,26 @@ YOLOv7模型加载和初始化，其中model_file为导出的ONNX模型格式。
> float nms_iou_threshold = 0.5)
> ```
>
-> 模型预测接口，输入图像直接输出检测结果。
+> Model prediction interface. Input images and output detection results.
>
-> **参数**
+> **Parameter**
>
-> > * **im**: 输入图像，注意需为HWC，BGR格式
-> > * **result**: 检测结果，包括检测框，各个框的置信度, DetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
-> > * **conf_threshold**: 检测框置信度过滤阈值
-> > * **nms_iou_threshold**: NMS处理过程中iou阈值
-
-### 类成员变量
-#### 预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
-
-> > * **size**(vector<int>): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
-> > * **padding_value**(vector<float>): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
-> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=ture` 表示不使用填充的方式，默认值为`is_no_pad=false`
-> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=false`
-> > * **stride**(int): 配合`stris_mini_pad`成员变量使用, 默认值为`stride=32`
-
-- [模型介绍](../../)
-- [Python部署](../python)
-- [视觉模型预测结果](../../../../../docs/api/vision_results/)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+> > * **im**: Input images in HWC or BGR format
+> > * **result**: Detection results, including detection box and confidence of each box. Refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for DetectionResult
+> > * **conf_threshold**: Filtering threshold of detection box confidence
+> > * **nms_iou_threshold**: iou threshold during NMS processing
+
+### Class Member Variable
+#### Pre-processing Parameter
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
+
+> > * **size**(vector<int>): This parameter changes the size of the resize used during preprocessing, containing two integer elements for [width, height] with default value [640, 640]
+> > * **padding_value**(vector<float>): This parameter is used to change the padding value of images during resize, containing three floating-point elements that represent the value of three channels. Default value [114, 114, 114]
+> > * **is_no_pad**(bool): Specify whether to resize the image through padding. `is_no_pad=ture` represents no paddling. Default `is_no_pad=false`
+> > * **is_mini_pad**(bool): This parameter sets the width and height of the image after resize to the value nearest to the `size` member variable and to the point where the padded pixel size is divisible by the `stride` member variable. Default `is_mini_pad=false`
+> > * **stride**(int): Used with the `stris_mini_pad` member variable. Default `stride=32`
+
+- [Model Description](../../)
+- [Python Deployment](../python)
+- [Vision Model Prediction Results](../../../../../docs/api/vision_results/)
+- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/yolov7/cpp/README_CN.md b/examples/vision/detection/yolov7/cpp/README_CN.md
new file mode 100644
index 0000000000..5de2c9c2cc
--- /dev/null
+++ b/examples/vision/detection/yolov7/cpp/README_CN.md
@@ -0,0 +1,112 @@
+[English](README.md) | 简体中文
+# YOLOv7 C++部署示例
+
+本目录下提供`infer.cc`快速完成YOLOv7在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试，支持此模型需保证FastDeploy版本0.7.0以上(x.x.x>=0.7.0)
+
+```bash
+mkdir build
+cd build
+# 下载FastDeploy预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz
+tar xvf fastdeploy-linux-x64-x.x.x.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x
+make -j
+
+wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_infer.tar
+tar -xf yolov7_infer.tar
+wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
+
+# CPU推理
+./infer_paddle_model_demo yolov7_infer 000000014439.jpg 0
+# GPU推理
+./infer_paddle_model_demo yolov7_infer 000000014439.jpg 1
+# 昆仑芯XPU推理
+./infer_paddle_model_demo yolov7_infer 000000014439.jpg 2
+# 华为昇腾推理
+./infer_paddle_model_demo yolov7_infer 000000014439.jpg 3
+```
+
+如果用户使用华为昇腾NPU部署, 请参考以下方式在部署前初始化部署环境:
+- [如何使用华为昇腾NPU部署](../../../../../docs/cn/faq/use_sdk_on_ascend.md)
+
+如果想要验证ONNX模型的推理，可以参考如下命令：
+```bash
+#下载官方转换好的yolov7 ONNX模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov7.onnx
+wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
+
+
+# CPU推理
+./infer_demo yolov7.onnx 000000014439.jpg 0
+# GPU推理
+./infer_demo yolov7.onnx 000000014439.jpg 1
+# GPU上TensorRT推理
+./infer_demo yolov7.onnx 000000014439.jpg 2
+```
+
+运行完成可视化结果如下图所示
+
+
+
+以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
+- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
+
+## YOLOv7 C++接口
+
+### YOLOv7类
+
+```c++
+fastdeploy::vision::detection::YOLOv7(
+ const string& model_file,
+ const string& params_file = "",
+ const RuntimeOption& runtime_option = RuntimeOption(),
+ const ModelFormat& model_format = ModelFormat::ONNX)
+```
+
+YOLOv7模型加载和初始化，其中model_file为导出的ONNX模型格式。
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为ONNX格式
+
+#### Predict函数
+
+> ```c++
+> YOLOv7::Predict(cv::Mat* im, DetectionResult* result,
+> float conf_threshold = 0.25,
+> float nms_iou_threshold = 0.5)
+> ```
+>
+> 模型预测接口，输入图像直接输出检测结果。
+>
+> **参数**
+>
+> > * **im**: 输入图像，注意需为HWC，BGR格式
+> > * **result**: 检测结果，包括检测框，各个框的置信度, DetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > * **conf_threshold**: 检测框置信度过滤阈值
+> > * **nms_iou_threshold**: NMS处理过程中iou阈值
+
+### 类成员变量
+#### 预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> > * **size**(vector<int>): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
+> > * **padding_value**(vector<float>): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
+> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=ture` 表示不使用填充的方式，默认值为`is_no_pad=false`
+> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=false`
+> > * **stride**(int): 配合`stris_mini_pad`成员变量使用, 默认值为`stride=32`
+
+- [模型介绍](../../)
+- [Python部署](../python)
+- [视觉模型预测结果](../../../../../docs/api/vision_results/)
+- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/yolov7/python/README.md b/examples/vision/detection/yolov7/python/README.md
index a925e78efa..2df6126ede 100755
--- a/examples/vision/detection/yolov7/python/README.md
+++ b/examples/vision/detection/yolov7/python/README.md
@@ -1,98 +1,99 @@
-简体中文 | [English](README_EN.md)
+English | [简体中文](README_CN.md)
-# YOLOv7 Python部署示例
-在部署前，需确认以下两个步骤
+# YOLOv7 Python Deployment Demo
-- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+Two steps before deployment:
-本目录下提供`infer.py`快速完成YOLOv7在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+- 1. The hardware and software environment meets the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. Install FastDeploy Python whl package. Please refer to [FastDeploy Python Installation](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+
+This doc provides a quick `infer.py` demo of YOLOv7 deployment on CPU/GPU, and accelerated GPU deployment by TensorRT. Run the following command:
```bash
-#下载部署示例代码
+# Download sample deployment code
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision/detection/yolov7/python/
-
wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_infer.tar
tar -xf yolov7_infer.tar
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
-# CPU推理
+# CPU
python infer_paddle_model.py --model yolov7_infer --image 000000014439.jpg --device cpu
-# GPU推理
+# GPU
python infer_paddle_model.py --model yolov7_infer --image 000000014439.jpg --device gpu
-# 昆仑芯XPU推理
+# KunlunXin XPU
python infer_paddle_model.py --model yolov7_infer --image 000000014439.jpg --device kunlunxin
-# 华为昇腾推理
+# Huawei Ascend
python infer_paddle_model.py --model yolov7_infer --image 000000014439.jpg --device ascend
```
-如果想要验证ONNX模型的推理，可以参考如下命令：
+If you want to test ONNX model:
```bash
-#下载yolov7模型文件和测试图片
+# Download yolov7 model files and test images
wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov7.onnx
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
-# CPU推理
+# CPU Inference
python infer.py --model yolov7.onnx --image 000000014439.jpg --device cpu
-# GPU推理
+# GPU
python infer.py --model yolov7.onnx --image 000000014439.jpg --device gpu
-# GPU上使用TensorRT推理
+# Infer with TensorRT on GPU
python infer.py --model yolov7.onnx --image 000000014439.jpg --device gpu --use_trt True
```
-运行完成可视化结果如下图所示
+The visualisation of the results is as follows.
-## YOLOv7 Python接口
+## YOLOv7 Python Interface
```python
fastdeploy.vision.detection.YOLOv7(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
```
-YOLOv7模型加载和初始化，其中model_file为导出的ONNX模型格式
+YOLOv7 model loading and initialisation, with model_file being the exported ONNX model format.
-**参数**
+**Parameters**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为ONNX
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. If the model format is ONNX, the parameter can be filled with an empty string.
+> * **runtime_option**(RuntimeOption): Back-end inference configuration. The default is None, i.e. the default is applied
+> * **model_format**(ModelFormat): Model format. The default is ONNX format
-### predict函数
+### Predict Function
> ```python
> YOLOv7.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
> ```
>
-> 模型预测结口，输入图像直接输出检测结果。
+> Model prediction interface with direct output of detection results from the image input.
>
-> **参数**
+> **Parameters**
>
-> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
-> > * **conf_threshold**(float): 检测框置信度过滤阈值
-> > * **nms_iou_threshold**(float): NMS处理过程中iou阈值
+> > * **image_data**(np.ndarray): Input image. Images need to be in HWC or BGR format
+> > * **conf_threshold**(float): Filter threshold for detection box confidence
+> > * **nms_iou_threshold**(float): iou thresholds during NMS processing
-> **返回**
+> **Return**
>
-> > 返回`fastdeploy.vision.DetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > Return to`fastdeploy.vision.DetectionResult`Struct. For more details, please refer to [Vision Model Results](../../../../../docs/api/vision_results/)
-### 类成员属性
-#### 预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+### Class Member Variables
-> > * **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
-> > * **padding_value**(list[float]): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
-> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=True` 表示不使用填充的方式，默认值为`is_no_pad=False`
-> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=False`
-> > * **stride**(int): 配合`stris_mini_padide`成员变量使用, 默认值为`stride=32`
+#### Pre-processing parameters
+Users can modify the following pre-processing parameters for their needs. This will affect the final reasoning and deployment results
+> > * **size**(list[int]): This parameter modifies the 'resize' during preprocessing and contains two integer elements representing [width, height]. The default value is [640, 640].
+> > * **padding_value**(list[float]): This parameter modifies the value of the padding when resizing the image. It contains three floating-point elements, representing the values of the three channels. The default value is [114, 114, 114].
+> > * **is_no_pad**(bool): This parameter determines whether the image is resized by padding, `is_no_pad=ture` means no padding is used. The default value is `is_no_pad=false`.
+> > * **is_mini_pad**(bool): This parameter allows the width and height of the image after resize to be the closest value to the `size` member variable, which the pixel size of the padding can be divided by the `stride` member variable. The default value is `is_mini_pad=false`.
+> > * **stride**(int): Used with`stris_mini_pad` member value. The default value is`stride=32`
-## 其它文档
+## Related files
-- [YOLOv7 模型介绍](..)
-- [YOLOv7 C++部署](../cpp)
-- [模型预测结果说明](../../../../../docs/api/vision_results/)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+- [YOLOv7 Model Introduction](..)
+- [YOLOv7 C++ Deployment](../cpp)
+- [Vision Model Results](../../../../../docs/api/vision_results/)
+- [how to change inference backend](../../../../../docs/en/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/yolov7/python/README_CN.md b/examples/vision/detection/yolov7/python/README_CN.md
new file mode 100755
index 0000000000..bb6d56e777
--- /dev/null
+++ b/examples/vision/detection/yolov7/python/README_CN.md
@@ -0,0 +1,98 @@
+[English](README.md) | 简体中文
+
+# YOLOv7 Python部署示例
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+本目录下提供`infer.py`快速完成YOLOv7在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+
+```bash
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd examples/vision/detection/yolov7/python/
+
+wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_infer.tar
+tar -xf yolov7_infer.tar
+wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
+
+# CPU推理
+python infer_paddle_model.py --model yolov7_infer --image 000000014439.jpg --device cpu
+# GPU推理
+python infer_paddle_model.py --model yolov7_infer --image 000000014439.jpg --device gpu
+# 昆仑芯XPU推理
+python infer_paddle_model.py --model yolov7_infer --image 000000014439.jpg --device kunlunxin
+# 华为昇腾推理
+python infer_paddle_model.py --model yolov7_infer --image 000000014439.jpg --device ascend
+```
+如果想要验证ONNX模型的推理，可以参考如下命令：
+```bash
+#下载yolov7模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov7.onnx
+wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
+
+# CPU推理
+python infer.py --model yolov7.onnx --image 000000014439.jpg --device cpu
+# GPU推理
+python infer.py --model yolov7.onnx --image 000000014439.jpg --device gpu
+# GPU上使用TensorRT推理
+python infer.py --model yolov7.onnx --image 000000014439.jpg --device gpu --use_trt True
+```
+
+运行完成可视化结果如下图所示
+
+
+
+## YOLOv7 Python接口
+
+```python
+fastdeploy.vision.detection.YOLOv7(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
+```
+
+YOLOv7模型加载和初始化，其中model_file为导出的ONNX模型格式
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为ONNX
+
+### predict函数
+
+> ```python
+> YOLOv7.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
+> ```
+>
+> 模型预测结口，输入图像直接输出检测结果。
+>
+> **参数**
+>
+> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
+> > * **conf_threshold**(float): 检测框置信度过滤阈值
+> > * **nms_iou_threshold**(float): NMS处理过程中iou阈值
+
+> **返回**
+>
+> > 返回`fastdeploy.vision.DetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+
+### 类成员属性
+#### 预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> > * **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
+> > * **padding_value**(list[float]): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
+> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=True` 表示不使用填充的方式，默认值为`is_no_pad=False`
+> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=False`
+> > * **stride**(int): 配合`stris_mini_padide`成员变量使用, 默认值为`stride=32`
+
+
+
+## 其它文档
+
+- [YOLOv7 模型介绍](..)
+- [YOLOv7 C++部署](../cpp)
+- [模型预测结果说明](../../../../../docs/api/vision_results/)
+- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/yolov7/python/README_EN.md b/examples/vision/detection/yolov7/python/README_EN.md
deleted file mode 100755
index ee7b486b3c..0000000000
--- a/examples/vision/detection/yolov7/python/README_EN.md
+++ /dev/null
@@ -1,98 +0,0 @@
-English | [简体中文](README.md)
-
-# YOLOv7 Python Deployment Demo
-
-Two steps before deployment:
-
-- 1. The hardware and software environment meets the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 2. Install FastDeploy Python whl package. Please refer to [FastDeploy Python Installation](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-
-
-This doc provides a quick `infer.py` demo of YOLOv7 deployment on CPU/GPU, and accelerated GPU deployment by TensorRT. Run the following command:
-
-```bash
-# Download sample deployment code
-git clone https://github.com/PaddlePaddle/FastDeploy.git
-cd examples/vision/detection/yolov7/python/
-wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_infer.tar
-tar -xf yolov7_infer.tar
-wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
-
-# CPU
-python infer_paddle_model.py --model yolov7_infer --image 000000014439.jpg --device cpu
-# GPU
-python infer_paddle_model.py --model yolov7_infer --image 000000014439.jpg --device gpu
-# KunlunXin XPU
-python infer_paddle_model.py --model yolov7_infer --image 000000014439.jpg --device kunlunxin
-# Huawei Ascend
-python infer_paddle_model.py --model yolov7_infer --image 000000014439.jpg --device ascend
-```
-If you want to test ONNX model:
-```bash
-# Download yolov7 model files and test images
-wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov7.onnx
-wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
-
-# CPU Inference
-python infer.py --model yolov7.onnx --image 000000014439.jpg --device cpu
-# GPU
-python infer.py --model yolov7.onnx --image 000000014439.jpg --device gpu
-# Infer with TensorRT on GPU
-python infer.py --model yolov7.onnx --image 000000014439.jpg --device gpu --use_trt True
-```
-
-The visualisation of the results is as follows.
-
-
-
-## YOLOv7 Python Interface
-
-```python
-fastdeploy.vision.detection.YOLOv7(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
-```
-
-YOLOv7 model loading and initialisation, with model_file being the exported ONNX model format.
-
-**Parameters**
-
-> * **model_file**(str): Model file path
-> * **params_file**(str): Parameter file path. If the model format is ONNX, the parameter can be filled with an empty string.
-> * **runtime_option**(RuntimeOption): Back-end inference configuration. The default is None, i.e. the default is applied
-> * **model_format**(ModelFormat): Model format. The default is ONNX format
-
-### Predict Function
-
-> ```python
-> YOLOv7.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
-> ```
->
-> Model prediction interface with direct output of detection results from the image input.
->
-> **Parameters**
->
-> > * **image_data**(np.ndarray): Input image. Images need to be in HWC or BGR format
-> > * **conf_threshold**(float): Filter threshold for detection box confidence
-> > * **nms_iou_threshold**(float): iou thresholds during NMS processing
-
-> **Return**
->
-> > Return to`fastdeploy.vision.DetectionResult`Struct. For more details, please refer to [Vision Model Results](../../../../../docs/api/vision_results/)
-
-### Class Member Variables
-
-#### Pre-processing parameters
-
-Users can modify the following pre-processing parameters for their needs. This will affect the final reasoning and deployment results
-
-> > * **size**(list[int]): This parameter modifies the 'resize' during preprocessing and contains two integer elements representing [width, height]. The default value is [640, 640].
-> > * **padding_value**(list[float]): This parameter modifies the value of the padding when resizing the image. It contains three floating-point elements, representing the values of the three channels. The default value is [114, 114, 114].
-> > * **is_no_pad**(bool): This parameter determines whether the image is resized by padding, `is_no_pad=ture` means no padding is used. The default value is `is_no_pad=false`.
-> > * **is_mini_pad**(bool): This parameter allows the width and height of the image after resize to be the closest value to the `size` member variable, which the pixel size of the padding can be divided by the `stride` member variable. The default value is `is_mini_pad=false`.
-> > * **stride**(int): Used with`stris_mini_pad` member value. The default value is`stride=32`
-
-## Related files
-
-- [YOLOv7 Model Introduction](..)
-- [YOLOv7 C++ Deployment](../cpp)
-- [Vision Model Results](../../../../../docs/api/vision_results/)
-- [how to change inference backend](../../../../../docs/en/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/yolov7/quantize/README.md b/examples/vision/detection/yolov7/quantize/README.md
index e1bbc2f699..9034a4b232 100755
--- a/examples/vision/detection/yolov7/quantize/README.md
+++ b/examples/vision/detection/yolov7/quantize/README.md
@@ -1,42 +1,30 @@
-# YOLOv7量化模型部署
-FastDeploy已支持部署量化模型,并提供一键模型自动化压缩的工具.
-用户可以使用一键模型自动化压缩工具,自行对模型量化后部署, 也可以直接下载FastDeploy提供的量化模型进行部署.
-
-## FastDeploy一键模型自动化压缩工具
-FastDeploy 提供了一键模型自动化压缩工具, 能够简单地通过输入一个配置文件, 对模型进行量化.
-详细教程请见: [一键模型自动化压缩工具](../../../../../tools/common_tools/auto_compression/)
-
-## 下载量化完成的YOLOv7模型
-用户也可以直接下载下表中的量化模型进行部署.(点击模型名字即可下载)
-
-
-Benchmark表格说明:
-- Runtime时延为模型在各种Runtime上的推理时延,包含CPU->GPU数据拷贝,GPU推理,GPU->CPU数据拷贝时间. 不包含模型各自的前后处理时间.
-- 端到端时延为模型在实际推理场景中的时延, 包含模型的前后处理.
-- 所测时延均为推理1000次后求得的平均值, 单位是毫秒.
-- INT8 + FP16 为在推理INT8量化模型的同时, 给Runtime 开启FP16推理选项
-- INT8 + FP16 + PM, 为在推理INT8量化模型和开启FP16的同时, 开启使用Pinned Memory的选项,可加速GPU->CPU数据拷贝的速度
-- 最大加速比, 为FP32时延除以INT8推理的最快时延,得到最大加速比.
-- 策略为量化蒸馏训练时, 采用少量无标签数据集训练得到量化模型, 并在全量验证集上验证精度, INT8精度并不代表最高的INT8精度.
-- CPU为Intel(R) Xeon(R) Gold 6271C, 所有测试中固定CPU线程数为1. GPU为Tesla T4, TensorRT版本8.4.15.
-
-#### Runtime Benchmark
-| 模型 |推理后端 |部署硬件 | FP32 Runtime时延 | INT8 Runtime时延 | INT8 + FP16 Runtime时延 | INT8+FP16+PM Runtime时延 | 最大加速比 | FP32 mAP | INT8 mAP | 量化方式 |
-| ------------------- | -----------------|-----------| -------- |-------- |-------- | --------- |-------- |----- |----- |----- |
-| [YOLOv7](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_quant.tar) | TensorRT | GPU | 27.47 | 6.52 | 6.74| 5.19| 5.29 | 51.1| 50.4|量化蒸馏训练 |
-| [YOLOv7](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_quant.tar) | Paddle-TensorRT | GPU | 27.87|None|6.91|5.86 | 4.76 | 51.1| 50.4|量化蒸馏训练 |
-| [YOLOv7](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_quant.tar) | ONNX Runtime | CPU | 996.65 | 467.15 |None|None | 2.13 | 51.1 | 43.3|量化蒸馏训练 |
-| [YOLOv7](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_quant.tar) | Paddle Inference | CPU | 995.85 | 477.93|None|None | 2.08 |51.1 | 46.2|量化蒸馏训练 |
-
-#### 端到端 Benchmark
-| 模型 |推理后端 |部署硬件 | FP32 End2End时延 | INT8 End2End时延 | INT8 + FP16 End2End时延 | INT8+FP16+PM End2End时延 | 最大加速比 | FP32 mAP | INT8 mAP | 量化方式 |
-| ------------------- | -----------------|-----------| -------- |-------- |-------- | --------- |-------- |----- |----- |----- |
-| [YOLOv7](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_quant.tar) | TensorRT | GPU | 36.47 | 18.81 | 20.33| 17.58| 2.07 | 51.1| 50.4|量化蒸馏训练 |
-| [YOLOv7](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_quant.tar) | Paddle-TensorRT | GPU | 37.06|None|20.26|17.53 | 2.11 | 51.1| 50.4|量化蒸馏训练 |
-| [YOLOv7](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_quant.tar) | ONNX Runtime | CPU | 988.85 | 478.08 |None|None | 2.07 | 51.1 | 43.3|量化蒸馏训练 |
-| [YOLOv7](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_quant.tar) | Paddle Inference | CPU | 1031.73 | 500.12|None|None | 2.06 |51.1 | 46.2|量化蒸馏训练 |
-
-## 详细部署文档
-
-- [Python部署](python)
-- [C++部署](cpp)
+English | [简体中文](README_CN.md)
+# YOLOv7 Quantized Model Deployment
+
+FastDeploy supports the deployment of quantized models and provides a one-click model quantization tool.
+Users can use the one-click model quantization tool to quantize and deploy the models themselves or download the quantized models provided by FastDeploy directly for deployment.
+
+## FastDeploy One-Click Model Quantization Tool
+
+FastDeploy provides a one-click quantization tool that allows users to quantize a model simply with a configuration file.
+For detailed tutorial, please refer to : [One-Click Model Quantization Tool](../../../../../tools/common_tools/auto_compression/)
+
+## Download Quantized YOLOv7 Model
+
+Users can also directly download the quantized models in the table below for deployment.
+
+| Model | Inference Backend | Hardware | FP32 Inference Time Delay | FP32 Inference Time Delay | Acceleration ratio | FP32 mAP | INT8 mAP | Method |
+| --------------------------------------------------------------------- | ----------------- | -------- | ------------------------- | ------------------------- | ------------------ | -------- | -------- | ------------------------------- |
+| [YOLOv7](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_quant.tar) | TensorRT | GPU | 24.57 | 9.40 | 2.61 | 51.1 | 50.8 | Quantized distillation training |
+| [YOLOv7](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_quant.tar) | Paddle Inference | CPU | 1022.55 | 490.87 | 2.08 | 51.1 | 46.3 | Quantized distillation training |
+
+The data in the above table shows the end-to-end inference performance of FastDeploy deployment before and after model quantization.
+
+- The test images are from COCO val2017.
+- The inference time delay is the inference latency on different Runtimes in milliseconds.
+- CPU is Intel(R) Xeon(R) Gold 6271C, GPU is Tesla T4, TensorRT version 8.4.15, and the fixed CPU thread is 1 for all tests.
+
+## More Detailed Tutorials
+
+- [Python Deployment](python)
+- [C++ Deployment](cpp)
diff --git a/examples/vision/detection/yolov7/quantize/README_CN.md b/examples/vision/detection/yolov7/quantize/README_CN.md
new file mode 100755
index 0000000000..6d5482b5a5
--- /dev/null
+++ b/examples/vision/detection/yolov7/quantize/README_CN.md
@@ -0,0 +1,43 @@
+[English](README.md) | 简体中文
+# YOLOv7量化模型部署
+FastDeploy已支持部署量化模型,并提供一键模型自动化压缩的工具.
+用户可以使用一键模型自动化压缩工具,自行对模型量化后部署, 也可以直接下载FastDeploy提供的量化模型进行部署.
+
+## FastDeploy一键模型自动化压缩工具
+FastDeploy 提供了一键模型自动化压缩工具, 能够简单地通过输入一个配置文件, 对模型进行量化.
+详细教程请见: [一键模型自动化压缩工具](../../../../../tools/common_tools/auto_compression/)
+
+## 下载量化完成的YOLOv7模型
+用户也可以直接下载下表中的量化模型进行部署.(点击模型名字即可下载)
+
+
+Benchmark表格说明:
+- Runtime时延为模型在各种Runtime上的推理时延,包含CPU->GPU数据拷贝,GPU推理,GPU->CPU数据拷贝时间. 不包含模型各自的前后处理时间.
+- 端到端时延为模型在实际推理场景中的时延, 包含模型的前后处理.
+- 所测时延均为推理1000次后求得的平均值, 单位是毫秒.
+- INT8 + FP16 为在推理INT8量化模型的同时, 给Runtime 开启FP16推理选项
+- INT8 + FP16 + PM, 为在推理INT8量化模型和开启FP16的同时, 开启使用Pinned Memory的选项,可加速GPU->CPU数据拷贝的速度
+- 最大加速比, 为FP32时延除以INT8推理的最快时延,得到最大加速比.
+- 策略为量化蒸馏训练时, 采用少量无标签数据集训练得到量化模型, 并在全量验证集上验证精度, INT8精度并不代表最高的INT8精度.
+- CPU为Intel(R) Xeon(R) Gold 6271C, 所有测试中固定CPU线程数为1. GPU为Tesla T4, TensorRT版本8.4.15.
+
+#### Runtime Benchmark
+| 模型 |推理后端 |部署硬件 | FP32 Runtime时延 | INT8 Runtime时延 | INT8 + FP16 Runtime时延 | INT8+FP16+PM Runtime时延 | 最大加速比 | FP32 mAP | INT8 mAP | 量化方式 |
+| ------------------- | -----------------|-----------| -------- |-------- |-------- | --------- |-------- |----- |----- |----- |
+| [YOLOv7](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_quant.tar) | TensorRT | GPU | 27.47 | 6.52 | 6.74| 5.19| 5.29 | 51.1| 50.4|量化蒸馏训练 |
+| [YOLOv7](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_quant.tar) | Paddle-TensorRT | GPU | 27.87|None|6.91|5.86 | 4.76 | 51.1| 50.4|量化蒸馏训练 |
+| [YOLOv7](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_quant.tar) | ONNX Runtime | CPU | 996.65 | 467.15 |None|None | 2.13 | 51.1 | 43.3|量化蒸馏训练 |
+| [YOLOv7](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_quant.tar) | Paddle Inference | CPU | 995.85 | 477.93|None|None | 2.08 |51.1 | 46.2|量化蒸馏训练 |
+
+#### 端到端 Benchmark
+| 模型 |推理后端 |部署硬件 | FP32 End2End时延 | INT8 End2End时延 | INT8 + FP16 End2End时延 | INT8+FP16+PM End2End时延 | 最大加速比 | FP32 mAP | INT8 mAP | 量化方式 |
+| ------------------- | -----------------|-----------| -------- |-------- |-------- | --------- |-------- |----- |----- |----- |
+| [YOLOv7](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_quant.tar) | TensorRT | GPU | 36.47 | 18.81 | 20.33| 17.58| 2.07 | 51.1| 50.4|量化蒸馏训练 |
+| [YOLOv7](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_quant.tar) | Paddle-TensorRT | GPU | 37.06|None|20.26|17.53 | 2.11 | 51.1| 50.4|量化蒸馏训练 |
+| [YOLOv7](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_quant.tar) | ONNX Runtime | CPU | 988.85 | 478.08 |None|None | 2.07 | 51.1 | 43.3|量化蒸馏训练 |
+| [YOLOv7](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_quant.tar) | Paddle Inference | CPU | 1031.73 | 500.12|None|None | 2.06 |51.1 | 46.2|量化蒸馏训练 |
+
+## 详细部署文档
+
+- [Python部署](python)
+- [C++部署](cpp)
diff --git a/examples/vision/detection/yolov7/quantize/README_EN.md b/examples/vision/detection/yolov7/quantize/README_EN.md
deleted file mode 100755
index 5a1add2e6c..0000000000
--- a/examples/vision/detection/yolov7/quantize/README_EN.md
+++ /dev/null
@@ -1,29 +0,0 @@
-# YOLOv7 Quantized Model Deployment
-
-FastDeploy supports the deployment of quantized models and provides a one-click model quantization tool.
-Users can use the one-click model quantization tool to quantize and deploy the models themselves or download the quantized models provided by FastDeploy directly for deployment.
-
-## FastDeploy One-Click Model Quantization Tool
-
-FastDeploy provides a one-click quantization tool that allows users to quantize a model simply with a configuration file.
-For detailed tutorial, please refer to : [One-Click Model Quantization Tool](../../../../../tools/common_tools/auto_compression/)
-
-## Download Quantized YOLOv7 Model
-
-Users can also directly download the quantized models in the table below for deployment.
-
-| Model | Inference Backend | Hardware | FP32 Inference Time Delay | FP32 Inference Time Delay | Acceleration ratio | FP32 mAP | INT8 mAP | Method |
-| --------------------------------------------------------------------- | ----------------- | -------- | ------------------------- | ------------------------- | ------------------ | -------- | -------- | ------------------------------- |
-| [YOLOv7](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_quant.tar) | TensorRT | GPU | 24.57 | 9.40 | 2.61 | 51.1 | 50.8 | Quantized distillation training |
-| [YOLOv7](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_quant.tar) | Paddle Inference | CPU | 1022.55 | 490.87 | 2.08 | 51.1 | 46.3 | Quantized distillation training |
-
-The data in the above table shows the end-to-end inference performance of FastDeploy deployment before and after model quantization.
-
-- The test images are from COCO val2017.
-- The inference time delay is the inference latency on different Runtimes in milliseconds.
-- CPU is Intel(R) Xeon(R) Gold 6271C, GPU is Tesla T4, TensorRT version 8.4.15, and the fixed CPU thread is 1 for all tests.
-
-## More Detailed Tutorials
-
-- [Python Deployment](python)
-- [C++ Deployment](cpp)
diff --git a/examples/vision/detection/yolov7end2end_ort/README.md b/examples/vision/detection/yolov7end2end_ort/README.md
index 8b733bd25f..3b393b7ff7 100644
--- a/examples/vision/detection/yolov7end2end_ort/README.md
+++ b/examples/vision/detection/yolov7end2end_ort/README.md
@@ -1,41 +1,43 @@
-# YOLOv7End2EndORT 准备部署模型
+English | [简体中文](README_CN.md)
-YOLOv7End2EndORT 部署实现来自[YOLOv7](https://github.com/WongKinYiu/yolov7/tree/v0.1)分支代码，和[基于COCO的预训练模型](https://github.com/WongKinYiu/yolov7/releases/tag/v0.1)。注意，YOLOv7End2EndORT是专门用于推理YOLOv7中导出模型带[ORT_NMS](https://github.com/WongKinYiu/yolov7/blob/main/models/experimental.py#L87) 版本的End2End模型，不带nms的模型推理请使用YOLOv7类，而 [TRT_NMS](https://github.com/WongKinYiu/yolov7/blob/main/models/experimental.py#L111) 版本的End2End模型请使用YOLOv7End2EndTRT进行推理。
+# YOLOv7End2EndORT Ready-to-deploy Model
- - （1）[官方库](https://github.com/WongKinYiu/yolov7/releases/tag/v0.1)提供的*.pt通过[导出ONNX模型](#导出ONNX模型)操作后，可进行部署；*.trt和*.pose模型不支持部署；
- - （2）自己数据训练的YOLOv7模型，按照[导出ONNX模型](#%E5%AF%BC%E5%87%BAONNX%E6%A8%A1%E5%9E%8B)操作后，参考[详细部署文档](#详细部署文档)完成部署。
+The YOLOv7End2EndORT deployment is based on [YOLOv7](https://github.com/WongKinYiu/yolov7/tree/v0.1)branch code and [Pre-trained Model Based on COCO](https://github.com/WongKinYiu/yolov7/releases/tag/v0.1). Attention: YOLOv7End2EndORT is designed for the inference of exported End2End models in the [ORT_NMS](https://github.com/WongKinYiu/yolov7/blob/main/models/experimental.py#L87) version in YOLOv7. YOLOv7 class is for the inference of models without nms. YOLOv7End2EndTRT is for the inference of End2End models in the [TRT_NMS](https://github.com/WongKinYiu/yolov7/blob/main/models/experimental.py#L111) version.
+ - （1）*.pt provided by [Official Repository](https://github.com/WongKinYiu/yolov7/releases/tag/v0.1) should [Export the ONNX Model](#导出ONNX模型) to complete the employment. The deployment of *.trt and *.pose models is not supported.
+ - （2）The YOLOv7 model trained by personal data should [Export the ONNX Model](#%E5%AF%BC%E5%87%BAONNX%E6%A8%A1%E5%9E%8B). Refer to [Detailed Deployment Documents](#详细部署文档) to complete the deployment.
-## 导出ONNX模型
+
+## Export the ONNX Model
```bash
-# 下载yolov7模型文件
+# Download yolov7 model files
wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7.pt
-# 导出带ORT_NMS的onnx格式文件 (Tips: 对应 YOLOv7 release v0.1 代码)
+# Export files in onnx format with ORT_NMS (Tips: Corresponding to the code of YOLOv7 release v0.1)
python export.py --weights yolov7.pt --grid --end2end --simplify --topk-all 100 --iou-thres 0.65 --conf-thres 0.35 --img-size 640 640 --max-wh 640
-# 导出其他模型的命令类似 将yolov7.pt替换成 yolov7x.pt yolov7-d6.pt yolov7-w6.pt ...
+# The commands for exporting other models are similar Replace yolov7.pt with yolov7x.pt yolov7-d6.pt yolov7-w6.pt ...
```
-## 下载预训练ONNX模型
+## Download the Pre-trained ONNX Model
-为了方便开发者的测试，下面提供了YOLOv7End2EndORT导出的各系列模型，开发者可直接下载使用。（下表中模型的精度来源于源官方库）
-| 模型 | 大小 | 精度 | 备注 |
+For developers' testing, models exported by YOLOv7End2EndORT are provided below. Developers can download them directly. (The accuracy in the following table is derived from the source official repository)
+| Model | Size | Accuracy | Note |
|:---------------------------------------------------------------- |:----- |:----- |:----- |
-| [yolov7-end2end-ort-nms](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-end2end-ort-nms.onnx) | 141MB | 51.4% | 此模型文件来源于[YOLOv7](https://github.com/WongKinYiu/yolov7)，GPL-3.0 License |
-| [yolov7x-end2end-ort-nms](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7x-end2end-ort-nms.onnx) | 273MB | 53.1% | 此模型文件来源于[YOLOv7](https://github.com/WongKinYiu/yolov7)，GPL-3.0 License |
-| [yolov7-w6-end2end-ort-nms](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-w6-end2end-ort-nms.onnx) | 269MB | 54.9% | 此模型文件来源于[YOLOv7](https://github.com/WongKinYiu/yolov7)，GPL-3.0 License |
-| [yolov7-e6-end2end-ort-nms](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-e6-end2end-ort-nms.onnx) | 372MB | 56.0% | 此模型文件来源于[YOLOv7](https://github.com/WongKinYiu/yolov7)，GPL-3.0 License |
-| [yolov7-d6-end2end-ort-nms](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-d6-end2end-ort-nms.onnx) | 511MB | 56.6% | 此模型文件来源于[YOLOv7](https://github.com/WongKinYiu/yolov7)，GPL-3.0 License |
-| [yolov7-e6e-end2end-ort-nms](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-e6e-end2end-ort-nms.onnx) | 579MB | 56.8% | 此模型文件来源于[YOLOv7](https://github.com/WongKinYiu/yolov7)，GPL-3.0 License |
+| [yolov7-end2end-ort-nms](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-end2end-ort-nms.onnx) | 141MB | 51.4% | This model file is sourced from [YOLOv7](https://github.com/WongKinYiu/yolov7)，GPL-3.0 License |
+| [yolov7x-end2end-ort-nms](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7x-end2end-ort-nms.onnx) | 273MB | 53.1% | This model file is sourced from [YOLOv7](https://github.com/WongKinYiu/yolov7)，GPL-3.0 License |
+| [yolov7-w6-end2end-ort-nms](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-w6-end2end-ort-nms.onnx) | 269MB | 54.9% | This model file is sourced from [YOLOv7](https://github.com/WongKinYiu/yolov7)，GPL-3.0 License |
+| [yolov7-e6-end2end-ort-nms](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-e6-end2end-ort-nms.onnx) | 372MB | 56.0% | This model file is sourced from [YOLOv7](https://github.com/WongKinYiu/yolov7)，GPL-3.0 License |
+| [yolov7-d6-end2end-ort-nms](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-d6-end2end-ort-nms.onnx) | 511MB | 56.6% | This model file is sourced from [YOLOv7](https://github.com/WongKinYiu/yolov7)，GPL-3.0 License |
+| [yolov7-e6e-end2end-ort-nms](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-e6e-end2end-ort-nms.onnx) | 579MB | 56.8% | This model file is sourced from [YOLOv7](https://github.com/WongKinYiu/yolov7)，GPL-3.0 License |
-## 详细部署文档
+## Detailed Deployment Documents
-- [Python部署](python)
-- [C++部署](cpp)
+- [Python Deployment](python)
+- [C++ Deployment](cpp)
-## 版本说明
+## Release Note
-- 本版本文档和代码基于[YOLOv7 0.1](https://github.com/WongKinYiu/yolov7/tree/v0.1) 编写
+- Document and code are based on [YOLOv7 0.1](https://github.com/WongKinYiu/yolov7/tree/v0.1)
diff --git a/examples/vision/detection/yolov7end2end_ort/README_CN.md b/examples/vision/detection/yolov7end2end_ort/README_CN.md
new file mode 100644
index 0000000000..af0a5dfe7c
--- /dev/null
+++ b/examples/vision/detection/yolov7end2end_ort/README_CN.md
@@ -0,0 +1,42 @@
+[English](README.md) | 简体中文
+# YOLOv7End2EndORT 准备部署模型
+
+YOLOv7End2EndORT 部署实现来自[YOLOv7](https://github.com/WongKinYiu/yolov7/tree/v0.1)分支代码，和[基于COCO的预训练模型](https://github.com/WongKinYiu/yolov7/releases/tag/v0.1)。注意，YOLOv7End2EndORT是专门用于推理YOLOv7中导出模型带[ORT_NMS](https://github.com/WongKinYiu/yolov7/blob/main/models/experimental.py#L87) 版本的End2End模型，不带nms的模型推理请使用YOLOv7类，而 [TRT_NMS](https://github.com/WongKinYiu/yolov7/blob/main/models/experimental.py#L111) 版本的End2End模型请使用YOLOv7End2EndTRT进行推理。
+
+ - （1）[官方库](https://github.com/WongKinYiu/yolov7/releases/tag/v0.1)提供的*.pt通过[导出ONNX模型](#导出ONNX模型)操作后，可进行部署；*.trt和*.pose模型不支持部署；
+ - （2）自己数据训练的YOLOv7模型，按照[导出ONNX模型](#%E5%AF%BC%E5%87%BAONNX%E6%A8%A1%E5%9E%8B)操作后，参考[详细部署文档](#详细部署文档)完成部署。
+
+
+## 导出ONNX模型
+
+```bash
+# 下载yolov7模型文件
+wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7.pt
+
+# 导出带ORT_NMS的onnx格式文件 (Tips: 对应 YOLOv7 release v0.1 代码)
+python export.py --weights yolov7.pt --grid --end2end --simplify --topk-all 100 --iou-thres 0.65 --conf-thres 0.35 --img-size 640 640 --max-wh 640
+# 导出其他模型的命令类似 将yolov7.pt替换成 yolov7x.pt yolov7-d6.pt yolov7-w6.pt ...
