apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 16:48:03 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[docs][win] add windows c++ sdk demo to examples (#136)

Browse Source 
* [docs] format docs with markdown with language tags

* [docs][win] add windows c++ sdk demo

* [docs][win] add windows c++ sdk demo to examples

* [docs][api] update runtime_option docs
This commit is contained in:
DefTruth
2022-08-22 10:53:00 +08:00
committed by GitHub
parent f7e4b8490f
commit beddcba900
54 changed files with 278 additions and 164 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@@ -63,11 +63,11 @@
- python 3.6\~3.9(Windows 10 3.8\~3.9) - python 3.6\~3.9(Windows 10 3.8\~3.9)
#### 安装 CPU Python 版本 #### 安装 CPU Python 版本
``` ```bash
pip install numpy opencv-python fastdeploy-python -f https://www.paddlepaddle.org.cn/whl/fastdeploy.html pip install numpy opencv-python fastdeploy-python -f https://www.paddlepaddle.org.cn/whl/fastdeploy.html
``` ```
#### 安装 GPU Python 版本 #### 安装 GPU Python 版本
``` ```bash
pip install numpy opencv-python fastdeploy-gpu-python -f https://www.paddlepaddle.org.cn/whl/fastdeploy.html pip install numpy opencv-python fastdeploy-gpu-python -f https://www.paddlepaddle.org.cn/whl/fastdeploy.html
``` ```
#### 安装 C++ 版本 #### 安装 C++ 版本

15
docs/api/runtime_option.md
View File

@@ -15,13 +15,13 @@ FastDeploy产品中的Runtime包含多个推理后端，其各关系如下所示
| GPU | 支持 | 支持 | 支持 | 支持 | | GPU | 支持 | 支持 | 支持 | 支持 |
在各模型的，均通过`RuntimeOption`来配置推理的后端，以及推理时的参数，例如在python中，加载模型后可通过如下代码打印推理配置 在各模型的，均通过`RuntimeOption`来配置推理的后端，以及推理时的参数，例如在python中，加载模型后可通过如下代码打印推理配置
``` ```python
model = fastdeploy.vision.ultralytics.YOLOv5("yolov5s.onnx") model = fastdeploy.vision.detection.YOLOv5("yolov5s.onnx")
print(model.runtime_option) print(model.runtime_option)
``` ```
可看下如下输出 可看下如下输出
``` ```python
RuntimeOption( RuntimeOption(
backend : Backend.ORT # 推理后端ONNXRuntime backend : Backend.ORT # 推理后端ONNXRuntime
cpu_thread_num : 8 # CPU线程数（仅当使用CPU推理时有效） cpu_thread_num : 8 # CPU线程数（仅当使用CPU推理时有效）
@@ -70,7 +70,7 @@ RuntimeOption(
> * **trt_max_shape**(dict[str : list[int]]): 当模型为动态shape，且实际推理时输入shape也会变化，通过此参数配置输入的最大shape > * **trt_max_shape**(dict[str : list[int]]): 当模型为动态shape，且实际推理时输入shape也会变化，通过此参数配置输入的最大shape
> * **trt_max_batch_size**(int): TensorRT推理时的最大batch数 > * **trt_max_batch_size**(int): TensorRT推理时的最大batch数
``` ```python
import fastdeploy as fd import fastdeploy as fd
option = fd.RuntimeOption() option = fd.RuntimeOption()
@@ -81,7 +81,8 @@ option.trt_min_shape = {"x": [1, 3, 224, 224]}
option.trt_opt_shape = {"x": [4, 3, 224, 224]} option.trt_opt_shape = {"x": [4, 3, 224, 224]}
option.trt_max_shape = {"x": [8, 3, 224, 224]} option.trt_max_shape = {"x": [8, 3, 224, 224]}
model = fd.vision.ppcls.Model("resnet50/inference.pdmodel", model = fd.vision.classification.PaddleClasModel(
"resnet50/inference.pdmodel",
"resnet50/inference.pdiparams", "resnet50/inference.pdiparams",
"resnet50/inference_cls.yaml", "resnet50/inference_cls.yaml",
runtime_option=option) runtime_option=option)
@@ -112,7 +113,7 @@ model = fd.vision.ppcls.Model("resnet50/inference.pdmodel",
> * **trt_max_shape**(map<string, vector<int>>): 当模型为动态shape，且实际推理时输入shape也会变化，通过此参数配置输入的最大shape > * **trt_max_shape**(map<string, vector<int>>): 当模型为动态shape，且实际推理时输入shape也会变化，通过此参数配置输入的最大shape
> * **trt_max_batch_size**(int): TensorRT推理时的最大batch数 > * **trt_max_batch_size**(int): TensorRT推理时的最大batch数
``` ```c++
#include "fastdeploy/vision.h" #include "fastdeploy/vision.h"
int main() { int main() {
@@ -121,7 +122,7 @@ int main() {
option.trt_opt_shape["x"] = {4, 3, 224, 224}; option.trt_opt_shape["x"] = {4, 3, 224, 224};
option.trt_max_shape["x"] = {8, 3, 224, 224}; option.trt_max_shape["x"] = {8, 3, 224, 224};
auto model = fastdeploy::vision::ppcls.Model( auto model = fastdeploy::vision::classification::PaddleClasModel(
"resnet50/inference.pdmodel", "resnet50/inference.pdmodel",
"resnet50/inference.pdiparams", "resnet50/inference.pdiparams",
"resnet50/inference_cls.yaml", "resnet50/inference_cls.yaml",

2
docs/api/vision_results/classification_result.md
View File

@@ -6,7 +6,7 @@ ClassifyResult代码定义在`csrcs/fastdeploy/vision/common/result.h`中，用
`fastdeploy::vision::ClassifyResult` `fastdeploy::vision::ClassifyResult`
``` ```c++
struct ClassifyResult { struct ClassifyResult {
std::vector<int32_t> label_ids; std::vector<int32_t> label_ids;
std::vector<float> scores; std::vector<float> scores;

2
docs/api/vision_results/detection_result.md
View File

@@ -6,7 +6,7 @@ DetectionResult代码定义在`csrcs/fastdeploy/vision/common/result.h`中，用
`fastdeploy::vision::DetectionResult` `fastdeploy::vision::DetectionResult`
``` ```c++
struct DetectionResult { struct DetectionResult {
std::vector<std::array<float, 4>> boxes; std::vector<std::array<float, 4>> boxes;
std::vector<float> scores; std::vector<float> scores;

3
docs/api/vision_results/face_detection_result.md
View File

@@ -6,7 +6,7 @@ FaceDetectionResult 代码定义在`csrcs/fastdeploy/vision/common/result.h`中
`fastdeploy::vision::FaceDetectionResult` `fastdeploy::vision::FaceDetectionResult`
``` ```c++
struct FaceDetectionResult { struct FaceDetectionResult {
std::vector<std::array<float, 4>> boxes; std::vector<std::array<float, 4>> boxes;
std::vector<std::array<float, 2>> landmarks; std::vector<std::array<float, 2>> landmarks;
@@ -32,4 +32,3 @@ struct FaceDetectionResult {
- **scores**(list of float): 成员变量，表示单张图片检测出来的所有目标置信度 - **scores**(list of float): 成员变量，表示单张图片检测出来的所有目标置信度
- **landmarks**(list of list(float)): 成员变量，表示单张图片检测出来的所有人脸的关键点 - **landmarks**(list of list(float)): 成员变量，表示单张图片检测出来的所有人脸的关键点
- **landmarks_per_face**(int): 成员变量，表示每个人脸框中的关键点的数量。 - **landmarks_per_face**(int): 成员变量，表示每个人脸框中的关键点的数量。

2
docs/api/vision_results/face_recognition_result.md
View File

@@ -5,7 +5,7 @@ FaceRecognitionResult 代码定义在`csrcs/fastdeploy/vision/common/result.h`
`fastdeploy::vision::FaceRecognitionResult` `fastdeploy::vision::FaceRecognitionResult`
``` ```c++
struct FaceRecognitionResult { struct FaceRecognitionResult {
std::vector<float> embedding; std::vector<float> embedding;
void Clear(); void Clear();

2
docs/api/vision_results/matting_result.md
View File

@@ -6,7 +6,7 @@ MattingResult 代码定义在`csrcs/fastdeploy/vision/common/result.h`中，用
`fastdeploy::vision::MattingResult` `fastdeploy::vision::MattingResult`
``` ```c++
struct MattingResult { struct MattingResult {
std::vector<float> alpha; std::vector<float> alpha;
std::vector<float> foreground; std::vector<float> foreground;

