部分內容from: Tensorflow C++ 從訓練到部署(1)：環境搭建
在之前的編譯中，已經編譯好了tensorflow_pkg相關的wheel。現在有一個需求，需要按照C++的代碼進行模型加載和訓練。查詢資料后發現，需要重新編譯一套TensorFlow支持的C++接口，主要是編譯出來libtensorflow_cc.so和libtensorflow_framework.so這兩個文件。
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
像這種嚴格與機器相關的選項，雖然可以加快執行速度，但是在使用之前一定要查明自己的目標機器是否適合。
中間可能會遇到之前的一些問題，功查找https://www.cnblogs.com/jourluohua/p/9180709.html
編譯完成后，安裝第三方庫
source tensorflow/contrib/makefile/build_all_linux.sh
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庫的話，需要拷貝tensorflow/c/相關的文件
之后是新建一個Python文件，去生成相關的pb文件（代碼來源於他人代碼，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
寫load_simple_net.cpp文件（代碼來源於他人代碼，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 1; } else { std::cout << "Session created successfully" << std::endl; } if (argc != 2) { std::cerr << std::endl << "Usage: ./project path_to_graph.pb" << std::endl; return 1; } // Load the protobuf graph GraphDef graph_def; std::string graph_path = argv[1]; status = ReadBinaryProto(Env::Default(), graph_path, &graph_def); if (!status.ok()) { std::cerr << status.ToString() << std::endl; return 1; } 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 1; } 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 1; } 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[0].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[0].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 0; }
添加CMakeLists文件，目錄結構變為
添加eigen庫，這里的原因是TensorFlow默認的eigen庫，里邊實際上是不支持C++接口的，不信的人可以試下，里邊的unsupported/CXX/Tensor里邊自己include了自己，會導致遞歸死循環包含錯誤，因此需要自己添加eigen庫，拷貝到當前目錄eigen3文件夾下
修改CMakeLists文件，內容為
cmake_minimum_required(VERSION 3.5) project(tensorflow_cpp) set(CMAKE_CXX_STANDARD 11) find_package(OpenCV 3.0 QUIET) if(NOT OpenCV_FOUND) find_package(OpenCV 2.4.3 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，進入該build文件中
cd ./build cmake .. make
這里有一個非常重要的點，/usr/local/lib/libtensorflow_cc.so /usr/local/lib/libtensorflow_framework.so的順序關系，如果順序不對，會一直報
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，按道理可以得到正確的值
Session created successfully Load graph protobuf successfully Add graph to session successfully Run session successfully Tensor<type: float shape: [] values: 6> Output value: 6
參考資料：
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