+```
+
+## 下载预训练ONNX模型
+
+为了方便开发者的测试，下面提供了YOLOv7End2EndORT导出的各系列模型，开发者可直接下载使用。（下表中模型的精度来源于源官方库）
+| 模型 | 大小 | 精度 | 备注 |
+|:---------------------------------------------------------------- |:----- |:----- |:----- |
+| [yolov7-end2end-ort-nms](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-end2end-ort-nms.onnx) | 141MB | 51.4% | 此模型文件来源于[YOLOv7](https://github.com/WongKinYiu/yolov7)，GPL-3.0 License |
+| [yolov7x-end2end-ort-nms](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7x-end2end-ort-nms.onnx) | 273MB | 53.1% | 此模型文件来源于[YOLOv7](https://github.com/WongKinYiu/yolov7)，GPL-3.0 License |
+| [yolov7-w6-end2end-ort-nms](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-w6-end2end-ort-nms.onnx) | 269MB | 54.9% | 此模型文件来源于[YOLOv7](https://github.com/WongKinYiu/yolov7)，GPL-3.0 License |
+| [yolov7-e6-end2end-ort-nms](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-e6-end2end-ort-nms.onnx) | 372MB | 56.0% | 此模型文件来源于[YOLOv7](https://github.com/WongKinYiu/yolov7)，GPL-3.0 License |
+| [yolov7-d6-end2end-ort-nms](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-d6-end2end-ort-nms.onnx) | 511MB | 56.6% | 此模型文件来源于[YOLOv7](https://github.com/WongKinYiu/yolov7)，GPL-3.0 License |
+| [yolov7-e6e-end2end-ort-nms](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-e6e-end2end-ort-nms.onnx) | 579MB | 56.8% | 此模型文件来源于[YOLOv7](https://github.com/WongKinYiu/yolov7)，GPL-3.0 License |
+
+
+## 详细部署文档
+
+- [Python部署](python)
+- [C++部署](cpp)
+
+
+## 版本说明
+
+- 本版本文档和代码基于[YOLOv7 0.1](https://github.com/WongKinYiu/yolov7/tree/v0.1) 编写
diff --git a/examples/vision/detection/yolov7end2end_ort/cpp/README.md b/examples/vision/detection/yolov7end2end_ort/cpp/README.md
index b5c18f183e..fc2128a1bf 100644
--- a/examples/vision/detection/yolov7end2end_ort/cpp/README.md
+++ b/examples/vision/detection/yolov7end2end_ort/cpp/README.md
@@ -1,50 +1,51 @@
-# YOLOv7End2EndORT C++部署示例
+English | [简体中文](README_CN.md)
+# YOLOv7End2EndORT C++ Deployment Example
-本目录下提供`infer.cc`快速完成YOLOv7End2EndORT在CPU/GPU部署的示例。
+This directory provides examples that `infer.cc` fast finishes the deployment of YOLOv7End2EndORT on CPU/GPU accelerated by TensorRT.
-在部署前，需确认以下两个步骤
+Two steps before deployment
-- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. Download the precompiled deployment library and samples code according to your development environment. Refer to [FastDeploy Precompiled Library](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-以Linux上推理为例，在本目录执行如下命令即可完成编译测试，支持此模型需保证FastDeploy版本0.7.0以上(x.x.x>=0.7.0)
+Taking the inference on Linux as an example, the compilation test can be completed by executing the following command in this directory. FastDeploy version 0.7.0 or above (x.x.x>=0.7.0) is required to support this model.
```bash
mkdir build
cd build
-# 下载FastDeploy预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
+# Download the FastDeploy precompiled library. Users can choose your appropriate version in the `FastDeploy Precompiled Library` mentioned above
wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz
tar xvf fastdeploy-linux-x64-x.x.x.tgz
cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x
make -j
-#下载官方转换好的yolov7模型文件和测试图片
+# Download the official converted yolov7 model files and test images
wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-end2end-ort-nms.onnx
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
-# CPU推理
+# CPU inference
./infer_demo yolov7-end2end-ort-nms.onnx 000000014439.jpg 0
-# GPU推理
+# GPU inference
./infer_demo yolov7-end2end-ort-nms.onnx 000000014439.jpg 1
-# TensorRT + GPU 部署 (暂不支持 会回退到 ORT + GPU)
+# TensorRT + GPU deployment (Not supported yet. Back to ORT + GPU)
./infer_demo yolov7-end2end-ort-nms.onnx 000000014439.jpg 2
```
-运行完成可视化结果如下图所示
+The visualized result after running is as follows
+
+
+
+
-以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
-- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
+The above command works for Linux or MacOS. For SDK use-pattern in Windows, refer to:
+
+- [How to use FastDeploy C++ SDK in Windows](../../../../../docs/cn/faq/use_sdk_on_windows.md)
-## YOLOX C++接口
+## YOLOX C++ Interface
-### YOLOX类
+### YOLOX Class
```c++
fastdeploy::vision::detection::YOLOX(
@@ -50,42 +53,45 @@ fastdeploy::vision::detection::YOLOX(
const ModelFormat& model_format = ModelFormat::ONNX)
```
-YOLOX模型加载和初始化，其中model_file为导出的ONNX模型格式。
+YOLOX model loading and initialization, among which model_file is the exported ONNX model format.
-**参数**
+**Parameter**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为ONNX格式
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. Merely passing an empty string when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. ONNX format by default
-#### Predict函数
+#### Predict Function
> ```c++
> YOLOX::Predict(cv::Mat* im, DetectionResult* result,
-> float conf_threshold = 0.25,
-> float nms_iou_threshold = 0.5)
+> float conf_threshold = 0.25,
+> float nms_iou_threshold = 0.5)
> ```
>
-> 模型预测接口，输入图像直接输出检测结果。
+> Model prediction interface. Input images and output detection results.
>
-> **参数**
+> **Parameter**
>
-> > * **im**: 输入图像，注意需为HWC，BGR格式
-> > * **result**: 检测结果，包括检测框，各个框的置信度, DetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
-> > * **conf_threshold**: 检测框置信度过滤阈值
-> > * **nms_iou_threshold**: NMS处理过程中iou阈值
-
-### 类成员变量
-#### 预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
-
-> > * **size**(vector<int>): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
-> > * **padding_value**(vector<float>): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
-> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=ture` 表示不使用填充的方式，默认值为`is_no_pad=false`
-> > * **is_decode_exported**(bool): 表示导出的YOLOX的onnx模型文件是否带坐标反算的decode部分, 默认值为`is_decode_exported=false`，官方默认的导出不带decode部分，如果您导出的模型带了decode，请将此参数设置为true
-
-- [模型介绍](../../)
-- [Python部署](../python)
-- [视觉模型预测结果](../../../../../docs/api/vision_results/)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+> > * **im**: Input images in HWC or BGR format
+> > * **result**: Detection results, including detection box and confidence of each box. Refer to [Vision Model Prediction Result](../../../../../docs/api/vision_results/) for DetectionResult
+> > * **conf_threshold**: Filtering threshold of detection box confidence
+> > * **nms_iou_threshold**: iou threshold during NMS processing
+
+### Class Member Variable
+
+#### Pre-processing Parameter
+
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
+
+> > * **size**(vector<int>): This parameter changes resize used during preprocessing, containing two integer elements for [width, height] with default value [640, 640]
+> > * **padding_value**(vector<float>): This parameter is used to change the padding value of images during resize, containing three floating-point elements that represent the value of three channels. Default value [114, 114, 114]
+> > * **is_no_pad**(bool): Specify whether to resize the image through padding. `is_no_pad=ture` represents no paddling. Default `is_no_pad=false`
+> > * **is_decode_exported**(bool): Whether the decode part with coordinate inversion is contained in the exported YOLOX onnx model files. Default `is_decode_exported=false`. The default export doesn’t cover this part. Set this parameter to true if your model is decode exported
+
+
+- [Model Description](../../)
+- [Python Deployment](../python)
+- [Vision Model Prediction Results](../../../../../docs/api/vision_results/)
+- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/yolox/cpp/README_CN.md b/examples/vision/detection/yolox/cpp/README_CN.md
new file mode 100644
index 0000000000..cec212445d
--- /dev/null
+++ b/examples/vision/detection/yolox/cpp/README_CN.md
@@ -0,0 +1,92 @@
+[English](README.md) | 简体中文
+# YOLOX C++部署示例
+
+本目录下提供`infer.cc`快速完成YOLOX在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试，支持此模型需保证FastDeploy版本0.7.0以上(x.x.x>=0.7.0)
+
+```bash
+mkdir build
+cd build
+# 下载FastDeploy预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz
+tar xvf fastdeploy-linux-x64-x.x.x.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x
+make -j
+
+#下载官方转换好的YOLOX模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/yolox_s.onnx
+wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
+
+
+# CPU推理
+./infer_demo yolox_s.onnx 000000014439.jpg 0
+# GPU推理
+./infer_demo yolox_s.onnx 000000014439.jpg 1
+# GPU上TensorRT推理
+./infer_demo yolox_s.onnx 000000014439.jpg 2
+```
+
+运行完成可视化结果如下图所示
+
+
+
+以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
+- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
+
+## YOLOX C++接口
+
+### YOLOX类
+
+```c++
+fastdeploy::vision::detection::YOLOX(
+ const string& model_file,
+ const string& params_file = "",
+ const RuntimeOption& runtime_option = RuntimeOption(),
+ const ModelFormat& model_format = ModelFormat::ONNX)
+```
+
+YOLOX模型加载和初始化，其中model_file为导出的ONNX模型格式。
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为ONNX格式
+
+#### Predict函数
+
+> ```c++
+> YOLOX::Predict(cv::Mat* im, DetectionResult* result,
+> float conf_threshold = 0.25,
+> float nms_iou_threshold = 0.5)
+> ```
+>
+> 模型预测接口，输入图像直接输出检测结果。
+>
+> **参数**
+>
+> > * **im**: 输入图像，注意需为HWC，BGR格式
+> > * **result**: 检测结果，包括检测框，各个框的置信度, DetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > * **conf_threshold**: 检测框置信度过滤阈值
+> > * **nms_iou_threshold**: NMS处理过程中iou阈值
+
+### 类成员变量
+#### 预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> > * **size**(vector<int>): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
+> > * **padding_value**(vector<float>): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
+> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=ture` 表示不使用填充的方式，默认值为`is_no_pad=false`
+> > * **is_decode_exported**(bool): 表示导出的YOLOX的onnx模型文件是否带坐标反算的decode部分, 默认值为`is_decode_exported=false`，官方默认的导出不带decode部分，如果您导出的模型带了decode，请将此参数设置为true
+
+- [模型介绍](../../)
+- [Python部署](../python)
+- [视觉模型预测结果](../../../../../docs/api/vision_results/)
+- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/yolox/python/README.md b/examples/vision/detection/yolox/python/README.md
index b4029d9654..308802698b 100644
--- a/examples/vision/detection/yolox/python/README.md
+++ b/examples/vision/detection/yolox/python/README.md
@@ -1,79 +1,80 @@
-# YOLOX Python部署示例
+English | [简体中文](README_CN.md)
+# YOLOX Python Deployment Example
-在部署前，需确认以下两个步骤
+Two steps before deployment
-- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. Install FastDeploy Python whl package. Refer to [FastDeploy Python Installation](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-本目录下提供`infer.py`快速完成YOLOX在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+This directory provides examples that `infer.py` fast finishes the deployment of YOLOX on CPU/GPU and GPU accelerated by TensorRT. The script is as follows
```bash
-#下载部署示例代码
+# Download the example code for deployment
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision/detection/yolox/python/
-#下载YOLOX模型文件和测试图片
+# Download YOLOX model files and test images
wget https://bj.bcebos.com/paddlehub/fastdeploy/yolox_s.onnx
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
-# CPU推理
+# CPU inference
python infer.py --model yolox_s.onnx --image 000000014439.jpg --device cpu
-# GPU推理
+# GPU inference
python infer.py --model yolox_s.onnx --image 000000014439.jpg --device gpu
-# GPU上使用TensorRT推理 (TensorRT在SDK中已包含，不需要单独安装)
+# TensorRT inference on GPU (TensorRT in SDK. No need Separate installation)
python infer.py --model yolox_s.onnx --image 000000014439.jpg --device gpu --use_trt True
```
-运行完成可视化结果如下图所示
+The visualized result after running is as follows
-## YOLOX Python接口
+## YOLOX Python Interface
```python
fastdeploy.vision.detection.YOLOX(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
```
-YOLOX模型加载和初始化，其中model_file为导出的ONNX模型格式
+YOLOX model loading and initialization, among which model_file is the exported ONNX model format
-**参数**
+**Parameter**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为ONNX
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. No need to set when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. ONNX format by default
-### predict函数
+### predict function
> ```python
> YOLOX.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
> ```
>
-> 模型预测结口，输入图像直接输出检测结果。
+> Model prediction interface. Input images and output results
>
-> **参数**
+> **Parameter**
>
-> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
-> > * **conf_threshold**(float): 检测框置信度过滤阈值
-> > * **nms_iou_threshold**(float): NMS处理过程中iou阈值
+> > * **image_data**(np.ndarray): Input data in HWC or BGR format
+> > * **conf_threshold**(float): Filtering threshold of detection box confidence
+> > * **nms_iou_threshold**(float): iou threshold during NMS processing
-> **返回**
+> **Return**
>
-> > 返回`fastdeploy.vision.DetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > Return `fastdeploy.vision.DetectionResult` structure, refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for its description
-### 类成员属性
-#### 预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+### Class Member Property
+#### Pre-processing Parameter
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
-> >* **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
-> >* **padding_value**(list[float]): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
-> >* **is_decode_exported**(bool): 表示导出的YOLOX的onnx模型文件是否带坐标反算的decode部分, 默认值为`is_decode_exported=False`，官方默认的导出不带decode部分，如果您导出的模型带了decode，请将此参数设置为True
+> >* **size**(list[int]): This parameter changes the size of the resize during preprocessing, containing two integer elements for [width, height] with default value [640, 640]
+> >* **padding_value**(list[float]): This parameter is used to change the padding value of images during resize, containing three floating-point elements that represent the value of three channels. Default [114, 114, 114]
+> >* **is_decode_exported**(bool): The default value is `is_decode_exported=False`. The official default export does not have the decoded part. If you export the model with the decoded part, please set this parameter to true
-## 其它文档
+## Other Documents
-- [YOLOX 模型介绍](..)
-- [YOLOX C++部署](../cpp)
-- [模型预测结果说明](../../../../../docs/api/vision_results/)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+- [YOLOX Model Description](..)
+- [YOLOX C++ Deployment](../cpp)
+- [Model Prediction Results](../../../../../docs/api/vision_results/)
+- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/detection/yolox/python/README_CN.md b/examples/vision/detection/yolox/python/README_CN.md
new file mode 100644
index 0000000000..59af2fc58b
--- /dev/null
+++ b/examples/vision/detection/yolox/python/README_CN.md
@@ -0,0 +1,80 @@
+[English](README.md) | 简体中文
+# YOLOX Python部署示例
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+本目录下提供`infer.py`快速完成YOLOX在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+
+```bash
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd examples/vision/detection/yolox/python/
+
+#下载YOLOX模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/yolox_s.onnx
+wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
+
+# CPU推理
+python infer.py --model yolox_s.onnx --image 000000014439.jpg --device cpu
+# GPU推理
+python infer.py --model yolox_s.onnx --image 000000014439.jpg --device gpu
+# GPU上使用TensorRT推理 (TensorRT在SDK中已包含，不需要单独安装)
+python infer.py --model yolox_s.onnx --image 000000014439.jpg --device gpu --use_trt True
+```
+
+运行完成可视化结果如下图所示
+
+
+
+## YOLOX Python接口
+
+```python
+fastdeploy.vision.detection.YOLOX(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
+```
+
+YOLOX模型加载和初始化，其中model_file为导出的ONNX模型格式
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为ONNX
+
+### predict函数
+
+> ```python
+> YOLOX.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
+> ```
+>
+> 模型预测结口，输入图像直接输出检测结果。
+>
+> **参数**
+>
+> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
+> > * **conf_threshold**(float): 检测框置信度过滤阈值
+> > * **nms_iou_threshold**(float): NMS处理过程中iou阈值
+
+> **返回**
+>
+> > 返回`fastdeploy.vision.DetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+
+### 类成员属性
+#### 预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> >* **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
+> >* **padding_value**(list[float]): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
+> >* **is_decode_exported**(bool): 表示导出的YOLOX的onnx模型文件是否带坐标反算的decode部分, 默认值为`is_decode_exported=False`，官方默认的导出不带decode部分，如果您导出的模型带了decode，请将此参数设置为True
+
+
+
+## 其它文档
+
+- [YOLOX 模型介绍](..)
+- [YOLOX C++部署](../cpp)
+- [模型预测结果说明](../../../../../docs/api/vision_results/)
+- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/facealign/README.md b/examples/vision/facealign/README.md
index df0b441112..07059d7567 100644
--- a/examples/vision/facealign/README.md
+++ b/examples/vision/facealign/README.md
@@ -1,9 +1,10 @@
-# 人脸对齐(人脸关键点检测）模型
+English | [简体中文](README_CN.md)
+# Face Alignment (Keypoint Detection) Model
-FastDeploy目前支持如下人脸对齐(关键点检测）模型部署
+FastDeploy currently supports the deployment of the following face alignment (keypoint detection) models
-| 模型 | 说明 | 模型格式 | 版本 |
+| Model | Description | Model Format | Version |
| :--- | :--- | :------- | :--- |
-| [Hsintao/pfld_106_face_landmarks](./pfld) | PFLD 系列模型 | ONNX | [CommitID:e150195](https://github.com/Hsintao/pfld_106_face_landmarks/commit/e150195) |
-| [Single430/FaceLandmark1000](./face_landmark_1000) | FaceLandmark1000 系列模型 | ONNX | [CommitID:1a951b6](https://github.com/Single430/FaceLandmark1000/tree/1a951b6) |
-| [jhb86253817/PIPNet](./pipnet) | PIPNet 系列模型 | ONNX | [CommitID:b9eab58](https://github.com/jhb86253817/PIPNet/tree/b9eab58) |
+| [Hsintao/pfld_106_face_landmarks](./pfld) | PFLD models | ONNX | [CommitID:e150195](https://github.com/Hsintao/pfld_106_face_landmarks/commit/e150195) |
+| [Single430/FaceLandmark1000](./face_landmark_1000) | FaceLandmark1000 models | ONNX | [CommitID:1a951b6](https://github.com/Single430/FaceLandmark1000/tree/1a951b6) |
+| [jhb86253817/PIPNet](./pipnet) | PIPNet models | ONNX | [CommitID:b9eab58](https://github.com/jhb86253817/PIPNet/tree/b9eab58) |
diff --git a/examples/vision/facealign/README_CN.md b/examples/vision/facealign/README_CN.md
new file mode 100644
index 0000000000..c8cc23e979
--- /dev/null
+++ b/examples/vision/facealign/README_CN.md
@@ -0,0 +1,10 @@
+[English](README.md) | 简体中文
+# 人脸对齐(人脸关键点检测）模型
+
+FastDeploy目前支持如下人脸对齐(关键点检测）模型部署
+
+| 模型 | 说明 | 模型格式 | 版本 |
+| :--- | :--- | :------- | :--- |
+| [Hsintao/pfld_106_face_landmarks](./pfld) | PFLD 系列模型 | ONNX | [CommitID:e150195](https://github.com/Hsintao/pfld_106_face_landmarks/commit/e150195) |
+| [Single430/FaceLandmark1000](./face_landmark_1000) | FaceLandmark1000 系列模型 | ONNX | [CommitID:1a951b6](https://github.com/Single430/FaceLandmark1000/tree/1a951b6) |
+| [jhb86253817/PIPNet](./pipnet) | PIPNet 系列模型 | ONNX | [CommitID:b9eab58](https://github.com/jhb86253817/PIPNet/tree/b9eab58) |
diff --git a/examples/vision/facealign/face_landmark_1000/README.md b/examples/vision/facealign/face_landmark_1000/README.md
index ce45cc285b..fa536df78f 100644
--- a/examples/vision/facealign/face_landmark_1000/README.md
+++ b/examples/vision/facealign/face_landmark_1000/README.md
@@ -1,25 +1,26 @@
-# FaceLandmark 模型部署
+English | [简体中文](README_CN.md)
+# FaceLandmark Model Deployment
-## 模型版本说明
+## Model Description
- [FaceLandmark1000](https://github.com/Single430/FaceLandmark1000/tree/1a951b6)
-## 支持模型列表
+## List of Supported Models
-目前FastDeploy支持如下模型的部署
+Now FastDeploy supports the deployment of the following models
-- [FaceLandmark1000 模型](https://github.com/Single430/FaceLandmark1000)
+- [FaceLandmark1000 Model](https://github.com/Single430/FaceLandmark1000)
-## 下载预训练模型
+## Download Pre-trained Models
-为了方便开发者的测试，下面提供了FaceLandmark导出的各系列模型，开发者可直接下载使用。
+For developers' testing, models exported by FaceLandmark are provided below. Developers can download and use them directly.
-| 模型 | 参数大小 | 精度 | 备注 |
+| Model | Parameter Size | Accuracy | Note |
|:---------------------------------------------------------------- |:----- |:----- | :------ |
| [FaceLandmark1000](https://bj.bcebos.com/paddlehub/fastdeploy/FaceLandmark1000.onnx) | 2.1M | - |
-## 详细部署文档
+## Detailed Deployment Tutorials
-- [Python部署](python)
-- [C++部署](cpp)
+- [Python Deployment](python)
+- [C++ Deployment](cpp)
diff --git a/examples/vision/facealign/face_landmark_1000/README_CN.md b/examples/vision/facealign/face_landmark_1000/README_CN.md
new file mode 100644
index 0000000000..05abfca47d
--- /dev/null
+++ b/examples/vision/facealign/face_landmark_1000/README_CN.md
@@ -0,0 +1,26 @@
+[English](README.md) | 简体中文
+# FaceLandmark 模型部署
+
+## 模型版本说明
+
+- [FaceLandmark1000](https://github.com/Single430/FaceLandmark1000/tree/1a951b6)
+
+## 支持模型列表
+
+目前FastDeploy支持如下模型的部署
+
+- [FaceLandmark1000 模型](https://github.com/Single430/FaceLandmark1000)
+
+## 下载预训练模型
+
+为了方便开发者的测试，下面提供了FaceLandmark导出的各系列模型，开发者可直接下载使用。
+
+| 模型 | 参数大小 | 精度 | 备注 |
+|:---------------------------------------------------------------- |:----- |:----- | :------ |
+| [FaceLandmark1000](https://bj.bcebos.com/paddlehub/fastdeploy/FaceLandmark1000.onnx) | 2.1M | - |
+
+
+## 详细部署文档
+
+- [Python部署](python)
+- [C++部署](cpp)
diff --git a/examples/vision/facealign/face_landmark_1000/cpp/README.md b/examples/vision/facealign/face_landmark_1000/cpp/README.md
index 00b5391b5e..00a5c2b40f 100644
--- a/examples/vision/facealign/face_landmark_1000/cpp/README.md
+++ b/examples/vision/facealign/face_landmark_1000/cpp/README.md
@@ -1,47 +1,48 @@
-# FaceLandmark1000 C++部署示例
+English | [简体中文](README_CN.md)
+# FaceLandmark1000 C++ Deployment Example
-本目录下提供`infer.cc`快速完成FaceLandmark1000在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+This directory provides examples that `infer.cc` fast finishes the deployment of FaceLandmark1000 on CPU/GPU and GPU accelerated by TensorRT.
-在部署前，需确认以下两个步骤
+Before deployment, two steps require confirmation.
-- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. Download the precompiled deployment library and samples code according to your development environment. Refer to [FastDeploy Precompiled Library](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试，支持此模型需保证FastDeploy版本1.0.2以上(x.x.x>=1.0.2), 或使用nightly built版本
+Taking the CPU inference on Linux as an example, the compilation test can be completed by executing the following command in this directory. FastDeploy version 1.0.2 or above (x.x.x>=1.0.2), or nightly built version is required to support this model.
```bash
mkdir build
cd build
-# 下载FastDeploy预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
+# Download the FastDeploy precompiled library. Users can choose your appropriate version in the `FastDeploy Precompiled Library` mentioned above
wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz
tar xvf fastdeploy-linux-x64-x.x.x.tgz
cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x
make -j
-#下载官方转换好的 FaceLandmark1000 模型文件和测试图片
+# Download the official converted FaceLandmark1000 model file and test images
wget https://bj.bcebos.com/paddlehub/fastdeploy/FaceLandmark1000.onnx
wget https://bj.bcebos.com/paddlehub/fastdeploy/facealign_input.png
-# CPU推理
+# CPU inference
./infer_demo --model FaceLandmark1000.onnx --image facealign_input.png --device cpu
-# GPU推理
+# GPU inference
./infer_demo --model FaceLandmark1000.onnx --image facealign_input.png --device gpu
-# GPU上TensorRT推理
+# TensorRT Inference on GPU
./infer_demo --model FaceLandmark1000.onnx --image facealign_input.png --device gpu --backend trt
```
-运行完成可视化结果如下图所示
+The visualized result after running is as follows
+
+
+
+
+
-以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
-- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
-## RetinaFace C++接口
+The above command works for Linux or MacOS. For SDK use-pattern in Windows, refer to:
+- [How to use FastDeploy C++ SDK in Windows](../../../../../docs/cn/faq/use_sdk_on_windows.md)
+## RetinaFace C++ Interface
-### RetinaFace类
+### RetinaFace Class
```c++
fastdeploy::vision::facedet::RetinaFace(
@@ -49,16 +50,16 @@ fastdeploy::vision::facedet::RetinaFace(
const ModelFormat& model_format = ModelFormat::ONNX)
```
-RetinaFace模型加载和初始化，其中model_file为导出的ONNX模型格式。
+RetinaFace model loading and initialization, among which model_file is the exported ONNX model format
-**参数**
+**Parameter**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为ONNX格式
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. Only passing an empty string when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. ONNX format by default
-#### Predict函数
+#### Predict function
> ```c++
> RetinaFace::Predict(cv::Mat* im, FaceDetectionResult* result,
@@ -66,26 +67,26 @@ RetinaFace模型加载和初始化，其中model_file为导出的ONNX模型格
> float nms_iou_threshold = 0.5)
> ```
>
-> 模型预测接口，输入图像直接输出检测结果。
+> Model prediction interface. Input images and output detection results.
>
-> **参数**
+> **Parameter**
>
-> > * **im**: 输入图像，注意需为HWC，BGR格式
-> > * **result**: 检测结果，包括检测框，各个框的置信度, FaceDetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
-> > * **conf_threshold**: 检测框置信度过滤阈值
-> > * **nms_iou_threshold**: NMS处理过程中iou阈值
-
-### 类成员变量
-#### 预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
-
-> > * **size**(vector<int>): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
-> > * **variance**(vector<float>): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[0, 0, 0]
-> > * **min_sizes**(vector<vector<int>>): retinaface中的anchor的宽高设置，默认是 {{16, 32}, {64, 128}, {256, 512}}，分别和步长8、16和32对应
-> > * **downsample_strides**(vector<int>): 通过此参数可以修改生成anchor的特征图的下采样倍数, 包含三个整型元素, 分别表示默认的生成anchor的下采样倍数, 默认值为[8, 16, 32]
-> > * **landmarks_per_face**(int): 指定当前模型检测的人脸所带的关键点个数，默认为5.
-
-- [模型介绍](../../)
-- [Python部署](../python)
-- [视觉模型预测结果](../../../../../docs/api/vision_results/)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+> > * **im**: Input images in HWC or BGR format
+> > * **result**: Detection results, including detection box and confidence of each box. Refer to [Vision Model Prediction Result](../../../../../docs/api/vision_results/) for FaceDetectionResult
+> > * **conf_threshold**: Filtering threshold of detection box confidence
+> > * **nms_iou_threshold**: iou threshold during NMS processing
+
+### Class Member Variable
+#### Pre-processing Parameter
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
+
+> > * **size**(vector<int>): This parameter changes the size of the resize used during preprocessing, containing two integer elements for [width, height] with default value [640, 640]
+> > * **variance**(vector<float>): This parameter is used to change the padding value of images during resize, containing three floating-point elements that represent the value of three channels. Default value [0, 0, 0]
+> > * **min_sizes**(vector<vector<int>>): Set width and height of anchor in retinaface. Default {{16, 32}, {64, 128}, {256, 512}}, corresponding to step size 8, 16 and 32
+> > * **downsample_strides**(vector<int>): This parameter is used to change the down-sampling multiple of the feature map that generates anchor, containing three integer elements that represent the default down-sampling multiple for generating anchor. Default value [8, 16, 32]
+> > * **landmarks_per_face**(int): Specify the number of keypoints in the face detected. Default 5
+
+- [Model Description](../../)
+- [Python Deployment](../python)
+- [Vision Model Prediction Results](../../../../../docs/api/vision_results/)
+- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/facedet/retinaface/cpp/README_CN.md b/examples/vision/facedet/retinaface/cpp/README_CN.md
new file mode 100644
index 0000000000..1f0621c321
--- /dev/null
+++ b/examples/vision/facedet/retinaface/cpp/README_CN.md
@@ -0,0 +1,92 @@
+[English](README.md) | 简体中文
+# RetinaFace C++部署示例
+
+本目录下提供`infer.cc`快速完成RetinaFace在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试，支持此模型需保证FastDeploy版本0.7.0以上(x.x.x>=0.7.0)
+
+```bash
+mkdir build
+cd build
+# 下载FastDeploy预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz
+tar xvf fastdeploy-linux-x64-x.x.x.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x
+make -j
+
+#下载官方转换好的RetinaFace模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/Pytorch_RetinaFace_mobile0.25-640-640.onnx
+wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/lite/resources/test_lite_face_detector_3.jpg
+
+
+# CPU推理
+./infer_demo Pytorch_RetinaFace_mobile0.25-640-640.onnx test_lite_face_detector_3.jpg 0
+# GPU推理
+./infer_demo Pytorch_RetinaFace_mobile0.25-640-640.onnx test_lite_face_detector_3.jpg 1
+# GPU上TensorRT推理
+./infer_demo Pytorch_RetinaFace_mobile0.25-640-640.onnx test_lite_face_detector_3.jpg 2
+```
+
+运行完成可视化结果如下图所示
+
+
+
+以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
+- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
+## RetinaFace C++接口
+
+### RetinaFace类
+
+```c++
+fastdeploy::vision::facedet::RetinaFace(
+ const string& model_file,
+ const string& params_file = "",
+ const RuntimeOption& runtime_option = RuntimeOption(),
+ const ModelFormat& model_format = ModelFormat::ONNX)
+```
+
+RetinaFace模型加载和初始化，其中model_file为导出的ONNX模型格式。
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为ONNX格式
+
+#### Predict函数
+
+> ```c++
+> RetinaFace::Predict(cv::Mat* im, FaceDetectionResult* result,
+> float conf_threshold = 0.25,
+> float nms_iou_threshold = 0.5)
+> ```
+>
+> 模型预测接口，输入图像直接输出检测结果。
+>
+> **参数**
+>
+> > * **im**: 输入图像，注意需为HWC，BGR格式
+> > * **result**: 检测结果，包括检测框，各个框的置信度, FaceDetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > * **conf_threshold**: 检测框置信度过滤阈值
+> > * **nms_iou_threshold**: NMS处理过程中iou阈值
+
+### 类成员变量
+#### 预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> > * **size**(vector<int>): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
+> > * **variance**(vector<float>): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[0, 0, 0]
+> > * **min_sizes**(vector<vector<int>>): retinaface中的anchor的宽高设置，默认是 {{16, 32}, {64, 128}, {256, 512}}，分别和步长8、16和32对应
+> > * **downsample_strides**(vector<int>): 通过此参数可以修改生成anchor的特征图的下采样倍数, 包含三个整型元素, 分别表示默认的生成anchor的下采样倍数, 默认值为[8, 16, 32]
+> > * **landmarks_per_face**(int): 指定当前模型检测的人脸所带的关键点个数，默认为5.
+
+- [模型介绍](../../)
+- [Python部署](../python)
+- [视觉模型预测结果](../../../../../docs/api/vision_results/)
+- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/facedet/retinaface/python/README.md b/examples/vision/facedet/retinaface/python/README.md
index 88136301e6..9a99974710 100644
--- a/examples/vision/facedet/retinaface/python/README.md
+++ b/examples/vision/facedet/retinaface/python/README.md
@@ -1,81 +1,82 @@
-# RetinaFace Python部署示例
+English | [简体中文](README_CN.md)
+# RetinaFace Python Deployment Example
-在部署前，需确认以下两个步骤
+Before deployment, two steps require confirmation
-- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. Install FastDeploy Python whl package. Refer to [FastDeploy Python Installation](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-本目录下提供`infer.py`快速完成RetinaFace在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+This directory provides examples that `infer.py` fast finishes the deployment of RetinaFace on CPU/GPU and GPU accelerated by TensorRT. The script is as follows
```bash
-#下载部署示例代码
+# Download the example code for deployment
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision//retinaface/python/
-#下载retinaface模型文件和测试图片
+# Download retinaface model files and test images
wget https://bj.bcebos.com/paddlehub/fastdeploy/Pytorch_RetinaFace_mobile0.25-640-640.onnx
wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/lite/resources/test_lite_face_detector_3.jpg
-# CPU推理
+# CPU inference
python infer.py --model Pytorch_RetinaFace_mobile0.25-640-640.onnx --image test_lite_face_detector_3.jpg --device cpu
-# GPU推理
+# GPU inference
python infer.py --model Pytorch_RetinaFace_mobile0.25-640-640.onnx --image test_lite_face_detector_3.jpg --device gpu
-# GPU上使用TensorRT推理
+# TensorRT inference on GPU
python infer.py --model Pytorch_RetinaFace_mobile0.25-640-640.onnx --image test_lite_face_detector_3.jpg --device gpu --use_trt True
```
-运行完成可视化结果如下图所示
+The visualized result after running is as follows
-## RetinaFace Python接口
+## RetinaFace Python Interface
```python
fastdeploy.vision.facedet.RetinaFace(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
```
-RetinaFace模型加载和初始化，其中model_file为导出的ONNX模型格式
+RetinaFace model loading and initialization, among which model_file is the exported ONNX model format
-**参数**
+**Parameter**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为ONNX
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. No need to set when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. ONNX format by default
-### predict函数
+### predict function
> ```python
> RetinaFace.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
> ```
>
-> 模型预测结口，输入图像直接输出检测结果。
+> Model prediction interface. Input images and output detection results.
>
-> **参数**
+> **Parameter**
>
-> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
-> > * **conf_threshold**(float): 检测框置信度过滤阈值
-> > * **nms_iou_threshold**(float): NMS处理过程中iou阈值
+> > * **image_data**(np.ndarray): Input data in HWC or BGR format
+> > * **conf_threshold**(float): Filtering threshold of detection box confidence
+> > * **nms_iou_threshold**(float): iou threshold during NMS processing
-> **返回**
+> **Return**
>
-> > 返回`fastdeploy.vision.FaceDetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > Return `fastdeploy.vision.FaceDetectionResult` structure. Refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for its description.
-### 类成员属性
-#### 预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+### Class Member Property
+#### Pre-processing Parameter
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
-> > * **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
-> > * **variance**(list[float]): 通过此参数可以指定retinaface中的方差variance值，默认是[0.1,0.2], 一般不用修改.
-> > * **min_sizes**(list[list[int]]): retinaface中的anchor的宽高设置，默认是 {{16, 32}, {64, 128}, {256, 512}}，分别和步长8、16和32对应
-> > * **downsample_strides**(list[int]): 通过此参数可以修改生成anchor的特征图的下采样倍数, 包含三个整型元素, 分别表示默认的生成anchor的下采样倍数, 默认值为[8, 16, 32]
-> > * **landmarks_per_face**(int): 指定当前模型检测的人脸所带的关键点个数，默认为5.
+> > * **size**(list[int]): This parameter changes the size of the resize used during preprocessing, containing two integer elements for [width, height] with default value [640, 640]
+> > * **variance**(list[float]): Specify the variance value in retinaface. Default [0.1,0.2]. Normally without modification.
+> > * **min_sizes**(list[list[int]]): Set width and height of anchor in retinaface. Default {{16, 32}, {64, 128}, {256, 512}}, corresponding to the step size 8, 16 and 32
+> > * **downsample_strides**(list[int]): This parameter is used to change the down-sampling multiple of the feature map that generates anchor, containing three integer elements that represent the default down-sampling multiple for generating anchor. Default value [8, 16, 32]
+> > * **landmarks_per_face**(int): Specify the number of keypoints in the face detected. Default 5.
-## 其它文档
+## Other Documents
-- [RetinaFace 模型介绍](..)
-- [RetinaFace C++部署](../cpp)
-- [模型预测结果说明](../../../../../docs/api/vision_results/)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+- [RetinaFace Model Description](..)
+- [RetinaFace C++ Deployment](../cpp)
+- [Model Prediction Results](../../../../../docs/api/vision_results/)
+- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/facedet/retinaface/python/README_CN.md b/examples/vision/facedet/retinaface/python/README_CN.md
new file mode 100644
index 0000000000..a4a32739b4
--- /dev/null
+++ b/examples/vision/facedet/retinaface/python/README_CN.md
@@ -0,0 +1,82 @@
+[English](README.md) | 简体中文
+# RetinaFace Python部署示例
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+本目录下提供`infer.py`快速完成RetinaFace在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+
+```bash
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd examples/vision//retinaface/python/
+
+#下载retinaface模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/Pytorch_RetinaFace_mobile0.25-640-640.onnx
+wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/lite/resources/test_lite_face_detector_3.jpg
+
+# CPU推理
+python infer.py --model Pytorch_RetinaFace_mobile0.25-640-640.onnx --image test_lite_face_detector_3.jpg --device cpu
+# GPU推理
+python infer.py --model Pytorch_RetinaFace_mobile0.25-640-640.onnx --image test_lite_face_detector_3.jpg --device gpu
+# GPU上使用TensorRT推理
+python infer.py --model Pytorch_RetinaFace_mobile0.25-640-640.onnx --image test_lite_face_detector_3.jpg --device gpu --use_trt True
+```
+
+运行完成可视化结果如下图所示
+
+
+
+## RetinaFace Python接口
+
+```python
+fastdeploy.vision.facedet.RetinaFace(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
+```
+
+RetinaFace模型加载和初始化，其中model_file为导出的ONNX模型格式
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为ONNX
+
+### predict函数
+
+> ```python
+> RetinaFace.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
+> ```
+>
+> 模型预测结口，输入图像直接输出检测结果。
+>
+> **参数**
+>
+> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
+> > * **conf_threshold**(float): 检测框置信度过滤阈值
+> > * **nms_iou_threshold**(float): NMS处理过程中iou阈值
+
+> **返回**
+>
+> > 返回`fastdeploy.vision.FaceDetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+
+### 类成员属性
+#### 预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> > * **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
+> > * **variance**(list[float]): 通过此参数可以指定retinaface中的方差variance值，默认是[0.1,0.2], 一般不用修改.
