用C++调用tensorflow在python下训练好的模型(centos7)

本文主要参考博客https://blog.csdn.net/luoyexuge/article/details/80399265 [1]
bazel安装参考:https://blog.csdn.net/luoyi131420/article/details/78585989 [2]

首先介绍下自己的环境是centos7，tensorflow版本是1.7，python是3.6（anaconda3）。

要调用tensorflow c++接口，首先要编译tensorflow，要装bazel，要装protobuf，要装Eigen；然后是用python训练模型并保存，最后才是调用训练好的模型，整体过程还是比较麻烦，下面按步骤一步步说明。

1.安装bazel
以下是引用的[2]

首先安装bazel依赖的环境：
sudo add-apt-repository ppa:webupd8team/java

sudo apt-get install openjdk-8-jdk openjdk-8-source

sudo apt-get install pkg-config zip g++ zlib1g-dev unzip

注意：如果你没有安装add-apt-repository命令，需要执行sudo apt-get install software-properties-common命令。

实际上我自己只缺jdk工具，加上我没有sudo权限，我自己是在网上直接下的jdk-8，链接是
http://www.oracle.com/technetwork/java/javase/downloads/java-archive-javase8-2177648.html
然后解压，最后将其路径添加到环境变量中：
export JAVA_HOME=/home/guozitao001/tools/jdk1.8.0_171
export PATH=$JAVA_HOME/bin:$PATH

然后去git上下载bazel的安装文件https://github.com/bazelbuild/bazel/releases，具体是文件bazel-0.15.0-installer-linux-x86_64.sh。
（1）终端切换到.sh文件存放的路径，文件添加可执行权限：
$ chmod +x bazel-0.5.3-installer-linux-x86_64.sh
（2）然后执行该文件：
$ ./bazel-0.5.3-installer-linux-x86_64.sh –user
注意：–user选项表示bazel安装到HOME/bin目录下，并设置.bazelrc的路径为HOME/.bazelrc。
安装完成后执行bazel看是否安装成功，这里我并没有添加环境变量就可以直接运行，大家根据自己需要添加。

2.安装protobuf

下载地址：https://github.com/google/protobuf/releases ，我下载的是3.5.1版本，如果你是下载新版的tensorflow，请确保protobuf版本也是最新的，安装步骤：
cd /protobuf
./configure
make
sudo make install
安装之后查看protobuf版本：
protoc --version

根据[1]的作者采坑经历所说，protoc一定要注意版本要和tensorflow匹配，总之这里3.5.1的protoc和tensorflow1.7是能够匹配的。

3.安装Eigen

wget http://bitbucket.org/eigen/eigen/get/3.3.4.tar.bz2
下载之后解压放在重新命名为eigen3，我存放的路径是,/Users/zhoumeixu/Downloads/eigen3

这个没什么好多说的，如果wget失败就直接用浏览器或者迅雷下载就是了。

4.tensorflow下载以及编译：
1下载TensorFlow ，使用 git clone - –recursive https://github.com/tensorflow/tensorflow
2.下载bazel工具（mac下载installer-darwin、linux用installer-linux）
3. 进入tensorflow的根目录
3.1 执行./configure 根据提示配置一下环境变量，这个不大重要。
要GPU的话要下载nvidia驱动的尽量装最新版的驱动吧还有cudnn version为5以上的这些在官网都有提及的
3.2 有显卡的执行 ” bazel build –config=opt –config=cuda //tensorflow:libtensorflow_cc.so ”
没显卡的 ” –config=cuda ” 就不要加了
bazel build –config=opt //tensorflow:libtensorflow_cc.so。
编译成功后会有bazel成功的提示。
3.3这里编译完过后，最后调用tensorflow模型的时候的时候提示文件tensorflow/tensorflow/core/platform/default/mutex.h缺2个头文件:nsync_cv.h,nsync_mu.h，仔细查找后，发现这两个头文件在python的site-papackages里面，它只是没找到而已，所以我们在mutex.h中将这两个头文件的路径补充完整：
这里写图片描述
这样之后调用就不会提示缺少头文件了。

