Add docs for external models (PaddlePaddle#95)

* first commit for yolov7 * pybind for yolov7 * CPP README.md * CPP README.md * modified yolov7.cc * README.md * python file modify * delete license in fastdeploy/ * repush the conflict part * README.md modified * README.md modified * file path modified * file path modified * file path modified * file path modified * file path modified * README modified * README modified * move some helpers to private * add examples for yolov7 * api.md modified * api.md modified * api.md modified * YOLOv7 * yolov7 release link * yolov7 release link * yolov7 release link * copyright * change some helpers to private * change variables to const and fix documents. * gitignore * Transfer some funtions to private member of class * Transfer some funtions to private member of class * Merge from develop (#9) * Fix compile problem in different python version (#26) * fix some usage problem in linux * Fix compile problem Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com> * Add PaddleDetetion/PPYOLOE model support (#22) * add ppdet/ppyoloe * Add demo code and documents * add convert processor to vision (#27) * update .gitignore * Added checking for cmake include dir * fixed missing trt_backend option bug when init from trt * remove un-need data layout and add pre-check for dtype * changed RGB2BRG to BGR2RGB in ppcls model * add model_zoo yolov6 c++/python demo * fixed CMakeLists.txt typos * update yolov6 cpp/README.md * add yolox c++/pybind and model_zoo demo * move some helpers to private * fixed CMakeLists.txt typos * add normalize with alpha and beta * add version notes for yolov5/yolov6/yolox * add copyright to yolov5.cc * revert normalize * fixed some bugs in yolox * fixed examples/CMakeLists.txt to avoid conflicts * add convert processor to vision * format examples/CMakeLists summary * Fix bug while the inference result is empty with YOLOv5 (#29) * Add multi-label function for yolov5 * Update README.md Update doc * Update fastdeploy_runtime.cc fix variable option.trt_max_shape wrong name * Update runtime_option.md Update resnet model dynamic shape setting name from images to x * Fix bug when inference result boxes are empty * Delete detection.py Co-authored-by: Jason <jiangjiajun@baidu.com> Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com> Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com> Co-authored-by: huangjianhui <852142024@qq.com> * first commit for yolor * for merge * Develop (#11) * Fix compile problem in different python version (#26) * fix some usage problem in linux * Fix compile problem Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com> * Add PaddleDetetion/PPYOLOE model support (#22) * add ppdet/ppyoloe * Add demo code and documents * add convert processor to vision (#27) * update .gitignore * Added checking for cmake include dir * fixed missing trt_backend option bug when init from trt * remove un-need data layout and add pre-check for dtype * changed RGB2BRG to BGR2RGB in ppcls model * add model_zoo yolov6 c++/python demo * fixed CMakeLists.txt typos * update yolov6 cpp/README.md * add yolox c++/pybind and model_zoo demo * move some helpers to private * fixed CMakeLists.txt typos * add normalize with alpha and beta * add version notes for yolov5/yolov6/yolox * add copyright to yolov5.cc * revert normalize * fixed some bugs in yolox * fixed examples/CMakeLists.txt to avoid conflicts * add convert processor to vision * format examples/CMakeLists summary * Fix bug while the inference result is empty with YOLOv5 (#29) * Add multi-label function for yolov5 * Update README.md Update doc * Update fastdeploy_runtime.cc fix variable option.trt_max_shape wrong name * Update runtime_option.md Update resnet model dynamic shape setting name from images to x * Fix bug when inference result boxes are empty * Delete detection.py Co-authored-by: Jason <jiangjiajun@baidu.com> Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com> Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com> Co-authored-by: huangjianhui <852142024@qq.com> * Yolor (#16) * Develop (#11) (#12) * Fix compile problem in different python version (#26) * fix some usage problem in linux * Fix compile problem Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com> * Add PaddleDetetion/PPYOLOE model support (#22) * add ppdet/ppyoloe * Add demo code and documents * add convert processor to vision (#27) * update .gitignore * Added checking for cmake include dir * fixed missing trt_backend option bug when init from trt * remove un-need data layout and add pre-check for dtype * changed RGB2BRG to BGR2RGB in ppcls model * add model_zoo yolov6 c++/python demo * fixed CMakeLists.txt typos * update yolov6 cpp/README.md * add yolox c++/pybind and model_zoo demo * move some helpers to private * fixed CMakeLists.txt typos * add normalize with alpha and beta * add version notes for yolov5/yolov6/yolox * add copyright to yolov5.cc * revert normalize * fixed some bugs in yolox * fixed examples/CMakeLists.txt to avoid conflicts * add convert processor to vision * format examples/CMakeLists summary * Fix bug while the inference result is empty with YOLOv5 (#29) * Add multi-label