+> > * **min_sizes**(list[list[int]]): retinaface中的anchor的宽高设置，默认是 {{16, 32}, {64, 128}, {256, 512}}，分别和步长8、16和32对应
+> > * **downsample_strides**(list[int]): 通过此参数可以修改生成anchor的特征图的下采样倍数, 包含三个整型元素, 分别表示默认的生成anchor的下采样倍数, 默认值为[8, 16, 32]
+> > * **landmarks_per_face**(int): 指定当前模型检测的人脸所带的关键点个数，默认为5.
+
+
+
+## 其它文档
+
+- [RetinaFace 模型介绍](..)
+- [RetinaFace C++部署](../cpp)
+- [模型预测结果说明](../../../../../docs/api/vision_results/)
+- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/facedet/scrfd/README.md b/examples/vision/facedet/scrfd/README.md
index a2aaffce87..8a06ef8ed5 100644
--- a/examples/vision/facedet/scrfd/README.md
+++ b/examples/vision/facedet/scrfd/README.md
@@ -1,39 +1,40 @@
-# SCRFD准备部署模型
+English | [简体中文](README_CN.md)
+# SCRFD Ready-to-deploy Model
- [SCRFD](https://github.com/deepinsight/insightface/tree/17cdeab12a35efcebc2660453a8cbeae96e20950)
- - （1）[官方库](https://github.com/deepinsight/insightface/)中提供的*.pt通过[导出ONNX模型](#导出ONNX模型)操作后，可进行部署；
- - （2）开发者基于自己数据训练的SCRFD模型，可按照[导出ONNX模型](#%E5%AF%BC%E5%87%BAONNX%E6%A8%A1%E5%9E%8B)后，完成部署。
+ - （1）The *.pt provided by the [Official Library](https://github.com/deepinsight/insightface/) can be deployed after the [Export ONNX Model](#导出ONNX模型) to complete the deployment；
+ - （2）As for SCRFD model trained on customized data, please follow [Export ONNX Model](#%E5%AF%BC%E5%87%BAONNX%E6%A8%A1%E5%9E%8B) to complete the deployment.
-## 导出ONNX模型
+## Export ONNX Model
```bash
- #下载scrfd模型文件
+ # Download scrfd model files
e.g. download from https://onedrive.live.com/?authkey=%21ABbFJx2JMhNjhNA&id=4A83B6B633B029CC%215542&cid=4A83B6B633B029CC
- # 安装官方库配置环境，此版本导出环境为：
- - 手动配置环境
+ # Install the official library to configure the environment. This version should be exported in the following environment:
+ - Configure the environment manually
torch==1.8.0
mmcv==1.3.5
mmdet==2.7.0
- - 通过docker配置
+ - Configure via docker
docker pull qyjdefdocker/onnx-scrfd-converter:v0.3
- # 导出onnx格式文件
- - 手动生成
+ # Export files in onnx format
+ - Manual generation
python tools/scrfd2onnx.py configs/scrfd/scrfd_500m.py weights/scrfd_500m.pth --shape 640 --input-img face-xxx.jpg
- docker
- docker的onnx目录中已有生成好的onnx文件
+ onnx files are in docker's onnx directory
```
-## 下载预训练ONNX模型
+## Download Pre-trained ONNX Models
-为了方便开发者的测试，下面提供了SCRFD导出的各系列模型，开发者可直接下载使用。（下表中模型的精度来源于源官方库）
-| 模型 | 大小 | 精度 |
+For developers' testing, models exported by SCRFD are provided below. Developers can download and use them directly. (The accuracy of the models in the table is sourced from the official library)
+| Model | Size | Accuracy |
|:---------------------------------------------------------------- |:----- |:----- |
| [SCRFD-500M-kps-160](https://bj.bcebos.com/paddlehub/fastdeploy/scrfd_500m_bnkps_shape160x160.onnx) | 2.5MB | - |
| [SCRFD-500M-160](https://bj.bcebos.com/paddlehub/fastdeploy/scrfd_500m_shape160x160.onnx) | 2.2MB | - |
@@ -57,12 +58,12 @@
| [SCRFD-10G-kps-1280](https://bj.bcebos.com/paddlehub/fastdeploy/scrfd_10g_bnkps_shape1280x1280.onnx) | 17MB | - |
| [SCRFD-10G-1280](https://bj.bcebos.com/paddlehub/fastdeploy/scrfd_10g_shape1280x1280.onnx) | 15MB | - |
-## 详细部署文档
+## Detailed Deployment Tutorials
-- [Python部署](python)
-- [C++部署](cpp)
+- [Python Deployement](python)
+- [C++ Deployment](cpp)
-## 版本说明
+## Release Note
-- 本版本文档和代码基于[SCRFD CommitID:17cdeab](https://github.com/deepinsight/insightface/tree/17cdeab12a35efcebc2660453a8cbeae96e20950) 编写
+- This tutorial and related code are written based on [SCRFD CommitID:17cdeab](https://github.com/deepinsight/insightface/tree/17cdeab12a35efcebc2660453a8cbeae96e20950)
diff --git a/examples/vision/facedet/scrfd/README_CN.md b/examples/vision/facedet/scrfd/README_CN.md
new file mode 100644
index 0000000000..16b6a232e8
--- /dev/null
+++ b/examples/vision/facedet/scrfd/README_CN.md
@@ -0,0 +1,69 @@
+[English](README.md) | 简体中文
+# SCRFD准备部署模型
+
+
+- [SCRFD](https://github.com/deepinsight/insightface/tree/17cdeab12a35efcebc2660453a8cbeae96e20950)
+ - （1）[官方库](https://github.com/deepinsight/insightface/)中提供的*.pt通过[导出ONNX模型](#导出ONNX模型)操作后，可进行部署；
+ - （2）开发者基于自己数据训练的SCRFD模型，可按照[导出ONNX模型](#%E5%AF%BC%E5%87%BAONNX%E6%A8%A1%E5%9E%8B)后，完成部署。
+
+
+## 导出ONNX模型
+
+ ```bash
+ #下载scrfd模型文件
+ e.g. download from https://onedrive.live.com/?authkey=%21ABbFJx2JMhNjhNA&id=4A83B6B633B029CC%215542&cid=4A83B6B633B029CC
+
+ # 安装官方库配置环境，此版本导出环境为：
+ - 手动配置环境
+ torch==1.8.0
+ mmcv==1.3.5
+ mmdet==2.7.0
+
+ - 通过docker配置
+ docker pull qyjdefdocker/onnx-scrfd-converter:v0.3
+
+ # 导出onnx格式文件
+ - 手动生成
+ python tools/scrfd2onnx.py configs/scrfd/scrfd_500m.py weights/scrfd_500m.pth --shape 640 --input-img face-xxx.jpg
+
+ - docker
+ docker的onnx目录中已有生成好的onnx文件
+
+ ```
+
+## 下载预训练ONNX模型
+
+为了方便开发者的测试，下面提供了SCRFD导出的各系列模型，开发者可直接下载使用。（下表中模型的精度来源于源官方库）
+| 模型 | 大小 | 精度 |
+|:---------------------------------------------------------------- |:----- |:----- |
+| [SCRFD-500M-kps-160](https://bj.bcebos.com/paddlehub/fastdeploy/scrfd_500m_bnkps_shape160x160.onnx) | 2.5MB | - |
+| [SCRFD-500M-160](https://bj.bcebos.com/paddlehub/fastdeploy/scrfd_500m_shape160x160.onnx) | 2.2MB | - |
+| [SCRFD-500M-kps-320](https://bj.bcebos.com/paddlehub/fastdeploy/scrfd_500m_bnkps_shape320x320.onnx) | 2.5MB | - |
+| [SCRFD-500M-320](https://bj.bcebos.com/paddlehub/fastdeploy/scrfd_500m_shape320x320.onnx) | 2.2MB | - |
+| [SCRFD-500M-kps-640](https://bj.bcebos.com/paddlehub/fastdeploy/scrfd_500m_bnkps_shape640x640.onnx) | 2.5MB | 90.97% |
+| [SCRFD-500M-640](https://bj.bcebos.com/paddlehub/fastdeploy/scrfd_500m_shape640x640.onnx) | 2.2MB | 90.57% |
+| [SCRFD-1G-160](https://bj.bcebos.com/paddlehub/fastdeploy/scrfd_1g_shape160x160.onnx ) | 2.5MB | - |
+| [SCRFD-1G-320](https://bj.bcebos.com/paddlehub/fastdeploy/scrfd_1g_shape320x320.onnx) | 2.5MB | - |
+| [SCRFD-1G-640](https://bj.bcebos.com/paddlehub/fastdeploy/scrfd_1g_shape640x640.onnx) | 2.5MB | 92.38% |
+| [SCRFD-2.5G-kps-160](https://bj.bcebos.com/paddlehub/fastdeploy/scrfd_2.5g_bnkps_shape160x160.onnx) | 3.2MB | - |
+| [SCRFD-2.5G-160](https://bj.bcebos.com/paddlehub/fastdeploy/scrfd_2.5g_shape160x160.onnx) | 2.6MB | - |
+| [SCRFD-2.5G-kps-320](https://bj.bcebos.com/paddlehub/fastdeploy/scrfd_2.5g_bnkps_shape320x320.onnx) | 3.2MB | - |
+| [SCRFD-2.5G-320](https://bj.bcebos.com/paddlehub/fastdeploy/scrfd_2.5g_shape320x320.onnx) | 2.6MB | - |
+| [SCRFD-2.5G-kps-640](https://bj.bcebos.com/paddlehub/fastdeploy/scrfd_2.5g_bnkps_shape640x640.onnx) | 3.2MB | 93.8% |
+| [SCRFD-2.5G-640](https://bj.bcebos.com/paddlehub/fastdeploy/scrfd_2.5g_shape640x640.onnx) | 2.6MB | 93.78% |
+| [SCRFD-10G-kps-320](https://bj.bcebos.com/paddlehub/fastdeploy/scrfd_10g_bnkps_shape320x320.onnx) | 17MB | - |
+| [SCRFD-10G-320](https://bj.bcebos.com/paddlehub/fastdeploy/scrfd_10g_shape320x320.onnx) | 15MB | - |
+| [SCRFD-10G-kps-640](https://bj.bcebos.com/paddlehub/fastdeploy/scrfd_10g_bnkps_shape640x640.onnx) | 17MB | 95.4% |
+| [SCRFD-10G-640](https://bj.bcebos.com/paddlehub/fastdeploy/scrfd_10g_shape640x640.onnx) | 15MB | 95.16% |
+| [SCRFD-10G-kps-1280](https://bj.bcebos.com/paddlehub/fastdeploy/scrfd_10g_bnkps_shape1280x1280.onnx) | 17MB | - |
+| [SCRFD-10G-1280](https://bj.bcebos.com/paddlehub/fastdeploy/scrfd_10g_shape1280x1280.onnx) | 15MB | - |
+
+## 详细部署文档
+
+- [Python部署](python)
+- [C++部署](cpp)
+
+
+## 版本说明
+
+- 本版本文档和代码基于[SCRFD CommitID:17cdeab](https://github.com/deepinsight/insightface/tree/17cdeab12a35efcebc2660453a8cbeae96e20950) 编写
diff --git a/examples/vision/facedet/scrfd/android/README.md b/examples/vision/facedet/scrfd/android/README.md
index 000c8a419e..289d10063b 100644
--- a/examples/vision/facedet/scrfd/android/README.md
+++ b/examples/vision/facedet/scrfd/android/README.md
@@ -1,84 +1,85 @@
-# 目标检测 SCRFD Android Demo 使用文档
+English | [简体中文](README_CN.md)
+# Target Detection SCRFD Android Demo Tutorial
-在 Android 上实现实时的人脸检测功能，此 Demo 有很好的的易用性和开放性，如在 Demo 中跑自己训练好的模型等。
+Real-time target detection on Android. This Demo is simple to use for everyone. For example, you can run your own trained model in the Demo.
-## 环境准备
+## Prepare the Environment
-1. 在本地环境安装好 Android Studio 工具，详细安装方法请见[Android Stuido 官网](https://developer.android.com/studio)。
-2. 准备一部 Android 手机，并开启 USB 调试模式。开启方法: `手机设置 -> 查找开发者选项 -> 打开开发者选项和 USB 调试模式`
+1. Install Android Studio in your local environment. Refer to [Android Stuido Official Website](https://developer.android.com/studio) for detailed tutorial.
+2. Prepare an Android phone and turn on the USB debug mode: `Settings -> Find developer options -> Open developer options and USB debug mode`
-## 部署步骤
+## Deployment steps
-1. 目标检测 SCRFD Demo 位于 `fastdeploy/examples/vision/facedet/scrfd/android` 目录
-2. 用 Android Studio 打开 scrfd/android 工程
-3. 手机连接电脑，打开 USB 调试和文件传输模式，并在 Android Studio 上连接自己的手机设备（手机需要开启允许从 USB 安装软件权限）
+1. The target detection SCRFD Demo is located in the `fastdeploy/examples/vision/facedet/scrfd/android` directory
+2. Use Android Studio to open the scrfd/android project
+3. Connect the phone to the computer, turn on USB debug mode and file transfer mode, and connect your phone to Android Studio (allow the phone to install software from USB)
| 
| |
-## SCRFD Java API 说明
-- 模型初始化 API: 模型初始化API包含两种方式，方式一是通过构造函数直接初始化；方式二是，通过调用init函数，在合适的程序节点进行初始化。PaddleSegModel初始化参数说明如下：
- - modelFile: String, paddle格式的模型文件路径，如 model.pdmodel
- - paramFile: String, paddle格式的参数文件路径，如 model.pdiparams
- - option: RuntimeOption，可选参数，模型初始化option。如果不传入该参数则会使用默认的运行时选项。
+## SCRFD Java API Description
+- Model initialized API: The initialized API contains two ways: Firstly, initialize directly through the constructor. Secondly, initialize at the appropriate program node by calling the init function. PicoDet initialization parameters are as follows:
+ - modelFile: String. Model file path in paddle format, such as model.pdmodel
+ - paramFile: String. Parameter file path in paddle format, such as model.pdiparams
+ - option: RuntimeOption. Optional parameter for model initialization. Default runtime options if not passing the parameter.
```java
-// 构造函数: constructor w/o label file
+// Constructor: constructor w/o label file
public SCRFD(); // 空构造函数，之后可以调用init初始化
public SCRFD(String modelFile, String paramsFile);
public SCRFD(String modelFile, String paramsFile, RuntimeOption option);
-// 手动调用init初始化: call init manually w/o label file
+// Call init manually for initialization: call init manually w/o label file
public boolean init(String modelFile, String paramsFile, RuntimeOption option);
```
-- 模型预测 API：模型预测API包含直接预测的API以及带可视化功能的API。直接预测是指，不保存图片以及不渲染结果到Bitmap上，仅预测推理结果。预测并且可视化是指，预测结果以及可视化，并将可视化后的图片保存到指定的途径，以及将可视化结果渲染在Bitmap(目前支持ARGB8888格式的Bitmap), 后续可将该Bitmap在camera中进行显示。
+- Model Prediction API: The Model Prediction API contains an API for direct prediction and an API for visualization. In direct prediction, we do not save the image and render the result on Bitmap. Instead, we merely predict the inference result. For prediction and visualization, the results are both predicted and visualized, the visualized images are saved to the specified path, and the visualized results are rendered in Bitmap (Now Bitmap in ARGB8888 format is supported). Afterward, the Bitmap can be displayed on the camera.
```java
-// 直接预测：不保存图片以及不渲染结果到Bitmap上
+// Direct prediction: No image saving and no result rendering to Bitmap
public FaceDetectionResult predict(Bitmap ARGB8888Bitmap)；
-public FaceDetectionResult predict(Bitmap ARGB8888Bitmap, float confThreshold, float nmsIouThreshold)； // 设置置信度阈值和NMS阈值
-// 预测并且可视化：预测结果以及可视化，并将可视化后的图片保存到指定的途径，以及将可视化结果渲染在Bitmap上
+public FaceDetectionResult predict(Bitmap ARGB8888Bitmap, float confThreshold, float nmsIouThreshold)； // Set confidence threshold and NMS threshold
+// Prediction and visualization: Predict and visualize the results, save the visualized image to the specified path, and render the visualized results on Bitmap
public FaceDetectionResult predict(Bitmap ARGB8888Bitmap, String savedImagePath, float confThreshold, float nmsIouThreshold);
-public FaceDetectionResult predict(Bitmap ARGB8888Bitmap, boolean rendering, float confThreshold, float nmsIouThreshold); // 只渲染 不保存图片
+public FaceDetectionResult predict(Bitmap ARGB8888Bitmap, boolean rendering, float confThreshold, float nmsIouThreshold); // Render without saving images
```
-- 模型资源释放 API：调用 release() API 可以释放模型资源，返回true表示释放成功，false表示失败；调用 initialized() 可以判断模型是否初始化成功，true表示初始化成功，false表示失败。
+- Model resource release API: Call release() API to release model resources. Return true for successful release and false for failure; call initialized() to determine whether the model was initialized successfully, with true indicating successful initialization and false indicating failure.
```java
-public boolean release(); // 释放native资源
-public boolean initialized(); // 检查是否初始化成功
+public boolean release(); // Release native resources
+public boolean initialized(); // Check if initialization is successful
```
-- RuntimeOption设置说明
+- RuntimeOption settings
```java
-public void enableLiteFp16(); // 开启fp16精度推理
-public void disableLiteFP16(); // 关闭fp16精度推理
-public void setCpuThreadNum(int threadNum); // 设置线程数
-public void setLitePowerMode(LitePowerMode mode); // 设置能耗模式
-public void setLitePowerMode(String modeStr); // 通过字符串形式设置能耗模式
+public void enableLiteFp16(); // Enable fp16 accuracy inference
+public void disableLiteFP16(); // Disable fp16 accuracy inference
+public void setCpuThreadNum(int threadNum); // Set thread numbers
+public void setLitePowerMode(LitePowerMode mode); // Set power mode
+public void setLitePowerMode(String modeStr); // Set power mode through character string
```
-- 模型结果SegmentationResult说明
+- Model SegmentationResult
```java
public class FaceDetectionResult {
- public float[][] mBoxes; // [n,4] 检测框 (x1,y1,x2,y2)
- public float[] mScores; // [n] 每个检测框得分(置信度，概率值)
- public float[][] mLandmarks; // [nx?,2] 每个检测到的人脸对应关键点
- int mLandmarksPerFace = 0; // 每个人脸对应的关键点个数
- public boolean initialized(); // 检测结果是否有效
+ public float[][] mBoxes; // [n,4] Detection box (x1,y1,x2,y2)
+ public float[] mScores; // [n] Score of each detection box (confidence, probability)
+ public float[][] mLandmarks; // [nx?,2] Each detected face keypoints
+ int mLandmarksPerFace = 0; // Number of detected face keypoints
+ public boolean initialized(); // Whether the result is valid
}
```
-其他参考：C++/Python对应的FaceDetectionResult说明: [api/vision_results/face_detection_result.md](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/api/vision_results/face_detection_result.md)
+Refer to [api/vision_results/face_detection_result.md](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/api/vision_results/face_detection_result.md) for C++/Python DetectionResult
-- 模型调用示例1：使用构造函数以及默认的RuntimeOption
+- Model Calling Example 1: Using Constructor and the default RuntimeOption
```java
import java.nio.ByteBuffer;
import android.graphics.Bitmap;
@@ -87,62 +88,62 @@ import android.opengl.GLES20;
import com.baidu.paddle.fastdeploy.vision.FaceDetectionResult;
import com.baidu.paddle.fastdeploy.vision.facedet.SCRFD;
-// 初始化模型
+// Initialize the model
SCRFD model = new SCRFD(
"scrfd_500m_bnkps_shape320x320_pd/model.pdmodel",
"scrfd_500m_bnkps_shape320x320_pd/model.pdiparams");
-// 读取图片: 以下仅为读取Bitmap的伪代码
+// Read the image: The following is merely the pseudo code to read Bitmap
ByteBuffer pixelBuffer = ByteBuffer.allocate(width * height * 4);
GLES20.glReadPixels(0, 0, width, height, GLES20.GL_RGBA, GLES20.GL_UNSIGNED_BYTE, pixelBuffer);
Bitmap ARGB8888ImageBitmap = Bitmap.createBitmap(width, height, Bitmap.Config.ARGB_8888);
ARGB8888ImageBitmap.copyPixelsFromBuffer(pixelBuffer);
-// 直接预测返回 FaceDetectionResult
+// Return FaceDetectionResult after direct prediction
FaceDetectionResult result = model.predict(ARGB8888ImageBitmap);
-// 释放模型资源
+// Release model resources
model.release();
```
-- 模型调用示例2: 在合适的程序节点，手动调用init，并自定义RuntimeOption
+- Model calling example 2: Manually call init at the appropriate program node and self-define RuntimeOption
```java
-// import 同上 ...
+// import is as the above...
import com.baidu.paddle.fastdeploy.RuntimeOption;
import com.baidu.paddle.fastdeploy.LitePowerMode;
import com.baidu.paddle.fastdeploy.vision.FaceDetectionResult;
import com.baidu.paddle.fastdeploy.vision.facedet.SCRFD;
-// 新建空模型
+// Create an empty model
SCRFD model = new SCRFD();
-// 模型路径
+// Model path
String modelFile = "scrfd_500m_bnkps_shape320x320_pd/model.pdmodel";
String paramFile = "scrfd_500m_bnkps_shape320x320_pd/model.pdiparams";
-// 指定RuntimeOption
+// Specify RuntimeOption
RuntimeOption option = new RuntimeOption();
option.setCpuThreadNum(2);
option.setLitePowerMode(LitePowerMode.LITE_POWER_HIGH);
option.enableLiteFp16();
-// 使用init函数初始化
+// Use init function for initialization
model.init(modelFile, paramFile, option);
-// Bitmap读取、模型预测、资源释放 同上 ...
+// Bitmap reading, model prediction, and resource release are as above ...
```
-更详细的用法请参考 [FaceDetMainActivity](./app/src/main/java/com/baidu/paddle/fastdeploy/app/examples/facedet/FaceDetMainActivity.java) 中的用法
+Refer to [FaceDetMainActivity](./app/src/main/java/com/baidu/paddle/fastdeploy/app/examples/facedet/FaceDetMainActivity.java) for more details
-## 替换 FastDeploy SDK和模型
-替换FastDeploy预测库和模型的步骤非常简单。预测库所在的位置为 `app/libs/fastdeploy-android-sdk-xxx.aar`，其中 `xxx` 表示当前您使用的预测库版本号。模型所在的位置为，`app/src/main/assets/models/scrfd_500m_bnkps_shape320x320_pd`。
-- 替换FastDeploy Android SDK: 下载或编译最新的FastDeploy Android SDK，解压缩后放在 `app/libs` 目录下；详细配置文档可参考:
- - [在 Android 中使用 FastDeploy Java SDK](../../../../../java/android/)
+## Replace FastDeploy SDK and Models
+It’s simple to replace the FastDeploy prediction library and models. The prediction library is located at `app/libs/fastdeploy-android-sdk-xxx.aar`, where `xxx` represents the version of your prediction library. The models are located at `app/src/main/assets/models/scrfd_500m_bnkps_shape320x320_pd`。
+- Replace the FastDeploy Android SDK: Download or compile the latest FastDeploy Android SDK, unzip and place it in the `app/libs` directory; For detailed configuration, refer to
+ - [FastDeploy Java SDK in Android](../../../../../java/android/)
-- 替换SCRFD模型的步骤：
- - 通过X2Paddle导出其他版本的SCRFD模型，请参考 [SCRFD文档](../README.md) 以及 [X2Paddle](https://github.com/PaddlePaddle/X2Paddle)
- - 将您的SCRFD模型放在 `app/src/main/assets/models` 目录下；
- - 修改 `app/src/main/res/values/strings.xml` 中模型路径的默认值，如：
+- Steps to replace SCRFD models:
+ - Other SCRFD models exported by X2Paddle, refer to [SCRFD document](../README.md) and [X2Paddle](https://github.com/PaddlePaddle/X2Paddle)
+ - Put your SCRFD model in `app/src/main/assets/models` directory;
+ - Modify the default value of the model path in `app/src/main/res/values/strings.xml`. For example,
```xml
-
+
+
+
| | |
+
+## SCRFD Java API 说明
+- 模型初始化 API: 模型初始化API包含两种方式，方式一是通过构造函数直接初始化；方式二是，通过调用init函数，在合适的程序节点进行初始化。PaddleSegModel初始化参数说明如下：
+ - modelFile: String, paddle格式的模型文件路径，如 model.pdmodel
+ - paramFile: String, paddle格式的参数文件路径，如 model.pdiparams
+ - option: RuntimeOption，可选参数，模型初始化option。如果不传入该参数则会使用默认的运行时选项。
+
+```java
+// 构造函数: constructor w/o label file
+public SCRFD(); // 空构造函数，之后可以调用init初始化
+public SCRFD(String modelFile, String paramsFile);
+public SCRFD(String modelFile, String paramsFile, RuntimeOption option);
+// 手动调用init初始化: call init manually w/o label file
+public boolean init(String modelFile, String paramsFile, RuntimeOption option);
+```
+- 模型预测 API：模型预测API包含直接预测的API以及带可视化功能的API。直接预测是指，不保存图片以及不渲染结果到Bitmap上，仅预测推理结果。预测并且可视化是指，预测结果以及可视化，并将可视化后的图片保存到指定的途径，以及将可视化结果渲染在Bitmap(目前支持ARGB8888格式的Bitmap), 后续可将该Bitmap在camera中进行显示。
+```java
+// 直接预测：不保存图片以及不渲染结果到Bitmap上
+public FaceDetectionResult predict(Bitmap ARGB8888Bitmap)；
+public FaceDetectionResult predict(Bitmap ARGB8888Bitmap, float confThreshold, float nmsIouThreshold)； // 设置置信度阈值和NMS阈值
+// 预测并且可视化：预测结果以及可视化，并将可视化后的图片保存到指定的途径，以及将可视化结果渲染在Bitmap上
+public FaceDetectionResult predict(Bitmap ARGB8888Bitmap, String savedImagePath, float confThreshold, float nmsIouThreshold);
+public FaceDetectionResult predict(Bitmap ARGB8888Bitmap, boolean rendering, float confThreshold, float nmsIouThreshold); // 只渲染 不保存图片
+```
+- 模型资源释放 API：调用 release() API 可以释放模型资源，返回true表示释放成功，false表示失败；调用 initialized() 可以判断模型是否初始化成功，true表示初始化成功，false表示失败。
+```java
+public boolean release(); // 释放native资源
+public boolean initialized(); // 检查是否初始化成功
+```
+
+- RuntimeOption设置说明
+```java
+public void enableLiteFp16(); // 开启fp16精度推理
+public void disableLiteFP16(); // 关闭fp16精度推理
+public void setCpuThreadNum(int threadNum); // 设置线程数
+public void setLitePowerMode(LitePowerMode mode); // 设置能耗模式
+public void setLitePowerMode(String modeStr); // 通过字符串形式设置能耗模式
+```
+
+- 模型结果SegmentationResult说明
+```java
+public class FaceDetectionResult {
+ public float[][] mBoxes; // [n,4] 检测框 (x1,y1,x2,y2)
+ public float[] mScores; // [n] 每个检测框得分(置信度，概率值)
+ public float[][] mLandmarks; // [nx?,2] 每个检测到的人脸对应关键点
+ int mLandmarksPerFace = 0; // 每个人脸对应的关键点个数
+ public boolean initialized(); // 检测结果是否有效
+}
+```
+其他参考：C++/Python对应的FaceDetectionResult说明: [api/vision_results/face_detection_result.md](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/api/vision_results/face_detection_result.md)
+
+
+- 模型调用示例1：使用构造函数以及默认的RuntimeOption
+```java
+import java.nio.ByteBuffer;
+import android.graphics.Bitmap;
+import android.opengl.GLES20;
+
+import com.baidu.paddle.fastdeploy.vision.FaceDetectionResult;
+import com.baidu.paddle.fastdeploy.vision.facedet.SCRFD;
+
+// 初始化模型
+SCRFD model = new SCRFD(
+ "scrfd_500m_bnkps_shape320x320_pd/model.pdmodel",
+ "scrfd_500m_bnkps_shape320x320_pd/model.pdiparams");
+
+// 读取图片: 以下仅为读取Bitmap的伪代码
+ByteBuffer pixelBuffer = ByteBuffer.allocate(width * height * 4);
+GLES20.glReadPixels(0, 0, width, height, GLES20.GL_RGBA, GLES20.GL_UNSIGNED_BYTE, pixelBuffer);
+Bitmap ARGB8888ImageBitmap = Bitmap.createBitmap(width, height, Bitmap.Config.ARGB_8888);
+ARGB8888ImageBitmap.copyPixelsFromBuffer(pixelBuffer);
+
+// 直接预测返回 FaceDetectionResult
+FaceDetectionResult result = model.predict(ARGB8888ImageBitmap);
+
+// 释放模型资源
+model.release();
+```
+
+- 模型调用示例2: 在合适的程序节点，手动调用init，并自定义RuntimeOption
+```java
+// import 同上 ...
+import com.baidu.paddle.fastdeploy.RuntimeOption;
+import com.baidu.paddle.fastdeploy.LitePowerMode;
+import com.baidu.paddle.fastdeploy.vision.FaceDetectionResult;
+import com.baidu.paddle.fastdeploy.vision.facedet.SCRFD;
+// 新建空模型
+SCRFD model = new SCRFD();
+// 模型路径
+String modelFile = "scrfd_500m_bnkps_shape320x320_pd/model.pdmodel";
+String paramFile = "scrfd_500m_bnkps_shape320x320_pd/model.pdiparams";
+// 指定RuntimeOption
+RuntimeOption option = new RuntimeOption();
+option.setCpuThreadNum(2);
+option.setLitePowerMode(LitePowerMode.LITE_POWER_HIGH);
+option.enableLiteFp16();
+// 使用init函数初始化
+model.init(modelFile, paramFile, option);
+// Bitmap读取、模型预测、资源释放 同上 ...
+```
+更详细的用法请参考 [FaceDetMainActivity](./app/src/main/java/com/baidu/paddle/fastdeploy/app/examples/facedet/FaceDetMainActivity.java) 中的用法
+
+## 替换 FastDeploy SDK和模型
+替换FastDeploy预测库和模型的步骤非常简单。预测库所在的位置为 `app/libs/fastdeploy-android-sdk-xxx.aar`，其中 `xxx` 表示当前您使用的预测库版本号。模型所在的位置为，`app/src/main/assets/models/scrfd_500m_bnkps_shape320x320_pd`。
+- 替换FastDeploy Android SDK: 下载或编译最新的FastDeploy Android SDK，解压缩后放在 `app/libs` 目录下；详细配置文档可参考:
+ - [在 Android 中使用 FastDeploy Java SDK](../../../../../java/android/)
+
+- 替换SCRFD模型的步骤：
+ - 通过X2Paddle导出其他版本的SCRFD模型，请参考 [SCRFD文档](../README.md) 以及 [X2Paddle](https://github.com/PaddlePaddle/X2Paddle)
+ - 将您的SCRFD模型放在 `app/src/main/assets/models` 目录下；
+ - 修改 `app/src/main/res/values/strings.xml` 中模型路径的默认值，如：
+```xml
+
+
-以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
-- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
+The above command works for Linux or MacOS. For SDK use-pattern in Windows, refer to:
+- [How to use FastDeploy C++ SDK in Windows](../../../../../docs/cn/faq/use_sdk_on_windows.md)
-## SCRFD C++接口
+## SCRFD C++ Interface
-### SCRFD类
+### SCRFD Class
```c++
fastdeploy::vision::facedet::SCRFD(
@@ -50,16 +51,16 @@ fastdeploy::vision::facedet::SCRFD(
const ModelFormat& model_format = ModelFormat::ONNX)
```
-SCRFD模型加载和初始化，其中model_file为导出的ONNX模型格式。
+SCRFD model loading and initialization, among which model_file is the exported ONNX model format
-**参数**
+**Parameter**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为ONNX格式
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. Only passing an empty string when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. ONNX format by default
-#### Predict函数
+#### Predict Function
> ```c++
> SCRFD::Predict(cv::Mat* im, FaceDetectionResult* result,
@@ -67,30 +68,30 @@ SCRFD模型加载和初始化，其中model_file为导出的ONNX模型格式。
> float nms_iou_threshold = 0.5)
> ```
>
-> 模型预测接口，输入图像直接输出检测结果。
+> Model prediction interface. Input images and output detection results.
>
-> **参数**
+> **Parameter**
>
-> > * **im**: 输入图像，注意需为HWC，BGR格式
-> > * **result**: 检测结果，包括检测框，各个框的置信度, FaceDetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
-> > * **conf_threshold**: 检测框置信度过滤阈值
-> > * **nms_iou_threshold**: NMS处理过程中iou阈值
-
-### 类成员变量
-#### 预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
-
-> > * **size**(vector<int>): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
-> > * **padding_value**(vector<float>): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
-> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=ture` 表示不使用填充的方式，默认值为`is_no_pad=false`
-> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=false`
-> > * **stride**(int): 配合`stris_mini_pad`成员变量使用, 默认值为`stride=32`
-> > * **downsample_strides**(vector<int>): 通过此参数可以修改生成anchor的特征图的下采样倍数, 包含三个整型元素, 分别表示默认的生成anchor的下采样倍数, 默认值为[8, 16, 32]
-> > * **landmarks_per_face**(int): 如果使用具有人脸关键点的输出, 可以修改人脸关键点数量, 默认值为`landmarks_per_face=5`
-> > * **use_kps**(bool): 通过此参数可以设置模型是否使用关键点,如果ONNX文件没有关键点输出则需要将`use_kps=false`, 并将`landmarks_per_face=0`, 默认值为`use_kps=true`
-> > * **num_anchors**(int): 通过此参数可以设置每个锚点预测的anchor数量, 需要跟进训练模型的参数设定, 默认值为`num_anchors=2`
-
-- [模型介绍](../../)
-- [Python部署](../python)
-- [视觉模型预测结果](../../../../../docs/api/vision_results/)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+> > * **im**: Input images in HWC or BGR format
+> > * **result**: Detection results, including detection box and confidence of each box. Refer to [Vision Model Prediction Result](../../../../../docs/api/vision_results/) for FaceDetectionResult
+> > * **conf_threshold**: Filtering threshold of detection box confidence
+> > * **nms_iou_threshold**: iou threshold during NMS processing
+
+### Class Member Variable
+#### Pre-processing Parameter
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
+
+> > * **size**(vector<int>): This parameter changes the size of the resize used during preprocessing, containing two integer elements for [width, height] with default value [640, 640]
+> > * **padding_value**(vector<float>): This parameter is used to change the padding value of images during resize, containing three floating-point elements that represent the value of three channels. Default value [114, 114, 114]
+> > * **is_no_pad**(bool): Specify whether to resize the image through padding or not. `is_no_pad=ture` represents no paddling. Default `is_no_pad=false`
+> > * **is_mini_pad**(bool): This parameter sets the width and height of the image after resize to the value nearest to the `size` member variable and to the point where the padded pixel size is divisible by the `stride` member variable. Default `is_mini_pad=false`
+> > * **stride**(int): Used with the `stris_mini_pad` member variable. Default `stride=32`
+> > * **downsample_strides**(vector<int>): This parameter is used to change the down-sampling multiple of the feature map that generates anchor, containing three integer elements that represent the default down-sampling multiple for generating anchor. Default [8, 16, 32]
+> > * **landmarks_per_face**(int): Modify the number of face keypoints if we use an output with face keypoints. Default `landmarks_per_face=5`
+> > * **use_kps**(bool): Whether to use keypoints or not. If the ONNX file has no keypoint output, set `use_kps=false` and `landmarks_per_face=0`. Default `use_kps=true`
+> > * **num_anchors**(int): Set the number predicted by each anchor. The parameters of the trained model need modification accordingly. Default `num_anchors=2`
+
+- [Model Description](../../)
+- [Python Deployment](../python)
+- [Vision Model Prediction Results](../../../../../docs/api/vision_results/)
+- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/facedet/scrfd/cpp/README_CN.md b/examples/vision/facedet/scrfd/cpp/README_CN.md
new file mode 100644
index 0000000000..1c01173b24
--- /dev/null
+++ b/examples/vision/facedet/scrfd/cpp/README_CN.md
@@ -0,0 +1,97 @@
+[English](README.md) | 简体中文
+# SCRFD C++部署示例
+
+本目录下提供`infer.cc`快速完成SCRFD在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试，支持此模型需保证FastDeploy版本0.7.0以上(x.x.x>=0.7.0)
+
+```bash
+mkdir build
+cd build
+# 下载FastDeploy预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz
+tar xvf fastdeploy-linux-x64-x.x.x.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x
+make -j
+
+#下载官方转换好的SCRFD模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/scrfd_500m_bnkps_shape640x640.onnx
+wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/lite/resources/test_lite_face_detector_3.jpg
+
+
+# CPU推理
+./infer_demo scrfd_500m_bnkps_shape640x640.onnx test_lite_face_detector_3.jpg 0
+# GPU推理
+./infer_demo scrfd_500m_bnkps_shape640x640.onnx test_lite_face_detector_3.jpg 1
+# GPU上TensorRT推理
+./infer_demo scrfd_500m_bnkps_shape640x640.onnx test_lite_face_detector_3.jpg 2
+```
+
+运行完成可视化结果如下图所示
+
+
+
+以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
+- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
+
+## SCRFD C++接口
+
+### SCRFD类
+
+```c++
+fastdeploy::vision::facedet::SCRFD(
+ const string& model_file,
+ const string& params_file = "",
+ const RuntimeOption& runtime_option = RuntimeOption(),
+ const ModelFormat& model_format = ModelFormat::ONNX)
+```
+
+SCRFD模型加载和初始化，其中model_file为导出的ONNX模型格式。
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为ONNX格式
+
+#### Predict函数
+
+> ```c++
+> SCRFD::Predict(cv::Mat* im, FaceDetectionResult* result,
+> float conf_threshold = 0.25,
+> float nms_iou_threshold = 0.5)
+> ```
+>
+> 模型预测接口，输入图像直接输出检测结果。
+>
+> **参数**
+>
+> > * **im**: 输入图像，注意需为HWC，BGR格式
+> > * **result**: 检测结果，包括检测框，各个框的置信度, FaceDetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > * **conf_threshold**: 检测框置信度过滤阈值
+> > * **nms_iou_threshold**: NMS处理过程中iou阈值
+
+### 类成员变量
+#### 预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> > * **size**(vector<int>): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
+> > * **padding_value**(vector<float>): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
+> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=ture` 表示不使用填充的方式，默认值为`is_no_pad=false`
+> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=false`
+> > * **stride**(int): 配合`stris_mini_pad`成员变量使用, 默认值为`stride=32`
+> > * **downsample_strides**(vector<int>): 通过此参数可以修改生成anchor的特征图的下采样倍数, 包含三个整型元素, 分别表示默认的生成anchor的下采样倍数, 默认值为[8, 16, 32]
+> > * **landmarks_per_face**(int): 如果使用具有人脸关键点的输出, 可以修改人脸关键点数量, 默认值为`landmarks_per_face=5`
+> > * **use_kps**(bool): 通过此参数可以设置模型是否使用关键点,如果ONNX文件没有关键点输出则需要将`use_kps=false`, 并将`landmarks_per_face=0`, 默认值为`use_kps=true`
+> > * **num_anchors**(int): 通过此参数可以设置每个锚点预测的anchor数量, 需要跟进训练模型的参数设定, 默认值为`num_anchors=2`
+
+- [模型介绍](../../)
+- [Python部署](../python)
+- [视觉模型预测结果](../../../../../docs/api/vision_results/)
+- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/facedet/scrfd/python/README.md b/examples/vision/facedet/scrfd/python/README.md
index d437fac96f..924913e332 100644
--- a/examples/vision/facedet/scrfd/python/README.md
+++ b/examples/vision/facedet/scrfd/python/README.md
@@ -1,84 +1,84 @@
-# SCRFD Python部署示例
+English | [简体中文](README_CN.md)
+# SCRFD Python Deployment Example
-在部署前，需确认以下两个步骤
+Before deployment, two steps require confirmation
-- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-
-本目录下提供`infer.py`快速完成SCRFD在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. Install FastDeploy Python whl package. Refer to [FastDeploy Python Installation](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+This directory provides examples that `infer.py` fast finishes the deployment of SCRFD on CPU/GPU and GPU accelerated by TensorRT. The script is as follows
```bash
-#下载部署示例代码
+# Download the example code for deployment
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision/facedet/scrfd/python/
-#下载SCRFD模型文件和测试图片
+# Download SCRFD model files and test images
wget https://bj.bcebos.com/paddlehub/fastdeploy/scrfd_500m_bnkps_shape640x640.onnx
wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/lite/resources/test_lite_face_detector_3.jpg
-# CPU推理
+# CPU inference
python infer.py --model scrfd_500m_bnkps_shape640x640.onnx --image test_lite_face_detector_3.jpg --device cpu
-# GPU推理
+# GPU inference
python infer.py --model scrfd_500m_bnkps_shape640x640.onnx --image test_lite_face_detector_3.jpg --device gpu
-# GPU上使用TensorRT推理
+# TensorRT inference on GPU
python infer.py --model scrfd_500m_bnkps_shape640x640.onnx --image test_lite_face_detector_3.jpg --device gpu --use_trt True
```
-运行完成可视化结果如下图所示
+The visualized result after running is as follows
-## SCRFD Python接口
+## SCRFD Python Interface
```python
fastdeploy.vision.facedet.SCRFD(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
```
-SCRFD模型加载和初始化，其中model_file为导出的ONNX模型格式
+SCRFD model loading and initialization, among which model_file is the exported ONNX model format
-**参数**
+**Parameter**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为ONNX
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. No need to set when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. ONNX format by default
-### predict函数
+### predict function
> ```python
> SCRFD.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
> ```
>
-> 模型预测结口，输入图像直接输出检测结果。
+> Model prediction interface. Input images and output detection results.
