Files
FastDeploy/examples/vision/keypointdetection/tiny_pose/cpp/README.md
huangjianhui b565c15bf7 [Model] Add tinypose single && pipeline model (#177)
* Add tinypose model

* Add PPTinypose python API

* Fix picodet preprocess bug && Add Tinypose examples

* Update tinypose example code

* Update ppseg preprocess if condition

* Update ppseg backend support type

* Update permute.h

* Update README.md

* Update code with comments

* Move files dir

* Delete premute.cc

* Add single model pptinypose

* Delete pptinypose old code in ppdet

* Code format

* Add ppdet + pptinypose pipeline model

* Fix bug for posedetpipeline

* Change Frontend to ModelFormat

* Change Frontend to ModelFormat in __init__.py

* Add python posedetpipeline/

* Update pptinypose example dir name

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Create keypointdetection_result.md

* Create README.md

* Create README.md

* Create README.md

* Update README.md

* Update README.md

* Create README.md

* Fix det_keypoint_unite_infer.py bug

* Create README.md

* Update PP-Tinypose by comment

* Update by comment

* Add pipeline directory

* Add pptinypose dir

* Update pptinypose to align accuracy

* Addd warpAffine processor

* Update GetCpuMat to  GetOpenCVMat

* Add comment for pptinypose && pipline

* Update docs/main_page.md

* Add README.md for pptinypose

* Add README for det_keypoint_unite

* Remove ENABLE_PIPELINE option

* Remove ENABLE_PIPELINE option

* Change pptinypose default backend

* PP-TinyPose Pipeline support multi PP-Detection models

* Update pp-tinypose comment

* Update by comments

* Add single test example

Co-authored-by: Jason <jiangjiajun@baidu.com>
2022-10-21 09:28:23 +08:00

3.6 KiB
Raw Blame History

PP-TinyPose C++部署示例

本目录下提供pptinypose_infer.cc快速完成PP-TinyPose在CPU/GPU以及GPU上通过TensorRT加速部署的单图单人关键点检测示例

注意: PP-Tinypose单模型目前只支持单图单人关键点检测因此输入的图片应只包含一个人或者进行过裁剪的图像。多人关键点检测请参考PP-TinyPose Pipeline

在部署前,需确认以下两个步骤

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

wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-gpu-0.3.0.tgz
tar xvf fastdeploy-linux-x64-gpu-0.3.0.tgz
cd fastdeploy-linux-x64-gpu-0.3.0/examples/vision/keypointdetection/tiny_pose/cpp/
mkdir build
cd build
cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/../../../../../../../fastdeploy-linux-x64-gpu-0.3.0
make -j

# 下载PP-TinyPose模型文件和测试图片
wget https://bj.bcebos.com/paddlehub/fastdeploy/PP_TinyPose_256x192_infer.tgz
tar -xvf PP_TinyPose_256x192_infer.tgz
wget https://bj.bcebos.com/paddlehub/fastdeploy/hrnet_demo.jpg


# CPU推理
./infer_tinypose_demo PP_TinyPose_256x192_infer hrnet_demo.jpg 0
# GPU推理
./infer_tinypose_demo PP_TinyPose_256x192_infer hrnet_demo.jpg 1
# GPU上TensorRT推理
./infer_tinypose_demo PP_TinyPose_256x192_infer hrnet_demo.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:

PP-TinyPose C++接口

PP-TinyPose类

fastdeploy::vision::keypointdetection::PPTinyPose(
        const string& model_file,
        const string& params_file = "",
        const string& config_file,
        const RuntimeOption& runtime_option = RuntimeOption(),
        const ModelFormat& model_format = ModelFormat::PADDLE)

PPTinyPose模型加载和初始化其中model_file为导出的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
  • config_file(str): 推理部署配置文件
  • 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

Predict函数

PPTinyPose::Predict(cv::Mat* im, KeyPointDetectionResult* result)

模型预测接口,输入图像直接输出关键点检测结果。

参数

  • im: 输入图像注意需为HWCBGR格式
  • result: 关键点检测结果,包括关键点的坐标以及关键点对应的概率值, KeyPointDetectionResult说明参考视觉模型预测结果

类成员属性

后处理参数

  • use_dark(bool): 是否使用DARK进行后处理参考论文