第8节：libtorch必用的代码段：加速开发你的C++深度学习模型

• 环境请参考上一篇
• • cmakelists.txt
  • TIPS

第一节：linux 开发AI算法以及libtorch部署算法详细教程-环境搭建

cmake_minimum_required (VERSION 3.8)

project(SOLDIER)
set(Torch_DIR "/libtorch/share/cmake/Torch")
set(PYTHON_EXECUTABLE "/usr/bin/python3")


find_package(Torch REQUIRED)
find_package(OpenCV REQUIRED)

set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS}")


set(CMAKE_BUILD_TYPE Debug)

include_directories(${OpenCV_INCLUDE_DIRS})

add_executable(run main.cpp)
target_link_libraries(run "${OpenCV_LIBS}" "${TORCH_LIBRARIES}")
set_property(TARGET run PROPERTY CXX_STANDARD 14)

#include 
#include
#include
#include 
#include 

// 选择GPU或CPU
void chooseDevice()
{
    torch::manual_seed(1);

  torch::DeviceType device_type;
  if (torch::cuda::is_available()) {
    std::cout << "CUDA available! Training on GPU." << std::endl;
    device_type = torch::kCUDA;
  } else {
    std::cout << "Training on CPU." << std::endl;
    device_type = torch::kCPU;
  }
  torch::Device device(device_type);
}

// 网络的定义
struct Net : torch::nn::Module {
  Net()
      : conv1(torch::nn::Conv2dOptions(1, 10, 5)),
        conv2(torch::nn::Conv2dOptions(10, 20, 5)),
        fc1(320, 50),
        fc2(50, 10) {
    register_module("conv1", conv1);
    register_module("conv2", conv2);
    register_module("conv2_drop", conv2_drop);
    register_module("fc1", fc1);
    register_module("fc2", fc2);
  }

  torch::Tensor forward(torch::Tensor x) {
    x = torch::relu(torch::max_pool2d(conv1->forward(x), 2));
    x = torch::relu(
        torch::max_pool2d(conv2_drop->forward(conv2->forward(x)), 2));
    x = x.view({-1, 320});
    x = torch::relu(fc1->forward(x));
    x = torch::dropout(x, 0.5, is_training());
    x = fc2->forward(x);
    return torch::log_softmax(x, 1);
  }

  torch::nn::Conv2d conv1;
  torch::nn::Conv2d conv2;
  torch::nn::Dropout2d conv2_drop;
  torch::nn::Linear fc1;
  torch::nn::Linear fc2;
};

int main()
{
    chooseDevice();
    Net model;
    // model.to(device);
    return 0;
}