2
docs/api/vision_results/segmentation_result.md
View File

@@ -6,7 +6,7 @@ SegmentationResult代码定义在`csrcs/fastdeploy/vision/common/result.h`中，
`fastdeploy::vision::DetectionResult` `fastdeploy::vision::DetectionResult`
``` ```c++
struct DetectionResult { struct DetectionResult {
std::vector<uint8_t> label_map; std::vector<uint8_t> label_map;
std::vector<float> score_map; std::vector<float> score_map;

4
docs/compile/how_to_build_linux_and_mac.md
View File

@@ -9,7 +9,7 @@
- TensorRT >= 8.4 (当ENABLE_TRT_BACKEND=ON) - TensorRT >= 8.4 (当ENABLE_TRT_BACKEND=ON)
## 编译C++ ## 编译C++
``` ```bash
git clone https://github.com/PaddlePaddle/FastDeploy.git git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy cd FastDeploy
git checkout develop git checkout develop
@@ -23,7 +23,7 @@ make install
编译后的预测库即在当前目录下的`fastdeploy-0.0.3` 编译后的预测库即在当前目录下的`fastdeploy-0.0.3`
## 编译Python安装包 ## 编译Python安装包
``` ```bash
git clone https://github.com/PaddlePaddle/FastDeploy.git git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy cd FastDeploy
git checkout develop git checkout develop

8
docs/compile/how_to_build_windows.md
View File

@@ -3,13 +3,13 @@
## 环境依赖 ## 环境依赖
- cmake >= 3.12 - cmake >= 3.12
- g++ >= 8.2 - Visual Studio 16 2019
- cuda >= 11.2 (当WITH_GPU=ON) - cuda >= 11.2 (当WITH_GPU=ON)
- cudnn >= 11.2 (当WITH_GPU=ON) - cudnn >= 11.2 (当WITH_GPU=ON)
- TensorRT >= 8.4 (当ENABLE_TRT_BACKEND=ON) - TensorRT >= 8.4 (当ENABLE_TRT_BACKEND=ON)
## 获取代码 ## 获取代码
``` ```bat
git clone https://github.com/PaddlePaddle/FastDeploy.git git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy cd FastDeploy
git checkout develop git checkout develop
@@ -19,7 +19,7 @@ git checkout develop
Windows菜单打开`x64 Native Tools Command Prompt for VS 2019`命令工具，其中`CMAKE_INSTALL_PREFIX`用于指定编译后生成的SDK路径 Windows菜单打开`x64 Native Tools Command Prompt for VS 2019`命令工具，其中`CMAKE_INSTALL_PREFIX`用于指定编译后生成的SDK路径
``` ```bat
mkdir build mkdir build
cd build cd build
cmake -G "Visual Studio 16 2019" -A x64 -DCMAKE_INSTALL_PREFIX=D:\Paddle\FastDeploy\build\fastdeploy-win-x64-0.2.0 -DENABLE_ORT_BACKEND=ON -DENABLE_VISION=ON .. cmake -G "Visual Studio 16 2019" -A x64 -DCMAKE_INSTALL_PREFIX=D:\Paddle\FastDeploy\build\fastdeploy-win-x64-0.2.0 -DENABLE_ORT_BACKEND=ON -DENABLE_VISION=ON ..
@@ -31,7 +31,7 @@ msbuild INSTALL.vcxproj /m /p:Configuration=Release /p:Platform=x64
## 编译Python Wheel包 ## 编译Python Wheel包
Python编译时，通过环境变量获取编译选项 Python编译时，通过环境变量获取编译选项
``` ```bat
git clone https://github.com/PaddlePaddle/FastDeploy.git git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy cd FastDeploy
git checkout develop git checkout develop

63
docs/compile/how_to_use_sdk_on_windows.md Normal file
View File

@@ -0,0 +1,63 @@
# 在 Windows 使用 FastDeploy C++ SDK
在 Windows 下使用 FastDeploy C++ SDK 与在 Linux 下使用稍有不同。以下以 PPYOLOE 为例进行演示在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/the%20software%20and%20hardware%20requirements.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/quick_start)
## 环境依赖
- cmake >= 3.12
- Visual Studio 16 2019
- cuda >= 11.2 (当WITH_GPU=ON)
- cudnn >= 11.2 (当WITH_GPU=ON)
- TensorRT >= 8.4 (当ENABLE_TRT_BACKEND=ON)
## 下载 FastDeploy Windows 10 C++ SDK
可以从以下链接下载编译好的 FastDeploy Windows 10 C++ SDK，SDK中包含了examples代码。
```text
https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-win-x64-gpu-0.2.0.zip
```
## 准备模型文件和测试图片
可以从以下链接下载模型文件和测试图片，并解压缩
```text
https://bj.bcebos.com/paddlehub/fastdeploy/ppyoloe_crn_l_300e_coco.tgz # (下载后解压缩)
https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
```
## 在 Windows 上编译 PPYOLOE
Windows菜单打开`x64 Native Tools Command Prompt for VS 2019`命令工具，cd到ppyoloe的demo路径
```bat
cd fastdeploy-win-x64-gpu-0.2.0\examples\vision\detection\paddledetection\cpp
```
```bat
mkdir build && cd build
cmake .. -G "Visual Studio 16 2019" -A x64 -DFASTDEPLOY_INSTALL_DIR=%cd%\..\..\..\..\..\..\..\fastdeploy-win-x64-gpu-0.2.0 -DCUDA_DIRECTORY="C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v11.2"
```
然后执行
```bat
msbuild infer_demo.sln /m:4 /p:Configuration=Release /p:Platform=x64
```
编译好的exe保存在Release目录下，在运行demo前，需要将模型和测试图片拷贝至该目录。另外，需要在终端指定DLL的搜索路径。请在build目录下执行以下命令。
```bat
set FASTDEPLOY_PATH=%cd%\..\..\..\..\..\..\..\fastdeploy-win-x64-gpu-0.2.0
set PATH=%FASTDEPLOY_PATH%\lib;%FASTDEPLOY_PATH%\third_libs\install\onnxruntime\lib;%FASTDEPLOY_PATH%\third_libs\install\opencv-win-x64-3.4.16\build\x64\vc15\bin;%FASTDEPLOY_PATH%\third_libs\install\paddle_inference\paddle\lib;%FASTDEPLOY_PATH%\third_libs\install\paddle_inference\third_party\install\mkldnn\lib;%FASTDEPLOY_PATH%\third_libs\install\paddle_inference\third_party\install\mklml\lib;%FASTDEPLOY_PATH%\third_libs\install\paddle2onnx\lib;%FASTDEPLOY_PATH%\third_libs\install\tensorrt\lib;%FASTDEPLOY_PATH%\third_libs\install\yaml-cpp\lib;%PATH%
```
注意，需要拷贝onnxruntime.dll到exe所在的目录。
```bat
copy /Y %FASTDEPLOY_PATH%\third_libs\install\onnxruntime\lib\onnxruntime* Release\
```
由于较新的Windows在System32系统目录下自带了onnxruntime.dll，因此就算设置了PATH，系统依然会出现onnxruntime的加载冲突。因此需要先拷贝demo用到的onnxruntime.dll到exe所在的目录。
```bat
where onnxruntime.dll
C:\Windows\System32\onnxruntime.dll # windows自带的onnxruntime.dll
```
## 运行 demo
```bat
cd Release
infer_ppyoloe_demo.exe ppyoloe_crn_l_300e_coco 000000014439.jpg 0 # CPU
infer_ppyoloe_demo.exe ppyoloe_crn_l_300e_coco 000000014439.jpg 1 # GPU
infer_ppyoloe_demo.exe ppyoloe_crn_l_300e_coco 000000014439.jpg 2 # GPU + TensorRT
```