function for yolov5 * Update README.md Update doc * Update fastdeploy_runtime.cc fix variable option.trt_max_shape wrong name * Update runtime_option.md Update resnet model dynamic shape setting name from images to x * Fix bug when inference result boxes are empty * Delete detection.py Co-authored-by: Jason <jiangjiajun@baidu.com> Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com> Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com> Co-authored-by: huangjianhui <852142024@qq.com> Co-authored-by: Jason <jiangjiajun@baidu.com> Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com> Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com> Co-authored-by: huangjianhui <852142024@qq.com> * Develop (#13) * Fix compile problem in different python version (#26) * fix some usage problem in linux * Fix compile problem Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com> * Add PaddleDetetion/PPYOLOE model support (#22) * add ppdet/ppyoloe * Add demo code and documents * add convert processor to vision (#27) * update .gitignore * Added checking for cmake include dir * fixed missing trt_backend option bug when init from trt * remove un-need data layout and add pre-check for dtype * changed RGB2BRG to BGR2RGB in ppcls model * add model_zoo yolov6 c++/python demo * fixed CMakeLists.txt typos * update yolov6 cpp/README.md * add yolox c++/pybind and model_zoo demo * move some helpers to private * fixed CMakeLists.txt typos * add normalize with alpha and beta * add version notes for yolov5/yolov6/yolox * add copyright to yolov5.cc * revert normalize * fixed some bugs in yolox * fixed examples/CMakeLists.txt to avoid conflicts * add convert processor to vision * format examples/CMakeLists summary * Fix bug while the inference result is empty with YOLOv5 (#29) * Add multi-label function for yolov5 * Update README.md Update doc * Update fastdeploy_runtime.cc fix variable option.trt_max_shape wrong name * Update runtime_option.md Update resnet model dynamic shape setting name from images to x * Fix bug when inference result boxes are empty * Delete detection.py Co-authored-by: Jason <jiangjiajun@baidu.com> Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com> Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com> Co-authored-by: huangjianhui <852142024@qq.com> * documents * documents * documents * documents * documents * documents * documents * documents * documents * documents * documents * documents * Develop (#14) * Fix compile problem in different python version (#26) * fix some usage problem in linux * Fix compile problem Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com> * Add PaddleDetetion/PPYOLOE model support (#22) * add ppdet/ppyoloe * Add demo code and documents * add convert processor to vision (#27) * update .gitignore * Added checking for cmake include dir * fixed missing trt_backend option bug when init from trt * remove un-need data layout and add pre-check for dtype * changed RGB2BRG to BGR2RGB in ppcls model * add model_zoo yolov6 c++/python demo * fixed CMakeLists.txt typos * update yolov6 cpp/README.md * add yolox c++/pybind and model_zoo demo * move some helpers to private * fixed CMakeLists.txt typos * add normalize with alpha and beta * add version notes for yolov5/yolov6/yolox * add copyright to yolov5.cc * revert normalize * fixed some bugs in yolox * fixed examples/CMakeLists.txt to avoid conflicts * add convert processor to vision * format examples/CMakeLists summary * Fix bug while the inference result is empty with YOLOv5 (#29) * Add multi-label function for yolov5 * Update README.md Update doc * Update fastdeploy_runtime.cc fix variable option.trt_max_shape wrong name * Update runtime_option.md Update resnet model dynamic shape setting name from images to x * Fix bug when inference result boxes are empty * Delete detection.py Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com> Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com> Co-authored-by: huangjianhui <852142024@qq.com> Co-authored-by: Jason <jiangjiajun@baidu.com> Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com> Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com> Co-authored-by: huangjianhui <852142024@qq.com> Co-authored-by: Jason <928090362@qq.com> * add is_dynamic for YOLO series (#22) * first commit test photo * yolov7 doc * yolov7 doc * yolov7 doc * yolov7 doc * add yolov5 docs * modify yolov5 doc * first commit for retinaface * first commit for retinaface * firt commit for ultraface * firt commit for ultraface * firt commit for yolov5face * firt commit for modnet and arcface * firt commit for modnet and arcface * first commit for partial_fc * first commit for partial_fc * first commit for yolox * first commit for yolov6 * first commit for nano_det Co-authored-by: Jason <jiangjiajun@baidu.com> Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com> Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com> Co-authored-by: huangjianhui <852142024@qq.com> Co-authored-by: Jason <928090362@qq.com>
DefTruth · Aug 11, 2022 · d8f312b · d8f312b
1 parent 7fb8dd7
commit d8f312b
Show file tree

Hide file tree

Showing 46 changed files with 2,318 additions and 25 deletions.
