Files
FastDeploy/examples/vision/sr/edvr/cpp
ChaoII c7ec14de95 [Model] add vsr serials models (#518)
* [Model] add vsr serials models

Signed-off-by: ChaoII <849453582@qq.com>

* [Model] add vsr serials models

Signed-off-by: ChaoII <849453582@qq.com>

* fix build problem

Signed-off-by: ChaoII <849453582@qq.com>

* fix code style

Signed-off-by: ChaoII <849453582@qq.com>

* modify according to review suggestions

Signed-off-by: ChaoII <849453582@qq.com>

* modify vsr trt example

Signed-off-by: ChaoII <849453582@qq.com>

* update sr directory

* fix BindPPSR

* add doxygen comment

* add sr unit test

* update model file url

Signed-off-by: ChaoII <849453582@qq.com>
Co-authored-by: Jason <jiangjiajun@baidu.com>
2022-11-21 10:58:28 +08:00
..
2022-11-21 10:58:28 +08:00

EDVR C++部署示例

本目录下提供infer.cc快速完成EDVR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EDVR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
# fastdeploy版本 >= 0.7.0
wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-gpu-0.7.0.tgz
tar xvf fastdeploy-linux-x64-gpu-0.7.0.tgz
cd fastdeploy-linux-x64-gpu-0.7.0/examples/vision/sr/edvr/cpp/
mkdir build && cd build
cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/../../../../../../../fastdeploy-linux-x64-gpu-0.7.0
make -j

# 下载EDVR模型文件和测试视频
wget https://bj.bcebos.com/paddlehub/fastdeploy/EDVR_M_wo_tsa_SRx4.tar
tar -xvf EDVR_M_wo_tsa_SRx4.tar
wget https://bj.bcebos.com/paddlehub/fastdeploy/vsr_src.mp4


# CPU推理
./infer_demo EDVR_M_wo_tsa_SRx4 vsr_src.mp4 0 2
# GPU推理
./infer_demo EDVR_M_wo_tsa_SRx4 vsr_src.mp4 1 2
# GPU上TensorRT推理
./infer_demo EDVR_M_wo_tsa_SRx4 vsr_src.mp4 2 2

以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:

EDVR C++接口

EDVR类

fastdeploy::vision::sr::EDVR(
        const string& model_file,
        const string& params_file = "",
        const RuntimeOption& runtime_option = RuntimeOption(),
        const ModelFormat& model_format = ModelFormat::PADDLE)

EDVR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
  • 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

EDVR::Predict(std::vector<cv::Mat>& imgs, std::vector<cv::Mat>& results)

模型预测接口,输入图像直接输出检测结果。

参数

  • imgs: 输入视频帧序列注意需为HWCBGR格式
  • results: 视频超分结果,超分后的视频帧序列