2
docs/develop.md
View File

@@ -1,7 +1,7 @@
# 代码提交说明 # 代码提交说明
FastDeploy使用clang-format, cpplint检查和格式化代码，提交代码前，需安装pre-commit FastDeploy使用clang-format, cpplint检查和格式化代码，提交代码前，需安装pre-commit
``` ```bash
git clone https://github.com/PaddlePaddle/FastDeploy.git git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy cd FastDeploy
git checkout develop git checkout develop

4
docs/quick_start/Python_prebuilt_wheels.md
View File

@@ -9,11 +9,11 @@ FastDeploy提供了在Windows/Linux/Mac上的预先编译Python Wheel包，开
- Mac 支持Python3.6~3.9 - Mac 支持Python3.6~3.9
## 安装 CPU Python 版本 ## 安装 CPU Python 版本
``` ```bash
pip install fastdeploy-python -f https://www.paddlepaddle.org.cn/whl/fastdeploy.html pip install fastdeploy-python -f https://www.paddlepaddle.org.cn/whl/fastdeploy.html
``` ```
## 安装 GPU Python 版本 ## 安装 GPU Python 版本
``` ```bash
pip install fastdeploy-gpu-python -f https://www.paddlepaddle.org.cn/whl/fastdeploy.html pip install fastdeploy-gpu-python -f https://www.paddlepaddle.org.cn/whl/fastdeploy.html
``` ```

9
examples/vision/classification/paddleclas/cpp/README.md
View File

@@ -9,7 +9,7 @@
以Linux上ResNet50_vd推理为例，在本目录执行如下命令即可完成编译测试 以Linux上ResNet50_vd推理为例，在本目录执行如下命令即可完成编译测试
``` ```bash
#下载SDK，编译模型examples代码（SDK中包含了examples代码） #下载SDK，编译模型examples代码（SDK中包含了examples代码）
wget https://bj.bcebos.com/paddlehub/fastdeploy/libs/0.2.0/fastdeploy-linux-x64-gpu-0.2.0.tgz wget https://bj.bcebos.com/paddlehub/fastdeploy/libs/0.2.0/fastdeploy-linux-x64-gpu-0.2.0.tgz
tar xvf fastdeploy-linux-x64-gpu-0.2.0.tgz tar xvf fastdeploy-linux-x64-gpu-0.2.0.tgz
@@ -33,11 +33,14 @@ wget https://gitee.com/paddlepaddle/PaddleClas/raw/release/2.4/deploy/images/Ima
./infer_demo ResNet50_vd_infer ILSVRC2012_val_00000010.jpeg 2 ./infer_demo ResNet50_vd_infer ILSVRC2012_val_00000010.jpeg 2
``` ```
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/compile/how_to_use_sdk_on_windows.md)
## PaddleClas C++接口 ## PaddleClas C++接口
### PaddleClas类 ### PaddleClas类
``` ```c++
fastdeploy::vision::classification::PaddleClasModel( fastdeploy::vision::classification::PaddleClasModel(
const string& model_file, const string& model_file,
const string& params_file, const string& params_file,
@@ -58,7 +61,7 @@ PaddleClas模型加载和初始化，其中model_file, params_file为训练模
#### Predict函数 #### Predict函数
> ``` > ```c++
> PaddleClasModel::Predict(cv::Mat* im, ClassifyResult* result, int topk = 1) > PaddleClasModel::Predict(cv::Mat* im, ClassifyResult* result, int topk = 1)
> ``` > ```
> >

8
examples/vision/classification/paddleclas/python/README.md
View File

@@ -7,7 +7,7 @@
本目录下提供`infer.py`快速完成ResNet50_vd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 本目录下提供`infer.py`快速完成ResNet50_vd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 #下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/vision/classification/paddleclas/python cd FastDeploy/examples/vision/classification/paddleclas/python
@@ -26,7 +26,7 @@ python infer.py --model ResNet50_vd_infer --image ILSVRC2012_val_00000010.jpeg -
``` ```
运行完成后返回结果如下所示 运行完成后返回结果如下所示
``` ```bash
ClassifyResult( ClassifyResult(
label_ids: 153, label_ids: 153,
scores: 0.686229, scores: 0.686229,
@@ -35,7 +35,7 @@ scores: 0.686229,
## PaddleClasModel Python接口 ## PaddleClasModel Python接口
``` ```python
fd.vision.classification.PaddleClasModel(model_file, params_file, config_file, runtime_option=None, model_format=Frontend.PADDLE) fd.vision.classification.PaddleClasModel(model_file, params_file, config_file, runtime_option=None, model_format=Frontend.PADDLE)
``` ```
@@ -51,7 +51,7 @@ PaddleClas模型加载和初始化，其中model_file, params_file为训练模
### predict函数 ### predict函数
> ``` > ```python
> PaddleClasModel.predict(input_image, topk=1) > PaddleClasModel.predict(input_image, topk=1)
> ``` > ```
> >

9
examples/vision/detection/nanodet_plus/cpp/README.md
View File

@@ -9,7 +9,7 @@
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 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 mkdir build
cd build cd build
wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz
@@ -34,11 +34,14 @@ wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/0000000
<img width="640" src="https://user-images.githubusercontent.com/67993288/184301689-87ee5205-2eff-4204-b615-24c400f01323.jpg"> <img width="640" src="https://user-images.githubusercontent.com/67993288/184301689-87ee5205-2eff-4204-b615-24c400f01323.jpg">
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/compile/how_to_use_sdk_on_windows.md)
## NanoDetPlus C++接口 ## NanoDetPlus C++接口
### NanoDetPlus类 ### NanoDetPlus类
``` ```c++
fastdeploy::vision::detection::NanoDetPlus( fastdeploy::vision::detection::NanoDetPlus(
const string& model_file, const string& model_file,
const string& params_file = "", const string& params_file = "",
@@ -57,7 +60,7 @@ NanoDetPlus模型加载和初始化，其中model_file为导出的ONNX模型格
#### Predict函数 #### Predict函数
> ``` > ```c++
> NanoDetPlus::Predict(cv::Mat* im, DetectionResult* result, > NanoDetPlus::Predict(cv::Mat* im, DetectionResult* result,
> float conf_threshold = 0.25, > float conf_threshold = 0.25,
> float nms_iou_threshold = 0.5) > float nms_iou_threshold = 0.5)

6
examples/vision/detection/nanodet_plus/python/README.md
View File

@@ -7,7 +7,7 @@
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 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 #下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision/detection/nanodet_plus/python/ cd examples/vision/detection/nanodet_plus/python/
@@ -30,7 +30,7 @@ python infer.py --model nanodet-plus-m_320.onnx --image 000000014439.jpg --devic
## NanoDetPlus Python接口 ## NanoDetPlus Python接口
``` ```python
fastdeploy.vision.detection.NanoDetPlus(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX) fastdeploy.vision.detection.NanoDetPlus(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX)
``` ```
@@ -45,7 +45,7 @@ NanoDetPlus模型加载和初始化，其中model_file为导出的ONNX模型格
### predict函数 ### predict函数
> ``` > ```python
> NanoDetPlus.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5) > NanoDetPlus.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
> ``` > ```
> >

9
examples/vision/detection/paddledetection/cpp/README.md
View File

@@ -9,7 +9,7 @@
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 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
``` ```bash
以ppyoloe为例进行推理部署 以ppyoloe为例进行推理部署
#下载SDK，编译模型examples代码（SDK中包含了examples代码） #下载SDK，编译模型examples代码（SDK中包含了examples代码）
@@ -34,12 +34,15 @@ tar xvf ppyoloe_crn_l_300e_coco.tgz
./infer_ppyoloe_demo ./ppyoloe_crn_l_300e_coco 000000014439.jpg 2 ./infer_ppyoloe_demo ./ppyoloe_crn_l_300e_coco 000000014439.jpg 2
``` ```
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/compile/how_to_use_sdk_on_windows.md)
## PaddleDetection C++接口 ## PaddleDetection C++接口
### 模型类 ### 模型类
PaddleDetection目前支持6种模型系列，类名分别为`PPYOLOE`, `PicoDet`, `PaddleYOLOX`, `PPYOLO`, `FasterRCNN`，所有类名的构造函数和预测函数在参数上完全一致，本文档以PPYOLOE为例讲解API PaddleDetection目前支持6种模型系列，类名分别为`PPYOLOE`, `PicoDet`, `PaddleYOLOX`, `PPYOLO`, `FasterRCNN`，所有类名的构造函数和预测函数在参数上完全一致，本文档以PPYOLOE为例讲解API
``` ```c++
fastdeploy::vision::detection::PPYOLOE( fastdeploy::vision::detection::PPYOLOE(
const string& model_file, const string& model_file,
const string& params_file, const string& params_file,
@@ -60,7 +63,7 @@ PaddleDetection PPYOLOE模型加载和初始化，其中model_file为导出的ON
#### Predict函数 #### Predict函数
> ``` > ```c++
> PPYOLOE::Predict(cv::Mat* im, DetectionResult* result) > PPYOLOE::Predict(cv::Mat* im, DetectionResult* result)
> ``` > ```
> >