>
-> **参数**
+> **Parameter**
>
-> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
-> > * **conf_threshold**(float): 检测框置信度过滤阈值
-> > * **nms_iou_threshold**(float): NMS处理过程中iou阈值
+> > * **image_data**(np.ndarray): Input data in HWC or BGR format
+> > * **conf_threshold**(float): Filtering threshold of detection box confidence
+> > * **nms_iou_threshold**(float): iou threshold during NMS processing
-> **返回**
+> **Return**
>
-> > 返回`fastdeploy.vision.FaceDetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > Return `fastdeploy.vision.FaceDetectionResult` structure. Refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for its description.
-### 类成员属性
-#### 预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+### Class Member Property
+#### Pre-processing Parameter
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
-> > * **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
-> > * **padding_value**(list[float]): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
-> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=True` 表示不使用填充的方式，默认值为`is_no_pad=False`
-> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=False`
-> > * **stride**(int): 配合`stris_mini_padide`成员变量使用, 默认值为`stride=32`
-> > * **downsample_strides**(list[int]): 通过此参数可以修改生成anchor的特征图的下采样倍数, 包含三个整型元素, 分别表示默认的生成anchor的下采样倍数, 默认值为[8, 16, 32]
-> > * **landmarks_per_face**(int): 如果使用具有人脸关键点的输出, 可以修改人脸关键点数量, 默认值为`landmarks_per_face=5`
-> > * **use_kps**(bool): 通过此参数可以设置模型是否使用关键点,如果ONNX文件没有关键点输出则需要将`use_kps=False`, 并将`landmarks_per_face=0`, 默认值为`use_kps=True`
-> > * **num_anchors**(int): 通过此参数可以设置每个锚点预测的anchor数量, 需要跟进训练模型的参数设定, 默认值为`num_anchors=2`
+> > * **size**(list[int]): This parameter changes the size of the resize used during preprocessing, containing two integer elements for [width, height] with default value [640, 640]
+> > * **padding_value**(list[float]): This parameter is used to change the padding value of images during resize, containing three floating-point elements that represent the value of three channels. Default value [114, 114, 114]
+> > * **is_no_pad**(bool): Specify whether to resize the image through padding or not. `is_no_pad=True` represents no paddling. Default `is_no_pad=False`
+> > * **is_mini_pad**(bool): This parameter sets the width and height of the image after resize to the value nearest to the `size` member variable and to the point where the padded pixel size is divisible by the `stride` member variable. Default `is_mini_pad=False`
+> > * **stride**(int): Used with the `stris_mini_padide` member variable. Default`stride=32`
+> > * **downsample_strides**(list[int]): This parameter is used to change the down-sampling multiple of the feature map that generates anchor, containing three integer elements that represent the default down-sampling multiple for generating anchor. Default [8, 16, 32]
+> > * **landmarks_per_face**(int): Modify the number of face keypoints if we use an output with face keypoints. Default `landmarks_per_face=5`
+> > * **use_kps**(bool): Whether to use keypoints or not. If the ONNX file has no keypoint output, set `use_kps=False` and `landmarks_per_face=0`. Default `use_kps=True`
+> > * **num_anchors**(int): Set the number predicted by each anchor. The parameters of the trained model need modification accordingly. Default `num_anchors=2`
-## 其它文档
+## Other Documents
-- [SCRFD 模型介绍](..)
-- [SCRFD C++部署](../cpp)
-- [模型预测结果说明](../../../../../docs/api/vision_results/)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+- [SCRFD Model Description](..)
+- [SCRFD C++ Deployment](../cpp)
+- [Model Prediction Results](../../../../../docs/api/vision_results/)
+- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/facedet/scrfd/python/README_CN.md b/examples/vision/facedet/scrfd/python/README_CN.md
new file mode 100644
index 0000000000..e1a2689634
--- /dev/null
+++ b/examples/vision/facedet/scrfd/python/README_CN.md
@@ -0,0 +1,85 @@
+[English](README.md) | 简体中文
+# SCRFD Python部署示例
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+本目录下提供`infer.py`快速完成SCRFD在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+
+```bash
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd examples/vision/facedet/scrfd/python/
+
+#下载SCRFD模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/scrfd_500m_bnkps_shape640x640.onnx
+wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/lite/resources/test_lite_face_detector_3.jpg
+
+# CPU推理
+python infer.py --model scrfd_500m_bnkps_shape640x640.onnx --image test_lite_face_detector_3.jpg --device cpu
+# GPU推理
+python infer.py --model scrfd_500m_bnkps_shape640x640.onnx --image test_lite_face_detector_3.jpg --device gpu
+# GPU上使用TensorRT推理
+python infer.py --model scrfd_500m_bnkps_shape640x640.onnx --image test_lite_face_detector_3.jpg --device gpu --use_trt True
+```
+
+运行完成可视化结果如下图所示
+
+
+
+## SCRFD Python接口
+
+```python
+fastdeploy.vision.facedet.SCRFD(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
+```
+
+SCRFD模型加载和初始化，其中model_file为导出的ONNX模型格式
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为ONNX
+
+### predict函数
+
+> ```python
+> SCRFD.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
+> ```
+>
+> 模型预测结口，输入图像直接输出检测结果。
+>
+> **参数**
+>
+> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
+> > * **conf_threshold**(float): 检测框置信度过滤阈值
+> > * **nms_iou_threshold**(float): NMS处理过程中iou阈值
+
+> **返回**
+>
+> > 返回`fastdeploy.vision.FaceDetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+
+### 类成员属性
+#### 预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> > * **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
+> > * **padding_value**(list[float]): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
+> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=True` 表示不使用填充的方式，默认值为`is_no_pad=False`
+> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=False`
+> > * **stride**(int): 配合`stris_mini_padide`成员变量使用, 默认值为`stride=32`
+> > * **downsample_strides**(list[int]): 通过此参数可以修改生成anchor的特征图的下采样倍数, 包含三个整型元素, 分别表示默认的生成anchor的下采样倍数, 默认值为[8, 16, 32]
+> > * **landmarks_per_face**(int): 如果使用具有人脸关键点的输出, 可以修改人脸关键点数量, 默认值为`landmarks_per_face=5`
+> > * **use_kps**(bool): 通过此参数可以设置模型是否使用关键点,如果ONNX文件没有关键点输出则需要将`use_kps=False`, 并将`landmarks_per_face=0`, 默认值为`use_kps=True`
+> > * **num_anchors**(int): 通过此参数可以设置每个锚点预测的anchor数量, 需要跟进训练模型的参数设定, 默认值为`num_anchors=2`
+
+
+## 其它文档
+
+- [SCRFD 模型介绍](..)
+- [SCRFD C++部署](../cpp)
+- [模型预测结果说明](../../../../../docs/api/vision_results/)
+- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/facedet/scrfd/rknpu2/README.md b/examples/vision/facedet/scrfd/rknpu2/README.md
index b77afe3620..a70dff7e89 100644
--- a/examples/vision/facedet/scrfd/rknpu2/README.md
+++ b/examples/vision/facedet/scrfd/rknpu2/README.md
@@ -1,10 +1,11 @@
-# SCRFD RKNPU2部署模型
+English | [简体中文](README_CN.md)
+# SCRFD RKNPU2 Deployment Models
-本教程提供SCRFD模型在RKNPU2环境下的部署，模型的详细介绍已经ONNX模型的下载请查看[模型介绍文档](../README.md)。
+This tutorial demonstrates the deployment of SCRFD models in RKNPU2. For model description and download of ONNX models, refer to [Model Description](../README.md)。
-## ONNX模型转换RKNN模型
+## From ONNX model to RKNN model
-下面以scrfd_500m_bnkps_shape640x640为例子，快速的转换SCRFD ONNX模型为RKNN量化模型。 以下命令在Ubuntu18.04下执行:
+Taking scrfd_500m_bnkps_shape640x640 as an example, the following commands in Ubuntu18.0 demonstrate how to fast convert SCRFD ONNX models to RKNN quantification models:
```bash
wget https://bj.bcebos.com/paddlehub/fastdeploy/rknpu2/scrfd_500m_bnkps_shape640x640.zip
unzip scrfd_500m_bnkps_shape640x640.zip
@@ -15,12 +16,12 @@ python /Path/To/FastDeploy/tools/rknpu2/export.py \
-## 详细部署文档
+## Detailed Deployment Tutorials
-- [Python部署](python/README.md)
-- [C++部署](cpp/README.md)
+- [Python Deployment](python/README.md)
+- [C++ Deployment](cpp/README.md)
-## 版本说明
+## Release Note
-- 本版本文档和代码基于[SCRFD CommitID:17cdeab](https://github.com/deepinsight/insightface/tree/17cdeab12a35efcebc2660453a8cbeae96e20950) 编写
+- This document and code are written based on [SCRFD CommitID:17cdeab](https://github.com/deepinsight/insightface/tree/17cdeab12a35efcebc2660453a8cbeae96e20950)
diff --git a/examples/vision/facedet/scrfd/rknpu2/README_CN.md b/examples/vision/facedet/scrfd/rknpu2/README_CN.md
new file mode 100644
index 0000000000..00a8c08440
--- /dev/null
+++ b/examples/vision/facedet/scrfd/rknpu2/README_CN.md
@@ -0,0 +1,27 @@
+[English](README.md) | 简体中文
+# SCRFD RKNPU2部署模型
+
+本教程提供SCRFD模型在RKNPU2环境下的部署，模型的详细介绍已经ONNX模型的下载请查看[模型介绍文档](../README.md)。
+
+## ONNX模型转换RKNN模型
+
+下面以scrfd_500m_bnkps_shape640x640为例子，快速的转换SCRFD ONNX模型为RKNN量化模型。 以下命令在Ubuntu18.04下执行:
+```bash
+wget https://bj.bcebos.com/paddlehub/fastdeploy/rknpu2/scrfd_500m_bnkps_shape640x640.zip
+unzip scrfd_500m_bnkps_shape640x640.zip
+python /Path/To/FastDeploy/tools/rknpu2/export.py \
+ --config_path tools/rknpu2/config/scrfd.yaml \
+ --target_platform rk3588
+```
+
+
+
+## 详细部署文档
+
+- [Python部署](python/README.md)
+- [C++部署](cpp/README.md)
+
+
+## 版本说明
+
+- 本版本文档和代码基于[SCRFD CommitID:17cdeab](https://github.com/deepinsight/insightface/tree/17cdeab12a35efcebc2660453a8cbeae96e20950) 编写
diff --git a/examples/vision/facedet/ultraface/README.md b/examples/vision/facedet/ultraface/README.md
index 222dde4956..ced821ed82 100644
--- a/examples/vision/facedet/ultraface/README.md
+++ b/examples/vision/facedet/ultraface/README.md
@@ -1,28 +1,29 @@
-# UltraFace准备部署模型
+English | [简体中文](README_CN.md)
+# UltraFace Ready-to-deploy Model
- [UltraFace](https://github.com/Linzaer/Ultra-Light-Fast-Generic-Face-Detector-1MB/commit/dffdddd)
- - （1）[官方库](https://github.com/Linzaer/Ultra-Light-Fast-Generic-Face-Detector-1MB/)中提供的*.onnx可下载, 也可以通过下面模型链接下载并进行部署
- - （2）开发者自己训练的模型，导出ONNX模型后，参考[详细部署文档](#详细部署文档)完成部署。
+ - （1）The *.onnx provided by the [Official Library](https://github.com/Linzaer/Ultra-Light-Fast-Generic-Face-Detector-1MB/) can be downloaded directly or through the following model link.
+ - （2）As for the model trained on customized data, export the onnx model and then refer to [Detailed Deployment Tutorials](#详细部署文档) to complete the deployment.
-## 下载预训练ONNX模型
+## Download Pre-trained ONNX Models
-为了方便开发者的测试，下面提供了UltraFace导出的各系列模型，开发者可直接下载使用。（下表中模型的精度来源于源官方库）
-| 模型 | 大小 | 精度 |
+For developers' testing, models exported by UltraFace are provided below. Developers can download and use them directly. (The accuracy of the models in the table is sourced from the official library)
+| Model | Size | Accuracy |
|:---------------------------------------------------------------- |:----- |:----- |
| [RFB-320](https://bj.bcebos.com/paddlehub/fastdeploy/version-RFB-320.onnx) | 1.3MB | 78.7 |
| [RFB-320-sim](https://bj.bcebos.com/paddlehub/fastdeploy/version-RFB-320-sim.onnx) | 1.2MB | 78.7 |
-## 详细部署文档
+## Detailed Deployment Tutorials
-- [Python部署](python)
-- [C++部署](cpp)
+- [Python Deployment](python)
+- [C++ Deployment](cpp)
-## 版本说明
+## Release Note
-- 本版本文档和代码基于[UltraFace CommitID:dffdddd](https://github.com/Linzaer/Ultra-Light-Fast-Generic-Face-Detector-1MB/commit/dffdddd) 编写
+- This tutorial and related code are written based on [UltraFace CommitID:dffdddd](https://github.com/Linzaer/Ultra-Light-Fast-Generic-Face-Detector-1MB/commit/dffdddd)
diff --git a/examples/vision/facedet/ultraface/README_CN.md b/examples/vision/facedet/ultraface/README_CN.md
new file mode 100644
index 0000000000..0d4604d761
--- /dev/null
+++ b/examples/vision/facedet/ultraface/README_CN.md
@@ -0,0 +1,29 @@
+[English](README.md) | 简体中文
+# UltraFace准备部署模型
+
+
+- [UltraFace](https://github.com/Linzaer/Ultra-Light-Fast-Generic-Face-Detector-1MB/commit/dffdddd)
+ - （1）[官方库](https://github.com/Linzaer/Ultra-Light-Fast-Generic-Face-Detector-1MB/)中提供的*.onnx可下载, 也可以通过下面模型链接下载并进行部署
+ - （2）开发者自己训练的模型，导出ONNX模型后，参考[详细部署文档](#详细部署文档)完成部署。
+
+
+
+## 下载预训练ONNX模型
+
+为了方便开发者的测试，下面提供了UltraFace导出的各系列模型，开发者可直接下载使用。（下表中模型的精度来源于源官方库）
+| 模型 | 大小 | 精度 |
+|:---------------------------------------------------------------- |:----- |:----- |
+| [RFB-320](https://bj.bcebos.com/paddlehub/fastdeploy/version-RFB-320.onnx) | 1.3MB | 78.7 |
+| [RFB-320-sim](https://bj.bcebos.com/paddlehub/fastdeploy/version-RFB-320-sim.onnx) | 1.2MB | 78.7 |
+
+
+
+## 详细部署文档
+
+- [Python部署](python)
+- [C++部署](cpp)
+
+
+## 版本说明
+
+- 本版本文档和代码基于[UltraFace CommitID:dffdddd](https://github.com/Linzaer/Ultra-Light-Fast-Generic-Face-Detector-1MB/commit/dffdddd) 编写
diff --git a/examples/vision/facedet/ultraface/cpp/README.md b/examples/vision/facedet/ultraface/cpp/README.md
index 8d512af0a9..da0fef6e9a 100644
--- a/examples/vision/facedet/ultraface/cpp/README.md
+++ b/examples/vision/facedet/ultraface/cpp/README.md
@@ -1,46 +1,49 @@
-# UltraFace C++部署示例
+English | [简体中文](README_CN.md)
-本目录下提供`infer.cc`快速完成UltraFace在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+# UltraFace C++ Deployment Example
-在部署前，需确认以下两个步骤
+This directory provides examples that `infer.cc` fast finishes the deployment of UltraFace on CPU/GPU and GPU accelerated by TensorRT.
-- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+Before deployment, two steps require confirmation
-以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试，支持此模型需保证FastDeploy版本0.7.0以上(x.x.x>=0.7.0)
+- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. Download the precompiled deployment library and samples code according to your development environment. Refer to [FastDeploy Precompiled Library](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+Taking the CPU inference on Linux as an example, the compilation test can be completed by executing the following command in this directory. FastDeploy version 0.7.0 or above (x.x.x>=0.7.0) is required to support this model.
```bash
mkdir build
cd build
-# 下载FastDeploy预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
+# Download the FastDeploy precompiled library. Users can choose your appropriate version in the `FastDeploy Precompiled Library` mentioned above
wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz
tar xvf fastdeploy-linux-x64-x.x.x.tgz
cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x
make -j
-#下载官方转换好的UltraFace模型文件和测试图片
+# Download the official converted UltraFace model files and test images
wget https://bj.bcebos.com/paddlehub/fastdeploy/version-RFB-320.onnx
wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/lite/resources/test_lite_face_detector_3.jpg
-# CPU推理
+# CPU inference
./infer_demo version-RFB-320.onnx test_lite_face_detector_3.jpg 0
-# GPU推理
+# GPU inference
./infer_demo version-RFB-320.onnx test_lite_face_detector_3.jpg 1
-# GPU上TensorRT推理
+# TensorRT inference on GPU
./infer_demo version-RFB-320.onnx test_lite_face_detector_3.jpg 2
```
-运行完成可视化结果如下图所示
+The visualized result after running is as follows
-以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
-- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
+The above command works for Linux or MacOS. For SDK use-pattern in Windows, refer to:
+
+- [How to use FastDeploy C++ SDK in Windows](../../../../../docs/cn/faq/use_sdk_on_windows.md)
-## UltraFace C++接口
+## UltraFace C++ Interface
-### UltraFace类
+### UltraFace Class
```c++
fastdeploy::vision::facedet::UltraFace(
@@ -50,39 +53,43 @@ fastdeploy::vision::facedet::UltraFace(
const ModelFormat& model_format = ModelFormat::ONNX)
```
-UltraFace模型加载和初始化，其中model_file为导出的ONNX模型格式。
+UltraFace model loading and initialization, among which model_file is the exported ONNX model format
-**参数**
+**Parameter**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为ONNX格式
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. Only passing an empty string when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. ONNX format by default
-#### Predict函数
+#### Predict Function
> ```c++
> UltraFace::Predict(cv::Mat* im, FaceDetectionResult* result,
-> float conf_threshold = 0.25,
-> float nms_iou_threshold = 0.5)
+> float conf_threshold = 0.25,
+> float nms_iou_threshold = 0.5)
> ```
>
-> 模型预测接口，输入图像直接输出检测结果。
+> Model prediction interface. Input images and output detection results.
>
-> **参数**
+> **Parameter**
>
-> > * **im**: 输入图像，注意需为HWC，BGR格式
-> > * **result**: 检测结果，包括检测框，各个框的置信度, FaceDetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
-> > * **conf_threshold**: 检测框置信度过滤阈值
-> > * **nms_iou_threshold**: NMS处理过程中iou阈值
+> > * **im**: Input images in HWC or BGR format
+> > * **result**: Detection results, including detection box and confidence of each box. Refer to [Vision Model Prediction Result](../../../../../docs/api/vision_results/) for FaceDetectionResult
+> > * **conf_threshold**: Filtering threshold of detection box confidence
+> > * **nms_iou_threshold**: iou threshold during NMS processing
+
+
+
+### Class Member Variable
+
+#### Pre-processing Parameter
-### 类成员变量
-#### 预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
-> > * **size**(vector<int>): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[320, 240]
+> > * **size**(vector<int>): This parameter changes the size of the resize used during preprocessing, containing two integer elements for [width, height] with default value [320, 240]
-- [模型介绍](../../)
-- [Python部署](../python)
-- [视觉模型预测结果](../../../../../docs/api/vision_results/)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+- [Model Description](../../)
+- [Python Deployment](../python)
+- [Vision Model Prediction Results](../../../../../docs/api/vision_results/)
+- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/facedet/ultraface/cpp/README_CN.md b/examples/vision/facedet/ultraface/cpp/README_CN.md
new file mode 100644
index 0000000000..cf21bd25b8
--- /dev/null
+++ b/examples/vision/facedet/ultraface/cpp/README_CN.md
@@ -0,0 +1,89 @@
+[English](README.md) | 简体中文
+# UltraFace C++部署示例
+
+本目录下提供`infer.cc`快速完成UltraFace在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试，支持此模型需保证FastDeploy版本0.7.0以上(x.x.x>=0.7.0)
+
+```bash
+mkdir build
+cd build
+# 下载FastDeploy预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz
+tar xvf fastdeploy-linux-x64-x.x.x.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x
+make -j
+
+#下载官方转换好的UltraFace模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/version-RFB-320.onnx
+wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/lite/resources/test_lite_face_detector_3.jpg
+
+
+# CPU推理
+./infer_demo version-RFB-320.onnx test_lite_face_detector_3.jpg 0
+# GPU推理
+./infer_demo version-RFB-320.onnx test_lite_face_detector_3.jpg 1
+# GPU上TensorRT推理
+./infer_demo version-RFB-320.onnx test_lite_face_detector_3.jpg 2
+```
+
+运行完成可视化结果如下图所示
+
+
+
+以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
+- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
+
+## UltraFace C++接口
+
+### UltraFace类
+
+```c++
+fastdeploy::vision::facedet::UltraFace(
+ const string& model_file,
+ const string& params_file = "",
+ const RuntimeOption& runtime_option = RuntimeOption(),
+ const ModelFormat& model_format = ModelFormat::ONNX)
+```
+
+UltraFace模型加载和初始化，其中model_file为导出的ONNX模型格式。
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为ONNX格式
+
+#### Predict函数
+
+> ```c++
+> UltraFace::Predict(cv::Mat* im, FaceDetectionResult* result,
+> float conf_threshold = 0.25,
+> float nms_iou_threshold = 0.5)
+> ```
+>
+> 模型预测接口，输入图像直接输出检测结果。
+>
+> **参数**
+>
+> > * **im**: 输入图像，注意需为HWC，BGR格式
+> > * **result**: 检测结果，包括检测框，各个框的置信度, FaceDetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > * **conf_threshold**: 检测框置信度过滤阈值
+> > * **nms_iou_threshold**: NMS处理过程中iou阈值
+
+### 类成员变量
+#### 预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> > * **size**(vector<int>): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[320, 240]
+
+- [模型介绍](../../)
+- [Python部署](../python)
+- [视觉模型预测结果](../../../../../docs/api/vision_results/)
+- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/facedet/ultraface/python/README.md b/examples/vision/facedet/ultraface/python/README.md
index 05fc5205f1..2d94499923 100644
--- a/examples/vision/facedet/ultraface/python/README.md
+++ b/examples/vision/facedet/ultraface/python/README.md
@@ -1,75 +1,76 @@
-# UltraFace Python部署示例
+English | [简体中文](README_CN.md)
+# UltraFace Python Deployment Example
-在部署前，需确认以下两个步骤
+Before deployment, two steps require confirmation
-- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. Install FastDeploy Python whl package. Refer to [FastDeploy Python Installation](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-本目录下提供`infer.py`快速完成UltraFace在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+This directory provides examples that `infer.py` fast finishes the deployment of UltraFace on CPU/GPU and GPU accelerated by TensorRT. The script is as follows
```bash
-#下载部署示例代码
+# Download the example code for deployment
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision/facedet/ultraface/python/
-#下载ultraface模型文件和测试图片
+# Download ultraface model files and test images
wget https://bj.bcebos.com/paddlehub/fastdeploy/version-RFB-320.onnx
wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/lite/resources/test_lite_face_detector_3.jpg
-# CPU推理
+# CPU inference
python infer.py --model version-RFB-320.onnx --image test_lite_face_detector_3.jpg --device cpu
-# GPU推理
+# GPU inference
python infer.py --model version-RFB-320.onnx --image test_lite_face_detector_3.jpg --device gpu
-# GPU上使用TensorRT推理
+# TensorRT inference on GPU
python infer.py --model version-RFB-320.onnx --image test_lite_face_detector_3.jpg --device gpu --use_trt True
```
-运行完成可视化结果如下图所示
+The visualized result after running is as follows
-## UltraFace Python接口
+## UltraFace Python Interface
```python
fastdeploy.vision.facedet.UltraFace(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
```
-UltraFace模型加载和初始化，其中model_file为导出的ONNX模型格式
+UltraFace model loading and initialization, among which model_file is the exported ONNX model format
-**参数**
+**Parameter**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为ONNX
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. No need to set when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. ONNX format by default
-### predict函数
+### predict function
> ```python
> UltraFace.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
> ```
>
-> 模型预测结口，输入图像直接输出检测结果。
+> Model prediction interface. Input images and output detection results.
>
-> **参数**
+> **Parameter**
>
-> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
-> > * **conf_threshold**(float): 检测框置信度过滤阈值
-> > * **nms_iou_threshold**(float): NMS处理过程中iou阈值
+> > * **image_data**(np.ndarray): Input data in HWC or BGR format
+> > * **conf_threshold**(float): Filtering threshold of detection box confidence
+> > * **nms_iou_threshold**(float): iou threshold during NMS processing
-> **返回**
+> **Return**
>
-> > 返回`fastdeploy.vision.FaceDetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > Return `fastdeploy.vision.FaceDetectionResult` structure. Refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for its description.
-### 类成员属性
-#### 预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+### Class Member Property
+#### Pre-processing Parameter
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
-> > * **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[320, 240]
+> > * **size**(list[int]): This parameter changes the size of the resize used during preprocessing, containing two integer elements for [width, height] with default value [320, 240]
-## 其它文档
+## Other Documents
-- [UltraFace 模型介绍](..)
-- [UltraFace C++部署](../cpp)
-- [模型预测结果说明](../../../../../docs/api/vision_results/)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+- [UltraFace Model Description](..)
+- [UltraFace C++ Deployment](../cpp)
+- [Model Prediction Results](../../../../../docs/api/vision_results/)
+- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/facedet/ultraface/python/README_CN.md b/examples/vision/facedet/ultraface/python/README_CN.md
new file mode 100644
index 0000000000..99c44ab3b9
--- /dev/null
+++ b/examples/vision/facedet/ultraface/python/README_CN.md
@@ -0,0 +1,76 @@
+[English](README.md) | 简体中文
+# UltraFace Python部署示例
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+本目录下提供`infer.py`快速完成UltraFace在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+
+```bash
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd examples/vision/facedet/ultraface/python/
+
+#下载ultraface模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/version-RFB-320.onnx
+wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/lite/resources/test_lite_face_detector_3.jpg
+
+# CPU推理
+python infer.py --model version-RFB-320.onnx --image test_lite_face_detector_3.jpg --device cpu
+# GPU推理
+python infer.py --model version-RFB-320.onnx --image test_lite_face_detector_3.jpg --device gpu
+# GPU上使用TensorRT推理
+python infer.py --model version-RFB-320.onnx --image test_lite_face_detector_3.jpg --device gpu --use_trt True
+```
+
+运行完成可视化结果如下图所示
+
+
+
+## UltraFace Python接口
+
+```python
+fastdeploy.vision.facedet.UltraFace(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
+```
+
+UltraFace模型加载和初始化，其中model_file为导出的ONNX模型格式
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为ONNX
+
+### predict函数
+
+> ```python
+> UltraFace.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
+> ```
+>
+> 模型预测结口，输入图像直接输出检测结果。
+>
+> **参数**
+>
+> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
+> > * **conf_threshold**(float): 检测框置信度过滤阈值
+> > * **nms_iou_threshold**(float): NMS处理过程中iou阈值
+
+> **返回**
+>
+> > 返回`fastdeploy.vision.FaceDetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+
+### 类成员属性
+#### 预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> > * **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[320, 240]
+
+## 其它文档
+
+- [UltraFace 模型介绍](..)
+- [UltraFace C++部署](../cpp)
+- [模型预测结果说明](../../../../../docs/api/vision_results/)
+- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/facedet/yolov5face/README.md b/examples/vision/facedet/yolov5face/README.md
index e845e568c4..4523c44775 100644
--- a/examples/vision/facedet/yolov5face/README.md
+++ b/examples/vision/facedet/yolov5face/README.md
@@ -1,44 +1,45 @@
-# YOLOv5Face准备部署模型
+English | [简体中文](README_CN.md)
+# YOLOv5Face Ready-to-deploy Model
- [YOLOv5Face](https://github.com/deepcam-cn/yolov5-face/commit/4fd1ead)
- - （1）[官方库](https://github.com/deepcam-cn/yolov5-face/)中提供的*.pt通过[导出ONNX模型](#导出ONNX模型)操作后，可进行部署；
- - （2）开发者基于自己数据训练的YOLOv5Face模型，可按照[导出ONNX模型](#%E5%AF%BC%E5%87%BAONNX%E6%A8%A1%E5%9E%8B)后，完成部署。
+ - （1）The *.pt provided by the [Official Library](https://github.com/deepcam-cn/yolov5-face/) can be deployed after the [Export ONNX Model](#导出ONNX模型) to complete the deployment；
+ - （2）As for YOLOv5Face model trained on customized data, please follow the operations guidelines in [Export ONNX Model](#%E5%AF%BC%E5%87%BAONNX%E6%A8%A1%E5%9E%8B) to complete the deployment.
-## 导出ONNX模型
+## Export ONNX Model
-访问[YOLOv5Face](https://github.com/deepcam-cn/yolov5-face)官方github库，按照指引下载安装，下载`yolov5s-face.pt` 模型，利用 `export.py` 得到`onnx`格式文件。
+Visit [YOLOv5Face](https://github.com/deepcam-cn/yolov5-face) official github repository, follow the guidelines to download the `yolov5s-face.pt` model, and employ `export.py` to get the file in `onnx` format.
-* 下载yolov5face模型文件
+* Download yolov5face model files
```
Link: https://pan.baidu.com/s/1fyzLxZYx7Ja1_PCIWRhxbw Link: eq0q
https://drive.google.com/file/d/1zxaHeLDyID9YU4-hqK7KNepXIwbTkRIO/view?usp=sharing
```
-* 导出onnx格式文件
+* Export files in onnx format
```bash
PYTHONPATH=. python export.py --weights weights/yolov5s-face.pt --img_size 640 640 --batch_size 1
```
-* onnx模型简化(可选)
+* onnx model simplification (optional)
```bash
onnxsim yolov5s-face.onnx yolov5s-face.onnx
```
-## 下载预训练ONNX模型
+## Download Pre-trained ONNX Model
-为了方便开发者的测试，下面提供了YOLOv5Face导出的各系列模型，开发者可直接下载使用。（下表中模型的精度来源于源官方库）
-| 模型 | 大小 | 精度 |
+For developers' testing, models exported by YOLOv5Face are provided below. Developers can download and use them directly. (The accuracy of the models in the table is sourced from the official library)
+| Model | Size | Accuracy |
|:---------------------------------------------------------------- |:----- |:----- |
| [YOLOv5s-Face](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s-face.onnx) | 30MB | 94.3 |
| [YOLOv5s-Face-bak](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5face-s-640x640.bak.onnx) | 30MB | -|
| [YOLOv5l-Face](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5face-l-640x640.onnx ) | 181MB | 95.8 |
-## 详细部署文档
+## Detailed Deployment Tutorials
-- [Python部署](python)
-- [C++部署](cpp)
+- [Python Deployment](python)
+- [C++ Deployment](cpp)
-## 版本说明
+## Release Note
-- 本版本文档和代码基于[YOLOv5Face CommitID:4fd1ead](https://github.com/deepcam-cn/yolov5-face/commit/4fd1ead) 编写
+- This tutorial and related code are written based on [YOLOv5Face CommitID:4fd1ead](https://github.com/deepcam-cn/yolov5-face/commit/4fd1ead)
diff --git a/examples/vision/facedet/yolov5face/README_CN.md b/examples/vision/facedet/yolov5face/README_CN.md
new file mode 100644
index 0000000000..723c44a900
--- /dev/null
+++ b/examples/vision/facedet/yolov5face/README_CN.md
@@ -0,0 +1,45 @@
+[English](README.md) | 简体中文
+# YOLOv5Face准备部署模型
+
+- [YOLOv5Face](https://github.com/deepcam-cn/yolov5-face/commit/4fd1ead)
+ - （1）[官方库](https://github.com/deepcam-cn/yolov5-face/)中提供的*.pt通过[导出ONNX模型](#导出ONNX模型)操作后，可进行部署；
+ - （2）开发者基于自己数据训练的YOLOv5Face模型，可按照[导出ONNX模型](#%E5%AF%BC%E5%87%BAONNX%E6%A8%A1%E5%9E%8B)后，完成部署。
+
+## 导出ONNX模型
+
+访问[YOLOv5Face](https://github.com/deepcam-cn/yolov5-face)官方github库，按照指引下载安装，下载`yolov5s-face.pt` 模型，利用 `export.py` 得到`onnx`格式文件。
+
+* 下载yolov5face模型文件
+ ```
+ Link: https://pan.baidu.com/s/1fyzLxZYx7Ja1_PCIWRhxbw Link: eq0q
+ https://drive.google.com/file/d/1zxaHeLDyID9YU4-hqK7KNepXIwbTkRIO/view?usp=sharing
+ ```
+
+* 导出onnx格式文件
+ ```bash
+ PYTHONPATH=. python export.py --weights weights/yolov5s-face.pt --img_size 640 640 --batch_size 1
+ ```
+* onnx模型简化(可选)
+ ```bash
+ onnxsim yolov5s-face.onnx yolov5s-face.onnx
+ ```
+
+## 下载预训练ONNX模型
+
+为了方便开发者的测试，下面提供了YOLOv5Face导出的各系列模型，开发者可直接下载使用。（下表中模型的精度来源于源官方库）
+| 模型 | 大小 | 精度 |
+|:---------------------------------------------------------------- |:----- |:----- |
+| [YOLOv5s-Face](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s-face.onnx) | 30MB | 94.3 |
+| [YOLOv5s-Face-bak](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5face-s-640x640.bak.onnx) | 30MB | -|
+| [YOLOv5l-Face](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5face-l-640x640.onnx ) | 181MB | 95.8 |
+
+
+## 详细部署文档
+
+- [Python部署](python)
+- [C++部署](cpp)
+
+
+## 版本说明
+
+- 本版本文档和代码基于[YOLOv5Face CommitID:4fd1ead](https://github.com/deepcam-cn/yolov5-face/commit/4fd1ead) 编写
diff --git a/examples/vision/facedet/yolov5face/cpp/README.md b/examples/vision/facedet/yolov5face/cpp/README.md
index a1df0620dd..1ca2a6bbe1 100644
--- a/examples/vision/facedet/yolov5face/cpp/README.md
+++ b/examples/vision/facedet/yolov5face/cpp/README.md
@@ -1,46 +1,47 @@
-# YOLOv5Face C++部署示例
+English | [简体中文](README_CN.md)
+# YOLOv5Face C++ Deployment Example
-本目录下提供`infer.cc`快速完成YOLOv5Face在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+This directory provides examples that `infer.cc` fast finishes the deployment of YOLOv5Face on CPU/GPU and GPU accelerated by TensorRT.
-在部署前，需确认以下两个步骤
+Before deployment, two steps require confirmation
-- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. Download the precompiled deployment library and samples code according to your development environment. Refer to [FastDeploy Precompiled Library](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试，支持此模型需保证FastDeploy版本0.7.0以上(x.x.x>=0.7.0)
+Taking the CPU inference on Linux as an example, the compilation test can be completed by executing the following command in this directory. FastDeploy version 0.7.0 or above (x.x.x>=0.7.0) is required to support this model.
```bash
mkdir build
cd build
-# 下载FastDeploy预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
+# Download the FastDeploy precompiled library. Users can choose your appropriate version in the `FastDeploy Precompiled Library` mentioned above
wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz
tar xvf fastdeploy-linux-x64-x.x.x.tgz
cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x
make -j
-#下载官方转换好的YOLOv5Face模型文件和测试图片
+# Download the official converted YOLOv5Face model files and test images
wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s-face.onnx
wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/lite/resources/test_lite_face_detector_3.jpg
-# CPU推理
+# CPU inference
./infer_demo yolov5s-face.onnx test_lite_face_detector_3.jpg 0
-# GPU推理
+# GPU inference
./infer_demo yolov5s-face.onnx test_lite_face_detector_3.jpg 1
-# GPU上TensorRT推理
+# TensorRT inference on GPU
./infer_demo yolov5s-face.onnx test_lite_face_detector_3.jpg 2
```
-运行完成可视化结果如下图所示
+The visualized result after running is as follows
-以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
-- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
+The above command works for Linux or MacOS. For SDK use-pattern in Windows, refer to:
+- [How to use FastDeploy C++ SDK in Windows](../../../../../docs/cn/faq/use_sdk_on_windows.md)
-## YOLOv5Face C++接口
+## YOLOv5Face C++ Interface
-### YOLOv5Face类
+### YOLOv5Face Class
```c++
fastdeploy::vision::facedet::YOLOv5Face(
@@ -50,16 +51,16 @@ fastdeploy::vision::facedet::YOLOv5Face(
const ModelFormat& model_format = ModelFormat::ONNX)
```
-YOLOv5Face模型加载和初始化，其中model_file为导出的ONNX模型格式。
+YOLOv5Face model loading and initialization, among which model_file is the exported ONNX model format.
