Raspberry 上的 Libtorch 无法加载 pt 文件，但可以在 ubuntu 上运行

Question

我正在尝试在 Raspberry PI 上使用 libtorch 构建 C++ 程序。该程序在 Ubuntu 上运行，但在 Raspberry 上构建时出现以下错误：

\n

error: use of deleted function \xc3\xa2\xe2\x82\xac\xcb\x9cvoid torch::jit::script::Module::operator=(const torch::jit::script::Module&)\xc3\xa2\xe2\x82\xac\xe2\x84\xa2\nIn file included from /usr/include/torch/csrc/jit/ir.h:18,\n                 from /usr/include/torch/csrc/jit/tracer.h:9,\n                 from /usr/include/torch/csrc/autograd/generated/variable_factories.h:8,\n                 from /usr/include/torch/csrc/api/include/torch/types.h:7,\n                 from /usr/include/torch/script.h:3,\n                 from /tmp/tmp.k6618dczxt/src/../include/suvoNet.h:26,\n                 from /tmp/tmp.k6618dczxt/src/../include/classifier.h:17,\n                 from /tmp/tmp.k6618dczxt/src/classifier.cpp:11:\n/usr/include/torch/csrc/jit/script/module.h:319:3: note: declared here\n   TH_DISALLOW_COPY_AND_ASSIGN(Module);\n

\n

这是崩溃的代码：

\n

MyClass::MyClass() {\n    try {\n        // Deserialize the ScriptModule from a file using torch::jit::load().\n        network = torch::jit::load(MODEL_FILE);\n    }\n    catch (const c10::Error& e) {\n        std::cerr << "Error loading the model\\n";\n        exit(-1);\n    }\n}\n\n

\n

已network声明为私有torch::jit::script::Module network

\n

我使用 github 上的 pyTorch 版本“1.0.0a0+8322165”为 Raspberry (ARM) 构建 libtorch

\n

Answer 1

TLDR：在 1.6.0 中编译 libtorch 并且工作正常。

如何为 Raspberry 编译 Libtorch 并在我的 C++ 项目中使用？

准备建造

增加 RBPi 隔夜利息

首先，如果您有 Raspberry PI 3 或更低版本，则需要增加 SWAP，因为该构建会占用 RAM。

如果您有 RBPi 4 或更高版本且 RAM 超过 3GB，请跳过此步骤。

修改文件/etc/dphys-swapfile：

CONF_SWAPFILE=2048M

然后调用以下命令来更新更改。

sudo dphys-swapfile setup

安装基础包

安装以下软件包：

sudo apt install build-essential make cmake git python3-pip libatlas-base-dev

Libtorch 需要 CMake>=3.15才能正确构建，使用 cmake --version``检查 cmake 版本

如果低于 3.15，请按照以下命令构建更新版本并删除旧版本：

wget https://github.com/Kitware/CMake/releases/download/v3.18.0-rc1/cmake-3.18.0-rc1.tar.gz
tar -xzf cmake-3.18.0-rc1.tar.gz
cd cmake<version>
mkdir build
cd build
cmake ..
make
sudo make install

sudo apt remove cmake
sudo ln -s /usr/local/bin/cmake /usr/bin/cmake
sudo ldconfig

从源代码构建 PyTorch 以获取 ARM 的 libtorch 后端

如果您没有 3GB 或 RAM，请不要忘记将 SWAP 增加到 2048M。

获取所有需要的库：

sudo apt install build-essential make cmake git python3-pip libatlas-base-dev

获取 PyTorch 源：

wget https://github.com/Kitware/CMake/releases/download/v3.18.0-rc1/cmake-3.18.0-rc1.tar.gz
tar -xzf cmake-3.18.0-rc1.tar.gz
cd cmake<version>
mkdir build
cd build
cmake ..
make
sudo make install

sudo apt remove cmake
sudo ln -s /usr/local/bin/cmake /usr/bin/cmake
sudo ldconfig

初始化所有子模块：

sudo apt-get update
sudo apt-get install build-essential tk-dev libncurses5-dev libncursesw5-dev libreadline6-dev libdb5.3-dev libgdbm-dev libsqlite3-dev libssl-dev libbz2-dev libexpat1-dev liblzma-dev zlib1g-dev

获取所有需要的库：

git clone --recursive https://github.com/pytorch/pytorch --branch=release/1.6
cd pytorch

获取 PyTorch 源：

git submodule update --init --recursive
git submodule update --remote third_party/protobuf # To prevent a bug I had

为构建设置环境变量。

将以下行添加到文件中~/.bashrc。

export NO_CUDA=1
export NO_DISTRIBUTED=1
export NO_MKLDNN=1 
export NO_NNPACK=1
export NO_QNNPACK=1

以 root 身份登录，并使用 .bashrc 文件设置环境变量

sudo su
source /home/<user>/.bashrc

安装python依赖项

pip3 install setuptools pyyaml numpy

构建并安装 PyTorch，是时候喝杯咖啡了，这需要一段时间。

不要忘记-E强制使用环境变量。

sudo apt-get update
sudo apt-get install build-essential tk-dev libncurses5-dev libncursesw5-dev libreadline6-dev libdb5.3-dev libgdbm-dev libsqlite3-dev libssl-dev libbz2-dev libexpat1-dev liblzma-dev zlib1g-dev

检查安装是否有效：

git clone --recursive https://github.com/pytorch/pytorch --branch=release/1.6
cd pytorch

使用 Torch 构建您的程序

在你的CMakeLists.txt：

cmake_minimum_required(VERSION 2.6)
project(projectName)

set(CMAKE_PREFIX_PATH "/home/pi/pytorch/torch") # Adding the directory where torch as been installed
set(CMAKE_CXX_STANDARD 14) # C14 required to compile Torch
set(CMAKE_CXX_STANDARD_REQUIRED TRUE)
add_compile_definitions(_GLIBCXX_USE_CXX11_ABI=0) # Torch is compiled with CXX11_ABI, so your program needs to be also, or you may have conflicts in some libraries (such as GTest for example)

# Specifying we are using pthread for UNIX systems.
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${TORCH_CXX_FLAGS} -pthread -Wall")

find_package(Torch REQUIRED)

if(NOT Torch_FOUND)
    message(FATAL_ERROR "Pytorch Not Found!")
endif(NOT Torch_FOUND)

message(STATUS "Pytorch status :")
message(STATUS "    libraries: ${TORCH_LIBRARIES}")
message(STATUS "    Torch Flags: ${TORCH_CXX_FLAGS}")

# Program executable
add_executable(projectName <sources>)

target_link_libraries(projectName PRIVATE pthread dl util ${TORCH_LIBRARIES})