6
examples/vision/detection/paddledetection/python/README.md
View File

@@ -7,7 +7,7 @@
本目录下提供`infer_xxx.py`快速完成PPYOLOE/PicoDet等模型在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 本目录下提供`infer_xxx.py`快速完成PPYOLOE/PicoDet等模型在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 #下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision/detection/paddledetection/python/ cd examples/vision/detection/paddledetection/python/
@@ -32,7 +32,7 @@ python infer_ppyoloe.py --model_dir ppyoloe_crn_l_300e_coco --image 000000014439
## PaddleDetection Python接口 ## PaddleDetection Python接口
``` ```python
fastdeploy.vision.detection.PPYOLOE(model_file, params_file, config_file, runtime_option=None, model_format=Frontend.PADDLE) fastdeploy.vision.detection.PPYOLOE(model_file, params_file, config_file, runtime_option=None, model_format=Frontend.PADDLE)
fastdeploy.vision.detection.PicoDet(model_file, params_file, config_file, runtime_option=None, model_format=Frontend.PADDLE) fastdeploy.vision.detection.PicoDet(model_file, params_file, config_file, runtime_option=None, model_format=Frontend.PADDLE)
fastdeploy.vision.detection.PaddleYOLOX(model_file, params_file, config_file, runtime_option=None, model_format=Frontend.PADDLE) fastdeploy.vision.detection.PaddleYOLOX(model_file, params_file, config_file, runtime_option=None, model_format=Frontend.PADDLE)
@@ -54,7 +54,7 @@ PaddleDetection模型加载和初始化，其中model_file， params_file为导
### predict函数 ### predict函数
PaddleDetection中各个模型，包括PPYOLOE/PicoDet/PaddleYOLOX/YOLOv3/PPYOLO/FasterRCNN，均提供如下同样的成员函数用于进行图像的检测 PaddleDetection中各个模型，包括PPYOLOE/PicoDet/PaddleYOLOX/YOLOv3/PPYOLO/FasterRCNN，均提供如下同样的成员函数用于进行图像的检测
> ``` > ```python
> PPYOLOE.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5) > PPYOLOE.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
> ``` > ```
> >

2
examples/vision/detection/scaledyolov4/README.md
View File

@@ -11,7 +11,7 @@
访问[ScaledYOLOv4](https://github.com/WongKinYiu/ScaledYOLOv4)官方github库，按照指引下载安装，下载`scaledyolov4.pt` 模型，利用 `models/export.py` 得到`onnx`格式文件。如果您导出的`onnx`模型出现问题，可以参考[ScaledYOLOv4#401](https://github.com/WongKinYiu/ScaledYOLOv4/issues/401)的解决办法 访问[ScaledYOLOv4](https://github.com/WongKinYiu/ScaledYOLOv4)官方github库，按照指引下载安装，下载`scaledyolov4.pt` 模型，利用 `models/export.py` 得到`onnx`格式文件。如果您导出的`onnx`模型出现问题，可以参考[ScaledYOLOv4#401](https://github.com/WongKinYiu/ScaledYOLOv4/issues/401)的解决办法
``` ```bash
#下载ScaledYOLOv4模型文件 #下载ScaledYOLOv4模型文件
Download from the goole drive https://drive.google.com/file/d/1aXZZE999sHMP1gev60XhNChtHPRMH3Fz/view?usp=sharing Download from the goole drive https://drive.google.com/file/d/1aXZZE999sHMP1gev60XhNChtHPRMH3Fz/view?usp=sharing

9
examples/vision/detection/scaledyolov4/cpp/README.md
View File

@@ -9,7 +9,7 @@
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 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 mkdir build
cd build cd build
wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz
@@ -34,11 +34,14 @@ wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/0000000
<img width="640" src="https://user-images.githubusercontent.com/67993288/184301908-7027cf41-af51-4485-bd32-87aca0e77336.jpg"> <img width="640" src="https://user-images.githubusercontent.com/67993288/184301908-7027cf41-af51-4485-bd32-87aca0e77336.jpg">
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/compile/how_to_use_sdk_on_windows.md)
## ScaledYOLOv4 C++接口 ## ScaledYOLOv4 C++接口
### ScaledYOLOv4类 ### ScaledYOLOv4类
``` ```c++
fastdeploy::vision::detection::ScaledYOLOv4( fastdeploy::vision::detection::ScaledYOLOv4(
const string& model_file, const string& model_file,
const string& params_file = "", const string& params_file = "",
@@ -57,7 +60,7 @@ ScaledYOLOv4模型加载和初始化，其中model_file为导出的ONNX模型格
#### Predict函数 #### Predict函数
> ``` > ```c++
> ScaledYOLOv4::Predict(cv::Mat* im, DetectionResult* result, > ScaledYOLOv4::Predict(cv::Mat* im, DetectionResult* result,
> float conf_threshold = 0.25, > float conf_threshold = 0.25,
> float nms_iou_threshold = 0.5) > float nms_iou_threshold = 0.5)

6
examples/vision/detection/scaledyolov4/python/README.md
View File

@@ -7,7 +7,7 @@
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 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 #下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision/detection/scaledyolov4/python/ cd examples/vision/detection/scaledyolov4/python/
@@ -30,7 +30,7 @@ python infer.py --model scaled_yolov4-p5.onnx --image 000000014439.jpg --device
## ScaledYOLOv4 Python接口 ## ScaledYOLOv4 Python接口
``` ```python
fastdeploy.vision.detection.ScaledYOLOv4(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX) fastdeploy.vision.detection.ScaledYOLOv4(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX)
``` ```
@@ -45,7 +45,7 @@ ScaledYOLOv4模型加载和初始化，其中model_file为导出的ONNX模型格
### predict函数 ### predict函数
> ``` > ```python
> ScaledYOLOv4.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5) > ScaledYOLOv4.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
> ``` > ```
> >

2
examples/vision/detection/yolor/README.md
View File

@@ -11,7 +11,7 @@
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 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 #下载yolor模型文件
wget https://github.com/WongKinYiu/yolor/releases/download/weights/yolor-d6-paper-570.pt wget https://github.com/WongKinYiu/yolor/releases/download/weights/yolor-d6-paper-570.pt

9
examples/vision/detection/yolor/cpp/README.md
View File

@@ -9,7 +9,7 @@
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 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 mkdir build
cd build cd build
wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz
@@ -34,11 +34,14 @@ wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/0000000
<img width="640" src="https://user-images.githubusercontent.com/67993288/184301926-fa3711bf-5984-4e61-9c98-7fdeacb622e9.jpg"> <img width="640" src="https://user-images.githubusercontent.com/67993288/184301926-fa3711bf-5984-4e61-9c98-7fdeacb622e9.jpg">
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/compile/how_to_use_sdk_on_windows.md)
## YOLOR C++接口 ## YOLOR C++接口
### YOLOR类 ### YOLOR类
``` ```c++
fastdeploy::vision::detection::YOLOR( fastdeploy::vision::detection::YOLOR(
const string& model_file, const string& model_file,
const string& params_file = "", const string& params_file = "",
@@ -57,7 +60,7 @@ YOLOR模型加载和初始化，其中model_file为导出的ONNX模型格式。
#### Predict函数 #### Predict函数
> ``` > ```c++
> YOLOR::Predict(cv::Mat* im, DetectionResult* result, > YOLOR::Predict(cv::Mat* im, DetectionResult* result,
> float conf_threshold = 0.25, > float conf_threshold = 0.25,
> float nms_iou_threshold = 0.5) > float nms_iou_threshold = 0.5)