**参数**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为ONNX格式
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. Only passing an empty string when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. ONNX format by default
-#### Predict函数
+#### Predict function
> ```c++
> YOLOv5Face::Predict(cv::Mat* im, FaceDetectionResult* result,
@@ -67,26 +68,26 @@ YOLOv5Face模型加载和初始化，其中model_file为导出的ONNX模型格
> float nms_iou_threshold = 0.5)
> ```
>
-> 模型预测接口，输入图像直接输出检测结果。
+> Model prediction interface. Input images and output detection results.
>
-> **参数**
+> **Parameter**
>
-> > * **im**: 输入图像，注意需为HWC，BGR格式
-> > * **result**: 检测结果，包括检测框，各个框的置信度, FaceDetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
-> > * **conf_threshold**: 检测框置信度过滤阈值
-> > * **nms_iou_threshold**: NMS处理过程中iou阈值
-
-### 类成员变量
-#### 预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
-
-> > * **size**(vector<int>): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
-> > * **padding_value**(vector<float>): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
-> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=ture` 表示不使用填充的方式，默认值为`is_no_pad=false`
-> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=false`
-> > * **stride**(int): 配合`is_mini_pad`成员变量使用, 默认值为`stride=32`
-> > * **landmarks_per_face**(int): 指定当前模型检测的人脸所带的关键点个数，默认为5.
-
-- [模型介绍](../../)
-- [Python部署](../python)
-- [视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > * **im**: Input images in HWC or BGR format
+> > * **result**: Detection results, including detection box and confidence of each box. Refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for FaceDetectionResult
+> > * **conf_threshold**: Filtering threshold of detection box confidence
+> > * **nms_iou_threshold**: iou threshold during NMS processing
+
+### Class Member Variable
+#### Pre-processing Parameter
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
+
+> > * **size**(vector<int>): This parameter changes the size of the resize used during preprocessing, containing two integer elements for [width, height] with default value [640, 640]
+> > * **padding_value**(vector<float>): This parameter is used to change the padding value of images during resize, containing three floating-point elements that represent the value of three channels. Default value [114, 114, 114]
+> > * **is_no_pad**(bool): Specify whether to resize the image through padding or not. `is_no_pad=ture` represents no paddling. Default `is_no_pad=false`
+> > * **is_mini_pad**(bool): This parameter sets the width and height of the image after resize to the value nearest to the `size` member variable and to the point where the padded pixel size is divisible by the `stride` member variable. Default `is_mini_pad=false`
+> > * **stride**(int): Used with the `is_mini_pad` member variable. Default `stride=32`
+> > * **landmarks_per_face**(int): Specify the number of keypoints in the face detected. Default 5.
+
+- [Model Description](../../)
+- [Python Deployment](../python)
+- [Vision Model Prediction Results](../../../../../docs/api/vision_results/)
diff --git a/examples/vision/facedet/yolov5face/cpp/README_CN.md b/examples/vision/facedet/yolov5face/cpp/README_CN.md
new file mode 100644
index 0000000000..7f62536844
--- /dev/null
+++ b/examples/vision/facedet/yolov5face/cpp/README_CN.md
@@ -0,0 +1,93 @@
+[English](README.md) | 简体中文
+# YOLOv5Face C++部署示例
+
+本目录下提供`infer.cc`快速完成YOLOv5Face在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试，支持此模型需保证FastDeploy版本0.7.0以上(x.x.x>=0.7.0)
+
+```bash
+mkdir build
+cd build
+# 下载FastDeploy预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz
+tar xvf fastdeploy-linux-x64-x.x.x.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x
+make -j
+
+#下载官方转换好的YOLOv5Face模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s-face.onnx
+wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/lite/resources/test_lite_face_detector_3.jpg
+
+
+# CPU推理
+./infer_demo yolov5s-face.onnx test_lite_face_detector_3.jpg 0
+# GPU推理
+./infer_demo yolov5s-face.onnx test_lite_face_detector_3.jpg 1
+# GPU上TensorRT推理
+./infer_demo yolov5s-face.onnx test_lite_face_detector_3.jpg 2
+```
+
+运行完成可视化结果如下图所示
+
+
+
+以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
+- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
+
+## YOLOv5Face C++接口
+
+### YOLOv5Face类
+
+```c++
+fastdeploy::vision::facedet::YOLOv5Face(
+ const string& model_file,
+ const string& params_file = "",
+ const RuntimeOption& runtime_option = RuntimeOption(),
+ const ModelFormat& model_format = ModelFormat::ONNX)
+```
+
+YOLOv5Face模型加载和初始化，其中model_file为导出的ONNX模型格式。
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为ONNX格式
+
+#### Predict函数
+
+> ```c++
+> YOLOv5Face::Predict(cv::Mat* im, FaceDetectionResult* result,
+> float conf_threshold = 0.25,
+> float nms_iou_threshold = 0.5)
+> ```
+>
+> 模型预测接口，输入图像直接输出检测结果。
+>
+> **参数**
+>
+> > * **im**: 输入图像，注意需为HWC，BGR格式
+> > * **result**: 检测结果，包括检测框，各个框的置信度, FaceDetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > * **conf_threshold**: 检测框置信度过滤阈值
+> > * **nms_iou_threshold**: NMS处理过程中iou阈值
+
+### 类成员变量
+#### 预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> > * **size**(vector<int>): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
+> > * **padding_value**(vector<float>): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
+> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=ture` 表示不使用填充的方式，默认值为`is_no_pad=false`
+> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=false`
+> > * **stride**(int): 配合`is_mini_pad`成员变量使用, 默认值为`stride=32`
+> > * **landmarks_per_face**(int): 指定当前模型检测的人脸所带的关键点个数，默认为5.
+
+- [模型介绍](../../)
+- [Python部署](../python)
+- [视觉模型预测结果](../../../../../docs/api/vision_results/)
diff --git a/examples/vision/facedet/yolov5face/python/README.md b/examples/vision/facedet/yolov5face/python/README.md
index 3148dc02a2..d014e441ff 100644
--- a/examples/vision/facedet/yolov5face/python/README.md
+++ b/examples/vision/facedet/yolov5face/python/README.md
@@ -1,79 +1,80 @@
-# YOLOv5Face Python部署示例
+English | [简体中文](README_CN.md)
+# YOLOv5Face Python Deployment Example
-在部署前，需确认以下两个步骤
+Before deployment, two steps require confirmation
-- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. Install FastDeploy Python whl package. Refer to [FastDeploy Python Installation](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-本目录下提供`infer.py`快速完成YOLOv5Face在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+This directory provides examples that `infer.py` fast finishes the deployment of YOLOv5Face on CPU/GPU and GPU accelerated by TensorRT. The script is as follows
```bash
-#下载部署示例代码
+# Download the example code for deployment
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision/facedet/yolov5face/python/
-#下载YOLOv5Face模型文件和测试图片
+# Download YOLOv5Face model files and test images
wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s-face.onnx
wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/lite/resources/test_lite_face_detector_3.jpg
-# CPU推理
+# CPU inference
python infer.py --model yolov5s-face.onnx --image test_lite_face_detector_3.jpg --device cpu
-# GPU推理
+# GPU inference
python infer.py --model yolov5s-face.onnx --image test_lite_face_detector_3.jpg --device gpu
-# GPU上使用TensorRT推理
+# TensorRT inference on GPU
python infer.py --model yolov5s-face.onnx --image test_lite_face_detector_3.jpg --device gpu --use_trt True
```
-运行完成可视化结果如下图所示
+The visualized result after running is as follows
-## YOLOv5Face Python接口
+## YOLOv5Face Python Interface
```python
fastdeploy.vision.facedet.YOLOv5Face(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
```
-YOLOv5Face模型加载和初始化，其中model_file为导出的ONNX模型格式
+YOLOv5Face model loading and initialization, among which model_file is the exported ONNX model format
-**参数**
+**Parameter**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为ONNX
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. No need to set when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. ONNX format by default
-### predict函数
+### predict function
> ```python
> YOLOv5Face.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
> ```
>
-> 模型预测结口，输入图像直接输出检测结果。
+> Model prediction interface. Input images and output detection results.
>
-> **参数**
+> **Parameter**
>
-> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
-> > * **conf_threshold**(float): 检测框置信度过滤阈值
-> > * **nms_iou_threshold**(float): NMS处理过程中iou阈值
+> > * **image_data**(np.ndarray): Input data in HWC or BGR format
+> > * **conf_threshold**(float): Filtering threshold of detection box confidence
+> > * **nms_iou_threshold**(float): iou threshold during NMS processing
-> **返回**
+> **Return**
>
-> > 返回`fastdeploy.vision.FaceDetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > Return `fastdeploy.vision.FaceDetectionResult` structure. Refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for its description.
-### 类成员属性
-#### 预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+### Class Member Property
+#### Pre-processing Parameter
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
-> > * **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
-> > * **padding_value**(list[float]): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
-> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=True` 表示不使用填充的方式，默认值为`is_no_pad=False`
-> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=False`
-> > * **stride**(int): 配合`is_mini_pad`成员变量使用, 默认值为`stride=32`
-> > * **landmarks_per_face**(int): 指定当前模型检测的人脸所带的关键点个数，默认为5.
+> > * **size**(list[int]): This parameter changes the size of the resize used during preprocessing, containing two integer elements for [width, height] with default value [640, 640]
+> > * **padding_value**(list[float]): This parameter is used to change the padding value of images during resize, containing three floating-point elements that represent the value of three channels. Default value [114, 114, 114]
+> > * **is_no_pad**(bool): Specify whether to resize the image through padding or not. `is_no_pad=True` represents no paddling. Default `is_no_pad=False`
+> > * **is_mini_pad**(bool): This parameter sets the width and height of the image after resize to the value nearest to the `size` member variable and to the point where the padded pixel size is divisible by the `stride` member variable. Default `is_mini_pad=False`
+> > * **stride**(int): Used with the `is_mini_pad` member variable. Default `stride=32`
+> > * **landmarks_per_face**(int): Specify the number of keypoints in the face detected. Default 5
-## 其它文档
+## Other documents
-- [YOLOv5Face 模型介绍](..)
-- [YOLOv5Face C++部署](../cpp)
-- [模型预测结果说明](../../../../../docs/api/vision_results/)
+- [YOLOv5Face Model Description](..)
+- [YOLOv5Face C++ Deployment](../cpp)
+- [Model Prediction Results](../../../../../docs/api/vision_results/)
diff --git a/examples/vision/facedet/yolov5face/python/README_CN.md b/examples/vision/facedet/yolov5face/python/README_CN.md
new file mode 100644
index 0000000000..472d926b42
--- /dev/null
+++ b/examples/vision/facedet/yolov5face/python/README_CN.md
@@ -0,0 +1,80 @@
+[English](README.md) | 简体中文
+# YOLOv5Face Python部署示例
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+本目录下提供`infer.py`快速完成YOLOv5Face在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+
+```bash
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd examples/vision/facedet/yolov5face/python/
+
+#下载YOLOv5Face模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s-face.onnx
+wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/lite/resources/test_lite_face_detector_3.jpg
+
+# CPU推理
+python infer.py --model yolov5s-face.onnx --image test_lite_face_detector_3.jpg --device cpu
+# GPU推理
+python infer.py --model yolov5s-face.onnx --image test_lite_face_detector_3.jpg --device gpu
+# GPU上使用TensorRT推理
+python infer.py --model yolov5s-face.onnx --image test_lite_face_detector_3.jpg --device gpu --use_trt True
+```
+
+运行完成可视化结果如下图所示
+
+
+
+## YOLOv5Face Python接口
+
+```python
+fastdeploy.vision.facedet.YOLOv5Face(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
+```
+
+YOLOv5Face模型加载和初始化，其中model_file为导出的ONNX模型格式
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为ONNX
+
+### predict函数
+
+> ```python
+> YOLOv5Face.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
+> ```
+>
+> 模型预测结口，输入图像直接输出检测结果。
+>
+> **参数**
+>
+> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
+> > * **conf_threshold**(float): 检测框置信度过滤阈值
+> > * **nms_iou_threshold**(float): NMS处理过程中iou阈值
+
+> **返回**
+>
+> > 返回`fastdeploy.vision.FaceDetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+
+### 类成员属性
+#### 预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> > * **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
+> > * **padding_value**(list[float]): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
+> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=True` 表示不使用填充的方式，默认值为`is_no_pad=False`
+> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=False`
+> > * **stride**(int): 配合`is_mini_pad`成员变量使用, 默认值为`stride=32`
+> > * **landmarks_per_face**(int): 指定当前模型检测的人脸所带的关键点个数，默认为5.
+
+## 其它文档
+
+- [YOLOv5Face 模型介绍](..)
+- [YOLOv5Face C++部署](../cpp)
+- [模型预测结果说明](../../../../../docs/api/vision_results/)
diff --git a/examples/vision/facedet/yolov7face/cpp/README.md b/examples/vision/facedet/yolov7face/cpp/README.md
index 3b68ff41c0..fd8b2a8f6f 100644
--- a/examples/vision/facedet/yolov7face/cpp/README.md
+++ b/examples/vision/facedet/yolov7face/cpp/README.md
@@ -1,55 +1,56 @@
-# YOLOv7Face C++部署示例
+English | [简体中文](README_CN.md)
+# YOLOv7Face C++ Deployment Example
-本目录下提供`infer.cc`快速完成YOLOv7Face在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+This directory provides examples that `infer.cc` fast finishes the deployment of YOLOv7Face on CPU/GPU and GPU accelerated by TensorRT.
-在部署前，需确认以下两个步骤
+Before deployment, two steps require confirmation
-- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. Download the precompiled deployment library and samples code according to your development environment. Refer to [FastDeploy Precompiled Library](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试
+Taking the CPU inference on Linux as an example, the compilation test can be completed by executing the following command in this directory.
```bash
mkdir build
cd build
-# 下载FastDeploy预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
+# Download the FastDeploy precompiled library. Users can choose your appropriate version in the `FastDeploy Precompiled Library` mentioned above
wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz # x.x.x > 1.0.2
tar xvf fastdeploy-linux-x64-x.x.x.tgz # x.x.x > 1.0.2
cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x # x.x.x > 1.0.2
make -j
-#下载官方转换好的YOLOv7Face模型文件和测试图片
+# Download the official converted YOLOv7Face model files and test images
wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/lite/resources/test_lite_face_detector_3.jpg
wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-lite-e.onnx
wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-tiny-face.onnx
-#使用yolov7-tiny-face.onnx模型
-# CPU推理
+# Use yolov7-tiny-face.onnx model
+# CPU inference
./infer_demo yolov7-tiny-face.onnx test_lite_face_detector_3.jpg 0
-# GPU推理
+# GPU inference
./infer_demo yolov7-tiny-face.onnx test_lite_face_detector_3.jpg 1
-# GPU上TensorRT推理
+# TensorRT inference on GPU
./infer_demo yolov7-tiny-face.onnx test_lite_face_detector_3.jpg 2
-#使用yolov7-lite-e.onnx模型
-# CPU推理
+# Use yolov7-lite-e.onnx model
+# CPU inference
./infer_demo yolov7-lite-e.onnx test_lite_face_detector_3.jpg 0
-# GPU推理
+# GPU inference
./infer_demo yolov7-lite-e.onnx test_lite_face_detector_3.jpg 1
-# GPU上TensorRT推理
+# TensorRT inference on GPU
./infer_demo yolov7-lite-e.onnx test_lite_face_detector_3.jpg 2
```
-运行完成可视化结果如下图所示
+The visualized result after running is as follows
-以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
-- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
+The above command works for Linux or MacOS. For SDK use-pattern in Windows, refer to:
+- [How to use FastDeploy C++ SDK in Windows](../../../../../docs/cn/faq/use_sdk_on_windows.md)
-## YOLOv7Face C++接口
+## YOLOv7Face C++ Interface
-### YOLOv7Face类
+### YOLOv7Face Class
```c++
fastdeploy::vision::facedet::YOLOv7Face(
@@ -59,16 +60,16 @@ fastdeploy::vision::facedet::YOLOv7Face(
const ModelFormat& model_format = ModelFormat::ONNX)
```
-YOLOv7Face模型加载和初始化，其中model_file为导出的ONNX模型格式。
+YOLOv7Face model loading and initialization, among which model_file is the exported ONNX model format
-**参数**
+**Parameter**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为ONNX格式
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. Only passing an empty string when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. ONNX format by default
-#### Predict函数
+#### Predict Function
> ```c++
> YOLOv7Face::Predict(cv::Mat* im, FaceDetectionResult* result,
@@ -76,15 +77,15 @@ YOLOv7Face模型加载和初始化，其中model_file为导出的ONNX模型格
> float nms_iou_threshold = 0.5)
> ```
>
-> 模型预测接口，输入图像直接输出检测结果。
+> Model prediction interface. Input images and output detection results.
>
-> **参数**
+> **Parameter**
>
-> > * **im**: 输入图像，注意需为HWC，BGR格式
-> > * **result**: 检测结果，包括检测框，各个框的置信度, FaceDetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
-> > * **conf_threshold**: 检测框置信度过滤阈值
-> > * **nms_iou_threshold**: NMS处理过程中iou阈值
-
-- [模型介绍](../../)
-- [Python部署](../python)
-- [视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > * **im**: Input images in HWC or BGR format
+> > * **result**: Detection results, including detection box and confidence of each box. Refer to [Vision Model Prediction Result](../../../../../docs/api/vision_results/) for FaceDetectionResult
+> > * **conf_threshold**: Filtering threshold of detection box confidence
+> > * **nms_iou_threshold**: iou threshold during NMS processing
+
+- [Model Description](../../)
+- [Python Deployment](../python)
+- [Vision Model Prediction Results](../../../../../docs/api/vision_results/)
diff --git a/examples/vision/facedet/yolov7face/cpp/README_CN.md b/examples/vision/facedet/yolov7face/cpp/README_CN.md
new file mode 100644
index 0000000000..452751645f
--- /dev/null
+++ b/examples/vision/facedet/yolov7face/cpp/README_CN.md
@@ -0,0 +1,91 @@
+[English](README.md) | 简体中文
+# YOLOv7Face C++部署示例
+
+本目录下提供`infer.cc`快速完成YOLOv7Face在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试
+
+```bash
+mkdir build
+cd build
+# 下载FastDeploy预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz # x.x.x > 1.0.2
+tar xvf fastdeploy-linux-x64-x.x.x.tgz # x.x.x > 1.0.2
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x # x.x.x > 1.0.2
+make -j
+
+#下载官方转换好的YOLOv7Face模型文件和测试图片
+wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/lite/resources/test_lite_face_detector_3.jpg
+wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-lite-e.onnx
+wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-tiny-face.onnx
+
+#使用yolov7-tiny-face.onnx模型
+# CPU推理
+./infer_demo yolov7-tiny-face.onnx test_lite_face_detector_3.jpg 0
+# GPU推理
+./infer_demo yolov7-tiny-face.onnx test_lite_face_detector_3.jpg 1
+# GPU上TensorRT推理
+./infer_demo yolov7-tiny-face.onnx test_lite_face_detector_3.jpg 2
+
+#使用yolov7-lite-e.onnx模型
+# CPU推理
+./infer_demo yolov7-lite-e.onnx test_lite_face_detector_3.jpg 0
+# GPU推理
+./infer_demo yolov7-lite-e.onnx test_lite_face_detector_3.jpg 1
+# GPU上TensorRT推理
+./infer_demo yolov7-lite-e.onnx test_lite_face_detector_3.jpg 2
+```
+
+运行完成可视化结果如下图所示
+
+
+
+以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
+- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
+
+## YOLOv7Face C++接口
+
+### YOLOv7Face类
+
+```c++
+fastdeploy::vision::facedet::YOLOv7Face(
+ const string& model_file,
+ const string& params_file = "",
+ const RuntimeOption& runtime_option = RuntimeOption(),
+ const ModelFormat& model_format = ModelFormat::ONNX)
+```
+
+YOLOv7Face模型加载和初始化，其中model_file为导出的ONNX模型格式。
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为ONNX格式
+
+#### Predict函数
+
+> ```c++
+> YOLOv7Face::Predict(cv::Mat* im, FaceDetectionResult* result,
+> float conf_threshold = 0.3,
+> float nms_iou_threshold = 0.5)
+> ```
+>
+> 模型预测接口，输入图像直接输出检测结果。
+>
+> **参数**
+>
+> > * **im**: 输入图像，注意需为HWC，BGR格式
+> > * **result**: 检测结果，包括检测框，各个框的置信度, FaceDetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > * **conf_threshold**: 检测框置信度过滤阈值
+> > * **nms_iou_threshold**: NMS处理过程中iou阈值
+
+- [模型介绍](../../)
+- [Python部署](../python)
+- [视觉模型预测结果](../../../../../docs/api/vision_results/)
diff --git a/examples/vision/facedet/yolov7face/python/README.md b/examples/vision/facedet/yolov7face/python/README.md
index 0c4dd0f57e..431fddd249 100644
--- a/examples/vision/facedet/yolov7face/python/README.md
+++ b/examples/vision/facedet/yolov7face/python/README.md
@@ -1,87 +1,89 @@
-# YOLOv7Face Python部署示例
+English | [简体中文](README_CN.md)
+# YOLOv7Face Python Deployment Example
-在部署前，需确认以下两个步骤
+Before deployment, two steps require confirmation
-- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. Install FastDeploy Python whl package. Refer to [FastDeploy Python Installation](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-本目录下提供`infer.py`快速完成YOLOv7Face在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+This directory provides examples that `infer.py` fast finishes the deployment of YOLOv7Face on CPU/GPU and GPU accelerated by TensorRT. The script is as follows
```bash
-#下载部署示例代码
+# Download the example code for deployment
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision/facedet/yolov7face/python/
-#下载YOLOv7Face模型文件和测试图片
+# Download YOLOv7Face model files and test images
wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/lite/resources/test_lite_face_detector_3.jpg
wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-lite-e.onnx
-#使用yolov7-tiny-face.onnx模型
-# CPU推理
+# Use yolov7-tiny-face.onnx model
+# CPU inference
python infer.py --model yolov7-tiny-face.onnx --image test_lite_face_detector_3.jpg --device cpu
-# GPU推理
+# GPU inference
python infer.py --model yolov7-tiny-face.onnx --image test_lite_face_detector_3.jpg --device gpu
-# GPU上使用TensorRT推理
+# TensorRT inference on GPU
python infer.py --model yolov7-tiny-face.onnx --image test_lite_face_detector_3.jpg --device gpu --use_trt True
-#使用yolov7-lite-e.onnx模型
-# CPU推理
+# Use yolov7-lite-e.onnx model
+# CPU inference
python infer.py --model yolov7-lite-e.onnx --image test_lite_face_detector_3.jpg --device cpu
-# GPU推理
+# GPU inference
python infer.py --model yolov7-lite-e.onnx --image test_lite_face_detector_3.jpg --device gpu
-# GPU上使用TensorRT推理
+# TensorRT inference on GPU
python infer.py --model yolov7-lite-e.onnx --image test_lite_face_detector_3.jpg --device gpu --use_trt True
```
-运行完成可视化结果如下图所示
+The visualized result after running is as follows
-## YOLOv7Face Python接口
+## YOLOv7Face Python Interface
```python
fastdeploy.vision.facedet.YOLOv7Face(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
```
-YOLOv7Face模型加载和初始化，其中model_file为导出的ONNX模型格式
+YOLOv7Face model loading and initialization, among which model_file is the exported ONNX model format
-**参数**
+**Parameter**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为ONNX
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. No need to set when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. ONNX format by default
-### predict函数
+### predict function
> ```python
> YOLOv7Face.predict(image_data, conf_threshold=0.3, nms_iou_threshold=0.5)
> ```
>
-> 模型预测结口，输入图像直接输出检测结果。
+> Model prediction interface. Input images and output detection results.
>
-> **参数**
+> **Parameter**
>
-> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
-> > * **conf_threshold**(float): 检测框置信度过滤阈值
-> > * **nms_iou_threshold**(float): NMS处理过程中iou阈值
+> > * **image_data**(np.ndarray): Input data in HWC or BGR format
+> > * **conf_threshold**(float): Filtering threshold of detection box confidence
+> > * **nms_iou_threshold**(float): iou threshold during NMS processing
-> **返回**
+
+> **Return**
>
-> > 返回`fastdeploy.vision.FaceDetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > Return `fastdeploy.vision.FaceDetectionResult` structure. Refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for its description.
-### 类成员属性
-#### 预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+### Class Member Property
+#### Pre-processing Parameter
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
-> > * **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
-> > * **padding_value**(list[float]): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
-> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=True` 表示不使用填充的方式，默认值为`is_no_pad=False`
-> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=False`
-> > * **stride**(int): 配合`is_mini_pad`成员变量使用, 默认值为`stride=32`
+> > * **size**(list[int]): This parameter changes the size of the resize used during preprocessing, containing two integer elements for [width, height] with default value [640, 640]
+> > * **padding_value**(list[float]): This parameter is used to change the padding value of images during resize, containing three floating-point elements that represent the value of three channels. Default value [114, 114, 114]
+> > * **is_no_pad**(bool): Specify whether to resize the image through padding or not. `is_no_pad=True` represents no paddling. Default `is_no_pad=False`
+> > * **is_mini_pad**(bool): This parameter sets the width and height of the image after resize to the value nearest to the `size` member variable and to the point where the padded pixel size is divisible by the `stride` member variable. Default `is_mini_pad=False`
+> > * **stride**(int): Used with the `is_mini_pad` member variable. Default `stride=32`
-## 其它文档
+## Other Documents
-- [YOLOv7Face 模型介绍](..)
-- [YOLOv7Face C++部署](../cpp)
-- [模型预测结果说明](../../../../../docs/api/vision_results/)
+- [YOLOv7Face Model Description](..)
+- [YOLOv7Face C++ Deployment](../cpp)
+- [Model Prediction Results](../../../../../docs/api/vision_results/)
diff --git a/examples/vision/facedet/yolov7face/python/README_CN.md b/examples/vision/facedet/yolov7face/python/README_CN.md
new file mode 100644
index 0000000000..9da41c6336
--- /dev/null
+++ b/examples/vision/facedet/yolov7face/python/README_CN.md
@@ -0,0 +1,88 @@
+[English](README.md) | 简体中文
+# YOLOv7Face Python部署示例
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+本目录下提供`infer.py`快速完成YOLOv7Face在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+
+```bash
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd examples/vision/facedet/yolov7face/python/
+
+#下载YOLOv7Face模型文件和测试图片
+wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/lite/resources/test_lite_face_detector_3.jpg
+wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov7-lite-e.onnx
+
+#使用yolov7-tiny-face.onnx模型
+# CPU推理
+python infer.py --model yolov7-tiny-face.onnx --image test_lite_face_detector_3.jpg --device cpu
+# GPU推理
+python infer.py --model yolov7-tiny-face.onnx --image test_lite_face_detector_3.jpg --device gpu
+# GPU上使用TensorRT推理
+python infer.py --model yolov7-tiny-face.onnx --image test_lite_face_detector_3.jpg --device gpu --use_trt True
+
+#使用yolov7-lite-e.onnx模型
+# CPU推理
+python infer.py --model yolov7-lite-e.onnx --image test_lite_face_detector_3.jpg --device cpu
+# GPU推理
+python infer.py --model yolov7-lite-e.onnx --image test_lite_face_detector_3.jpg --device gpu
+# GPU上使用TensorRT推理
+python infer.py --model yolov7-lite-e.onnx --image test_lite_face_detector_3.jpg --device gpu --use_trt True
+```
+
+运行完成可视化结果如下图所示
+
+
+
+## YOLOv7Face Python接口
+
+```python
+fastdeploy.vision.facedet.YOLOv7Face(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
+```
+
+YOLOv7Face模型加载和初始化，其中model_file为导出的ONNX模型格式
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为ONNX
+
+### predict函数
+
+> ```python
+> YOLOv7Face.predict(image_data, conf_threshold=0.3, nms_iou_threshold=0.5)
+> ```
+>
+> 模型预测结口，输入图像直接输出检测结果。
+>
+> **参数**
+>
+> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
+> > * **conf_threshold**(float): 检测框置信度过滤阈值
+> > * **nms_iou_threshold**(float): NMS处理过程中iou阈值
+
+> **返回**
+>
+> > 返回`fastdeploy.vision.FaceDetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+
+### 类成员属性
+#### 预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> > * **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
+> > * **padding_value**(list[float]): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
+> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=True` 表示不使用填充的方式，默认值为`is_no_pad=False`
+> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=False`
+> > * **stride**(int): 配合`is_mini_pad`成员变量使用, 默认值为`stride=32`
+
+## 其它文档
+
+- [YOLOv7Face 模型介绍](..)
+- [YOLOv7Face C++部署](../cpp)
+- [模型预测结果说明](../../../../../docs/api/vision_results/)
diff --git a/examples/vision/faceid/README.md b/examples/vision/faceid/README.md
index b897314cbb..344f73a5f8 100644
--- a/examples/vision/faceid/README.md
+++ b/examples/vision/faceid/README.md
@@ -1,18 +1,13 @@
-# 人脸识别模型
+English | [简体中文](README_CN.md)
+# Face recognition Model
-## 模型支持列表
+FastDeploy currently supports the deployment of the following face recognition models
-FastDeploy目前支持如下人脸识别模型部署
-
-| 模型 | 说明 | 模型格式 | 版本 |
+| Model | Description | Model Format | Version |
|:---------------------------------------|:---------------|:-----------|:------------------------------------------------------------------------------|
-| [deepinsight/ArcFace](./insightface) | ArcFace 系列模型 | ONNX | [CommitID:babb9a5](https://github.com/deepinsight/insightface/commit/babb9a5) |
-| [deepinsight/CosFace](./insightface) | CosFace 系列模型 | ONNX | [CommitID:babb9a5](https://github.com/deepinsight/insightface/commit/babb9a5) |
-| [deepinsight/PartialFC](./insightface) | PartialFC 系列模型 | ONNX | [CommitID:babb9a5](https://github.com/deepinsight/insightface/commit/babb9a5) |
-| [deepinsight/VPL](./insightface) | VPL 系列模型 | ONNX | [CommitID:babb9a5](https://github.com/deepinsight/insightface/commit/babb9a5) |
-| [paddleclas/AdaFace](./adaface) | AdaFace 系列模型 | PADDLE | [CommitID:babb9a5](https://github.com/PaddlePaddle/PaddleClas/tree/v2.4.0) |
-
-## 模型demo简介
-
-ArcFace,CosFace,PartialFC,VPL同属于deepinsight系列，因此demo使用ONNX作为推理框架。AdaFace则采用PaddleInference作为推理框架。
+| [deepinsight/ArcFace](./insightface) | ArcFace models | ONNX | [CommitID:babb9a5](https://github.com/deepinsight/insightface/commit/babb9a5) |
+| [deepinsight/CosFace](./insightface) | CosFace models | ONNX | [CommitID:babb9a5](https://github.com/deepinsight/insightface/commit/babb9a5) |
+| [deepinsight/PartialFC](./insightface) | PartialFC models | ONNX | [CommitID:babb9a5](https://github.com/deepinsight/insightface/commit/babb9a5) |
+| [deepinsight/VPL](./insightface) | VPL models | ONNX | [CommitID:babb9a5](https://github.com/deepinsight/insightface/commit/babb9a5) |
+| [paddleclas/AdaFace](./adaface) | AdaFace models | PADDLE | [CommitID:babb9a5](https://github.com/PaddlePaddle/PaddleClas/tree/v2.4.0) |
diff --git a/examples/vision/faceid/README_CN.md b/examples/vision/faceid/README_CN.md
new file mode 100644
index 0000000000..260b304c8b
--- /dev/null
+++ b/examples/vision/faceid/README_CN.md
@@ -0,0 +1,19 @@
+[English](README.md) | 简体中文
+# 人脸识别模型
+
+
+## 模型支持列表
+
+FastDeploy目前支持如下人脸识别模型部署
+
+| 模型 | 说明 | 模型格式 | 版本 |
+|:---------------------------------------|:---------------|:-----------|:------------------------------------------------------------------------------|
+| [deepinsight/ArcFace](./insightface) | ArcFace 系列模型 | ONNX | [CommitID:babb9a5](https://github.com/deepinsight/insightface/commit/babb9a5) |
+| [deepinsight/CosFace](./insightface) | CosFace 系列模型 | ONNX | [CommitID:babb9a5](https://github.com/deepinsight/insightface/commit/babb9a5) |
+| [deepinsight/PartialFC](./insightface) | PartialFC 系列模型 | ONNX | [CommitID:babb9a5](https://github.com/deepinsight/insightface/commit/babb9a5) |
+| [deepinsight/VPL](./insightface) | VPL 系列模型 | ONNX | [CommitID:babb9a5](https://github.com/deepinsight/insightface/commit/babb9a5) |
+| [paddleclas/AdaFace](./adaface) | AdaFace 系列模型 | PADDLE | [CommitID:babb9a5](https://github.com/PaddlePaddle/PaddleClas/tree/v2.4.0) |
+
+## 模型demo简介
+
+ArcFace,CosFace,PartialFC,VPL同属于deepinsight系列，因此demo使用ONNX作为推理框架。AdaFace则采用PaddleInference作为推理框架。
diff --git a/examples/vision/faceid/adaface/README.md b/examples/vision/faceid/adaface/README.md
index 6a88af7179..a83c13e3df 100644
--- a/examples/vision/faceid/adaface/README.md
+++ b/examples/vision/faceid/adaface/README.md
@@ -1,32 +1,32 @@
-# AdaFace准备部署模型
+English | [简体中文](README_CN.md)
+# AdaFace Ready-to-deploy Model
- [PaddleClas](https://github.com/PaddlePaddle/PaddleClas/)
- - [官方库](https://github.com/PaddlePaddle/PaddleClas/)中训练过后的Paddle模型导出Paddle静态图模型操作后，可进行部署；
+ - Paddle models trained in the [official repository](https://github.com/PaddlePaddle/PaddleClas/) are available for deployment after exporting Paddle static graph models；
-## 简介
-一直以来，低质量图像的人脸识别都具有挑战性，因为低质量图像的人脸属性是模糊和退化的。将这样的图片输入模型时，将不能很好的实现分类。
-而在人脸识别任务中，我们经常会利用opencv的仿射变换来矫正人脸数据，这时数据会出现低质量退化的现象。如何解决低质量图片的分类问题成为了模型落地时的痛点问题。
+## Introduction
+Face recognition of low-quality images has been challenging because the face attributes of these images are blurred and degraded. We cannot realize optimal classification after such images are fed into the model.
+In face recognition, we often use the affine transformation of opencv to correct the face data that will degrade in low quality. The classification of low-quality images becomes a crucial problem during model development.
-在AdaFace这项工作中，作者在损失函数中引入了另一个因素，即图像质量。作者认为，强调错误分类样本的策略应根据其图像质量进行调整。
-具体来说，简单或困难样本的相对重要性应该基于样本的图像质量来给定。据此作者提出了一种新的损失函数来通过图像质量强调不同的困难样本的重要性。
+In AdaFace, we introduce another factor in the loss function, namely image quality. We maintain that the strategy of emphasizing misclassified samples should be adjusted according to their image quality.
+Specifically, the importance of easy and difficult samples should be given based on the their image quality. Accordingly, we propose a new loss function to emphasize the importance of different difficult samples by their image quality.
-由上，AdaFace缓解了低质量图片在输入网络后输出结果精度变低的情况，更加适合在人脸识别任务落地中使用。
+In a nutshell, AdaFace improves the situation that low-quality images become less accurate after input to the network, which is more effective in the task of face recognition.
+## Export Paddle Static Graph Model
+Taking AdaFace as an example:
+Refer to [AIStudio](https://aistudio.baidu.com/aistudio/projectdetail/4479879?contributionType=1) for training and export of the code.
-## 导出Paddle静态图模型
-以AdaFace为例:
-训练和导出代码，请参考[AIStudio](https://aistudio.baidu.com/aistudio/projectdetail/4479879?contributionType=1)
+## Download Pre-trained Paddle Static Graph Model
-## 下载预训练Paddle静态图模型
+For developers' testing, converted models are provided below. Developers can download and use them directly. (The accuracy of the models in the table is sourced from the model introduction in AIStudio)
-为了方便开发者的测试，下面提供了我转换过的各系列模型，开发者可直接下载使用。（下表中模型的精度来源于源官方库）其中精度指标来源于AIStudio中对各模型的介绍。
-
-| 模型 | 大小 | 精度 (AgeDB_30) |
+| Model | Size | Accuracy (AgeDB_30) |
|:----------------------------------------------------------------------------------------------|:------|:--------------|
| [AdaFace-MobileFacenet](https://bj.bcebos.com/paddlehub/fastdeploy/mobilefacenet_adaface.tgz) | 3.2MB | 95.5 |
-## 详细部署文档
+## Detailed Deployment Tutorials
-- [Python部署](python)
-- [C++部署](cpp)
+- [Python Deployment](python)
+- [C++ Deployment](cpp)
diff --git a/examples/vision/faceid/adaface/README_CN.md b/examples/vision/faceid/adaface/README_CN.md
new file mode 100644
index 0000000000..5421bd612f
--- /dev/null
+++ b/examples/vision/faceid/adaface/README_CN.md
@@ -0,0 +1,33 @@
+[English](README.md) | 简体中文
+# AdaFace准备部署模型
+
+- [PaddleClas](https://github.com/PaddlePaddle/PaddleClas/)
+ - [官方库](https://github.com/PaddlePaddle/PaddleClas/)中训练过后的Paddle模型导出Paddle静态图模型操作后，可进行部署；
+
+## 简介
+一直以来，低质量图像的人脸识别都具有挑战性，因为低质量图像的人脸属性是模糊和退化的。将这样的图片输入模型时，将不能很好的实现分类。
+而在人脸识别任务中，我们经常会利用opencv的仿射变换来矫正人脸数据，这时数据会出现低质量退化的现象。如何解决低质量图片的分类问题成为了模型落地时的痛点问题。
+
+在AdaFace这项工作中，作者在损失函数中引入了另一个因素，即图像质量。作者认为，强调错误分类样本的策略应根据其图像质量进行调整。
+具体来说，简单或困难样本的相对重要性应该基于样本的图像质量来给定。据此作者提出了一种新的损失函数来通过图像质量强调不同的困难样本的重要性。
+
+由上，AdaFace缓解了低质量图片在输入网络后输出结果精度变低的情况，更加适合在人脸识别任务落地中使用。
+
+
+## 导出Paddle静态图模型
+以AdaFace为例:
+训练和导出代码，请参考[AIStudio](https://aistudio.baidu.com/aistudio/projectdetail/4479879?contributionType=1)
+
+
+## 下载预训练Paddle静态图模型
+
+为了方便开发者的测试，下面提供了我转换过的各系列模型，开发者可直接下载使用。（下表中模型的精度来源于源官方库）其中精度指标来源于AIStudio中对各模型的介绍。
+
+| 模型 | 大小 | 精度 (AgeDB_30) |
+|:----------------------------------------------------------------------------------------------|:------|:--------------|
+| [AdaFace-MobileFacenet](https://bj.bcebos.com/paddlehub/fastdeploy/mobilefacenet_adaface.tgz) | 3.2MB | 95.5 |
+
+## 详细部署文档
+
+- [Python部署](python)
+- [C++部署](cpp)
diff --git a/examples/vision/faceid/adaface/cpp/README.md b/examples/vision/faceid/adaface/cpp/README.md
index f284b2fd00..a3b99e4544 100755
--- a/examples/vision/faceid/adaface/cpp/README.md
+++ b/examples/vision/faceid/adaface/cpp/README.md
@@ -1,17 +1,18 @@
-# AdaFace C++部署示例
-本目录下提供infer_xxx.py快速完成AdaFace模型在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+English | [简体中文](README_CN.md)
+# AdaFace C++ Deployment Example
+This directory provides examples that `infer_xxx.py` fast finishes the deployment of AdaFace on CPU/GPU and GPU accelerated by TensorRT.
