TensorFlow C++接口编译和使用

部分内容from: Tensorflow C++ 从训练到部署(1)：环境搭建

在之前的编译中，已经编译好了tensorflow_pkg相关的wheel。现在有一个需求，需要按照C++的代码进行模型加载和训练。查询资料后发现，需要重新编译一套TensorFlow支持的C++接口，主要是编译出来libtensorflow_cc.so和libtensorflow_framework.so这两个文件。

bazel build -c opt --copt=-mavx --copt=-msse4.2 --config=monolithic //tensorflow:libtensorflow_cc.so
bazel build -c opt --copt=-mavx  --copt=-msse4.2 --config=monolithic //tensorflow:libtensorflow_framework.so

像这种严格与机器相关的选项，虽然可以加快执行速度，但是在使用之前一定要查明自己的目标机器是否适合。

中间可能会遇到之前的一些问题，功查找https://www.cnblogs.com/jourluohua/p/9180709.html

编译完成后，安装第三方库

source tensorflow/contrib/makefile/build_all_linux.sh

若出现 /autogen.sh: 4: autoreconf: not found 错误，安装 sudo apt-get install autoconf automake libtool

安装头文件和lib文件（不安装也可以，主要是要在CMakeLists文件中配置好就可以）

sudo cp -r bazel-genfiles/ /usr/local/include/tf
sudo cp -r tensorflow/cc /usr/local/include/tf/tensorflow
sudo cp -r tensorflow/core /usr/local/include/tf/tensorflow
sudo cp -r third_party /usr/local/include/tf
sudo cp bazel-bin/tensorflow/libtensorflow_cc.so /usr/local/lib
sudo cp bazel-bin/tensorflow/libtensorflow_framework.so /usr/local/lib

如果你使用的是C的接口，用的是libtensorflow.so库的话，需要拷贝tensorflow/c/相关的文件

之后是新建一个Python文件，去生成相关的pb文件（代码来源于他人代码，有修改）

#!/usr/bin/env python

import tensorflow.compat.v1 as tf
import numpy as np

with tf.Session() as sess:

    a=tf.placeholder(tf.float32,shape=None, name='a')
    b=tf.placeholder(tf.float32,shape=None, name='b')
    c = tf.multiply(a, b, name='c')

    sess.run(tf.global_variables_initializer())

    tf.train.write_graph(sess.graph_def, 'model/', 'simple.pb', as_text=False)

    res = sess.run(c, feed_dict={'a:0': 2.0, 'b:0': 3.0})
    print("res = ", res)

生成了model/simple.pb文件

写load_simple_net.cpp文件（代码来源于他人代码，有修改https://gitee.com/liuzc/tensorflow_cpp.git）

#include "tensorflow/core/public/session.h"
#include "tensorflow/core/platform/env.h"

using namespace tensorflow;
int main(int argc, char* argv[]) {
    // Initialize a tensorflow session
    Session* session;
    Status status = NewSession(SessionOptions(), &session);
    if (!status.ok()) {
        std::cerr << status.ToString() << std::endl;
        return ;
    } else {
        std::cout << "Session created successfully" << std::endl;
    }

    if (argc != )
    {
        std::cerr << std::endl << "Usage: ./project path_to_graph.pb" << std::endl;
        return ;
    }

    // Load the protobuf graph
    GraphDef graph_def;
    std::string graph_path = argv[];
    status = ReadBinaryProto(Env::Default(), graph_path, &graph_def);
    if (!status.ok()) {
        std::cerr << status.ToString() << std::endl;
        return ;
    } else {
        std::cout << "Load graph protobuf successfully" << std::endl;
    }

    // Add the graph to the session
    status = session->Create(graph_def);
    if (!status.ok()) {
        std::cerr << status.ToString() << std::endl;
        return ;
    } else {
        std::cout << "Add graph to session successfully" << std::endl;
    }

    // Setup inputs and outputs:

    // Our graph doesn't require any inputs, since it specifies default values,
    // but we'll change an input to demonstrate.
    Tensor a(DT_FLOAT, TensorShape());
    a.scalar<float>()() = 2.0;