6
examples/vision/detection/yolor/python/README.md
View File

@@ -7,7 +7,7 @@
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 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 #下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision/detection/yolor/python/ cd examples/vision/detection/yolor/python/
@@ -30,7 +30,7 @@ python infer.py --model yolor-p6-paper-541-640-640.onnx --image 000000014439.jpg
## YOLOR Python接口 ## YOLOR Python接口
``` ```python
fastdeploy.vision.detection.YOLOR(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX) fastdeploy.vision.detection.YOLOR(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX)
``` ```
@@ -45,7 +45,7 @@ YOLOR模型加载和初始化，其中model_file为导出的ONNX模型格式
### predict函数 ### predict函数
> ``` > ```python
> YOLOR.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5) > YOLOR.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
> ``` > ```
> >

9
examples/vision/detection/yolov5/cpp/README.md
View File

@@ -9,7 +9,7 @@
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 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 mkdir build
cd build cd build
wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz
@@ -34,11 +34,14 @@ wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/0000000
<img width="640" src="https://user-images.githubusercontent.com/67993288/184309358-d803347a-8981-44b6-b589-4608021ad0f4.jpg"> <img width="640" src="https://user-images.githubusercontent.com/67993288/184309358-d803347a-8981-44b6-b589-4608021ad0f4.jpg">
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/compile/how_to_use_sdk_on_windows.md)
## YOLOv5 C++接口 ## YOLOv5 C++接口
### YOLOv5类 ### YOLOv5类
``` ```c++
fastdeploy::vision::detection::YOLOv5( fastdeploy::vision::detection::YOLOv5(
const string& model_file, const string& model_file,
const string& params_file = "", const string& params_file = "",
@@ -57,7 +60,7 @@ YOLOv5模型加载和初始化，其中model_file为导出的ONNX模型格式。
#### Predict函数 #### Predict函数
> ``` > ```c++
> YOLOv5::Predict(cv::Mat* im, DetectionResult* result, > YOLOv5::Predict(cv::Mat* im, DetectionResult* result,
> float conf_threshold = 0.25, > float conf_threshold = 0.25,
> float nms_iou_threshold = 0.5) > float nms_iou_threshold = 0.5)

6
examples/vision/detection/yolov5/python/README.md
View File

@@ -7,7 +7,7 @@
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 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 #下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision/detection/yolov5/python/ cd examples/vision/detection/yolov5/python/
@@ -30,7 +30,7 @@ python infer.py --model yolov5s.onnx --image 000000014439.jpg --device gpu --use
## YOLOv5 Python接口 ## YOLOv5 Python接口
``` ```python
fastdeploy.vision.detection.YOLOv5(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX) fastdeploy.vision.detection.YOLOv5(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX)
``` ```
@@ -45,7 +45,7 @@ YOLOv5模型加载和初始化，其中model_file为导出的ONNX模型格式
### predict函数 ### predict函数
> ``` > ```python
> YOLOv5.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5) > YOLOv5.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
> ``` > ```
> >

6
examples/vision/detection/yolov5lite/README.md
View File

@@ -12,7 +12,7 @@
- 自动获取 - 自动获取
访问[YOLOv5Lite](https://github.com/ppogg/YOLOv5-Lite) 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) 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) #下载yolov5-lite模型文件(.onnx)
Download from https://drive.google.com/file/d/1bJByk9eoS6pv8Z3N4bcLRCV3i7uk24aU/view Download from https://drive.google.com/file/d/1bJByk9eoS6pv8Z3N4bcLRCV3i7uk24aU/view
官方Repo也支持百度云下载 官方Repo也支持百度云下载
@@ -27,7 +27,7 @@
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。 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) #下载yolov5-lite模型文件(.pt)
Download from https://drive.google.com/file/d/1oftzqOREGqDCerf7DtD5BZp9YWELlkMe/view Download from https://drive.google.com/file/d/1oftzqOREGqDCerf7DtD5BZp9YWELlkMe/view
官方Repo也支持百度云下载 官方Repo也支持百度云下载
@@ -39,7 +39,7 @@
``` ```
- 导出无decode模块的ONNX文件(不需要修改代码) - 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 #下载yolov5-lite模型文件
Download from https://drive.google.com/file/d/1oftzqOREGqDCerf7DtD5BZp9YWELlkMe/view Download from https://drive.google.com/file/d/1oftzqOREGqDCerf7DtD5BZp9YWELlkMe/view
官方Repo也支持百度云下载 官方Repo也支持百度云下载

9
examples/vision/detection/yolov5lite/cpp/README.md
View File

@@ -9,7 +9,7 @@
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 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 mkdir build
cd build cd build
wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz
@@ -34,11 +34,14 @@ wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/0000000
<img width="640" src="https://user-images.githubusercontent.com/67993288/184301943-263c8153-a52a-4533-a7c1-ee86d05d314b.jpg"> <img width="640" src="https://user-images.githubusercontent.com/67993288/184301943-263c8153-a52a-4533-a7c1-ee86d05d314b.jpg">
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/compile/how_to_use_sdk_on_windows.md)
## YOLOv5Lite C++接口 ## YOLOv5Lite C++接口
### YOLOv5Lite类 ### YOLOv5Lite类
``` ```c++
fastdeploy::vision::detection::YOLOv5Lite( fastdeploy::vision::detection::YOLOv5Lite(
const string& model_file, const string& model_file,
const string& params_file = "", const string& params_file = "",
@@ -57,7 +60,7 @@ YOLOv5Lite模型加载和初始化，其中model_file为导出的ONNX模型格
#### Predict函数 #### Predict函数
> ``` > ```c++
> YOLOv5Lite::Predict(cv::Mat* im, DetectionResult* result, > YOLOv5Lite::Predict(cv::Mat* im, DetectionResult* result,
> float conf_threshold = 0.25, > float conf_threshold = 0.25,
> float nms_iou_threshold = 0.5) > float nms_iou_threshold = 0.5)

6
examples/vision/detection/yolov5lite/python/README.md
View File

@@ -7,7 +7,7 @@
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 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 #下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision/detection/yolov5lite/python/ cd examples/vision/detection/yolov5lite/python/
@@ -30,7 +30,7 @@ python infer.py --model v5Lite-g-sim-640.onnx --image 000000014439.jpg --device
## YOLOv5Lite Python接口 ## YOLOv5Lite Python接口
``` ```python
fastdeploy.vision.detection.YOLOv5Lite(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX) fastdeploy.vision.detection.YOLOv5Lite(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX)
``` ```
@@ -45,7 +45,7 @@ YOLOv5Lite模型加载和初始化，其中model_file为导出的ONNX模型格
### predict函数 ### predict函数
> ``` > ```python
> YOLOv5Lite.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5) > YOLOv5Lite.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
> ``` > ```
> >

9
examples/vision/detection/yolov6/cpp/README.md
View File

@@ -9,7 +9,7 @@
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 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 mkdir build
cd build cd build
wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz
@@ -34,11 +34,14 @@ wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/0000000
<img width="640" src="https://user-images.githubusercontent.com/67993288/184301725-390e4abb-db2b-482d-931d-469381322626.jpg"> <img width="640" src="https://user-images.githubusercontent.com/67993288/184301725-390e4abb-db2b-482d-931d-469381322626.jpg">
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/compile/how_to_use_sdk_on_windows.md)
## YOLOv6 C++接口 ## YOLOv6 C++接口
### YOLOv6类 ### YOLOv6类
``` ```c++
fastdeploy::vision::detection::YOLOv6( fastdeploy::vision::detection::YOLOv6(
const string& model_file, const string& model_file,
const string& params_file = "", const string& params_file = "",
@@ -57,7 +60,7 @@ YOLOv6模型加载和初始化，其中model_file为导出的ONNX模型格式。
#### Predict函数 #### Predict函数
> ``` > ```c++
> YOLOv6::Predict(cv::Mat* im, DetectionResult* result, > YOLOv6::Predict(cv::Mat* im, DetectionResult* result,
> float conf_threshold = 0.25, > float conf_threshold = 0.25,
> float nms_iou_threshold = 0.5) > float nms_iou_threshold = 0.5)

6
examples/vision/detection/yolov6/python/README.md
View File

@@ -7,7 +7,7 @@
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 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 #下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision/detection/yolov6/python/ cd examples/vision/detection/yolov6/python/
@@ -31,7 +31,7 @@ python infer.py --model yolov6s.onnx --image 000000014439.jpg --device gpu --use
## YOLOv6 Python接口 ## YOLOv6 Python接口
``` ```python
fastdeploy.vision.detection.YOLOv6(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX) fastdeploy.vision.detection.YOLOv6(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX)
``` ```
@@ -46,7 +46,7 @@ YOLOv6模型加载和初始化，其中model_file为导出的ONNX模型格式
### predict函数 ### predict函数
> ``` > ```python
> YOLOv6.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5) > YOLOv6.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
> ``` > ```
> >