-以AdaFace为例提供`infer.cc`快速完成AdaFace在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+Taking AdaFace as an example, we demonstrate how `infer.cc` fast finishes the deployment of AdaFace on CPU/GPU and GPU accelerated by TensorRT.
-在部署前，需确认以下两个步骤
+Before deployment, two steps require confirmation
-- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. Download the precompiled deployment library and samples code according to your development environment. Refer to [FastDeploy Precompiled Library](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试，支持此模型需保证FastDeploy版本0.7.0以上(x.x.x>=0.7.0)
+Taking the CPU inference on Linux as an example, the compilation test can be completed by executing the following command in this directory. FastDeploy version 0.7.0 or above (x.x.x>=0.7.0) is required to support this model.
```bash
-# “如果预编译库不包含本模型，请从最新代码编译SDK”
+# “If the precompiled library does not contain this model, compile SDK from the latest code”
mkdir build
cd build
wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz
@@ -19,19 +20,19 @@ tar xvf fastdeploy-linux-x64-x.x.x.tgz
cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x
make -j
-#下载测试图片
+# Download test images
wget https://bj.bcebos.com/paddlehub/fastdeploy/rknpu2/face_demo.zip
unzip face_demo.zip
-# 如果为Paddle模型，运行以下代码
+# Run the following code if the model is in Paddle format
wget https://bj.bcebos.com/paddlehub/fastdeploy/mobilefacenet_adaface.tgz
tar zxvf mobilefacenet_adaface.tgz -C ./
-# CPU推理
+# CPU inference
./infer_adaface_demo mobilefacenet_adaface/mobilefacenet_adaface.pdmodel \
mobilefacenet_adaface/mobilefacenet_adaface.pdiparams \
face_0.jpg face_1.jpg face_2.jpg 0
-# GPU推理
+# GPU inference
./infer_adaface_demo mobilefacenet_adaface/mobilefacenet_adaface.pdmodel \
mobilefacenet_adaface/mobilefacenet_adaface.pdiparams \
face_0.jpg face_1.jpg face_2.jpg 1
@@ -41,13 +42,13 @@ tar zxvf mobilefacenet_adaface.tgz -C ./
mobilefacenet_adaface/mobilefacenet_adaface.pdiparams \
face_0.jpg face_1.jpg face_2.jpg 2
-# 昆仑芯XPU推理
+# KunlunXin XPU inference
./infer_demo mobilefacenet_adaface/mobilefacenet_adaface.pdmodel \
mobilefacenet_adaface/mobilefacenet_adaface.pdiparams \
face_0.jpg face_1.jpg face_2.jpg 3
```
-运行完成可视化结果如下图所示
+The visualized result after running is as follows
@@ -55,12 +56,12 @@ tar zxvf mobilefacenet_adaface.tgz -C ./
+
+
+
@@ -70,56 +70,56 @@ Cosine 01: 0.7483505506964364
Cosine 02: -0.09605773855893639
```
-## AdaFace Python接口
+## AdaFace Python Interface
```python
fastdeploy.vision.faceid.AdaFace(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.PADDLE)
```
-AdaFace模型加载和初始化，其中model_file为导出的ONNX模型格式或PADDLE静态图格式
+AdaFace model loading and initialization, among which model_file is the exported ONNX model format or PADDLE static graph format
-**参数**
+**Parameter**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为PADDLE
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. No need to set when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. Paddle format by default
-### predict函数
+### predict function
> ```python
> AdaFace.predict(image_data)
> ```
>
-> 模型预测结口，输入图像直接输出检测结果。
+> Model prediction interface. Input images and output detection results.
>
-> **参数**
+> **Parameter**
>
-> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
+> > * **image_data**(np.ndarray): Input data in HWC or BGR format
-> **返回**
+> **Return**
>
-> > 返回`fastdeploy.vision.FaceRecognitionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > Return `fastdeploy.vision.FaceRecognitionResult` structure. Refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for its description.
-### 类成员属性
-#### 预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+### Class Member Property
+#### Pre-processing Parameter
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
-#### AdaFacePreprocessor的成员变量
-以下变量为AdaFacePreprocessor的成员变量
-> > * **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[112, 112]
-> > * **alpha**(list[float]): 预处理归一化的alpha值，计算公式为`x'=x*alpha+beta`，alpha默认为[1. / 127.5, 1.f / 127.5, 1. / 127.5]
-> > * **beta**(list[float]): 预处理归一化的beta值，计算公式为`x'=x*alpha+beta`，beta默认为[-1.f, -1.f, -1.f]
-> > * **swap_rb**(bool): 预处理是否将BGR转换成RGB，默认True
+#### Member variables of AdaFacePreprocessor
+The member variables of AdaFacePreprocessor are as follows
+> > * **size**(list[int]): This parameter changes the size of the resize during preprocessing, containing two integer elements for [width, height] with default value [112, 112]
+> > * **alpha**(list[float]): Preprocess normalized alpha, and calculated as `x'=x*alpha+beta`. alpha defaults to [1. / 127.5, 1.f / 127.5, 1. / 127.5]
+> > * **beta**(list[float]): Preprocess normalized alpha, and calculated as `x'=x*alpha+beta`. beta defaults to [-1.f, -1.f, -1.f]
+> > * **swap_rb**(bool): Whether to convert BGR to RGB in pre-processing. Default true
-#### AdaFacePostprocessor的成员变量
-以下变量为AdaFacePostprocessor的成员变量
-> > * **l2_normalize**(bool): 输出人脸向量之前是否执行l2归一化，默认False
+#### Member variables of AdaFacePostprocessor
+The member variables of AdaFacePostprocessor are as follows
+> > * **l2_normalize**(bool): Whether to perform l2 normalization before outputting the face vector. Default false.
-## 其它文档
+## Other Documents
-- [AdaFace 模型介绍](..)
-- [AdaFace C++部署](../cpp)
-- [模型预测结果说明](../../../../../docs/api/vision_results/)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+- [AdaFace Model Description](..)
+- [AdaFace C++ Deployment](../cpp)
+- [Model Prediction Results](../../../../../docs/api/vision_results/)
+- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/faceid/adaface/python/README_CN.md b/examples/vision/faceid/adaface/python/README_CN.md
new file mode 100644
index 0000000000..5421bd612f
--- /dev/null
+++ b/examples/vision/faceid/adaface/python/README_CN.md
@@ -0,0 +1,33 @@
+[English](README.md) | 简体中文
+# AdaFace准备部署模型
+
+- [PaddleClas](https://github.com/PaddlePaddle/PaddleClas/)
+ - [官方库](https://github.com/PaddlePaddle/PaddleClas/)中训练过后的Paddle模型导出Paddle静态图模型操作后，可进行部署；
+
+## 简介
+一直以来，低质量图像的人脸识别都具有挑战性，因为低质量图像的人脸属性是模糊和退化的。将这样的图片输入模型时，将不能很好的实现分类。
+而在人脸识别任务中，我们经常会利用opencv的仿射变换来矫正人脸数据，这时数据会出现低质量退化的现象。如何解决低质量图片的分类问题成为了模型落地时的痛点问题。
+
+在AdaFace这项工作中，作者在损失函数中引入了另一个因素，即图像质量。作者认为，强调错误分类样本的策略应根据其图像质量进行调整。
+具体来说，简单或困难样本的相对重要性应该基于样本的图像质量来给定。据此作者提出了一种新的损失函数来通过图像质量强调不同的困难样本的重要性。
+
+由上，AdaFace缓解了低质量图片在输入网络后输出结果精度变低的情况，更加适合在人脸识别任务落地中使用。
+
+
+## 导出Paddle静态图模型
+以AdaFace为例:
+训练和导出代码，请参考[AIStudio](https://aistudio.baidu.com/aistudio/projectdetail/4479879?contributionType=1)
+
+
+## 下载预训练Paddle静态图模型
+
+为了方便开发者的测试，下面提供了我转换过的各系列模型，开发者可直接下载使用。（下表中模型的精度来源于源官方库）其中精度指标来源于AIStudio中对各模型的介绍。
+
+| 模型 | 大小 | 精度 (AgeDB_30) |
+|:----------------------------------------------------------------------------------------------|:------|:--------------|
+| [AdaFace-MobileFacenet](https://bj.bcebos.com/paddlehub/fastdeploy/mobilefacenet_adaface.tgz) | 3.2MB | 95.5 |
+
+## 详细部署文档
+
+- [Python部署](python)
+- [C++部署](cpp)
diff --git a/examples/vision/faceid/insightface/README.md b/examples/vision/faceid/insightface/README.md
index ba17f31c71..00ec594a91 100644
--- a/examples/vision/faceid/insightface/README.md
+++ b/examples/vision/faceid/insightface/README.md
@@ -1,37 +1,38 @@
-# InsightFace准备部署模型
+English | [简体中文](README_CN.md)
+# InsightFace Ready-to-deploy Model
- [InsightFace](https://github.com/deepinsight/insightface/commit/babb9a5)
- - （1）[官方库](https://github.com/deepinsight/insightface/)中提供的*.pt通过[导出ONNX模型](#导出ONNX模型)操作后，可进行部署；
- - （2）开发者基于自己数据训练的InsightFace模型，可按照[导出ONNX模型](#%E5%AF%BC%E5%87%BAONNX%E6%A8%A1%E5%9E%8B)后，完成部署。
+ - （1）The *.pt provided by the [Official Library](https://github.com/deepinsight/insightface/) can be deployed after the [Export ONNX Model](#导出ONNX模型)；
+ - （2）As for InsightFace model trained on customized data, please follow the operations guidelines in [Export ONNX Model](#%E5%AF%BC%E5%87%BAONNX%E6%A8%A1%E5%9E%8B) to complete the deployment.
-## 支持模型列表
-目前FastDeploy支持如下模型的部署
+## List of Supported Models
+Now FastDeploy supports the deployment of the following models
- ArcFace
- CosFace
- PartialFC
- VPL
-## 导出ONNX模型
-以ArcFace为例:
-访问[ArcFace](https://github.com/deepinsight/insightface/tree/master/recognition/arcface_torch)官方github库，按照指引下载安装，下载pt模型文件，利用 `torch2onnx.py` 得到`onnx`格式文件。
+## Export ONNX Model
+Taking ArcFace as an example:
+Visit [ArcFace](https://github.com/deepinsight/insightface/tree/master/recognition/arcface_torch) official github repository, follow the guidelines to download pt model files, and employ `torch2onnx.py` to get the file in `onnx` format.
-* 下载ArcFace模型文件
+* Download ArcFace model files
```bash
Link: https://pan.baidu.com/share/init?surl=CL-l4zWqsI1oDuEEYVhj-g code: e8pw
```
-* 导出onnx格式文件
+* Export files in onnx format
```bash
PYTHONPATH=. python ./torch2onnx.py ms1mv3_arcface_r100_fp16/backbone.pth --output ms1mv3_arcface_r100.onnx --network r100 --simplify 1
```
-## 下载预训练ONNX模型
+## Download Pre-trained ONNX Model
-为了方便开发者的测试，下面提供了InsightFace导出的各系列模型，开发者可直接下载使用。（下表中模型的精度来源于源官方库）其中精度指标来源于InsightFace中对各模型的介绍，详情各参考InsightFace中的说明
+For developers' testing, models exported by InsightFace are provided below. Developers can download and use them directly. (The accuracy of the models in the table is sourced from the official library) The accuracy metric is sourced from the model description in InsightFace. Refer to the introduction in InsightFace for more details.
-| 模型 | 大小 | 精度 (AgeDB_30) |
+| Model | Size | Accuracy (AgeDB_30) |
|:-------------------------------------------------------------------------------------------|:------|:--------------|
| [CosFace-r18](https://bj.bcebos.com/paddlehub/fastdeploy/glint360k_cosface_r18.onnx) | 92MB | 97.7 |
| [CosFace-r34](https://bj.bcebos.com/paddlehub/fastdeploy/glint360k_cosface_r34.onnx) | 131MB | 98.3 |
@@ -48,12 +49,12 @@
-## 详细部署文档
+## Detailed Deployment Tutorials
-- [Python部署](python)
-- [C++部署](cpp)
+- [Python Deployment](python)
+- [C++ Deployment](cpp)
-## 版本说明
+## Release Note
-- 本版本文档和代码基于[InsightFace CommitID:babb9a5](https://github.com/deepinsight/insightface/commit/babb9a5) 编写
+- This tutorial and related code are written based on [InsightFace CommitID:babb9a5](https://github.com/deepinsight/insightface/commit/babb9a5)
diff --git a/examples/vision/faceid/insightface/README_CN.md b/examples/vision/faceid/insightface/README_CN.md
new file mode 100644
index 0000000000..0bdf7864f1
--- /dev/null
+++ b/examples/vision/faceid/insightface/README_CN.md
@@ -0,0 +1,60 @@
+[English](README.md) | 简体中文
+# InsightFace准备部署模型
+
+- [InsightFace](https://github.com/deepinsight/insightface/commit/babb9a5)
+ - （1）[官方库](https://github.com/deepinsight/insightface/)中提供的*.pt通过[导出ONNX模型](#导出ONNX模型)操作后，可进行部署；
+ - （2）开发者基于自己数据训练的InsightFace模型，可按照[导出ONNX模型](#%E5%AF%BC%E5%87%BAONNX%E6%A8%A1%E5%9E%8B)后，完成部署。
+
+
+## 支持模型列表
+目前FastDeploy支持如下模型的部署
+- ArcFace
+- CosFace
+- PartialFC
+- VPL
+
+
+## 导出ONNX模型
+以ArcFace为例:
+访问[ArcFace](https://github.com/deepinsight/insightface/tree/master/recognition/arcface_torch)官方github库，按照指引下载安装，下载pt模型文件，利用 `torch2onnx.py` 得到`onnx`格式文件。
+
+* 下载ArcFace模型文件
+ ```bash
+ Link: https://pan.baidu.com/share/init?surl=CL-l4zWqsI1oDuEEYVhj-g code: e8pw
+ ```
+
+* 导出onnx格式文件
+ ```bash
+ PYTHONPATH=. python ./torch2onnx.py ms1mv3_arcface_r100_fp16/backbone.pth --output ms1mv3_arcface_r100.onnx --network r100 --simplify 1
+ ```
+
+## 下载预训练ONNX模型
+
+为了方便开发者的测试，下面提供了InsightFace导出的各系列模型，开发者可直接下载使用。（下表中模型的精度来源于源官方库）其中精度指标来源于InsightFace中对各模型的介绍，详情各参考InsightFace中的说明
+
+| 模型 | 大小 | 精度 (AgeDB_30) |
+|:-------------------------------------------------------------------------------------------|:------|:--------------|
+| [CosFace-r18](https://bj.bcebos.com/paddlehub/fastdeploy/glint360k_cosface_r18.onnx) | 92MB | 97.7 |
+| [CosFace-r34](https://bj.bcebos.com/paddlehub/fastdeploy/glint360k_cosface_r34.onnx) | 131MB | 98.3 |
+| [CosFace-r50](https://bj.bcebos.com/paddlehub/fastdeploy/glint360k_cosface_r50.onnx) | 167MB | 98.3 |
+| [CosFace-r100](https://bj.bcebos.com/paddlehub/fastdeploy/glint360k_cosface_r100.onnx) | 249MB | 98.4 |
+| [ArcFace-r18](https://bj.bcebos.com/paddlehub/fastdeploy/ms1mv3_arcface_r18.onnx) | 92MB | 97.7 |
+| [ArcFace-r34](https://bj.bcebos.com/paddlehub/fastdeploy/ms1mv3_arcface_r34.onnx) | 131MB | 98.1 |
+| [ArcFace-r50](https://bj.bcebos.com/paddlehub/fastdeploy/ms1mv3_arcface_r50.onnx) | 167MB | - |
+| [ArcFace-r100](https://bj.bcebos.com/paddlehub/fastdeploy/ms1mv3_arcface_r100.onnx) | 249MB | 98.4 |
+| [ArcFace-r100_lr0.1](https://bj.bcebos.com/paddlehub/fastdeploy/ms1mv3_r100_lr01.onnx) | 249MB | 98.4 |
+| [PartialFC-r34](https://bj.bcebos.com/paddlehub/fastdeploy/partial_fc_glint360k_r50.onnx) | 167MB | - |
+| [PartialFC-r50](https://bj.bcebos.com/paddlehub/fastdeploy/partial_fc_glint360k_r100.onnx) | 249MB | - |
+
+
+
+
+## 详细部署文档
+
+- [Python部署](python)
+- [C++部署](cpp)
+
+
+## 版本说明
+
+- 本版本文档和代码基于[InsightFace CommitID:babb9a5](https://github.com/deepinsight/insightface/commit/babb9a5) 编写
diff --git a/examples/vision/faceid/insightface/cpp/README.md b/examples/vision/faceid/insightface/cpp/README.md
index 1722d9d5db..d56b40aa37 100644
--- a/examples/vision/faceid/insightface/cpp/README.md
+++ b/examples/vision/faceid/insightface/cpp/README.md
@@ -1,13 +1,14 @@
-# InsightFace C++部署示例
-本目录下提供infer_xxx.cc快速完成InsighFace模型包括ArcFace\CosFace\VPL\Partial_FC在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
-以ArcFace为例提供`infer_arcface.cc`快速完成ArcFace在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+English | [简体中文](README_CN.md)
+# InsightFace C++ Deployment Example
+This direct ory provides examples that `infer_xxx.cc` fast finishes the deployment of InsighFace, including ArcFace\CosFace\VPL\Partial_FC on CPU/GPU and GPU accelerated by TensorRT.
+Taking ArcFace as an example, we demonstrate how `infer_arcface.cc` fast finishes the deployment of InsighFace on CPU/GPU and GPU accelerated by TensorRT.
-在部署前，需确认以下两个步骤
+Before deployment, two steps require confirmation
-- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. Download the precompiled deployment library and samples code according to your development environment. Refer to [FastDeploy Precompiled Library](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试
+Taking the CPU inference on Linux as an example, the compilation test can be completed by executing the following command in this directory.
```bash
mkdir build
@@ -17,20 +18,20 @@ tar xvf fastdeploy-linux-x64-x.x.x.tgz
cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x
make -j
-#下载官方转换好的ArcFace模型文件和测试图片
+# Download the official converted ArcFace model files and test images
wget https://bj.bcebos.com/paddlehub/fastdeploy/ms1mv3_arcface_r100.onnx
wget https://bj.bcebos.com/paddlehub/fastdeploy/rknpu2/face_demo.zip
unzip face_demo.zip
-# CPU推理
+# CPU inference
./infer_arcface_demo ms1mv3_arcface_r100.onnx face_0.jpg face_1.jpg face_2.jpg 0
-# GPU推理
+# GPU inference
./infer_arcface_demo ms1mv3_arcface_r100.onnx face_0.jpg face_1.jpg face_2.jpg 1
-# GPU上TensorRT推理
+# TensorRT inference on GPU
./infer_arcface_demo ms1mv3_arcface_r100.onnx face_0.jpg face_1.jpg face_2.jpg 2
```
-运行完成可视化结果如下图所示
+The visualized result after running is as follows
@@ -38,12 +39,12 @@ unzip face_demo.zip
+
+
+
@@ -56,7 +56,7 @@ Detect Done! Cosine 01: 0.814385, Cosine 02:-0.059388
```
-## InsightFace Python接口
+## InsightFace Python Interface
```python
fastdeploy.vision.faceid.ArcFace(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
@@ -65,50 +65,50 @@ fastdeploy.vision.faceid.PartialFC(model_file, params_file=None, runtime_option=
fastdeploy.vision.faceid.VPL(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
```
-ArcFace模型加载和初始化，其中model_file为导出的ONNX模型格式
+ArcFace model loading and initialization, among which model_file is the exported ONNX model format
-**参数**
+**Parameter**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为ONNX
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. No need to set when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. ONNX format by default
-### predict函数
+### predict function
> ```python
> ArcFace.predict(image_data)
> ```
>
-> 模型预测结口，输入图像直接输出检测结果。
+> Model prediction interface. Input images and output detection results.
>
-> **参数**
+> **Parameter**
>
-> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
+> > * **image_data**(np.ndarray): Input data in HWC or BGR format
-> **返回**
+> **Return**
>
-> > 返回`fastdeploy.vision.FaceRecognitionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > Return `fastdeploy.vision.FaceRecognitionResult` structure. Refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for its description.
-### 类成员属性
-#### 预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+### Class Member Property
+#### Pre-processing Parameter
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
-#### AdaFacePreprocessor的成员变量
-以下变量为AdaFacePreprocessor的成员变量
-> > * **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[112, 112]
-> > * **alpha**(list[float]): 预处理归一化的alpha值，计算公式为`x'=x*alpha+beta`，alpha默认为[1. / 127.5, 1.f / 127.5, 1. / 127.5]
-> > * **beta**(list[float]): 预处理归一化的beta值，计算公式为`x'=x*alpha+beta`，beta默认为[-1.f, -1.f, -1.f]
-> > * **swap_rb**(bool): 预处理是否将BGR转换成RGB，默认True
+#### Member variables of AdaFacePreprocessor
+Member variables of AdaFacePreprocessor are as follows
+> > * **size**(list[int]): This parameter changes the size of the resize during preprocessing, containing two integer elements for [width, height] with default value [112, 112]
+> > * **alpha**(list[float]): Preprocess normalized alpha, and calculated as `x'=x*alpha+beta`. alpha defaults to [1. / 127.5, 1.f / 127.5, 1. / 127.5]
+> > * **beta**(list[float]): Preprocess normalized beta, and calculated as `x'=x*alpha+beta`，beta defaults to [-1.f, -1.f, -1.f]
+> > * **swap_rb**(bool): Whether to convert BGR to RGB in pre-processing. Default True
-#### AdaFacePostprocessor的成员变量
-以下变量为AdaFacePostprocessor的成员变量
-> > * **l2_normalize**(bool): 输出人脸向量之前是否执行l2归一化，默认False
+#### Member variables of AdaFacePostprocessor
+Member variables of AdaFacePostprocessor are as follows
+> > * **l2_normalize**(bool): Whether to perform l2 normalization before outputting the face vector. Default False.
-## 其它文档
+## Other Documents
-- [InsightFace 模型介绍](..)
-- [InsightFace C++部署](../cpp)
-- [模型预测结果说明](../../../../../docs/api/vision_results/)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+- [InsightFace Model Description](..)
+- [InsightFace C++ Deployment](../cpp)
+- [Model Prediction Results](../../../../../docs/api/vision_results/)
+- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/faceid/insightface/python/README_CN.md b/examples/vision/faceid/insightface/python/README_CN.md
new file mode 100644
index 0000000000..b30921b7e7
--- /dev/null
+++ b/examples/vision/faceid/insightface/python/README_CN.md
@@ -0,0 +1,115 @@
+[English](README.md) | 简体中文
+# InsightFace Python部署示例
+本目录下提供infer_xxx.py快速完成InsighFace模型包括ArcFace\CosFace\VPL\Partial_FC在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+以ArcFace为例子, 提供`infer_arcface.py`快速完成ArcFace在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+
+```bash
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd examples/vision/faceid/insightface/python/
+
+#下载ArcFace模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/ms1mv3_arcface_r100.onnx
+wget https://bj.bcebos.com/paddlehub/fastdeploy/rknpu2/face_demo.zip
+unzip face_demo.zip
+
+# CPU推理
+python infer_arcface.py --model ms1mv3_arcface_r100.onnx \
+ --face face_0.jpg \
+ --face_positive face_1.jpg \
+ --face_negative face_2.jpg \
+ --device cpu
+# GPU推理
+python infer_arcface.py --model ms1mv3_arcface_r100.onnx \
+ --face face_0.jpg \
+ --face_positive face_1.jpg \
+ --face_negative face_2.jpg \
+ --device gpu
+# GPU上使用TensorRT推理
+python infer_arcface.py --model ms1mv3_arcface_r100.onnx \
+ --face face_0.jpg \
+ --face_positive face_1.jpg \
+ --face_negative face_2.jpg \
+ --device gpu \
+ --use_trt True
+```
+
+运行完成可视化结果如下图所示
+
+
+
+
+
+
+
+
+
+
+
@@ -42,12 +43,12 @@ wget https://bj.bcebos.com/paddlehub/fastdeploy/matting_bgr.jpg
+
+
+
+
@@ -34,52 +35,51 @@ python infer.py --model modnet_photographic_portrait_matting.onnx --image mattin
+
+
+
+
@@ -43,12 +43,12 @@ wget https://bj.bcebos.com/paddlehub/fastdeploy/matting_bgr.jpg
+
+
+
+
+
+
+
+
@@ -43,10 +44,10 @@ wget https://bj.bcebos.com/paddlehub/fastdeploy/video.mp4
+
+
+
+
@@ -48,41 +49,41 @@ python infer.py --model rvm_mobilenetv3_trt.onnx --video video.mp4 --bg matting_
+
+
+
+
+
+
+
+
-## PPOCRv2 C++接口
+## PPOCRv2 C++ Interface
-### PPOCRv2类
+### PPOCRv2 Class
```
fastdeploy::pipeline::PPOCRv2(fastdeploy::vision::ocr::DBDetector* det_model,
@@ -68,43 +64,43 @@ fastdeploy::pipeline::PPOCRv2(fastdeploy::vision::ocr::DBDetector* det_model,
fastdeploy::vision::ocr::Recognizer* rec_model);
```
-PPOCRv2 的初始化，由检测，分类和识别模型串联构成
+The initialization of PPOCRv2, consisting of detection, classification and recognition models
-**参数**
+**Parameter**
-> * **DBDetector**(model): OCR中的检测模型
-> * **Classifier**(model): OCR中的分类模型
-> * **Recognizer**(model): OCR中的识别模型
+> * **DBDetector**(model): Detection model in OCR
+> * **Classifier**(model): Classification model in OCR
+> * **Recognizer**(model): Recognition model in OCR
```
fastdeploy::pipeline::PPOCRv2(fastdeploy::vision::ocr::DBDetector* det_model,
fastdeploy::vision::ocr::Recognizer* rec_model);
```
-PPOCRv2 的初始化，由检测，识别模型串联构成(无分类器)
+The initialization of PPOCRv2, consisting of detection and recognition models (No classifier)
-**参数**
+**Parameter**
-> * **DBDetector**(model): OCR中的检测模型
-> * **Recognizer**(model): OCR中的识别模型
+> * **DBDetector**(model): Detection model in OCROCR中的检测模型
+> * **Recognizer**(model): Recognition model in OCR
-#### Predict函数
+#### Predict Function
> ```
> bool Predict(cv::Mat* img, fastdeploy::vision::OCRResult* result);
> bool Predict(const cv::Mat& img, fastdeploy::vision::OCRResult* result);
> ```
>
-> 模型预测接口，输入一张图片，返回OCR预测结果
+> Model prediction interface. Input images and output OCR prediction results
>
-> **参数**
+> **Parameter**
>
-> > * **img**: 输入图像，注意需为HWC，BGR格式
-> > * **result**: OCR预测结果,包括由检测模型输出的检测框位置,分类模型输出的方向分类,以及识别模型输出的识别结果, OCRResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > * **img**: Input images in HWC or BGR format
+> > * **result**: OCR prediction results, including the position of the detection box from the detection model, the classification of the direction from the classification model, and the recognition result from the recognition model. Refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for OCRResult
-## DBDetector C++接口
+## DBDetector C++ Interface
-### DBDetector类
+### DBDetector Class
```
fastdeploy::vision::ocr::DBDetector(const std::string& model_file, const std::string& params_file = "",
@@ -112,18 +108,18 @@ fastdeploy::vision::ocr::DBDetector(const std::string& model_file, const std::st
const ModelFormat& model_format = ModelFormat::PADDLE);
```
-DBDetector模型加载和初始化，其中模型为paddle模型格式。
+DBDetector model loading and initialization. The model is in paddle format.
-**参数**
+**Parameter**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为Paddle格式
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. Merely passing an empty string when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. Paddle format by default
-### Classifier类与DBDetector类相同
+### The same applies to Classifier Class
-### Recognizer类
+### Recognizer Class
```
Recognizer(const std::string& model_file,
const std::string& params_file = "",
@@ -131,31 +127,31 @@ DBDetector模型加载和初始化，其中模型为paddle模型格式。
const RuntimeOption& custom_option = RuntimeOption(),
const ModelFormat& model_format = ModelFormat::PADDLE);
```
-Recognizer类初始化时,需要在label_path参数中,输入识别模型所需的label文件，其他参数均与DBDetector类相同
+For the initialization of the Recognizer class, users should input the label file required by the recognition model in the label_path parameter. Other parameters are the same as the DBDetector class
-**参数**
-> * **label_path**(str): 识别模型的label文件路径
+**Parameter**
+> * **label_path**(str): The label path of the recognition model
-### 类成员变量
-#### DBDetector预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+### Class Member Variable
+#### DBDetector Pre-processing Parameter
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
-> > * **max_side_len**(int): 检测算法前向时图片长边的最大尺寸，当长边超出这个值时会将长边resize到这个大小，短边等比例缩放,默认为960
-> > * **det_db_thresh**(double): DB模型输出预测图的二值化阈值，默认为0.3
-> > * **det_db_box_thresh**(double): DB模型输出框的阈值，低于此值的预测框会被丢弃，默认为0.6
-> > * **det_db_unclip_ratio**(double): DB模型输出框扩大的比例，默认为1.5
-> > * **det_db_score_mode**(string):DB后处理中计算文本框平均得分的方式,默认为slow，即求polygon区域的平均分数的方式
-> > * **use_dilation**(bool):是否对检测输出的feature map做膨胀处理,默认为Fasle
+> > * **max_side_len**(int): The long side’s maximum size of the oriented view before detection. The long side will be resized to this size when exceeding the value. And the short side will be scaled in equal proportion. Default 960
+> > * **det_db_thresh**(double): The binarization threshold of the prediction image from DB models. Default 0.3
+> > * **det_db_box_thresh**(double): The threshold for the output box of DB models, below which the predicted box is discarded. Default 0.6
+> > * **det_db_unclip_ratio**(double): The expansion ratio of the DB model output box. Default 1.5
+> > * **det_db_score_mode**(string): The way to calculate the average score of the text box in DB post-processing. Default slow, which is identical to the calculation of the polygon area’s average score
+> > * **use_dilation**(bool): Whether to expand the feature map from the detection. Default False
-#### Classifier预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+#### Classifier Pre-processing Parameter
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
-> > * **cls_thresh**(double): 当分类模型输出的得分超过此阈值，输入的图片将被翻转，默认为0.9
+> > * **cls_thresh**(double): The input image will be flipped when the score output by the classification model exceeds this threshold. Default 0.9
-## 其它文档
+## Other Documents
-- [PPOCR 系列模型介绍](../../)
-- [PPOCRv2 Python部署](../python)
-- [模型预测结果说明](../../../../../docs/api/vision_results/)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+- [PPOCR Model Description](../../)
+- [PPOCRv2 Python Deployment](../python)
+- [Model Prediction Results](../../../../../docs/api/vision_results/)
+- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/ocr/PP-OCRv2/cpp/README_CN.md b/examples/vision/ocr/PP-OCRv2/cpp/README_CN.md
new file mode 100644
index 0000000000..ec8b0c16b3
--- /dev/null
+++ b/examples/vision/ocr/PP-OCRv2/cpp/README_CN.md
@@ -0,0 +1,162 @@
+[English](README.md) | 简体中文
+# PPOCRv2 C++部署示例
+
+本目录下提供`infer.cc`快速完成PPOCRv2在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试，支持此模型需保证FastDeploy版本0.7.0以上(x.x.x>=0.7.0)
+
+```
+mkdir build
+cd build
+# 下载FastDeploy预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz
+tar xvf fastdeploy-linux-x64-x.x.x.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x
+make -j
+
+
+# 下载模型,图片和字典文件
+wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar
+tar -xvf ch_PP-OCRv2_det_infer.tar
+
+wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar
+tar -xvf ch_ppocr_mobile_v2.0_cls_infer.tar
+
+wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar
+tar -xvf ch_PP-OCRv2_rec_infer.tar
+
+wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/doc/imgs/12.jpg
+
+wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/ppocr/utils/ppocr_keys_v1.txt
+
+# CPU推理
+./infer_demo ./ch_PP-OCRv2_det_infer ./ch_ppocr_mobile_v2.0_cls_infer ./ch_PP-OCRv2_rec_infer ./ppocr_keys_v1.txt ./12.jpg 0
+# GPU推理
+./infer_demo ./ch_PP-OCRv2_det_infer ./ch_ppocr_mobile_v2.0_cls_infer ./ch_PP-OCRv2_rec_infer ./ppocr_keys_v1.txt ./12.jpg 1
+# GPU上TensorRT推理
+./infer_demo ./ch_PP-OCRv2_det_infer ./ch_ppocr_mobile_v2.0_cls_infer ./ch_PP-OCRv2_rec_infer ./ppocr_keys_v1.txt ./12.jpg 2
+# GPU上Paddle-TRT推理
+./infer_demo ./ch_PP-OCRv2_det_infer ./ch_ppocr_mobile_v2.0_cls_infer ./ch_PP-OCRv2_rec_infer ./ppocr_keys_v1.txt ./12.jpg 3
+# 昆仑芯XPU推理
+./infer_demo ./ch_PP-OCRv2_det_infer ./ch_ppocr_mobile_v2.0_cls_infer ./ch_PP-OCRv2_rec_infer ./ppocr_keys_v1.txt ./12.jpg 4
+# 华为昇腾推理, 需要使用静态shape的demo, 若用户需要连续地预测图片, 输入图片尺寸需要准备为统一尺寸
+./infer_static_shape_demo ./ch_PP-OCRv2_det_infer ./ch_ppocr_mobile_v2.0_cls_infer ./ch_PP-OCRv2_rec_infer ./ppocr_keys_v1.txt ./12.jpg 1
+```
+
+以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
+- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
+
+如果用户使用华为昇腾NPU部署, 请参考以下方式在部署前初始化部署环境:
+- [如何使用华为昇腾NPU部署](../../../../../docs/cn/faq/use_sdk_on_ascend.md)
+
+运行完成可视化结果如下图所示
+
+
+
+
+## PPOCRv2 C++接口
+
+### PPOCRv2类
+
+```
+fastdeploy::pipeline::PPOCRv2(fastdeploy::vision::ocr::DBDetector* det_model,
+ fastdeploy::vision::ocr::Classifier* cls_model,
+ fastdeploy::vision::ocr::Recognizer* rec_model);
+```
+
+PPOCRv2 的初始化，由检测，分类和识别模型串联构成
+
+**参数**
+
+> * **DBDetector**(model): OCR中的检测模型
+> * **Classifier**(model): OCR中的分类模型
+> * **Recognizer**(model): OCR中的识别模型
+
+```
+fastdeploy::pipeline::PPOCRv2(fastdeploy::vision::ocr::DBDetector* det_model,
+ fastdeploy::vision::ocr::Recognizer* rec_model);
+```
+PPOCRv2 的初始化，由检测，识别模型串联构成(无分类器)
+
+**参数**
+
+> * **DBDetector**(model): OCR中的检测模型
+> * **Recognizer**(model): OCR中的识别模型
+
+#### Predict函数
+
+> ```
+> bool Predict(cv::Mat* img, fastdeploy::vision::OCRResult* result);
+> bool Predict(const cv::Mat& img, fastdeploy::vision::OCRResult* result);
+> ```
+>
+> 模型预测接口，输入一张图片，返回OCR预测结果
+>
+> **参数**
+>
+> > * **img**: 输入图像，注意需为HWC，BGR格式
+> > * **result**: OCR预测结果,包括由检测模型输出的检测框位置,分类模型输出的方向分类,以及识别模型输出的识别结果, OCRResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
+
+
+## DBDetector C++接口
+
+### DBDetector类
+
+```
+fastdeploy::vision::ocr::DBDetector(const std::string& model_file, const std::string& params_file = "",
+ const RuntimeOption& custom_option = RuntimeOption(),
+ const ModelFormat& model_format = ModelFormat::PADDLE);
+```
+
+DBDetector模型加载和初始化，其中模型为paddle模型格式。
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为Paddle格式
+
+### Classifier类与DBDetector类相同
+
+### Recognizer类
+```
+ Recognizer(const std::string& model_file,
+ const std::string& params_file = "",
+ const std::string& label_path = "",
+ const RuntimeOption& custom_option = RuntimeOption(),
+ const ModelFormat& model_format = ModelFormat::PADDLE);
+```
+Recognizer类初始化时,需要在label_path参数中,输入识别模型所需的label文件，其他参数均与DBDetector类相同
+
+**参数**
+> * **label_path**(str): 识别模型的label文件路径
+
+
+### 类成员变量
+#### DBDetector预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> > * **max_side_len**(int): 检测算法前向时图片长边的最大尺寸，当长边超出这个值时会将长边resize到这个大小，短边等比例缩放,默认为960
+> > * **det_db_thresh**(double): DB模型输出预测图的二值化阈值，默认为0.3
+> > * **det_db_box_thresh**(double): DB模型输出框的阈值，低于此值的预测框会被丢弃，默认为0.6
+> > * **det_db_unclip_ratio**(double): DB模型输出框扩大的比例，默认为1.5
+> > * **det_db_score_mode**(string):DB后处理中计算文本框平均得分的方式,默认为slow，即求polygon区域的平均分数的方式
+> > * **use_dilation**(bool):是否对检测输出的feature map做膨胀处理,默认为Fasle
+
+#### Classifier预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> > * **cls_thresh**(double): 当分类模型输出的得分超过此阈值，输入的图片将被翻转，默认为0.9
+
+## 其它文档
+
+- [PPOCR 系列模型介绍](../../)
+- [PPOCRv2 Python部署](../python)
+- [模型预测结果说明](../../../../../docs/api/vision_results/)
+- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/ocr/PP-OCRv2/python/README.md b/examples/vision/ocr/PP-OCRv2/python/README.md
index 1ea95695f3..53316be248 100755
--- a/examples/vision/ocr/PP-OCRv2/python/README.md
+++ b/examples/vision/ocr/PP-OCRv2/python/README.md
@@ -1,15 +1,16 @@
-# PPOCRv2 Python部署示例
+English | [简体中文](README_CN.md)
+# PPOCRv2 Python Deployment Example
-在部署前，需确认以下两个步骤
+Two steps before deployment
-- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. Install FastDeploy Python whl package. Refer to [FastDeploy Python Installation](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-本目录下提供`infer.py`快速完成PPOCRv2在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+This directory provides examples that `infer.py` fast finishes the deployment of PPOCRv2 on CPU/GPU and GPU accelerated by TensorRT. The script is as follows
```
-# 下载模型,图片和字典文件
+# Download model, image, and dictionary files
wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar
tar -xvf ch_PP-OCRv2_det_infer.tar
@@ -24,109 +25,107 @@ wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/doc/imgs/12.jpg
wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/ppocr/utils/ppocr_keys_v1.txt
-#下载部署示例代码
+# Download the example code for deployment
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vison/ocr/PP-OCRv2/python/
-# CPU推理
+# CPU inference
python infer.py --det_model ch_PP-OCRv2_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv2_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device cpu
-# GPU推理
+# GPU inference
python infer.py --det_model ch_PP-OCRv2_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv2_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device gpu
-# GPU上使用TensorRT推理
+# TensorRT inference on GPU
python infer.py --det_model ch_PP-OCRv2_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv2_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device gpu --backend trt
-# 昆仑芯XPU推理
+# KunlunXin XPU inference
python infer.py --det_model ch_PP-OCRv2_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv2_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device kunlunxin
-# 华为昇腾推理,需要使用静态shape脚本, 若用户需要连续地预测图片, 输入图片尺寸需要准备为统一尺寸
-python infer_static_shape.py --det_model ch_PP-OCRv2_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv2_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device ascend
```
-运行完成可视化结果如下图所示
+The visualized result after running is as follows
-## PPOCRv2 Python接口
+## PPOCRv2 Python Interface
```
fd.vision.ocr.PPOCRv2(det_model=det_model, cls_model=cls_model, rec_model=rec_model)
```
-PPOCRv2的初始化,输入的参数是检测模型，分类模型和识别模型，其中cls_model可选，如无需求，可设置为None
+To initialize PPOCRv2, the input parameters correspond to detection model, classification model, and recognition model. Among them, cls_model is optional. It can be set to None if there is no demand
-**参数**
+**Parameter**
-> * **det_model**(model): OCR中的检测模型
-> * **cls_model**(model): OCR中的分类模型
-> * **rec_model**(model): OCR中的识别模型
+> * **det_model**(model): Detection model in OCR
+> * **cls_model**(model): Classification model in OCR
+> * **rec_model**(model): Recognition model in OCR
-### predict函数
+### predict function
> ```
> result = ppocr_v2.predict(im)
> ```
>
-> 模型预测接口，输入是一张图片
+> Model prediction interface. Input one image.