diff --git a/examples/vision/detection/README.md → examples/vision/README.md b/examples/vision/detection/README.md → examples/vision/README.md
diff --git a/examples/vision/detection/nanodet_plus/README.md b/examples/vision/detection/nanodet_plus/README.md
@@ -0,0 +1,22 @@
+# NanoDetPlus准备部署模型
+
+## 模型版本说明
+
+- [NanoDetPlus v1.0.0-alpha-1](https://github.com/RangiLyu/nanodet/releases/tag/v1.0.0-alpha-1)
+  - （1）[链接中](https://github.com/RangiLyu/nanodet/releases/tag/v1.0.0-alpha-1)的*.onnx可直接进行部署
+
+
+## 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。
+
+| 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)
diff --git a/examples/vision/detection/nanodet_plus/cpp/CMakeLists.txt b/examples/vision/detection/nanodet_plus/cpp/CMakeLists.txt
@@ -0,0 +1,14 @@
+PROJECT(infer_demo C CXX)
+CMAKE_MINIMUM_REQUIRED (VERSION 3.12)
+
+# 指定下载解压后的fastdeploy库路径
+option(FASTDEPLOY_INSTALL_DIR "Path of downloaded fastdeploy sdk.")
+
+include(${FASTDEPLOY_INSTALL_DIR}/FastDeploy.cmake)
+
+# 添加FastDeploy依赖头文件
+include_directories(${FASTDEPLOY_INCS})
+
+add_executable(infer_demo ${PROJECT_SOURCE_DIR}/infer.cc)
+# 添加FastDeploy库依赖
+target_link_libraries(infer_demo ${FASTDEPLOY_LIBS})
diff --git a/examples/vision/detection/nanodet_plus/cpp/README.md b/examples/vision/detection/nanodet_plus/cpp/README.md
@@ -0,0 +1,85 @@
+# NanoDetPlus C++部署示例
+
+本目录下提供`infer.cc`快速完成NanoDetPlus在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/quick_start/requirements.md)  
+- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/compile/prebuild_libraries.md)
+
+以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试
+
+```
+mkdir build
+cd build
+wget https://xxx.tgz
+tar xvf fastdeploy-linux-x64-0.2.0.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.0
+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
+
+<img width="640" src="https://user-images.githubusercontent.com/67993288/183847558-abcd9a57-9cd9-4891-b09a-710963c99b74.jpg">
+
+## NanoDetPlus C++接口
+
+### NanoDetPlus类
+
+```
+fastdeploy::vision::detection::NanoDetPlus(
+        const string& model_file,
+        const string& params_file = "",
+        const RuntimeOption& runtime_option = RuntimeOption(),
+        const Frontend& model_format = Frontend::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**(Frontend): 模型格式，默认为ONNX格式
+
+#### Predict函数
+
+> ```
+> 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
+
+> > * **size**(vector&lt;int&gt;): 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&lt;float&gt;): 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/)
diff --git a/examples/vision/detection/nanodet_plus/python/README.md b/examples/vision/detection/nanodet_plus/python/README.md
@@ -0,0 +1,79 @@
+# 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/quick_start/requirements.md)  
+- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/quick_start/install.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
+
+```
+#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
+
+
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd examples/vison/detection/nanodet_plus/python/
+
+# 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
+
+<img width="640" src="https://user-images.githubusercontent.com/67993288/183847558-abcd9a57-9cd9-4891-b09a-710963c99b74.jpg">
+
+## NanoDetPlus Python接口
+
+```
+fastdeploy.vision.detection.NanoDetPlus(model_file, params_file=None, runtime_option=None, model_format=Frontend.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**(Frontend): 模型格式，默认为ONNX
+
+### predict函数
+
+> ```
+> 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
+
+> > * **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
+
+- [NanoDetPlus 模型介绍](..)
