Cannot compile TorchScript C++ demo

OS: Win10 x64
LibTorch Version: 1.3.1
I downloaded libtorch from the following links:

Download here (Release version):
https://download.pytorch.org/libtorch/cpu/libtorch-win-shared-with-deps-1.3.1.zip

Download here (Debug version):
https://download.pytorch.org/libtorch/cpu/libtorch-win-shared-with-deps-debug-1.3.1.zip

Then I add a new console application in VS2017 community edition. The whole solution contains only a main.cpp:

#include <torch/script.h> // One-stop header.

#include <iostream>
#include <memory>

int main(int argc, const char* argv[]) {
  if (argc != 2) {
    std::cerr << "usage: example-app <path-to-exported-script-module>\n";
    return -1;
  }


  torch::jit::script::Module module;
  try {
    // Deserialize the ScriptModule from a file using torch::jit::load().
    module = torch::jit::load(argv[1]);
  }
  catch (const c10::Error& e) {
    std::cerr << "error loading the model\n";
    return -1;
  }

  std::cout << "ok\n";
}

(from this tutorial: https://pytorch.org/tutorials/advanced/cpp_export.html#a-minimal-c-application)

Then I add the include folders and lib directories. But I cannot successfully compile this solution. The error saying:

I’ve googled this issue several days, but I still not find the key to it.
I’ve checked the Release/Debug mode, set off the Conformance mode, compile libtorch from source…
all failed.

Can anyone help me solve this problem? Any suggestions will be apreciated!

The code is trying to load a Pytorch model from a directory, I’m little confused with what you mean by torchscript.

Compile failure.
Before load a pytorch model, the solution should be compiled successfully.

Did you go through the CMake setup before compile this script?