>
-> **参数**
+> **Parameter**
>
-> > * **im**(np.ndarray): 输入数据，每张图片注意需为HWC，BGR格式
+> > * **im**(np.ndarray): Input data in HWC or BGR format
-> **返回**
+> **Return**
>
-> > 返回`fastdeploy.vision.OCRResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > Return the `fastdeploy.vision.OCRResult` structure. Refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for its description.
-## DBDetector Python接口
+## DBDetector Python Interface
-### DBDetector类
+### DBDetector Class
```
fastdeploy.vision.ocr.DBDetector(model_file, params_file, runtime_option=None, model_format=ModelFormat.PADDLE)
```
-DBDetector模型加载和初始化，其中模型为paddle模型格式。
+DBDetector model loading and initialization. The model is in paddle format.
-**参数**
+**Parameter**
-> * **model_file**(str): 模型文件路径
-> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
-> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
-> * **model_format**(ModelFormat): 模型格式，默认为PADDLE格式
+> * **model_file**(str): Model file path
+> * **params_file**(str): Parameter file path. Merely passing an empty string when the model is in ONNX format
+> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
+> * **model_format**(ModelFormat): Model format. PADDLE format by default
-### Classifier类与DBDetector类相同
+### The same applies to the Classifier class
-### Recognizer类
+### Recognizer Class
```
fastdeploy.vision.ocr.Recognizer(rec_model_file,rec_params_file,rec_label_file,
runtime_option=rec_runtime_option,model_format=ModelFormat.PADDLE)
```
-Recognizer类初始化时,需要在rec_label_file参数中,输入识别模型所需的label文件路径，其他参数均与DBDetector类相同
+To initialize the Recognizer class, users need to input the label file path required by the recognition model in the rec_label_file parameter. Other parameters are the same as those of DBDetector class
-**参数**
-> * **label_path**(str): 识别模型的label文件路径
+**Parameter**
+> * **label_path**(str): The label path of the recognition model
-### 类成员变量
+### Class Member Variable
-#### DBDetector预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+#### DBDetector Pre-processing Parameter
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
-> > * **max_side_len**(int): 检测算法前向时图片长边的最大尺寸，当长边超出这个值时会将长边resize到这个大小，短边等比例缩放,默认为960
-> > * **det_db_thresh**(double): DB模型输出预测图的二值化阈值，默认为0.3
-> > * **det_db_box_thresh**(double): DB模型输出框的阈值，低于此值的预测框会被丢弃，默认为0.6
-> > * **det_db_unclip_ratio**(double): DB模型输出框扩大的比例，默认为1.5
-> > * **det_db_score_mode**(string):DB后处理中计算文本框平均得分的方式,默认为slow，即求polygon区域的平均分数的方式
-> > * **use_dilation**(bool):是否对检测输出的feature map做膨胀处理,默认为Fasle
+> > * **max_side_len**(int): The long side’s maximum size of the oriented view before detection. The long side will be resized to this size when exceeding the value. And the short side will be scaled in equal proportion. Default 960
+> > * **det_db_thresh**(double): The binarization threshold of the prediction image from DB models. Default 0.3
+> > * **det_db_box_thresh**(double): The threshold for the output box of DB models, below which the predicted box is discarded. Default 0.6
+> > * **det_db_unclip_ratio**(double): The expansion ratio of the DB model output box. Default 1.5
+> > * **det_db_score_mode**(string): The way to calculate the average score of the text box in DB post-processing. Default slow, which is identical to the calculation of the polygon area’s average score
+> > * **use_dilation**(bool): Whether to expand the feature map from the detection. Default False
-#### Classifier预处理参数
-用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+#### Classifier Pre-processing Parameter
+Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
-> > * **cls_thresh**(double): 当分类模型输出的得分超过此阈值，输入的图片将被翻转，默认为0.9
+> > * **cls_thresh**(double): The input image will be flipped when the score output by the classification model exceeds this threshold. Default 0.9
-## 其它文档
+## Other Documents
-- [PPOCR 系列模型介绍](../../)
-- [PPOCRv2 C++部署](../cpp)
-- [模型预测结果说明](../../../../../docs/api/vision_results/)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+- [PPOCR Model Description](../../)
+- [PPOCRv2 C++ Deployment](../cpp)
+- [Model Prediction Results](../../../../../docs/api/vision_results/)
+- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/ocr/PP-OCRv2/python/README_CN.md b/examples/vision/ocr/PP-OCRv2/python/README_CN.md
new file mode 100644
index 0000000000..9eea8ba5c8
--- /dev/null
+++ b/examples/vision/ocr/PP-OCRv2/python/README_CN.md
@@ -0,0 +1,133 @@
+[English](README.md) | 简体中文
+# PPOCRv2 Python部署示例
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+本目录下提供`infer.py`快速完成PPOCRv2在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+
+```
+
+# 下载模型,图片和字典文件
+wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar
+tar -xvf ch_PP-OCRv2_det_infer.tar
+
+wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar
+tar -xvf ch_ppocr_mobile_v2.0_cls_infer.tar
+
+wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar
+tar -xvf ch_PP-OCRv2_rec_infer.tar
+
+wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/doc/imgs/12.jpg
+
+wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/ppocr/utils/ppocr_keys_v1.txt
+
+
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd examples/vison/ocr/PP-OCRv2/python/
+
+# CPU推理
+python infer.py --det_model ch_PP-OCRv2_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv2_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device cpu
+# GPU推理
+python infer.py --det_model ch_PP-OCRv2_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv2_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device gpu
+# GPU上使用TensorRT推理
+python infer.py --det_model ch_PP-OCRv2_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv2_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device gpu --backend trt
+# 昆仑芯XPU推理
+python infer.py --det_model ch_PP-OCRv2_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv2_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device kunlunxin
+# 华为昇腾推理,需要使用静态shape脚本, 若用户需要连续地预测图片, 输入图片尺寸需要准备为统一尺寸
+python infer_static_shape.py --det_model ch_PP-OCRv2_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv2_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device ascend
+```
+
+运行完成可视化结果如下图所示
+
+
+## PPOCRv2 Python接口
+
+```
+fd.vision.ocr.PPOCRv2(det_model=det_model, cls_model=cls_model, rec_model=rec_model)
+```
+PPOCRv2的初始化,输入的参数是检测模型，分类模型和识别模型，其中cls_model可选，如无需求，可设置为None
+
+**参数**
+
+> * **det_model**(model): OCR中的检测模型
+> * **cls_model**(model): OCR中的分类模型
+> * **rec_model**(model): OCR中的识别模型
+
+### predict函数
+
+> ```
+> result = ppocr_v2.predict(im)
+> ```
+>
+> 模型预测接口，输入是一张图片
+>
+> **参数**
+>
+> > * **im**(np.ndarray): 输入数据，每张图片注意需为HWC，BGR格式
+
+> **返回**
+>
+> > 返回`fastdeploy.vision.OCRResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+
+
+
+## DBDetector Python接口
+
+### DBDetector类
+
+```
+fastdeploy.vision.ocr.DBDetector(model_file, params_file, runtime_option=None, model_format=ModelFormat.PADDLE)
+```
+
+DBDetector模型加载和初始化，其中模型为paddle模型格式。
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为PADDLE格式
+
+### Classifier类与DBDetector类相同
+
+### Recognizer类
+```
+fastdeploy.vision.ocr.Recognizer(rec_model_file,rec_params_file,rec_label_file,
+ runtime_option=rec_runtime_option,model_format=ModelFormat.PADDLE)
+```
+Recognizer类初始化时,需要在rec_label_file参数中,输入识别模型所需的label文件路径，其他参数均与DBDetector类相同
+
+**参数**
+> * **label_path**(str): 识别模型的label文件路径
+
+
+
+### 类成员变量
+
+#### DBDetector预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> > * **max_side_len**(int): 检测算法前向时图片长边的最大尺寸，当长边超出这个值时会将长边resize到这个大小，短边等比例缩放,默认为960
+> > * **det_db_thresh**(double): DB模型输出预测图的二值化阈值，默认为0.3
+> > * **det_db_box_thresh**(double): DB模型输出框的阈值，低于此值的预测框会被丢弃，默认为0.6
+> > * **det_db_unclip_ratio**(double): DB模型输出框扩大的比例，默认为1.5
+> > * **det_db_score_mode**(string):DB后处理中计算文本框平均得分的方式,默认为slow，即求polygon区域的平均分数的方式
+> > * **use_dilation**(bool):是否对检测输出的feature map做膨胀处理,默认为Fasle
+
+#### Classifier预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> > * **cls_thresh**(double): 当分类模型输出的得分超过此阈值，输入的图片将被翻转，默认为0.9
+
+
+
+## 其它文档
+
+- [PPOCR 系列模型介绍](../../)
+- [PPOCRv2 C++部署](../cpp)
+- [模型预测结果说明](../../../../../docs/api/vision_results/)
+- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/ocr/PP-OCRv2/serving/README.md b/examples/vision/ocr/PP-OCRv2/serving/README.md
index b7a636477d..2049564c9e 100644
--- a/examples/vision/ocr/PP-OCRv2/serving/README.md
+++ b/examples/vision/ocr/PP-OCRv2/serving/README.md
@@ -1,12 +1,13 @@
-# PP-OCRv2服务化部署示例
+English | [简体中文](README_CN.md)
+# PP-OCRv2 Serving Deployment
-除了`下载的模型`和`rec前处理的1个参数`以外PP-OCRv2的服务化部署与PP-OCRv3服务化部署全部一样，请参考[PP-OCRv3服务化部署](../../PP-OCRv3/serving)。
+The serving deployment of PP-OCRv2 is identical to that of PP-OCRv3 except for `downloaded models` and `1 parameter for rec pre-processing`. Refer to [PP-OCRv3 serving deployment](../../PP-OCRv3/serving)
-## 下载模型
-将下载链接中的`v3`改为`v2`即可。
+## Download models
+Change `v3` into `v2` in the download link.
-## 修改rec前处理参数
-在[model.py](../../PP-OCRv3/serving/models/det_postprocess/1/model.py#L109)文件**109行添加以下代码**：
+## Modify the rec pre-processing parameter
+**Add the following code to line 109** in the file [model.py](../../PP-OCRv3/serving/models/det_postprocess/1/model.py#L109):
```
self.rec_preprocessor.cls_image_shape[1] = 32
```
diff --git a/examples/vision/ocr/PP-OCRv2/serving/README_CN.md b/examples/vision/ocr/PP-OCRv2/serving/README_CN.md
new file mode 100644
index 0000000000..f83e8b0b4d
--- /dev/null
+++ b/examples/vision/ocr/PP-OCRv2/serving/README_CN.md
@@ -0,0 +1,13 @@
+[English](README.md) | 简体中文
+# PP-OCRv2服务化部署示例
+
+除了`下载的模型`和`rec前处理的1个参数`以外PP-OCRv2的服务化部署与PP-OCRv3服务化部署全部一样，请参考[PP-OCRv3服务化部署](../../PP-OCRv3/serving)。
+
+## 下载模型
+将下载链接中的`v3`改为`v2`即可。
+
+## 修改rec前处理参数
+在[model.py](../../PP-OCRv3/serving/models/det_postprocess/1/model.py#L109)文件**109行添加以下代码**：
+```
+self.rec_preprocessor.cls_image_shape[1] = 32
+```
diff --git a/examples/vision/ocr/PP-OCRv3/android/README.md b/examples/vision/ocr/PP-OCRv3/android/README.md
index f4e23ab992..a92fb72246 100644
--- a/examples/vision/ocr/PP-OCRv3/android/README.md
+++ b/examples/vision/ocr/PP-OCRv3/android/README.md
@@ -1,94 +1,94 @@
-# OCR文字识别 Android Demo 使用文档
+English | [简体中文](README_CN.md)
+# OCR Text Recognition Android Demo Tutorial
-在 Android 上实现实时的OCR文字识别功能，此 Demo 有很好的的易用性和开放性，如在 Demo 中跑自己训练好的模型等。
+Real-time OCR text recognition on Android. This demo is easy to use for everyone. For example, you can run your own trained model in the demo.
-## 环境准备
+## Prepare the Environment
-1. 在本地环境安装好 Android Studio 工具，详细安装方法请见[Android Stuido 官网](https://developer.android.com/studio)。
-2. 准备一部 Android 手机，并开启 USB 调试模式。开启方法: `手机设置 -> 查找开发者选项 -> 打开开发者选项和 USB 调试模式`
+1. Install Android Studio in your local environment. Refer to [Android Studio Official Website](https://developer.android.com/studio) for detailed tutorial.
+2. Prepare an Android phone and turn on the USB debug mode. Opening: `Settings -> Find developer options -> Open developer options and USB debug mode`
-## 部署步骤
+## Deployment steps
-1. OCR文字识别 Demo 位于 `fastdeploy/examples/vision/ocr/PP-OCRv3/android` 目录
-2. 用 Android Studio 打开 PP-OCRv3/android 工程
-3. 手机连接电脑，打开 USB 调试和文件传输模式，并在 Android Studio 上连接自己的手机设备（手机需要开启允许从 USB 安装软件权限）
+1. The OCR text recognition Demo is located in the `fastdeploy/examples/vision/ocr/PP-OCRv3/android`
+2. Open PP-OCRv2/android project with Android Studio
+3. Connect the phone to the computer, turn on USB debug mode and file transfer mode, and connect your phone to Android Studio (allow the phone to install software from USB)
+
+
-## 其它文档
+## Other Documents
-- [C++ API查阅](https://baidu-paddle.github.io/fastdeploy-api/cpp/html/)
-- [PPOCR 系列模型介绍](../../)
-- [PPOCRv3 Python部署](../python)
-- [模型预测结果说明](../../../../../docs/cn/faq/how_to_change_backend.md)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+- [C++ API Reference](https://baidu-paddle.github.io/fastdeploy-api/cpp/html/)
+- [PPOCR Model Description](../../)
+- [PPOCRv3 Python Deployment](../python)
+- [Model Prediction Results](../../../../../docs/cn/faq/how_to_change_backend.md)
+- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/ocr/PP-OCRv3/cpp/README_CN.md b/examples/vision/ocr/PP-OCRv3/cpp/README_CN.md
new file mode 100644
index 0000000000..167d2d9524
--- /dev/null
+++ b/examples/vision/ocr/PP-OCRv3/cpp/README_CN.md
@@ -0,0 +1,67 @@
+[English](README.md) | 简体中文
+# PPOCRv3 C++部署示例
+
+本目录下提供`infer.cc`快速完成PPOCRv3在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试，支持此模型需保证FastDeploy版本0.7.0以上(x.x.x>=0.7.0)
+
+```
+mkdir build
+cd build
+# 下载FastDeploy预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz
+tar xvf fastdeploy-linux-x64-x.x.x.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x
+make -j
+
+
+# 下载模型,图片和字典文件
+wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar
+tar -xvf ch_PP-OCRv3_det_infer.tar
+
+wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar
+tar -xvf ch_ppocr_mobile_v2.0_cls_infer.tar
+
+wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar
+tar -xvf ch_PP-OCRv3_rec_infer.tar
+
+wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/doc/imgs/12.jpg
+
+wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/ppocr/utils/ppocr_keys_v1.txt
+
+# CPU推理
+./infer_demo ./ch_PP-OCRv3_det_infer ./ch_ppocr_mobile_v2.0_cls_infer ./ch_PP-OCRv3_rec_infer ./ppocr_keys_v1.txt ./12.jpg 0
+# GPU推理
+./infer_demo ./ch_PP-OCRv3_det_infer ./ch_ppocr_mobile_v2.0_cls_infer ./ch_PP-OCRv3_rec_infer ./ppocr_keys_v1.txt ./12.jpg 1
+# GPU上TensorRT推理
+./infer_demo ./ch_PP-OCRv3_det_infer ./ch_ppocr_mobile_v2.0_cls_infer ./ch_PP-OCRv3_rec_infer ./ppocr_keys_v1.txt ./12.jpg 2
+# GPU上Paddle-TRT推理
+./infer_demo ./ch_PP-OCRv3_det_infer ./ch_ppocr_mobile_v2.0_cls_infer ./ch_PP-OCRv3_rec_infer ./ppocr_keys_v1.txt ./12.jpg 3
+# 昆仑芯XPU推理
+./infer_demo ./ch_PP-OCRv3_det_infer ./ch_ppocr_mobile_v2.0_cls_infer ./ch_PP-OCRv3_rec_infer ./ppocr_keys_v1.txt ./12.jpg 4
+# 华为昇腾推理,需要使用静态shape的demo, 若用户需要连续地预测图片, 输入图片尺寸需要准备为统一尺寸
+./infer_static_shape_demo ./ch_PP-OCRv3_det_infer ./ch_ppocr_mobile_v2.0_cls_infer ./ch_PP-OCRv3_rec_infer ./ppocr_keys_v1.txt ./12.jpg 1
+```
+
+以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
+- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
+
+如果用户使用华为昇腾NPU部署, 请参考以下方式在部署前初始化部署环境:
+- [如何使用华为昇腾NPU部署](../../../../../docs/cn/faq/use_sdk_on_ascend.md)
+
+运行完成可视化结果如下图所示
+
+
+
+## 其它文档
+
+- [C++ API查阅](https://baidu-paddle.github.io/fastdeploy-api/cpp/html/)
+- [PPOCR 系列模型介绍](../../)
+- [PPOCRv3 Python部署](../python)
+- [模型预测结果说明](../../../../../docs/cn/faq/how_to_change_backend.md)
+- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/ocr/PP-OCRv3/mini_program/README.md b/examples/vision/ocr/PP-OCRv3/mini_program/README.md
index 447a02e725..b80e6acb09 100644
--- a/examples/vision/ocr/PP-OCRv3/mini_program/README.md
+++ b/examples/vision/ocr/PP-OCRv3/mini_program/README.md
@@ -1,40 +1,40 @@
+English | [简体中文](README_CN.md)
+# PP-OCRv3 Wechat Mini-program Deployment Example
-# PP-OCRv3 微信小程序部署示例
+This document introduces the deployment of PP-OCRv3 model from PaddleOCR in Wechat mini-program, and the js interface in the @paddle-js-models/ocr npm package.
-本节介绍部署PaddleOCR的PP-OCRv3模型在微信小程序中运行，以及@paddle-js-models/ocr npm包中的js接口。
+## Deploy PP-OCRv3 models in Wechat Mini-program
-## 微信小程序部署PP-OCRv3模型
+For the deployment of PP-OCRv3 models in Wechat mini-program, refer to [**reference document**](../../../../application/js/mini_program)
-PP-OCRv3模型部署到微信小程序[**参考文档**](../../../../application/js/mini_program)
-
-## PP-OCRv3 js接口
+## PP-OCRv3 js interface
```
import * as ocr from "@paddle-js-models/ocr";
await ocr.init(detConfig, recConfig);
const res = await ocr.recognize(img, option, postConfig);
```
-ocr模型加载和初始化，其中模型为Paddle.js模型格式，js模型转换方式参考[文档](../../../../application/js/web_demo/README.md)
+ocr model loading and initialization, where the model is in Paddle.js model format. For the conversion of js models, refer to [document](../../../../application/js/web_demo/README.md)
-**init函数参数**
+**init function parameter**
-> * **detConfig**(dict): 文本检测模型配置参数，默认值为 {modelPath: 'https://js-models.bj.bcebos.com/PaddleOCR/PP-OCRv3/ch_PP-OCRv3_det_infer_js_960/model.json', fill: '#fff', mean: [0.485, 0.456, 0.406],std: [0.229, 0.224, 0.225]}; 其中，modelPath为文本检测模型路径，fill 为图像预处理padding的值，mean和std分别为预处理的均值和标准差
-> * **recConfig**(dict)): 文本识别模型配置参数，默认值为 {modelPath: 'https://js-models.bj.bcebos.com/PaddleOCR/PP-OCRv3/ch_PP-OCRv3_rec_infer_js/model.json', fill: '#000', mean: [0.5, 0.5, 0.5], std: [0.5, 0.5, 0.5]}; 其中，modelPath为文本检测模型路径，fill 为图像预处理padding的值，mean和std分别为预处理的均值和标准差
+> * **detConfig**(dict): The configuration parameter for text detection model. Default {modelPath: 'https://js-models.bj.bcebos.com/PaddleOCR/PP-OCRv3/ch_PP-OCRv3_det_infer_js_960/model.json', fill: '#fff', mean: [0.485, 0.456, 0.406],std: [0.229, 0.224, 0.225]}; Among them, modelPath is the path of the text detection model; fill is the padding value in the image pre-processing; mean and std are the mean and standard deviation in the pre-processing
+> * **recConfig**(dict)): The configuration parameter for text recognition model. Default {modelPath: 'https://js-models.bj.bcebos.com/PaddleOCR/PP-OCRv3/ch_PP-OCRv3_rec_infer_js/model.json', fill: '#000', mean: [0.5, 0.5, 0.5], std: [0.5, 0.5, 0.5]}; Among them, modelPath is the path of the text detection model, fill is the padding value in the image pre-processing, and mean/std are the mean and standard deviation in the pre-processing
-**recognize函数参数**
+**recognize function parameter**
-> * **img**(HTMLImageElement): 输入图像参数，类型为HTMLImageElement。
-> * **option**(dict): 可视化文本检测框的canvas参数，可不用设置。
-> * **postConfig**(dict): 文本检测后处理参数，默认值为：{shape: 960, thresh: 0.3, box_thresh: 0.6, unclip_ratio:1.5}; thresh是输出预测图的二值化阈值；box_thresh是输出框的阈值，低于此值的预测框会被丢弃，unclip_ratio是输出框扩大的比例。
+> * **img**(HTMLImageElement): Enter an image parameter in HTMLImageElement.
+> * **option**(dict): The canvas parameter of the visual text detection box. No need to set.
+> * **postConfig**(dict): Text detection post-processing parameter. Default: {shape: 960, thresh: 0.3, box_thresh: 0.6, unclip_ratio:1.5}; thresh is the binarization threshold of the output prediction image; box_thresh is the threshold of the output box, below which the prediction box will be discarded; unclip_ratio is the expansion ratio of the output box.
-## 其它文档
+## Other Documents
-- [PP-OCR 系列模型介绍](../../)
-- [PP-OCRv3 C++部署](../cpp)
-- [模型预测结果说明](../../../../../docs/api/vision_results/)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
-- [PP-OCRv3模型web demo文档](../../../../application/js/web_demo/README.md)
+- [PP-OCR Model Description](../../)
+- [PP-OCRv3 C++ Deployment](../cpp)
+- [Model Prediction Results](../../../../../docs/api/vision_results/)
+- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
+- [Web demo document of PP-OCRv3 models](../../../../application/js/web_demo/README.md)
diff --git a/examples/vision/ocr/PP-OCRv3/mini_program/README_CN.md b/examples/vision/ocr/PP-OCRv3/mini_program/README_CN.md
new file mode 100644
index 0000000000..e3a9691008
--- /dev/null
+++ b/examples/vision/ocr/PP-OCRv3/mini_program/README_CN.md
@@ -0,0 +1,40 @@
+[English](README.md) | 简体中文
+# PP-OCRv3 微信小程序部署示例
+
+本节介绍部署PaddleOCR的PP-OCRv3模型在微信小程序中运行，以及@paddle-js-models/ocr npm包中的js接口。
+
+
+## 微信小程序部署PP-OCRv3模型
+
+PP-OCRv3模型部署到微信小程序[**参考文档**](../../../../application/js/mini_program)
+
+
+## PP-OCRv3 js接口
+
+```
+import * as ocr from "@paddle-js-models/ocr";
+await ocr.init(detConfig, recConfig);
+const res = await ocr.recognize(img, option, postConfig);
+```
+ocr模型加载和初始化，其中模型为Paddle.js模型格式，js模型转换方式参考[文档](../../../../application/js/web_demo/README.md)
+
+**init函数参数**
+
+> * **detConfig**(dict): 文本检测模型配置参数，默认值为 {modelPath: 'https://js-models.bj.bcebos.com/PaddleOCR/PP-OCRv3/ch_PP-OCRv3_det_infer_js_960/model.json', fill: '#fff', mean: [0.485, 0.456, 0.406],std: [0.229, 0.224, 0.225]}; 其中，modelPath为文本检测模型路径，fill 为图像预处理padding的值，mean和std分别为预处理的均值和标准差
+> * **recConfig**(dict)): 文本识别模型配置参数，默认值为 {modelPath: 'https://js-models.bj.bcebos.com/PaddleOCR/PP-OCRv3/ch_PP-OCRv3_rec_infer_js/model.json', fill: '#000', mean: [0.5, 0.5, 0.5], std: [0.5, 0.5, 0.5]}; 其中，modelPath为文本检测模型路径，fill 为图像预处理padding的值，mean和std分别为预处理的均值和标准差
+
+
+**recognize函数参数**
+
+> * **img**(HTMLImageElement): 输入图像参数，类型为HTMLImageElement。
+> * **option**(dict): 可视化文本检测框的canvas参数，可不用设置。
+> * **postConfig**(dict): 文本检测后处理参数，默认值为：{shape: 960, thresh: 0.3, box_thresh: 0.6, unclip_ratio:1.5}; thresh是输出预测图的二值化阈值；box_thresh是输出框的阈值，低于此值的预测框会被丢弃，unclip_ratio是输出框扩大的比例。
+
+
+## 其它文档
+
+- [PP-OCR 系列模型介绍](../../)
+- [PP-OCRv3 C++部署](../cpp)
+- [模型预测结果说明](../../../../../docs/api/vision_results/)
+- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+- [PP-OCRv3模型web demo文档](../../../../application/js/web_demo/README.md)
diff --git a/examples/vision/ocr/PP-OCRv3/python/README.md b/examples/vision/ocr/PP-OCRv3/python/README.md
index 3fcf372e05..99217ceea0 100755
--- a/examples/vision/ocr/PP-OCRv3/python/README.md
+++ b/examples/vision/ocr/PP-OCRv3/python/README.md
@@ -1,15 +1,16 @@
-# PPOCRv3 Python部署示例
+English | [简体中文](README_CN.md)
+# PPOCRv3 Python Deployment Example
-在部署前，需确认以下两个步骤
+Two steps before deployment
-- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. Install FastDeploy Python whl package. Refer to [FastDeploy Python Installation](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
-本目录下提供`infer.py`快速完成PPOCRv3在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+This directory provides examples that `infer.py` fast finishes the deployment of PPOCRv3 on CPU/GPU and GPU accelerated by TensorRT. The script is as follows
```
-# 下载模型,图片和字典文件
+# Download model, image, and dictionary files
wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar
tar xvf ch_PP-OCRv3_det_infer.tar
@@ -23,32 +24,32 @@ wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/doc/imgs/12.jpg
wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/ppocr/utils/ppocr_keys_v1.txt
-#下载部署示例代码
+# Download the example code for deployment
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vison/ocr/PP-OCRv3/python/
-# CPU推理
+# CPU inference
python infer.py --det_model ch_PP-OCRv3_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv3_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device cpu
-# GPU推理
+# GPU inference
python infer.py --det_model ch_PP-OCRv3_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv3_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device gpu
-# GPU上使用TensorRT推理
+# TensorRT inference on GPU
python infer.py --det_model ch_PP-OCRv3_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv3_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device gpu --backend trt
-# 昆仑芯XPU推理
+# KunlunXin XPU inference
python infer.py --det_model ch_PP-OCRv3_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv3_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device kunlunxin
-# 华为昇腾推理,需要使用静态shape脚本, 若用户需要连续地预测图片, 输入图片尺寸需要准备为统一尺寸
+# HUAWEI Ascend inference requires static shape script. The size of input images should be consistent if you want to continuously predict images.
python infer_static_shape.py --det_model ch_PP-OCRv3_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv3_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device ascend
```
-运行完成可视化结果如下图所示
+The visualized result after running is as follows
-## 其它文档
+## Other Documents
-- [Python API文档查阅](https://baidu-paddle.github.io/fastdeploy-api/python/html/)
-- [PPOCR 系列模型介绍](../../)
-- [PPOCRv3 C++部署](../cpp)
-- [模型预测结果说明](../../../../../docs/api/vision_results/)
-- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
+- [Python API reference](https://baidu-paddle.github.io/fastdeploy-api/python/html/)
+- [PPOCR Model Description](../../)
+- [PPOCRv3 C++ Deployment](../cpp)
+- [Model Prediction Results](../../../../../docs/api/vision_results/)
+- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/ocr/PP-OCRv3/python/README_CN.md b/examples/vision/ocr/PP-OCRv3/python/README_CN.md
new file mode 100644
index 0000000000..845cc91abf
--- /dev/null
+++ b/examples/vision/ocr/PP-OCRv3/python/README_CN.md
@@ -0,0 +1,55 @@
+[English](README.md) | 简体中文
+# PPOCRv3 Python部署示例
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+本目录下提供`infer.py`快速完成PPOCRv3在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+
+```
+
+# 下载模型,图片和字典文件
+wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar
+tar xvf ch_PP-OCRv3_det_infer.tar
+
+wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar
+tar -xvf ch_ppocr_mobile_v2.0_cls_infer.tar
+
+wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar
+tar xvf ch_PP-OCRv3_rec_infer.tar
+
+wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/doc/imgs/12.jpg
+
+wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/ppocr/utils/ppocr_keys_v1.txt
+
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd examples/vison/ocr/PP-OCRv3/python/
+
+# CPU推理
+python infer.py --det_model ch_PP-OCRv3_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv3_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device cpu
+# GPU推理
+python infer.py --det_model ch_PP-OCRv3_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv3_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device gpu
+# GPU上使用TensorRT推理
+python infer.py --det_model ch_PP-OCRv3_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv3_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device gpu --backend trt
+# 昆仑芯XPU推理
+python infer.py --det_model ch_PP-OCRv3_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv3_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device kunlunxin
+# 华为昇腾推理,需要使用静态shape脚本, 若用户需要连续地预测图片, 输入图片尺寸需要准备为统一尺寸
+python infer_static_shape.py --det_model ch_PP-OCRv3_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv3_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device ascend
+```
+
+运行完成可视化结果如下图所示
+
+
+
+
+
+## 其它文档
+
+- [Python API文档查阅](https://baidu-paddle.github.io/fastdeploy-api/python/html/)
+- [PPOCR 系列模型介绍](../../)
+- [PPOCRv3 C++部署](../cpp)
+- [模型预测结果说明](../../../../../docs/api/vision_results/)
+- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
diff --git a/examples/vision/ocr/PP-OCRv3/serving/README.md b/examples/vision/ocr/PP-OCRv3/serving/README.md
index a870b2d19a..1ad4c70090 100755
--- a/examples/vision/ocr/PP-OCRv3/serving/README.md
+++ b/examples/vision/ocr/PP-OCRv3/serving/README.md
@@ -1,37 +1,37 @@
-# PP-OCR服务化部署示例
+English | [简体中文](README_CN.md)
+# PP-OCR Serving Deployment Example
-在服务化部署前，需确认
+Before the serving deployment, please confirm
-- 1. 服务化镜像的软硬件环境要求和镜像拉取命令请参考[FastDeploy服务化部署](../../../../../serving/README_CN.md)
+- 1. Refer to [FastDeploy Serving Deployment](../../../../../serving/README_CN.md) for software and hardware environment requirements and image pull commands
-## 介绍
-本文介绍了使用FastDeploy搭建OCR文字识别服务的方法.
+## Introduction
+This document describes how to build an OCR text recognition service with FastDeploy.
-服务端必须在docker内启动,而客户端不是必须在docker容器内.
+The server must be started in docker, while the client does not need to be in a docker container.
-**本文所在路径($PWD)下的models里包含模型的配置和代码(服务端会加载模型和代码以启动服务), 需要将其映射到docker中使用.**
+**The models in the path ($PWD) contain the model configuration and code (the server will load the models and code to start the service), which needs to be mapped to docker.**
-OCR由det(检测)、cls(分类)和rec(识别)三个模型组成.
+OCR consists of det (detection), cls (classification) and rec (recognition) models.
-服务化部署串联的示意图如下图所示,其中`pp_ocr`串联了`det_preprocess`、`det_runtime`和`det_postprocess`,`cls_pp`串联了`cls_runtime`和`cls_postprocess`,`rec_pp`串联了`rec_runtime`和`rec_postprocess`.
-
-特别的是,在`det_postprocess`中会多次调用`cls_pp`和`rec_pp`服务,来实现对检测结果(多个框)进行分类和识别,,最后返回给用户最终的识别结果。
+The diagram of the serving deployment is shown below, where `pp_ocr` connects to `det_preprocess`、`det_runtime` and `det_postprocess`,`cls_pp` connects to `cls_runtime` and `cls_postprocess`,`rec_pp` connects to `rec_runtime` and `rec_postprocess`.
+In particular, `cls_pp` and `rec_pp` services are called multiple times in `det_postprocess` to realize the classification and identification of the detection results (multiple boxes), and finally return the identification results to users.