+- [NanoDetPlus C++部署](../cpp)
+- [模型预测结果说明](../../../../../docs/api/vision_results/)
diff --git a/examples/vision/detection/yolov5/README.md b/examples/vision/detection/yolov5/README.md
@@ -0,0 +1,28 @@
+# YOLOv7准备部署模型
+
+## 模型版本说明
+
+- [YOLOv5 v6.0](https://github.com/ultralytics/yolov5/releases/tag/v6.0)
+  - （1）[链接中](https://github.com/ultralytics/yolov5/releases/tag/v6.0)的*.onnx可直接进行部署；
+  - （2）开发者基于自己数据训练的YOLOv5 v6.0模型，可使用[YOLOv5](https://github.com/ultralytics/yolov5)中的`export.py`导出ONNX文件后后，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YOLOv7导出的各系列模型，开发者可直接下载使用。
+
+| 模型                                                               | 大小    | 精度    |
+|:---------------------------------------------------------------- |:----- |:----- |
+| [YOLOv5n](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5n.onnx) | 1.9MB | 28.4% |
+| [YOLOv5s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s.onnx) | 7.2MB | 37.2% |
+| [YOLOv5m](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5m.onnx) | 21.2MB | 45.2% |
+| [YOLOv5l](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5l.onnx) | 46.5MB | 48.8% |
+| [YOLOv5x](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5x.onnx) | 86.7MB | 50.7% |
+
+
+
+
+## 详细部署文档
+
+- [Python部署](python)
+- [C++部署](cpp)
diff --git a/examples/vision/detection/yolov5/cpp/CMakeLists.txt b/examples/vision/detection/yolov5/cpp/CMakeLists.txt
@@ -0,0 +1,14 @@
+PROJECT(infer_demo C CXX)
+CMAKE_MINIMUM_REQUIRED (VERSION 3.12)
+
+# 指定下载解压后的fastdeploy库路径
+option(FASTDEPLOY_INSTALL_DIR "Path of downloaded fastdeploy sdk.")
+
+include(${FASTDEPLOY_INSTALL_DIR}/FastDeploy.cmake)
+
+# 添加FastDeploy依赖头文件
+include_directories(${FASTDEPLOY_INCS})
+
+add_executable(infer_demo ${PROJECT_SOURCE_DIR}/infer.cc)
+# 添加FastDeploy库依赖
+target_link_libraries(infer_demo ${FASTDEPLOY_LIBS})
diff --git a/examples/vision/detection/yolov5/cpp/README.md b/examples/vision/detection/yolov5/cpp/README.md
@@ -0,0 +1,85 @@
+# YOLOv5 C++部署示例
+
+本目录下提供`infer.cc`快速完成YOLOv5在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/quick_start/requirements.md)  
+- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/compile/prebuild_libraries.md)
+
+以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试
+
+```
+mkdir build
+cd build
+wget https://xxx.tgz
+tar xvf fastdeploy-linux-x64-0.2.0.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.0
+make -j
+
+#下载官方转换好的yolov5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
+
+<img width="640" src="https://user-images.githubusercontent.com/67993288/183847558-abcd9a57-9cd9-4891-b09a-710963c99b74.jpg">
+
+## YOLOv5 C++接口
+
+### YOLOv5类
+
+```
+fastdeploy::vision::detection::YOLOv5(
+        const string& model_file,
+        const string& params_file = "",
+        const RuntimeOption& runtime_option = RuntimeOption(),
+        const Frontend& model_format = Frontend::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**(Frontend): 模型格式，默认为ONNX格式
+
+#### Predict函数
+
+> ```
+> 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
+
+> > * **size**(vector&lt;int&gt;): 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&lt;float&gt;): 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/)