[Model] Add FSANet model (#448)

* add yolov5cls

* fixed bugs

* fixed bugs

* fixed preprocess bug

* add yolov5cls readme

* deal with comments

* Add YOLOv5Cls Note

* add yolov5cls test

* add rvm support

* support rvm model

* add rvm demo

* fixed bugs

* add rvm readme

* add TRT support

* add trt support

* add rvm test

* add EXPORT.md

* rename export.md

* rm poros doxyen

* deal with comments

* deal with comments

* add rvm video_mode note

* add fsanet

* fixed bug

* update readme

* fixed for ci

* deal with comments

* deal with comments

* deal with comments

Co-authored-by: Jason <jiangjiajun@baidu.com>
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
This commit is contained in:
WJJ1995
2022-11-04 11:00:35 +08:00
committed by GitHub
parent ce828ecb38
commit 7150e6405c
31 changed files with 922 additions and 22 deletions

View File

@@ -0,0 +1,74 @@
# FSANet C++部署示例
本目录下提供`infer.cc`快速完成FSANet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保证 FastDeploy 版本0.6.0以上(x.x.x >= 0.6.0)支持FSANet模型
```bash
mkdir build
cd build
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 FSANet 模型文件和测试图片
wget https://bj.bcebos.com/paddlehub/fastdeploy/fsanet-var.onnx
wget https://bj.bcebos.com/paddlehub/fastdeploy/headpose_input.png
# CPU推理
./infer_demo --model fsanet-var.onnx --image headpose_input.png --device cpu
# GPU推理
./infer_demo --model fsanet-var.onnx --image headpose_input.png --device gpu
# GPU上TensorRT推理
./infer_demo --model fsanet-var.onnx --image headpose_input.png --device gpu --backend trt
```
运行完成可视化结果如下图所示
<div width="520">
<img width="500" height="514" float="left" src="https://user-images.githubusercontent.com/19977378/198279932-3eee424e-98a2-4249-bdeb-0f79127cbc9d.png">
</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/cn/faq/use_sdk_on_windows.md)
## FSANet C++接口
### FSANet 类
```c++
fastdeploy::vision::headpose::FSANet(
const string& model_file,
const string& params_file = "",
const RuntimeOption& runtime_option = RuntimeOption(),
const ModelFormat& model_format = ModelFormat::ONNX)
```
FSANet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++
> FSANet::Predict(cv::Mat* im, HeadPoseResult* result)
> ```
>
> 模型预测接口,输入图像直接输出头部姿态预测结果。
>
> **参数**
>
> > * **im**: 输入图像注意需为HWCBGR格式
> > * **result**: 头部姿态预测结果, HeadPoseResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
### 类成员变量
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&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[112, 112]
- [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)