-## 使用 -### 1. 服务端 +## Usage +### 1. Server #### 1.1 Docker ```bash -# 下载仓库代码 +# Download the repository code git clone https://github.com/PaddlePaddle/FastDeploy.git cd FastDeploy/examples/vision/ocr/PP-OCRv3/serving/ -# 下载模型,图片和字典文件 +# Dpwnload model, image, and dictionary files wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar tar xvf ch_PP-OCRv3_det_infer.tar && mv ch_PP-OCRv3_det_infer 1 mv 1/inference.pdiparams 1/model.pdiparams && mv 1/inference.pdmodel 1/model.pdmodel @@ -54,41 +54,41 @@ mv ppocr_keys_v1.txt models/rec_postprocess/1/ wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/doc/imgs/12.jpg -# x.y.z为镜像版本号，需参照serving文档替换为数字 +# x.y.z represent the image version. Refer to serving document to replace them with numbers docker pull registry.baidubce.com/paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10 docker run -dit --net=host --name fastdeploy --shm-size="1g" -v $PWD:/ocr_serving registry.baidubce.com/paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10 bash docker exec -it -u root fastdeploy bash ``` -#### 1.2 安装(在docker内) +#### 1.2 Installation (in docker) ```bash ldconfig apt-get install libgl1 ``` -#### 1.3 启动服务端(在docker内) +#### 1.3 Start the server (in docker) ```bash fastdeployserver --model-repository=/ocr_serving/models ``` -参数: - - `model-repository`(required): 整套模型streaming_pp_tts存放的路径. - - `http-port`(optional): HTTP服务的端口号. 默认: `8000`. 本示例中未使用该端口. - - `grpc-port`(optional): GRPC服务的端口号. 默认: `8001`. - - `metrics-port`(optional): 服务端指标的端口号. 默认: `8002`. 本示例中未使用该端口. +Parameter: + - `model-repository`(required): The storage path of the entire model streaming_pp_tts. + - `http-port`(optional): Port number for the HTTP service. Default: `8000`. This port is not used in this example. + - `grpc-port`(optional): Port number for the GRPC service. Default: `8001`. + - `metrics-port`(optional): Port number for the serer metric. Default: `8002`. This port is not used in this example. -### 2. 客户端 -#### 2.1 安装 +### 2. Client +#### 2.1 Installation ```bash pip3 install tritonclient[all] ``` -#### 2.2 发送请求 +#### 2.2 Send Requests ```bash python3 client.py ``` -## 配置修改 +## Configuration Change -当前默认配置在GPU上运行， 如果要在CPU或其他推理引擎上运行。 需要修改`models/runtime/config.pbtxt`中配置，详情请参考[配置文档](../../../../../serving/docs/zh_CN/model_configuration.md) +The current default configuration runs on GPU. If you want to run it on CPU or other inference engines, please modify the configuration in `models/runtime/config.pbtxt`. Refer to [Configuration Document](../../../../../serving/docs/zh_CN/model_configuration.md) for more information. diff --git a/examples/vision/ocr/PP-OCRv3/serving/README_CN.md b/examples/vision/ocr/PP-OCRv3/serving/README_CN.md new file mode 100644 index 0000000000..3f68e69ff4 --- /dev/null +++ b/examples/vision/ocr/PP-OCRv3/serving/README_CN.md @@ -0,0 +1,95 @@ +[English](README.md) | 简体中文 +# PP-OCR服务化部署示例 + +在服务化部署前，需确认 + +- 1. 服务化镜像的软硬件环境要求和镜像拉取命令请参考[FastDeploy服务化部署](../../../../../serving/README_CN.md) + +## 介绍 +本文介绍了使用FastDeploy搭建OCR文字识别服务的方法. + +服务端必须在docker内启动,而客户端不是必须在docker容器内. + +**本文所在路径($PWD)下的models里包含模型的配置和代码(服务端会加载模型和代码以启动服务), 需要将其映射到docker中使用.** + +OCR由det(检测)、cls(分类)和rec(识别)三个模型组成. + +服务化部署串联的示意图如下图所示,其中`pp_ocr`串联了`det_preprocess`、`det_runtime`和`det_postprocess`,`cls_pp`串联了`cls_runtime`和`cls_postprocess`,`rec_pp`串联了`rec_runtime`和`rec_postprocess`. + +特别的是,在`det_postprocess`中会多次调用`cls_pp`和`rec_pp`服务,来实现对检测结果(多个框)进行分类和识别,,最后返回给用户最终的识别结果。 + +
+
+
+
+
+ +## 使用 +### 1. 服务端 +#### 1.1 Docker +```bash +# 下载仓库代码 +git clone https://github.com/PaddlePaddle/FastDeploy.git +cd FastDeploy/examples/vision/ocr/PP-OCRv3/serving/ + +# 下载模型,图片和字典文件 +wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar +tar xvf ch_PP-OCRv3_det_infer.tar && mv ch_PP-OCRv3_det_infer 1 +mv 1/inference.pdiparams 1/model.pdiparams && mv 1/inference.pdmodel 1/model.pdmodel +mv 1 models/det_runtime/ && rm -rf ch_PP-OCRv3_det_infer.tar + +wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar +tar xvf ch_ppocr_mobile_v2.0_cls_infer.tar && mv ch_ppocr_mobile_v2.0_cls_infer 1 +mv 1/inference.pdiparams 1/model.pdiparams && mv 1/inference.pdmodel 1/model.pdmodel +mv 1 models/cls_runtime/ && rm -rf ch_ppocr_mobile_v2.0_cls_infer.tar + +wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar +tar xvf ch_PP-OCRv3_rec_infer.tar && mv ch_PP-OCRv3_rec_infer 1 +mv 1/inference.pdiparams 1/model.pdiparams && mv 1/inference.pdmodel 1/model.pdmodel +mv 1 models/rec_runtime/ && rm -rf ch_PP-OCRv3_rec_infer.tar + +mkdir models/pp_ocr/1 && mkdir models/rec_pp/1 && mkdir models/cls_pp/1 + +wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/ppocr/utils/ppocr_keys_v1.txt +mv ppocr_keys_v1.txt models/rec_postprocess/1/ + +wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/doc/imgs/12.jpg + +# x.y.z为镜像版本号，需参照serving文档替换为数字 +docker pull registry.baidubce.com/paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10 +docker run -dit --net=host --name fastdeploy --shm-size="1g" -v $PWD:/ocr_serving registry.baidubce.com/paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10 bash +docker exec -it -u root fastdeploy bash +``` + +#### 1.2 安装(在docker内) +```bash +ldconfig +apt-get install libgl1 +``` + +#### 1.3 启动服务端(在docker内) +```bash +fastdeployserver --model-repository=/ocr_serving/models +``` + +参数: + - `model-repository`(required): 整套模型streaming_pp_tts存放的路径. + - `http-port`(optional): HTTP服务的端口号. 默认: `8000`. 本示例中未使用该端口. + - `grpc-port`(optional): GRPC服务的端口号. 默认: `8001`. + - `metrics-port`(optional): 服务端指标的端口号. 默认: `8002`. 本示例中未使用该端口. + + +### 2. 客户端 +#### 2.1 安装 +```bash +pip3 install tritonclient[all] +``` + +#### 2.2 发送请求 +```bash +python3 client.py +``` + +## 配置修改 + +当前默认配置在GPU上运行， 如果要在CPU或其他推理引擎上运行。 需要修改`models/runtime/config.pbtxt`中配置，详情请参考[配置文档](../../../../../serving/docs/zh_CN/model_configuration.md) diff --git a/examples/vision/ocr/PP-OCRv3/web/README.md b/examples/vision/ocr/PP-OCRv3/web/README.md index b13e7547d5..454afa1586 100644 --- a/examples/vision/ocr/PP-OCRv3/web/README.md +++ b/examples/vision/ocr/PP-OCRv3/web/README.md @@ -1,40 +1,39 @@ +English | [简体中文](README_CN.md) +# PP-OCRv3 Frontend Deployment Example -# PP-OCRv3 前端部署示例 +This document introduces the deployment of PaddleOCR's PP-OCRv3 models to run in the browser, and the js interface in the @paddle-js-models/ocr npm package. -本节介绍部署PaddleOCR的PP-OCRv3模型在浏览器中运行，以及@paddle-js-models/ocr npm包中的js接口。 +## Frontend Deployment PP-OCRv3 Model -## 前端部署PP-OCRv3模型 +For PP-OCRv3 model web demo, refer to [**reference document**](../../../../application/js/web_demo/) -PP-OCRv3模型web demo使用[**参考文档**](../../../../application/js/web_demo/) - -## PP-OCRv3 js接口 +## PP-OCRv3 js Interface ``` import * as ocr from "@paddle-js-models/ocr"; await ocr.init(detConfig, recConfig); const res = await ocr.recognize(img, option, postConfig); ``` -ocr模型加载和初始化，其中模型为Paddle.js模型格式，js模型转换方式参考[文档](../../../../application/js/web_demo/README.md) - -**init函数参数** +ocr model loading and initialization, where the model is in Paddle.js model format. For the conversion of js models, refer to [the document](../../../../application/js/web_demo/README.md) -> * **detConfig**(dict): 文本检测模型配置参数，默认值为 {modelPath: 'https://js-models.bj.bcebos.com/PaddleOCR/PP-OCRv3/ch_PP-OCRv3_det_infer_js_960/model.json', fill: '#fff', mean: [0.485, 0.456, 0.406],std: [0.229, 0.224, 0.225]}; 其中，modelPath为文本检测模型路径，fill 为图像预处理padding的值，mean和std分别为预处理的均值和标准差 -> * **recConfig**(dict)): 文本识别模型配置参数，默认值为 {modelPath: 'https://js-models.bj.bcebos.com/PaddleOCR/PP-OCRv3/ch_PP-OCRv3_rec_infer_js/model.json', fill: '#000', mean: [0.5, 0.5, 0.5], std: [0.5, 0.5, 0.5]}; 其中，modelPath为文本检测模型路径，fill 为图像预处理padding的值，mean和std分别为预处理的均值和标准差 +**init function parameter** +> * **detConfig**(dict): The configuration parameter for the text detection model. Default {modelPath: 'https://js-models.bj.bcebos.com/PaddleOCR/PP-OCRv3/ch_PP-OCRv3_det_infer_js_960/model.json', fill: '#fff', mean: [0.485, 0.456, 0.406],std: [0.229, 0.224, 0.225]}; Among them, modelPath is the path of the text detection model, fill is the padding value in the image pre-processing, and mean/std are the mean and standard deviation in the pre-processing. +> * **recConfig**(dict)): The configuration parameter for the text recognition model. Default {modelPath: 'https://js-models.bj.bcebos.com/PaddleOCR/PP-OCRv3/ch_PP-OCRv3_rec_infer_js/model.json', fill: '#000', mean: [0.5, 0.5, 0.5], std: [0.5, 0.5, 0.5]}; Among them, modelPath is the path of the text detection model, fill is the padding value in the image pre-processing, and mean/std are the mean and standard deviation in the pre-processing. -**recognize函数参数** -> * **img**(HTMLImageElement): 输入图像参数，类型为HTMLImageElement。 -> * **option**(dict): 可视化文本检测框的canvas参数，可不用设置。 -> * **postConfig**(dict): 文本检测后处理参数，默认值为：{shape: 960, thresh: 0.3, box_thresh: 0.6, unclip_ratio:1.5}; thresh是输出预测图的二值化阈值；box_thresh是输出框的阈值，低于此值的预测框会被丢弃，unclip_ratio是输出框扩大的比例。 +**recognize function parameter** +> * **img**(HTMLImageElement): Enter an image parameter in HTMLImageElement. +> * **option**(dict): The canvas parameter of the visual text detection box. No need to set. +> * **postConfig**(dict): Text detection post-processing parameter. Default: {shape: 960, thresh: 0.3, box_thresh: 0.6, unclip_ratio:1.5}; thresh is the binarization threshold of the output prediction image. box_thresh is the threshold of the output box, below which the prediction box will be discarded. unclip_ratio is the expansion ratio of the output box. -## 其它文档 +## Other Documents -- [PP-OCR 系列模型介绍](../../) -- [PP-OCRv3 C++部署](../cpp) -- [模型预测结果说明](../../../../../docs/api/vision_results/) -- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md) -- [PP-OCRv3 微信小程序部署文档](../mini_program/) +- [PP-OCR Model Description](../../) +- [PP-OCRv3 C++ Deployment](../cpp) +- [Model Prediction Results](../../../../../docs/api/vision_results/) +- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md) +- [PP-OCRv3 Wechat mini-program deployment document](../mini_program/) diff --git a/examples/vision/ocr/PP-OCRv3/web/README_CN.md b/examples/vision/ocr/PP-OCRv3/web/README_CN.md new file mode 100644 index 0000000000..a383f8c525 --- /dev/null +++ b/examples/vision/ocr/PP-OCRv3/web/README_CN.md @@ -0,0 +1,40 @@ +[English](README.md) | 简体中文 +# PP-OCRv3 前端部署示例 + +本节介绍部署PaddleOCR的PP-OCRv3模型在浏览器中运行，以及@paddle-js-models/ocr npm包中的js接口。 + + +## 前端部署PP-OCRv3模型 + +PP-OCRv3模型web demo使用[**参考文档**](../../../../application/js/web_demo/) + + +## PP-OCRv3 js接口 + +``` +import * as ocr from "@paddle-js-models/ocr"; +await ocr.init(detConfig, recConfig); +const res = await ocr.recognize(img, option, postConfig); +``` +ocr模型加载和初始化，其中模型为Paddle.js模型格式，js模型转换方式参考[文档](../../../../application/js/web_demo/README.md) + +**init函数参数** + +> * **detConfig**(dict): 文本检测模型配置参数，默认值为 {modelPath: 'https://js-models.bj.bcebos.com/PaddleOCR/PP-OCRv3/ch_PP-OCRv3_det_infer_js_960/model.json', fill: '#fff', mean: [0.485, 0.456, 0.406],std: [0.229, 0.224, 0.225]}; 其中，modelPath为文本检测模型路径，fill 为图像预处理padding的值，mean和std分别为预处理的均值和标准差 +> * **recConfig**(dict)): 文本识别模型配置参数，默认值为 {modelPath: 'https://js-models.bj.bcebos.com/PaddleOCR/PP-OCRv3/ch_PP-OCRv3_rec_infer_js/model.json', fill: '#000', mean: [0.5, 0.5, 0.5], std: [0.5, 0.5, 0.5]}; 其中，modelPath为文本检测模型路径，fill 为图像预处理padding的值，mean和std分别为预处理的均值和标准差 + + +**recognize函数参数** + +> * **img**(HTMLImageElement): 输入图像参数，类型为HTMLImageElement。 +> * **option**(dict): 可视化文本检测框的canvas参数，可不用设置。 +> * **postConfig**(dict): 文本检测后处理参数，默认值为：{shape: 960, thresh: 0.3, box_thresh: 0.6, unclip_ratio:1.5}; thresh是输出预测图的二值化阈值；box_thresh是输出框的阈值，低于此值的预测框会被丢弃，unclip_ratio是输出框扩大的比例。 + + +## 其它文档 + +- [PP-OCR 系列模型介绍](../../) +- [PP-OCRv3 C++部署](../cpp) +- [模型预测结果说明](../../../../../docs/api/vision_results/) +- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md) +- [PP-OCRv3 微信小程序部署文档](../mini_program/) diff --git a/examples/vision/ocr/README.md b/examples/vision/ocr/README.md index 22a72a0bbe..97f0d61460 100644 --- a/examples/vision/ocr/README.md +++ b/examples/vision/ocr/README.md @@ -1,19 +1,20 @@ -# PaddleOCR 模型部署 +English | [简体中文](README_CN.md) +# PaddleOCR Model Deployment -## PaddleOCR为多个模型组合串联任务，包含 -- 文本检测 `DBDetector` -- [可选]方向分类 `Classifer` 用于调整进入文字识别前的图像方向 -- 文字识别 `Recognizer` 用于从图像中识别出文字 +## PaddleOCR contains a series of tasks with multiple models, including +- Text detection `DBDetector` +- [Optional] Direction classification `Classifer` is used to adjust the direction of images before text recognition +- Character recognition `Recognizer` is used to recognize characters from images -根据不同场景, FastDeploy汇总提供如下OCR任务部署, 用户需同时下载3个模型与字典文件（或2个，分类器可选), 完成OCR整个预测流程 +According to different scenarios, FastDeploy provides the following OCR task deployment. Users need to download three models and dictionary files (or two, optional classifier) simultaneously to complete the entire OCR prediction process -### PP-OCR 中英文系列模型 -下表中的模型下载链接由PaddleOCR模型库提供, 详见[PP-OCR系列模型列表](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.6/doc/doc_ch/models_list.md) +### PP-OCR Model in English and Chinese Scenarios +The model download links in the following table are provided by PaddleOCR model library. Refer to [PP-OCR Model List](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.6/doc/doc_ch/models_list.md) for details -| OCR版本 | 文本框检测 | 方向分类模型 | 文字识别 |字典文件| 说明 | +| OCR version | Text box detection | Direction classification model | Character recognition | Dictionary file | Note | |:----|:----|:----|:----|:----|:--------| -| ch_PP-OCRv3[推荐] |[ch_PP-OCRv3_det](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar) | [ch_ppocr_mobile_v2.0_cls](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) | [ch_PP-OCRv3_rec](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar) | [ppocr_keys_v1.txt](https://bj.bcebos.com/paddlehub/fastdeploy/ppocr_keys_v1.txt) | OCRv3系列原始超轻量模型，支持中英文、多语种文本检测 | -| en_PP-OCRv3[推荐] |[en_PP-OCRv3_det](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_infer.tar) | [ch_ppocr_mobile_v2.0_cls](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) | [en_PP-OCRv3_rec](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_infer.tar) | [en_dict.txt](https://bj.bcebos.com/paddlehub/fastdeploy/en_dict.txt) | OCRv3系列原始超轻量模型，支持英文与数字识别，除检测模型和识别模型的训练数据与中文模型不同以外，无其他区别 | -| ch_PP-OCRv2 |[ch_PP-OCRv2_det](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar) | [ch_ppocr_mobile_v2.0_cls](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) | [ch_PP-OCRv2_rec](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar) | [ppocr_keys_v1.txt](https://bj.bcebos.com/paddlehub/fastdeploy/ppocr_keys_v1.txt) | OCRv2系列原始超轻量模型，支持中英文、多语种文本检测 | -| ch_PP-OCRv2_mobile |[ch_ppocr_mobile_v2.0_det](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) | [ch_ppocr_mobile_v2.0_cls](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) | [ch_ppocr_mobile_v2.0_rec](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) | [ppocr_keys_v1.txt](https://bj.bcebos.com/paddlehub/fastdeploy/ppocr_keys_v1.txt) | OCRv2系列原始超轻量模型，支持中英文、多语种文本检测,比PPOCRv2更加轻量 | -| ch_PP-OCRv2_server |[ch_ppocr_server_v2.0_det](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) | [ch_ppocr_mobile_v2.0_cls](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) | [ch_ppocr_server_v2.0_rec](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) |[ppocr_keys_v1.txt](https://bj.bcebos.com/paddlehub/fastdeploy/ppocr_keys_v1.txt) | OCRv2服务器系列模型, 支持中英文、多语种文本检测，比超轻量模型更大，但效果更好| +| ch_PP-OCRv3[Recommended] |[ch_PP-OCRv3_det](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar) | [ch_ppocr_mobile_v2.0_cls](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) | [ch_PP-OCRv3_rec](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar) | [ppocr_keys_v1.txt](https://bj.bcebos.com/paddlehub/fastdeploy/ppocr_keys_v1.txt) | OCRv3 Original Ultra-Lightweight Model supports text detection in Chinese, English and multiple languages | +| en_PP-OCRv3[Recommended] |[en_PP-OCRv3_det](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_infer.tar) | [ch_ppocr_mobile_v2.0_cls](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) | [en_PP-OCRv3_rec](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_infer.tar) | [en_dict.txt](https://bj.bcebos.com/paddlehub/fastdeploy/en_dict.txt) | OCRv3 Original Ultra-Lightweight Model supports English and digital recognition. Its training data of detection model and recognition model is different from that of Chinese model, and no other differences can be detected | +| ch_PP-OCRv2 |[ch_PP-OCRv2_det](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar) | [ch_ppocr_mobile_v2.0_cls](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) | [ch_PP-OCRv2_rec](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar) | [ppocr_keys_v1.txt](https://bj.bcebos.com/paddlehub/fastdeploy/ppocr_keys_v1.txt) | OCRv2 Original Ultra-Lightweight Model supports text detection in Chinese, English and multiple languages | +| ch_PP-OCRv2_mobile |[ch_ppocr_mobile_v2.0_det](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) | [ch_ppocr_mobile_v2.0_cls](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) | [ch_ppocr_mobile_v2.0_rec](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) | [ppocr_keys_v1.txt](https://bj.bcebos.com/paddlehub/fastdeploy/ppocr_keys_v1.txt) | OCRv2 Original Ultra-Lightweight Model Supports text detection in Chinese, English and multiple languages with lighter weight than PPOCRv2 | +| ch_PP-OCRv2_server |[ch_ppocr_server_v2.0_det](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) | [ch_ppocr_mobile_v2.0_cls](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) | [ch_ppocr_server_v2.0_rec](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) |[ppocr_keys_v1.txt](https://bj.bcebos.com/paddlehub/fastdeploy/ppocr_keys_v1.txt) | OCRv2 Server Model supports text detection in Chinese, English and multiple languages. It has better effects though being larger than the ultra-lightweight model | diff --git a/examples/vision/ocr/README_CN.md b/examples/vision/ocr/README_CN.md new file mode 100644 index 0000000000..9cf63c52d4 --- /dev/null +++ b/examples/vision/ocr/README_CN.md @@ -0,0 +1,20 @@ +[English](README.md) | 简体中文 +# PaddleOCR 模型部署 + +## PaddleOCR为多个模型组合串联任务，包含 +- 文本检测 `DBDetector` +- [可选]方向分类 `Classifer` 用于调整进入文字识别前的图像方向 +- 文字识别 `Recognizer` 用于从图像中识别出文字 + +根据不同场景, FastDeploy汇总提供如下OCR任务部署, 用户需同时下载3个模型与字典文件（或2个，分类器可选), 完成OCR整个预测流程 + +### PP-OCR 中英文系列模型 +下表中的模型下载链接由PaddleOCR模型库提供, 详见[PP-OCR系列模型列表](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.6/doc/doc_ch/models_list.md) + +| OCR版本 | 文本框检测 | 方向分类模型 | 文字识别 |字典文件| 说明 | +|:----|:----|:----|:----|:----|:--------| +| ch_PP-OCRv3[推荐] |[ch_PP-OCRv3_det](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar) | [ch_ppocr_mobile_v2.0_cls](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) | [ch_PP-OCRv3_rec](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar) | [ppocr_keys_v1.txt](https://bj.bcebos.com/paddlehub/fastdeploy/ppocr_keys_v1.txt) | OCRv3系列原始超轻量模型，支持中英文、多语种文本检测 | +| en_PP-OCRv3[推荐] |[en_PP-OCRv3_det](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_infer.tar) | [ch_ppocr_mobile_v2.0_cls](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) | [en_PP-OCRv3_rec](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_infer.tar) | [en_dict.txt](https://bj.bcebos.com/paddlehub/fastdeploy/en_dict.txt) | OCRv3系列原始超轻量模型，支持英文与数字识别，除检测模型和识别模型的训练数据与中文模型不同以外，无其他区别 | +| ch_PP-OCRv2 |[ch_PP-OCRv2_det](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar) | [ch_ppocr_mobile_v2.0_cls](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) | [ch_PP-OCRv2_rec](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar) | [ppocr_keys_v1.txt](https://bj.bcebos.com/paddlehub/fastdeploy/ppocr_keys_v1.txt) | OCRv2系列原始超轻量模型，支持中英文、多语种文本检测 | +| ch_PP-OCRv2_mobile |[ch_ppocr_mobile_v2.0_det](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) | [ch_ppocr_mobile_v2.0_cls](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) | [ch_ppocr_mobile_v2.0_rec](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) | [ppocr_keys_v1.txt](https://bj.bcebos.com/paddlehub/fastdeploy/ppocr_keys_v1.txt) | OCRv2系列原始超轻量模型，支持中英文、多语种文本检测,比PPOCRv2更加轻量 | +| ch_PP-OCRv2_server |[ch_ppocr_server_v2.0_det](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) | [ch_ppocr_mobile_v2.0_cls](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) | [ch_ppocr_server_v2.0_rec](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) |[ppocr_keys_v1.txt](https://bj.bcebos.com/paddlehub/fastdeploy/ppocr_keys_v1.txt) | OCRv2服务器系列模型, 支持中英文、多语种文本检测，比超轻量模型更大，但效果更好| diff --git a/examples/vision/segmentation/paddleseg/README.md b/examples/vision/segmentation/paddleseg/README.md index 0b0cda349f..de578cb226 100644 --- a/examples/vision/segmentation/paddleseg/README.md +++ b/examples/vision/segmentation/paddleseg/README.md @@ -1,47 +1,49 @@ -# PaddleSeg 模型部署 +English | [简体中文](README_CN.md) +# PaddleSeg Model Deployment -## 模型版本说明 +## Model Description - [PaddleSeg develop](https://github.com/PaddlePaddle/PaddleSeg/tree/develop) -目前FastDeploy支持如下模型的部署 +FastDeploy currently supports the deployment of the following models -- [U-Net系列模型](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/configs/unet/README.md) -- [PP-LiteSeg系列模型](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/configs/pp_liteseg/README.md) -- [PP-HumanSeg系列模型](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/contrib/PP-HumanSeg/README.md) -- [FCN系列模型](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/configs/fcn/README.md) -- [DeepLabV3系列模型](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/configs/deeplabv3/README.md) +- [U-Net models](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/configs/unet/README.md) +- [PP-LiteSeg models](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/configs/pp_liteseg/README.md) +- [PP-HumanSeg models](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/contrib/PP-HumanSeg/README.md) +- [FCN models](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/configs/fcn/README.md) +- [DeepLabV3 models](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/configs/deeplabv3/README.md) -【注意】如你部署的为**PP-Matting**、**PP-HumanMatting**以及**ModNet**请参考[Matting模型部署](../../matting) +【Attention】For **PP-Matting**、**PP-HumanMatting** and **ModNet** deployment, please refer to [Matting Model Deployment](../../matting) -## 准备PaddleSeg部署模型 +## Prepare PaddleSeg Deployment Model -PaddleSeg模型导出，请参考其文档说明[模型导出](https://github.com/PaddlePaddle/PaddleSeg/blob/develop/docs/model_export_cn.md) +For the export of the PaddleSeg model, refer to [Model Export](https://github.com/PaddlePaddle/PaddleSeg/blob/develop/docs/model_export_cn.md) for more information -**注意** -- PaddleSeg导出的模型包含`model.pdmodel`、`model.pdiparams`和`deploy.yaml`三个文件，FastDeploy会从yaml文件中获取模型在推理时需要的预处理信息 +**Attention** +- The exported PaddleSeg model contains three files, including `model.pdmodel`、`model.pdiparams` and `deploy.yaml`. FastDeploy will get the pre-processing information for inference from yaml files. -## 下载预训练模型 +## Download Pre-trained Model -为了方便开发者的测试，下面提供了PaddleSeg导出的部分模型 -- without-argmax导出方式为：**不指定**`--input_shape`，**指定**`--output_op none` -- with-argmax导出方式为：**不指定**`--input_shape`，**指定**`--output_op argmax` +For developers' testing, part of the PaddleSeg exported models are provided below. +- without-argmax export mode: **Not specified**`--input_shape`，**specified**`--output_op none` +- with-argmax export mode：**Not specified**`--input_shape`，**specified**`--output_op argmax` -开发者可直接下载使用。 +Developers can download directly. -| 模型 | 参数文件大小 |输入Shape | mIoU | mIoU (flip) | mIoU (ms+flip) | + +| Model | Parameter Size | Input Shape | mIoU | mIoU (flip) | mIoU (ms+flip) | |:---------------------------------------------------------------- |:----- |:----- | :----- | :----- | :----- | | [Unet-cityscapes-with-argmax](https://bj.bcebos.com/paddlehub/fastdeploy/Unet_cityscapes_with_argmax_infer.tgz) \| [Unet-cityscapes-without-argmax](https://bj.bcebos.com/paddlehub/fastdeploy/Unet_cityscapes_without_argmax_infer.tgz) | 52MB | 1024x512 | 65.00% | 66.02% | 66.89% | | [PP-LiteSeg-B(STDC2)-cityscapes-with-argmax](https://bj.bcebos.com/paddlehub/fastdeploy/PP_LiteSeg_B_STDC2_cityscapes_with_argmax_infer.tgz) \| [PP-LiteSeg-B(STDC2)-cityscapes-without-argmax](https://bj.bcebos.com/paddlehub/fastdeploy/PP_LiteSeg_B_STDC2_cityscapes_without_argmax_infer.tgz) | 31MB | 1024x512 | 79.04% | 79.52% | 79.85% | -|[PP-HumanSegV1-Lite-with-argmax(通用人像分割模型)](https://bj.bcebos.com/paddlehub/fastdeploy/Portrait_PP_HumanSegV1_Lite_with_argmax_infer.tgz) \| [PP-HumanSegV1-Lite-without-argmax(通用人像分割模型)](https://bj.bcebos.com/paddlehub/fastdeploy/PP_HumanSegV1_Lite_infer.tgz) | 543KB | 192x192 | 86.2% | - | - | -|[PP-HumanSegV2-Lite-with-argmax(通用人像分割模型)](https://bj.bcebos.com/paddlehub/fastdeploy/PP_HumanSegV2_Lite_192x192_with_argmax_infer.tgz) \| [PP-HumanSegV2-Lite-without-argmax(通用人像分割模型)](https://bj.bcebos.com/paddlehub/fastdeploy/PP_HumanSegV2_Lite_192x192_infer.tgz) | 12MB | 192x192 | 92.52% | - | - | -| [PP-HumanSegV2-Mobile-with-argmax(通用人像分割模型)](https://bj.bcebos.com/paddlehub/fastdeploy/PP_HumanSegV2_Mobile_192x192_with_argmax_infer.tgz) \| [PP-HumanSegV2-Mobile-without-argmax(通用人像分割模型)](https://bj.bcebos.com/paddlehub/fastdeploy/PP_HumanSegV2_Mobile_192x192_infer.tgz) | 29MB | 192x192 | 93.13% | - | - | -|[PP-HumanSegV1-Server-with-argmax(通用人像分割模型)](https://bj.bcebos.com/paddlehub/fastdeploy/PP_HumanSegV1_Server_with_argmax_infer.tgz) \| [PP-HumanSegV1-Server-without-argmax(通用人像分割模型)](https://bj.bcebos.com/paddlehub/fastdeploy/PP_HumanSegV1_Server_infer.tgz) | 103MB | 512x512 | 96.47% | - | - | -| [Portait-PP-HumanSegV2-Lite-with-argmax(肖像分割模型)](https://bj.bcebos.com/paddlehub/fastdeploy/Portrait_PP_HumanSegV2_Lite_256x144_with_argmax_infer.tgz) \| [Portait-PP-HumanSegV2-Lite-without-argmax(肖像分割模型)](https://bj.bcebos.com/paddlehub/fastdeploy/Portrait_PP_HumanSegV2_Lite_256x144_infer.tgz) | 3.6M | 256x144 | 96.63% | - | - | -| [FCN-HRNet-W18-cityscapes-with-argmax](https://bj.bcebos.com/paddlehub/fastdeploy/FCN_HRNet_W18_cityscapes_with_argmax_infer.tgz) \| [FCN-HRNet-W18-cityscapes-without-argmax](https://bj.bcebos.com/paddlehub/fastdeploy/FCN_HRNet_W18_cityscapes_without_argmax_infer.tgz)(暂时不支持ONNXRuntime的GPU推理) | 37MB | 1024x512 | 78.97% | 79.49% | 79.74% | +|[PP-HumanSegV1-Lite-with-argmax(General Portrait Segmentation Model)](https://bj.bcebos.com/paddlehub/fastdeploy/Portrait_PP_HumanSegV1_Lite_with_argmax_infer.tgz) \| [PP-HumanSegV1-Lite-without-argmax(General Portrait Segmentation Model)](https://bj.bcebos.com/paddlehub/fastdeploy/PP_HumanSegV1_Lite_infer.tgz) | 543KB | 192x192 | 86.2% | - | - | +|[PP-HumanSegV2-Lite-with-argmax(General Portrait Segmentation Model)](https://bj.bcebos.com/paddlehub/fastdeploy/PP_HumanSegV2_Lite_192x192_with_argmax_infer.tgz) \| [PP-HumanSegV2-Lite-without-argmax(General Portrait Segmentation Model)](https://bj.bcebos.com/paddlehub/fastdeploy/PP_HumanSegV2_Lite_192x192_infer.tgz) | 12MB | 192x192 | 92.52% | - | - | +| [PP-HumanSegV2-Mobile-with-argmax(General Portrait Segmentation Model)](https://bj.bcebos.com/paddlehub/fastdeploy/PP_HumanSegV2_Mobile_192x192_with_argmax_infer.tgz) \| [PP-HumanSegV2-Mobile-without-argmax(General Portrait Segmentation Model)](https://bj.bcebos.com/paddlehub/fastdeploy/PP_HumanSegV2_Mobile_192x192_infer.tgz) | 29MB | 192x192 | 93.13% | - | - | +|[PP-HumanSegV1-Server-with-argmax(General Portrait Segmentation Model)](https://bj.bcebos.com/paddlehub/fastdeploy/PP_HumanSegV1_Server_with_argmax_infer.tgz) \| [PP-HumanSegV1-Server-without-argmax(General Portrait Segmentation Model)](https://bj.bcebos.com/paddlehub/fastdeploy/PP_HumanSegV1_Server_infer.tgz) | 103MB | 512x512 | 96.47% | - | - | +| [Portait-PP-HumanSegV2-Lite-with-argmax(Portrait Segmentation Model)](https://bj.bcebos.com/paddlehub/fastdeploy/Portrait_PP_HumanSegV2_Lite_256x144_with_argmax_infer.tgz) \| [Portait-PP-HumanSegV2-Lite-without-argmax(Portrait Segmentation Model)](https://bj.bcebos.com/paddlehub/fastdeploy/Portrait_PP_HumanSegV2_Lite_256x144_infer.tgz) | 3.6M | 256x144 | 96.63% | - | - | +| [FCN-HRNet-W18-cityscapes-with-argmax](https://bj.bcebos.com/paddlehub/fastdeploy/FCN_HRNet_W18_cityscapes_with_argmax_infer.tgz) \| [FCN-HRNet-W18-cityscapes-without-argmax](https://bj.bcebos.com/paddlehub/fastdeploy/FCN_HRNet_W18_cityscapes_without_argmax_infer.tgz)(GPU inference for ONNXRuntime is not supported now) | 37MB | 1024x512 | 78.97% | 79.49% | 79.74% | | [Deeplabv3-ResNet101-OS8-cityscapes-with-argmax](https://bj.bcebos.com/paddlehub/fastdeploy/Deeplabv3_ResNet101_OS8_cityscapes_with_argmax_infer.tgz) \| [Deeplabv3-ResNet101-OS8-cityscapes-without-argmax](https://bj.bcebos.com/paddlehub/fastdeploy/Deeplabv3_ResNet101_OS8_cityscapes_without_argmax_infer.tgz) | 150MB | 1024x512 | 79.90% | 80.22% | 80.47% | -## 详细部署文档 +## Detailed Deployment Tutorials -- [Python部署](python) -- [C++部署](cpp) +- [Python Deployment](python) +- [C++ Deployment](cpp) diff --git a/examples/vision/segmentation/paddleseg/README_CN.md b/examples/vision/segmentation/paddleseg/README_CN.md new file mode 100644 index 0000000000..7306a5f4f8 --- /dev/null +++ b/examples/vision/segmentation/paddleseg/README_CN.md @@ -0,0 +1,34 @@ +[English](README.md) | 简体中文 +# 视觉模型部署 + +本目录下提供了各类视觉模型的部署，主要涵盖以下任务类型 + +| 任务类型 | 说明 | 预测结果结构体 | +|:-------------- |:----------------------------------- |:-------------------------------------------------------------------------------- | +| Detection | 目标检测，输入图像，检测图像中物体位置，并返回检测框坐标及类别和置信度 | [DetectionResult](../../docs/api/vision_results/detection_result.md) | +| Segmentation | 语义分割，输入图像，给出图像中每个像素的分类及置信度 | [SegmentationResult](../../docs/api/vision_results/segmentation_result.md) | +| Classification | 图像分类，输入图像，给出图像的分类结果和置信度 | [ClassifyResult](../../docs/api/vision_results/classification_result.md) | +| FaceDetection | 人脸检测，输入图像，检测图像中人脸位置，并返回检测框坐标及人脸关键点 | [FaceDetectionResult](../../docs/api/vision_results/face_detection_result.md) | +| FaceAlignment | 人脸对齐(人脸关键点检测)，输入图像，返回人脸关键点 | [FaceAlignmentResult](../../docs/api/vision_results/face_alignment_result.md) | +| KeypointDetection | 关键点检测，输入图像，返回图像中人物行为的各个关键点坐标和置信度 | [KeyPointDetectionResult](../../docs/api/vision_results/keypointdetection_result.md) | +| FaceRecognition | 人脸识别，输入图像，返回可用于相似度计算的人脸特征的embedding | [FaceRecognitionResult](../../docs/api/vision_results/face_recognition_result.md) | +| Matting | 抠图，输入图像，返回图片的前景每个像素点的Alpha值 | [MattingResult](../../docs/api/vision_results/matting_result.md) | +| OCR | 文本框检测，分类，文本框内容识别，输入图像，返回文本框坐标，文本框的方向类别以及框内的文本内容 | [OCRResult](../../docs/api/vision_results/ocr_result.md) | +| MOT | 多目标跟踪，输入图像，检测图像中物体位置，并返回检测框坐标，对象id及类别置信度 | [MOTResult](../../docs/api/vision_results/mot_result.md) | +| HeadPose | 头部姿态估计，返回头部欧拉角 | [HeadPoseResult](../../docs/api/vision_results/headpose_result.md) | + +## FastDeploy API设计 + +视觉模型具有较有统一任务范式，在设计API时（包括C++/Python），FastDeploy将视觉模型的部署拆分为四个步骤 + +- 模型加载 +- 图像预处理 +- 模型推理 +- 推理结果后处理 + +FastDeploy针对飞桨的视觉套件，以及外部热门模型，提供端到端的部署服务，用户只需准备模型，按以下步骤即可完成整个模型的部署 + +- 加载模型 +- 调用`predict`接口 + +FastDeploy在各视觉模型部署时，也支持一键切换后端推理引擎，详情参阅[如何切换模型推理引擎](../../docs/cn/faq/how_to_change_backend.md)。 diff --git a/examples/vision/segmentation/paddleseg/a311d/README.md b/examples/vision/segmentation/paddleseg/a311d/README.md index 3fbf6ed5e0..07870aa590 100755 --- a/examples/vision/segmentation/paddleseg/a311d/README.md +++ b/examples/vision/segmentation/paddleseg/a311d/README.md @@ -1,11 +1,12 @@ -# PP-LiteSeg 量化模型在 A311D 上的部署 -目前 FastDeploy 已经支持基于 Paddle Lite 部署 PP-LiteSeg 量化模型到 A311D 上。 +English | [简体中文](README_CN.md) +# Deployment of PP-LiteSeg Quantification Model on A311D +Now FastDeploy allows deploying PP-LiteSeg quantization model to A311D based on Paddle Lite. -模型的量化和量化模型的下载请参考：[模型量化](../quantize/README.md) +For model quantization and download of quantized models, refer to [Model Quantization](../quantize/README.md) -## 详细部署文档 +## Detailed Deployment Tutorials -在 A311D 上只支持 C++ 的部署。 +Only C++ deployment is supported on A311D. -- [C++部署](cpp) +- [C++ deployment](cpp) diff --git a/examples/vision/segmentation/paddleseg/a311d/README_CN.md b/examples/vision/segmentation/paddleseg/a311d/README_CN.md new file mode 100644 index 0000000000..dad4f39248 --- /dev/null +++ b/examples/vision/segmentation/paddleseg/a311d/README_CN.md @@ -0,0 +1,12 @@ +[English](README.md) | 简体中文 +# PP-LiteSeg 量化模型在 A311D 上的部署 +目前 FastDeploy 已经支持基于 Paddle Lite 部署 PP-LiteSeg 量化模型到 A311D 上。 + +模型的量化和量化模型的下载请参考：[模型量化](../quantize/README.md) + + +## 详细部署文档 + +在 A311D 上只支持 C++ 的部署。 + +- [C++部署](cpp) diff --git a/examples/vision/segmentation/paddleseg/cpp/README.md b/examples/vision/segmentation/paddleseg/cpp/README.md index 07f9f4c62d..4c5be9f6c1 100755 --- a/examples/vision/segmentation/paddleseg/cpp/README.md +++ b/examples/vision/segmentation/paddleseg/cpp/README.md @@ -1,57 +1,53 @@ -# PaddleSeg C++部署示例 +English | [简体中文](README_CN.md) +# PaddleSeg C++ Deployment Example -本目录下提供`infer.cc`快速完成Unet在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。 +This directory provides examples that `infer.cc` fast finishes the deployment of Unet on CPU/GPU and GPU accelerated by TensorRT. -在部署前，需确认以下两个步骤 +Before deployment, two steps require confirmation -- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md) -- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md) +- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md) +- 2. Download the precompiled deployment library and samples code according to your development environment. Refer to [FastDeploy Precompiled Library](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md) -【注意】如你部署的为**PP-Matting**、**PP-HumanMatting**以及**ModNet**请参考[Matting模型部署](../../../matting) +【Attention】For the deployment of **PP-Matting**、**PP-HumanMatting** and **ModNet**, refer to [Matting Model Deployment](../../../matting) -以Linux上推理为例，在本目录执行如下命令即可完成编译测试，支持此模型需保证FastDeploy版本1.0.0以上(x.x.x>=1.0.0) +Taking the inference on Linux as an example, the compilation test can be completed by executing the following command in this directory. FastDeploy version 1.0.0 or above (x.x.x>=1.0.0) is required to support this model. ```bash mkdir build cd build -# 下载FastDeploy预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用 +# Download the FastDeploy precompiled library. Users can choose your appropriate version in the `FastDeploy Precompiled Library` mentioned above wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz tar xvf fastdeploy-linux-x64-x.x.x.tgz cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x make -j -# 下载Unet模型文件和测试图片 +# Download Unet model files and test images wget https://bj.bcebos.com/paddlehub/fastdeploy/Unet_cityscapes_without_argmax_infer.tgz tar -xvf Unet_cityscapes_without_argmax_infer.tgz wget https://paddleseg.bj.bcebos.com/dygraph/demo/cityscapes_demo.png -# CPU推理 +# CPU inference ./infer_demo Unet_cityscapes_without_argmax_infer cityscapes_demo.png 0 -# GPU推理 +# GPU inference ./infer_demo Unet_cityscapes_without_argmax_infer cityscapes_demo.png 1 -# GPU上TensorRT推理 +# TensorRT inference on GPU ./infer_demo Unet_cityscapes_without_argmax_infer cityscapes_demo.png 2 -# 昆仑芯XPU推理 +# kunlunxin XPU inference ./infer_demo Unet_cityscapes_without_argmax_infer cityscapes_demo.png 3 -# 华为昇腾推理 -./infer_demo Unet_cityscapes_without_argmax_infer cityscapes_demo.png 4 ``` -运行完成可视化结果如下图所示 +The visualized result after running is as follows
+
+