2
examples/vision/detection/yolov7/README.md
View File

@@ -10,7 +10,7 @@
## 导出ONNX模型 ## 导出ONNX模型
``` ```bash
# 下载yolov7模型文件 # 下载yolov7模型文件
wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7.pt wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7.pt

9
examples/vision/detection/yolov7/cpp/README.md
View File

@@ -9,7 +9,7 @@
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 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 mkdir build
cd build cd build
wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz
@@ -34,11 +34,14 @@ wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/0000000
<img width="640" src="https://user-images.githubusercontent.com/67993288/183847558-abcd9a57-9cd9-4891-b09a-710963c99b74.jpg"> <img width="640" src="https://user-images.githubusercontent.com/67993288/183847558-abcd9a57-9cd9-4891-b09a-710963c99b74.jpg">
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/compile/how_to_use_sdk_on_windows.md)
## YOLOv7 C++接口 ## YOLOv7 C++接口
### YOLOv7类 ### YOLOv7类
``` ```c++
fastdeploy::vision::detection::YOLOv7( fastdeploy::vision::detection::YOLOv7(
const string& model_file, const string& model_file,
const string& params_file = "", const string& params_file = "",
@@ -57,7 +60,7 @@ YOLOv7模型加载和初始化，其中model_file为导出的ONNX模型格式。
#### Predict函数 #### Predict函数
> ``` > ```c++
> YOLOv7::Predict(cv::Mat* im, DetectionResult* result, > YOLOv7::Predict(cv::Mat* im, DetectionResult* result,
> float conf_threshold = 0.25, > float conf_threshold = 0.25,
> float nms_iou_threshold = 0.5) > float nms_iou_threshold = 0.5)

6
examples/vision/detection/yolov7/python/README.md
View File

@@ -7,7 +7,7 @@
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 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 #下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision/detection/yolov7/python/ cd examples/vision/detection/yolov7/python/
@@ -30,7 +30,7 @@ python infer.py --model yolov7.onnx --image 000000014439.jpg --device gpu --use_
## YOLOv7 Python接口 ## YOLOv7 Python接口
``` ```python
fastdeploy.vision.detection.YOLOv7(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX) fastdeploy.vision.detection.YOLOv7(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX)
``` ```
@@ -45,7 +45,7 @@ YOLOv7模型加载和初始化，其中model_file为导出的ONNX模型格式
### predict函数 ### predict函数
> ``` > ```python
> YOLOv7.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5) > YOLOv7.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
> ``` > ```
> >

9
examples/vision/detection/yolox/cpp/README.md
View File

@@ -9,7 +9,7 @@
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 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 mkdir build
cd build cd build
wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz
@@ -34,11 +34,14 @@ wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/0000000
<img width="640" src="https://user-images.githubusercontent.com/67993288/184301746-04595d76-454a-4f07-8c7d-6f41418f8ae3.jpg"> <img width="640" src="https://user-images.githubusercontent.com/67993288/184301746-04595d76-454a-4f07-8c7d-6f41418f8ae3.jpg">
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/compile/how_to_use_sdk_on_windows.md)
## YOLOX C++接口 ## YOLOX C++接口
### YOLOX类 ### YOLOX类
``` ```c++
fastdeploy::vision::detection::YOLOX( fastdeploy::vision::detection::YOLOX(
const string& model_file, const string& model_file,
const string& params_file = "", const string& params_file = "",
@@ -57,7 +60,7 @@ YOLOX模型加载和初始化，其中model_file为导出的ONNX模型格式。
#### Predict函数 #### Predict函数
> ``` > ```c++
> YOLOX::Predict(cv::Mat* im, DetectionResult* result, > YOLOX::Predict(cv::Mat* im, DetectionResult* result,
> float conf_threshold = 0.25, > float conf_threshold = 0.25,
> float nms_iou_threshold = 0.5) > float nms_iou_threshold = 0.5)

6
examples/vision/detection/yolox/python/README.md
View File

@@ -7,7 +7,7 @@
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 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 #下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision/detection/yolox/python/ cd examples/vision/detection/yolox/python/
@@ -30,7 +30,7 @@ python infer.py --model yolox_s.onnx --image 000000014439.jpg --device gpu --use
## YOLOX Python接口 ## YOLOX Python接口
``` ```python
fastdeploy.vision.detection.YOLOX(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX) fastdeploy.vision.detection.YOLOX(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX)
``` ```
@@ -45,7 +45,7 @@ YOLOX模型加载和初始化，其中model_file为导出的ONNX模型格式
### predict函数 ### predict函数
> ``` > ```python
> YOLOX.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5) > YOLOX.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
> ``` > ```
> >

8
examples/vision/facedet/retinaface/cpp/README.md
View File

@@ -9,7 +9,7 @@
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 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 mkdir build
cd build cd build
wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz
@@ -34,11 +34,13 @@ wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/li
<img width="640" src="https://user-images.githubusercontent.com/67993288/184301763-1b950047-c17f-4819-b175-c743b699c3b1.jpg"> <img width="640" src="https://user-images.githubusercontent.com/67993288/184301763-1b950047-c17f-4819-b175-c743b699c3b1.jpg">
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/compile/how_to_use_sdk_on_windows.md)
## RetinaFace C++接口 ## RetinaFace C++接口
### RetinaFace类 ### RetinaFace类
``` ```c++
fastdeploy::vision::facedet::RetinaFace( fastdeploy::vision::facedet::RetinaFace(
const string& model_file, const string& model_file,
const string& params_file = "", const string& params_file = "",
@@ -57,7 +59,7 @@ RetinaFace模型加载和初始化，其中model_file为导出的ONNX模型格
#### Predict函数 #### Predict函数
> ``` > ```c++
> RetinaFace::Predict(cv::Mat* im, FaceDetectionResult* result, > RetinaFace::Predict(cv::Mat* im, FaceDetectionResult* result,
> float conf_threshold = 0.25, > float conf_threshold = 0.25,
> float nms_iou_threshold = 0.5) > float nms_iou_threshold = 0.5)

6
examples/vision/facedet/retinaface/python/README.md
View File

@@ -7,7 +7,7 @@
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 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 #下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision//retinaface/python/ cd examples/vision//retinaface/python/
@@ -30,7 +30,7 @@ python infer.py --model Pytorch_RetinaFace_mobile0.25-640-640.onnx --image test_
## RetinaFace Python接口 ## RetinaFace Python接口
``` ```python
fastdeploy.vision.facedet.RetinaFace(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX) fastdeploy.vision.facedet.RetinaFace(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX)
``` ```
@@ -45,7 +45,7 @@ RetinaFace模型加载和初始化，其中model_file为导出的ONNX模型格
### predict函数 ### predict函数
> ``` > ```python
> RetinaFace.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5) > RetinaFace.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
> ``` > ```
> >

2
examples/vision/facedet/scrfd/README.md
View File

@@ -8,7 +8,7 @@
## 导出ONNX模型 ## 导出ONNX模型
``` ```bash
#下载scrfd模型文件 #下载scrfd模型文件
e.g. download from https://onedrive.live.com/?authkey=%21ABbFJx2JMhNjhNA&id=4A83B6B633B029CC%215542&cid=4A83B6B633B029CC e.g. download from https://onedrive.live.com/?authkey=%21ABbFJx2JMhNjhNA&id=4A83B6B633B029CC%215542&cid=4A83B6B633B029CC

9
examples/vision/facedet/scrfd/cpp/README.md
View File

@@ -9,7 +9,7 @@
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 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 mkdir build
cd build cd build
wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz
@@ -34,11 +34,14 @@ wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/li
<img width="640" src="https://user-images.githubusercontent.com/67993288/184301789-1981d065-208f-4a6b-857c-9a0f9a63e0b1.jpg"> <img width="640" src="https://user-images.githubusercontent.com/67993288/184301789-1981d065-208f-4a6b-857c-9a0f9a63e0b1.jpg">
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/compile/how_to_use_sdk_on_windows.md)
## SCRFD C++接口 ## SCRFD C++接口
### SCRFD类 ### SCRFD类
``` ```c++
fastdeploy::vision::facedet::SCRFD( fastdeploy::vision::facedet::SCRFD(
const string& model_file, const string& model_file,
const string& params_file = "", const string& params_file = "",
@@ -57,7 +60,7 @@ SCRFD模型加载和初始化，其中model_file为导出的ONNX模型格式。
#### Predict函数 #### Predict函数
> ``` > ```c++
> SCRFD::Predict(cv::Mat* im, FaceDetectionResult* result, > SCRFD::Predict(cv::Mat* im, FaceDetectionResult* result,
> float conf_threshold = 0.25, > float conf_threshold = 0.25,
> float nms_iou_threshold = 0.5) > float nms_iou_threshold = 0.5)

