apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 00:33:03 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity
Files
a51e5a6e55a5cdf1e693d91b3360e4b77e2c1d69
FastDeploy/examples/vision/matting/ppmatting/cpp
History
DefTruth a51e5a6e55 [Android] Add android aar package (#416) 
* [Android] Add Android build docs and demo (#26)

* [Backend] Add override flag to lite backend

* [Docs] Add Android C++ SDK build docs

* [Doc] fix android_build_docs typos

* Update CMakeLists.txt

* Update android.md

* [Doc] Add PicoDet Android demo docs

* [Doc] Update PicoDet Andorid demo docs

* [Doc] Update PaddleClasModel Android demo docs

* [Doc] Update fastdeploy android jni docs

* [Doc] Update fastdeploy android jni usage docs

* [Android] init fastdeploy android jar package

* [Backend] support int8 option for lite backend

* [Model] add Backend::Lite to paddle model

* [Backend] use CopyFromCpu for lite backend.

* [Android] package jni srcs and java api into aar

* Update infer.cc

* Update infer.cc

* [Android] Update package build.gradle

* [Android] Update android app examples

* [Android] update android detection app
2022-10-26 17:01:14 +08:00
..
CMakeLists.txt
Change cmake minimal version
2022-09-28 17:45:02 +08:00
infer.cc
[Android] Add android aar package (#416)
2022-10-26 17:01:14 +08:00
README.md
Bump up to version 0.3.0 (#371)
2022-10-15 22:01:27 +08:00

README.md

PP-Matting C++部署示例

本目录下提供infer.cc快速完成PP-Matting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

以Linux上 PP-Matting 推理为例，在本目录执行如下命令即可完成编译测试（如若只需在CPU上部署，可在Fastdeploy C++预编译库下载CPU推理库）

#下载SDK，编译模型examples代码（SDK中包含了examples代码）
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/matting/ppmatting/cpp/
mkdir build && cd build
cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/../../../../../../../fastdeploy-linux-x64-gpu-0.3.0
make -j

# 下载PP-Matting模型文件和测试图片
wget https://bj.bcebos.com/paddlehub/fastdeploy/PP-Matting-512.tgz
tar -xvf PP-Matting-512.tgz
wget https://bj.bcebos.com/paddlehub/fastdeploy/matting_input.jpg
wget https://bj.bcebos.com/paddlehub/fastdeploy/matting_bgr.jpg


# CPU推理
./infer_demo PP-Matting-512 matting_input.jpg matting_bgr.jpg 0
# GPU推理
./infer_demo PP-Matting-512 matting_input.jpg matting_bgr.jpg 1
# GPU上TensorRT推理
./infer_demo PP-Matting-512 matting_input.jpg matting_bgr.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-Matting C++接口

PPMatting类

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

PP-Matting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

PPMatting::Predict(cv::Mat* im, MattingResult* result)

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: 分割结果，包括分割预测的标签以及标签对应的概率值, MattingResult说明参考视觉模型预测结果

类成员属性

预处理参数

用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果