神经网络初探——Libtorch篇 之 环境搭建VS2022+CUDA

安装环境

• Thinkpad p15v
  • i7-10750H CPU @ 2.60GHz
  • NVIDIA Quadro P620
  • 32GB Memory
• win10
  • 21H1 OS Build 19043.1645
• Microsoft Visual Studio Community 2022
  • (64-bit) - Current Version 17.1.4

相关下载

• libtorch
  • 网站地址
  • 下载连接 debug release
• NVIDIA

  • Driver

    • NVIDIA RTX / QUADRO DESKTOP AND NOTEBOOK DRIVER RELEASE 510

  • CUDA

    • CUDA Toolkit 11.1.0 Win10 Download

  • cuDNN

    • cuDNN v8.0.5 (November 9th, 2020), for CUDA 11.1 Download

软件配置

VS2022

• 新建控制台工程
  

• 配置include 目录
  [VC++ Directories] → [Include Driectories]

  • [你的libtorch目录]\include\
[你的libtorch目录]\include\torch\csrc\api\include

• 配置 library 目录
  [VC++ Directories] → [Library Directories]

  • [你的libtorch目录]\lib\

• 配置 链接器
  [Linker] → [Input] → [Additional Dependencies]

  c10.lib
  c10_cuda.lib
  torch.lib
  torch_cpu.lib
  torch_cuda.lib
  torch_cuda_cpp.lib
  torch_cuda_cu.lib
  pytorch_jni.lib
  libprotobufd.lib
  libprotobuf-lited.lib
  libprotocd.lib
  caffe2_detectron_ops_gpu.lib
  caffe2_module_test_dynamic.lib
  clog.lib
  cpuinfo.lib
  

  [Linker] → [Command Line] → [Additional Options]
  /INCLUDE:?searchsorted_cuda@native@at@@YA?AVTensor@2@AEBV32@0_N1@Z /INCLUDE:?warp_size@cuda@at@@YAHXZ
  注意第二个/INCLUDE前面有个空格

• 配置 运行环境

  • [Debugging] → [Environment]
    • PATH=%PATH%;[你的libtorch目录]\lib\

测试

• 编写 cpp 如下

#include <iostream>

#include <torch/torch.h>
#include <ATen/ATen.h>
#include <torch/script.h>

int main()
{
    torch::Tensor tensor = torch::rand({ 5,3 });
    std::cout << tensor << std::endl;
    std::cout << torch::cuda::is_available() << std::endl; // 测试CUDA是否可用
    std::cout << torch::cuda::cudnn_is_available() << std::endl; // 测试CUDNN是否可用
}

• 运行结果
  
  有两个1就对了