6
examples/vision/facedet/scrfd/python/README.md
View File

@@ -7,7 +7,7 @@
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 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 #下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision/facedet/scrfd/python/ cd examples/vision/facedet/scrfd/python/
@@ -30,7 +30,7 @@ python infer.py --model scrfd_500m_bnkps_shape640x640.onnx --image test_lite_fac
## SCRFD Python接口 ## SCRFD Python接口
``` ```python
fastdeploy.vision.facedet.SCRFD(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX) fastdeploy.vision.facedet.SCRFD(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX)
``` ```
@@ -45,7 +45,7 @@ SCRFD模型加载和初始化，其中model_file为导出的ONNX模型格式
### predict函数 ### predict函数
> ``` > ```python
> SCRFD.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5) > SCRFD.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
> ``` > ```
> >

9
examples/vision/facedet/ultraface/cpp/README.md
View File

@@ -9,7 +9,7 @@
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 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 mkdir build
cd build cd build
wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz
@@ -34,11 +34,14 @@ wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/li
<img width="640" src="https://user-images.githubusercontent.com/67993288/184301821-0788483b-a72b-42b0-a566-b6430f184f6e.jpg"> <img width="640" src="https://user-images.githubusercontent.com/67993288/184301821-0788483b-a72b-42b0-a566-b6430f184f6e.jpg">
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/compile/how_to_use_sdk_on_windows.md)
## UltraFace C++接口 ## UltraFace C++接口
### UltraFace类 ### UltraFace类
``` ```c++
fastdeploy::vision::facedet::UltraFace( fastdeploy::vision::facedet::UltraFace(
const string& model_file, const string& model_file,
const string& params_file = "", const string& params_file = "",
@@ -57,7 +60,7 @@ UltraFace模型加载和初始化，其中model_file为导出的ONNX模型格式
#### Predict函数 #### Predict函数
> ``` > ```c++
> UltraFace::Predict(cv::Mat* im, FaceDetectionResult* result, > UltraFace::Predict(cv::Mat* im, FaceDetectionResult* result,
> float conf_threshold = 0.25, > float conf_threshold = 0.25,
> float nms_iou_threshold = 0.5) > float nms_iou_threshold = 0.5)

6
examples/vision/facedet/ultraface/python/README.md
View File

@@ -7,7 +7,7 @@
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 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 #下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision/facedet/ultraface/python/ cd examples/vision/facedet/ultraface/python/
@@ -30,7 +30,7 @@ python infer.py --model version-RFB-320.onnx --image test_lite_face_detector_3.j
## UltraFace Python接口 ## UltraFace Python接口
``` ```python
fastdeploy.vision.facedet.UltraFace(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX) fastdeploy.vision.facedet.UltraFace(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX)
``` ```
@@ -45,7 +45,7 @@ UltraFace模型加载和初始化，其中model_file为导出的ONNX模型格式
### predict函数 ### predict函数
> ``` > ```python
> UltraFace.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5) > UltraFace.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
> ``` > ```
> >

9
examples/vision/facedet/yolov5face/cpp/README.md
View File

@@ -9,7 +9,7 @@
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 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 mkdir build
cd build cd build
wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz
@@ -34,11 +34,14 @@ wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/li
<img width="640" src="https://user-images.githubusercontent.com/67993288/184301839-a29aefae-16c9-4196-bf9d-9c6cf694f02d.jpg"> <img width="640" src="https://user-images.githubusercontent.com/67993288/184301839-a29aefae-16c9-4196-bf9d-9c6cf694f02d.jpg">
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/compile/how_to_use_sdk_on_windows.md)
## YOLOv5Face C++接口 ## YOLOv5Face C++接口
### YOLOv5Face类 ### YOLOv5Face类
``` ```c++
fastdeploy::vision::facedet::YOLOv5Face( fastdeploy::vision::facedet::YOLOv5Face(
const string& model_file, const string& model_file,
const string& params_file = "", const string& params_file = "",
@@ -57,7 +60,7 @@ YOLOv5Face模型加载和初始化，其中model_file为导出的ONNX模型格
#### Predict函数 #### Predict函数
> ``` > ```c++
> YOLOv5Face::Predict(cv::Mat* im, FaceDetectionResult* result, > YOLOv5Face::Predict(cv::Mat* im, FaceDetectionResult* result,
> float conf_threshold = 0.25, > float conf_threshold = 0.25,
> float nms_iou_threshold = 0.5) > float nms_iou_threshold = 0.5)

6
examples/vision/facedet/yolov5face/python/README.md
View File

@@ -7,7 +7,7 @@
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 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 #下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision/facedet/yolov5face/python/ cd examples/vision/facedet/yolov5face/python/
@@ -30,7 +30,7 @@ python infer.py --model yolov5s-face.onnx --image test_lite_face_detector_3.jpg
## YOLOv5Face Python接口 ## YOLOv5Face Python接口
``` ```python
fastdeploy.vision.facedet.YOLOv5Face(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX) fastdeploy.vision.facedet.YOLOv5Face(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX)
``` ```
@@ -45,7 +45,7 @@ YOLOv5Face模型加载和初始化，其中model_file为导出的ONNX模型格
### predict函数 ### predict函数
> ``` > ```python
> YOLOv5Face.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5) > YOLOv5Face.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
> ``` > ```
> >

2
examples/vision/faceid/insightface/README.md
View File

@@ -18,7 +18,7 @@
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。 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 * 下载ArcFace模型文件
``` ```bash
Link: https://pan.baidu.com/share/init?surl=CL-l4zWqsI1oDuEEYVhj-g code: e8pw Link: https://pan.baidu.com/share/init?surl=CL-l4zWqsI1oDuEEYVhj-g code: e8pw
``` ```

15
examples/vision/faceid/insightface/cpp/README.md
View File

@@ -9,7 +9,7 @@
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 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 mkdir build
cd build cd build
wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz
@@ -40,11 +40,14 @@ wget https://bj.bcebos.com/paddlehub/test_samples/test_lite_focal_arcface_2.JPG
<img width="220" float="left" src="https://user-images.githubusercontent.com/67993288/184321622-d9a494c3-72f3-47f1-97c5-8a2372de491f.JPG"> <img width="220" float="left" src="https://user-images.githubusercontent.com/67993288/184321622-d9a494c3-72f3-47f1-97c5-8a2372de491f.JPG">
</div> </div>
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/compile/how_to_use_sdk_on_windows.md)
## InsightFace C++接口 ## InsightFace C++接口
### ArcFace类 ### ArcFace类
``` ```c++
fastdeploy::vision::faceid::ArcFace( fastdeploy::vision::faceid::ArcFace(
const string& model_file, const string& model_file,
const string& params_file = "", const string& params_file = "",
@@ -56,7 +59,7 @@ ArcFace模型加载和初始化，其中model_file为导出的ONNX模型格式
### CosFace类 ### CosFace类
``` ```c++
fastdeploy::vision::faceid::CosFace( fastdeploy::vision::faceid::CosFace(
const string& model_file, const string& model_file,
const string& params_file = "", const string& params_file = "",
@@ -68,7 +71,7 @@ CosFace模型加载和初始化，其中model_file为导出的ONNX模型格式
### PartialFC类 ### PartialFC类
``` ```c++
fastdeploy::vision::faceid::PartialFC( fastdeploy::vision::faceid::PartialFC(
const string& model_file, const string& model_file,
const string& params_file = "", const string& params_file = "",
@@ -80,7 +83,7 @@ PartialFC模型加载和初始化，其中model_file为导出的ONNX模型格式
### VPL类 ### VPL类
``` ```c++
fastdeploy::vision::faceid::VPL( fastdeploy::vision::faceid::VPL(
const string& model_file, const string& model_file,
const string& params_file = "", const string& params_file = "",
@@ -98,7 +101,7 @@ VPL模型加载和初始化，其中model_file为导出的ONNX模型格式。
#### Predict函数 #### Predict函数
> ``` > ```c++
> ArcFace::Predict(cv::Mat* im, FaceRecognitionResult* result, > ArcFace::Predict(cv::Mat* im, FaceRecognitionResult* result,
> float conf_threshold = 0.25, > float conf_threshold = 0.25,
> float nms_iou_threshold = 0.5) > float nms_iou_threshold = 0.5)