    Tensor b(DT_FLOAT, TensorShape());
    b.scalar<float>()() = 3.0;

    std::vector<std::pair<string, tensorflow::Tensor>> inputs = {
            { "a:0", a },
            { "b:0", b },
    };

    // The session will initialize the outputs
    std::vector<tensorflow::Tensor> outputs;

    // Run the session, evaluating our "c" operation from the graph
    status = session->Run(inputs, {"c:0"}, {}, &outputs);
    if (!status.ok()) {
        std::cerr << status.ToString() << std::endl;
        return ;
    } else {
        std::cout << "Run session successfully" << std::endl;
    }

    // Grab the first output (we only evaluated one graph node: "c")
    // and convert the node to a scalar representation.
    auto output_c = outputs[].scalar<float>();

    // (There are similar methods for vectors and matrices here:
    // https://github.com/tensorflow/tensorflow/blob/master/tensorflow/core/public/tensor.h)

    // Print the results
    std::cout << outputs[].DebugString() << std::endl; // Tensor<type: float shape: [] values: 30>
    std::cout << "Output value: " << output_c() << std::endl; // 30

    // Free any resources used by the session
    session->Close();

    return ;
}

添加CMakeLists文件，目录结构变为

添加eigen库，这里的原因是TensorFlow默认的eigen库，里边实际上是不支持C++接口的，不信的人可以试下，里边的unsupported/CXX/Tensor里边自己include了自己，会导致递归死循环包含错误，因此需要自己添加eigen库，拷贝到当前目录eigen3文件夹下

修改CMakeLists文件，内容为

cmake_minimum_required(VERSION 3.5)
project(tensorflow_cpp)

set(CMAKE_CXX_STANDARD )

find_package(OpenCV 3.0 QUIET)
if(NOT OpenCV_FOUND)
    find_package(OpenCV 2.4. QUIET)
    if(NOT OpenCV_FOUND)
        message(FATAL_ERROR "OpenCV > 2.4.3 not found.")
    endif()
endif()

set(TENSORFLOW_INCLUDES
        /usr/local/include/tf/
        /usr/local/include/tf/bazel-genfiles
        /usr/local/include/tf/tensorflow/
        /usr/local/include/tf/tensorflow/third-party
        )

set(TENSORFLOW_LIBS
        /usr/local/lib/libtensorflow_cc.so
        /usr/local/lib/libtensorflow_framework.so
        )

include_directories(
        ${TENSORFLOW_INCLUDES}
        ${PROJECT_SOURCE_DIR}/eigen3
)

add_executable(load_simple_net load_simple_net.cpp)
target_link_libraries(load_simple_net
        ${TENSORFLOW_LIBS}
        ${OpenCV_LIBS}
        )

新建build文件，进入该build文件中

cd ./build
cmake ..
make

这里有一个非常重要的点，/usr/local/lib/libtensorflow_cc.so /usr/local/lib/libtensorflow_framework.so的顺序关系，如果顺序不对，会一直报

E tensorflow/core/common_runtime/session.cc:89] Not found: No session factory registered for the given session options: {target: "" config: } Registered factories are {}.

使用./load_simple_net  ../model/simple.pb，按道理可以得到正确的值

Session created successfully
Load graph protobuf successfully
Add graph to session successfully
Run session successfully
Tensor<type: float shape: [] values: >
Output value: 

参考资料：

https://medium.com/jim-fleming/loading-tensorflow-graphs-via-host-languages-be10fd81876f

https://medium.com/jim-fleming/loading-a-tensorflow-graph-with-the-c-api-4caaff88463f#.z4qeoyfb0

https://www.tensorflow.org/install/install_c

http://www.liuxiao.org/2018/08/ubuntu-tensorflow-c-%e4%bb%8e%e8%ae%ad%e7%bb%83%e5%88%b0%e9%a2%84%e6%b5%8b1%ef%bc%9a%e7%8e%af%e5%a2%83%e6%90%ad%e5%bb%ba/

https://blog.csdn.net/melissa_cjt/article/details/85983659

https://www.cnblogs.com/shouhuxianjian/p/9416934.html