8
examples/vision/faceid/insightface/python/README.md
View File

@@ -8,7 +8,7 @@
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 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 #下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision/faceid/insightface/python/ cd examples/vision/faceid/insightface/python/
@@ -35,7 +35,7 @@ python infer_arcface.py --model ms1mv3_arcface_r100.onnx --face test_lite_focal_
<img width="220" float="left" src="https://user-images.githubusercontent.com/67993288/184321622-d9a494c3-72f3-47f1-97c5-8a2372de491f.JPG"> <img width="220" float="left" src="https://user-images.githubusercontent.com/67993288/184321622-d9a494c3-72f3-47f1-97c5-8a2372de491f.JPG">
</div> </div>
``` ```bash
Prediction Done! Prediction Done!
--- [Face 0]:FaceRecognitionResult: [Dim(512), Min(-2.309220), Max(2.372197), Mean(0.016987)] --- [Face 0]:FaceRecognitionResult: [Dim(512), Min(-2.309220), Max(2.372197), Mean(0.016987)]
--- [Face 1]:FaceRecognitionResult: [Dim(512), Min(-2.288258), Max(1.995104), Mean(-0.003400)] --- [Face 1]:FaceRecognitionResult: [Dim(512), Min(-2.288258), Max(1.995104), Mean(-0.003400)]
@@ -46,7 +46,7 @@ Detect Done! Cosine 01: 0.814385, Cosine 02:-0.059388
## InsightFace Python接口 ## InsightFace Python接口
``` ```python
fastdeploy.vision.faceid.ArcFace(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX) fastdeploy.vision.faceid.ArcFace(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX)
fastdeploy.vision.faceid.CosFace(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX) fastdeploy.vision.faceid.CosFace(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX)
fastdeploy.vision.faceid.PartialFC(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX) fastdeploy.vision.faceid.PartialFC(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX)
@@ -64,7 +64,7 @@ ArcFace模型加载和初始化，其中model_file为导出的ONNX模型格式
### predict函数 ### predict函数
> ``` > ```python
> ArcFace.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5) > ArcFace.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
> ``` > ```
> >

9
examples/vision/matting/modnet/cpp/README.md
View File

@@ -9,7 +9,7 @@
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 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 mkdir build
cd build cd build
wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz
@@ -36,11 +36,14 @@ wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/li
<img width="640" src="https://user-images.githubusercontent.com/67993288/184301892-457f7014-2dc0-4ad1-b688-43b41fac299a.jpg"> <img width="640" src="https://user-images.githubusercontent.com/67993288/184301892-457f7014-2dc0-4ad1-b688-43b41fac299a.jpg">
<img width="640" src="https://user-images.githubusercontent.com/67993288/184301871-c234dfdf-3b3d-46e4-8886-e1ac156c9e4a.jpg"> <img width="640" src="https://user-images.githubusercontent.com/67993288/184301871-c234dfdf-3b3d-46e4-8886-e1ac156c9e4a.jpg">
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/compile/how_to_use_sdk_on_windows.md)
## MODNet C++接口 ## MODNet C++接口
### MODNet类 ### MODNet类
``` ```c++
fastdeploy::vision::matting::MODNet( fastdeploy::vision::matting::MODNet(
const string& model_file, const string& model_file,
const string& params_file = "", const string& params_file = "",
@@ -59,7 +62,7 @@ MODNet模型加载和初始化，其中model_file为导出的ONNX模型格式。
#### Predict函数 #### Predict函数
> ``` > ```c++
> MODNet::Predict(cv::Mat* im, MattingResult* result, > MODNet::Predict(cv::Mat* im, MattingResult* result,
> float conf_threshold = 0.25, > float conf_threshold = 0.25,
> float nms_iou_threshold = 0.5) > float nms_iou_threshold = 0.5)

6
examples/vision/matting/modnet/python/README.md
View File

@@ -7,7 +7,7 @@
本目录下提供`infer.py`快速完成MODNet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 本目录下提供`infer.py`快速完成MODNet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 #下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision/matting/modnet/python/ cd examples/vision/matting/modnet/python/
@@ -31,7 +31,7 @@ python infer.py --model modnet_photographic_portrait_matting.onnx --image test_l
## MODNet Python接口 ## MODNet Python接口
``` ```python
fastdeploy.vision.matting.MODNet(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX) fastdeploy.vision.matting.MODNet(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX)
``` ```
@@ -46,7 +46,7 @@ MODNet模型加载和初始化，其中model_file为导出的ONNX模型格式
### predict函数 ### predict函数
> ``` > ```python
> MODNet.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5) > MODNet.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
> ``` > ```
> >

9
examples/vision/segmentation/paddleseg/cpp/README.md
View File

@@ -9,7 +9,7 @@
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 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 mkdir build
cd build cd build
wget https://bj.bcebos.com/paddlehub/fastdeploy/libs/0.2.0/fastdeploy-linux-x64-gpu-0.2.0.tgz wget https://bj.bcebos.com/paddlehub/fastdeploy/libs/0.2.0/fastdeploy-linux-x64-gpu-0.2.0.tgz
@@ -37,11 +37,14 @@ wget https://paddleseg.bj.bcebos.com/dygraph/demo/cityscapes_demo.png
<img src="https://user-images.githubusercontent.com/16222477/184588768-45ee673b-ef1f-40f4-9fbd-6b1a9ce17c59.png", width=512px, height=256px /> <img src="https://user-images.githubusercontent.com/16222477/184588768-45ee673b-ef1f-40f4-9fbd-6b1a9ce17c59.png", width=512px, height=256px />
</div> </div>
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/compile/how_to_use_sdk_on_windows.md)
## PaddleSeg C++接口 ## PaddleSeg C++接口
### PaddleSeg类 ### PaddleSeg类
``` ```c++
fastdeploy::vision::segmentation::PaddleSegModel( fastdeploy::vision::segmentation::PaddleSegModel(
const string& model_file, const string& model_file,
const string& params_file = "", const string& params_file = "",
@@ -62,7 +65,7 @@ PaddleSegModel模型加载和初始化，其中model_file为导出的Paddle模
#### Predict函数 #### Predict函数
> ``` > ```c++
> PaddleSegModel::Predict(cv::Mat* im, DetectionResult* result) > PaddleSegModel::Predict(cv::Mat* im, DetectionResult* result)
> ``` > ```
> >

6
examples/vision/segmentation/paddleseg/python/README.md
View File

@@ -7,7 +7,7 @@
本目录下提供`infer.py`快速完成Unet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 本目录下提供`infer.py`快速完成Unet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 #下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/vision/segmentation/paddleseg/python cd FastDeploy/examples/vision/segmentation/paddleseg/python
@@ -32,7 +32,7 @@ python infer.py --model Unet_cityscapes_without_argmax_infer --image cityscapes_
## PaddleSegModel Python接口 ## PaddleSegModel Python接口
``` ```python
fd.vision.segmentation.PaddleSegModel(model_file, params_file, config_file, runtime_option=None, model_format=Frontend.PADDLE) fd.vision.segmentation.PaddleSegModel(model_file, params_file, config_file, runtime_option=None, model_format=Frontend.PADDLE)
``` ```
@@ -48,7 +48,7 @@ PaddleSeg模型加载和初始化，其中model_file, params_file以及config_fi
### predict函数 ### predict函数
> ``` > ```python
> PaddleSegModel.predict(input_image) > PaddleSegModel.predict(input_image)
> ``` > ```
> >

1
requirements.txt
View File

@@ -1,3 +1,4 @@
wheel
requests requests
tqdm tqdm
numpy numpy