4.python训练tensorflow模型：
下面训练tensorflow模型的pb模型，[1]作者做了个简单的线性回归模型及生成pb格式模型代码：

# coding:utf-8
# python 3.6
import tensorflow as  tf
import  numpy as np
import  os
tf.app.flags.DEFINE_integer('training_iteration', 1000,
'number of training iterations.')
tf.app.flags.DEFINE_integer('model_version', 1, 'version number of the model.')
tf.app.flags.DEFINE_string('work_dir', 'model/', 'Working directory.')
FLAGS = tf.app.flags.FLAGS

sess = tf.InteractiveSession()

x = tf.placeholder('float', shape=[None, 5],name="inputs")
y_ = tf.placeholder('float', shape=[None, 1])
w = tf.get_variable('w', shape=[5, 1], initializer=tf.truncated_normal_initializer)
b = tf.get_variable('b', shape=[1], initializer=tf.zeros_initializer)
sess.run(tf.global_variables_initializer())
y = tf.add(tf.matmul(x, w) , b,name="outputs")
ms_loss = tf.reduce_mean((y - y_) ** 2)
train_step = tf.train.GradientDescentOptimizer(0.005).minimize(ms_loss)
train_x = np.random.randn(1000, 5)
# let the model learn the equation of y = x1 * 1 + x2 * 2 + x3 * 3
train_y = np.sum(train_x * np.array([1, 2, 3,4,5]) + np.random.randn(1000, 5) / 100, axis=1).reshape(-1, 1)
for i in range(FLAGS.training_iteration):
    loss, _ = sess.run([ms_loss, train_step], feed_dict={x: train_x, y_: train_y})
    if i%100==0:
        print("loss is:",loss)
        graph = tf.graph_util.convert_variables_to_constants(sess, sess.graph_def,
                                                             ["inputs", "outputs"])
        tf.train.write_graph(graph, ".", FLAGS.work_dir + "liner.pb",
                             as_text=False)
print('Done exporting!')

注意这里一定要把需要输入和输出的变量要以string形式的name在tf.graph_util.convert_variables_to_constants中进行保存，比如说这里的inputs和outputs。得到一个后缀为pb的文件
然后加载该模型，验证是否成功保存模型：

import tensorflow as tf
import  numpy as np
logdir = '/Users/zhoumeixu/Documents/python/credit-nlp-ner/model/'
output_graph_path = logdir+'liner.pb'
with tf.Graph().as_default():
    output_graph_def = tf.GraphDef()
    with open(output_graph_path, "rb") as f:
        output_graph_def.ParseFromString(f.read())
        _ = tf.import_graph_def(output_graph_def,name="")
    with tf.Session() as sess:
        input = sess.graph.get_tensor_by_name("inputs:0")
        output = sess.graph.get_tensor_by_name("outputs:0")
        result = sess.run(output, feed_dict={input: np.reshape([1.0,1.0,1.0,1.0,1.0],[-1,5])})
        print(result)

运行结果:[[14.998546]]，该结果完全符合预期。

5.C++项目代码，一共有4个文件

model_loader_base.h:

#ifndef CPPTENSORFLOW_MODEL_LOADER_BASE_H
#define CPPTENSORFLOW_MODEL_LOADER_BASE_H
#include <iostream>
#include <vector>
#include "tensorflow/core/public/session.h"
#include "tensorflow/core/platform/env.h"

using namespace tensorflow;

namespace tf_model {

/**
 * Base Class for feature adapter, common interface convert input format to tensors
 * */
    class FeatureAdapterBase{
    public:
        FeatureAdapterBase() {};

        virtual ~FeatureAdapterBase() {};

        virtual void assign(std::string, std::vector<double>*) = 0;  // tensor_name, tensor_double_vector

        std::vector<std::pair<std::string, tensorflow::Tensor> > input;

    };

    class ModelLoaderBase {
    public:

        ModelLoaderBase() {};

        virtual ~ModelLoaderBase() {};

        virtual int load(tensorflow::Session*, const std::string) = 0;     //pure virutal function load method

        virtual int predict(tensorflow::Session*, const FeatureAdapterBase&, const std::string, double*) = 0;

        tensorflow::GraphDef graphdef; //Graph Definition for current model

    };

}

#endif //CPPTENSORFLOW_MODEL_LOADER_BASE_H

ann_model_loader.h:

#ifndef CPPTENSORFLOW_ANN_MODEL_LOADER_H
#define CPPTENSORFLOW_ANN_MODEL_LOADER_H

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

using namespace tensorflow;

namespace tf_model {

/**
 * @brief: Model Loader for Feed Forward Neural Network
 * */
    class ANNFeatureAdapter: public FeatureAdapterBase {
    public:

        ANNFeatureAdapter();

        ~ANNFeatureAdapter();

        void assign(std::string tname, std::vector<double>*) override; // (tensor_name, tensor)

    };

    class ANNModelLoader: public ModelLoaderBase {
    public:
        ANNModelLoader();

        ~ANNModelLoader();

        int load(tensorflow::Session*, const std::string) override;    //Load graph file and new session

        int predict(tensorflow::Session*, const FeatureAdapterBase&, const std::string, double*) override;

    };

}


#endif //CPPTENSORFLOW_ANN_MODEL_LOADER_H

ann_model_loader.cpp:

#include <iostream>
#include <vector>
#include <map>
#include "ann_model_loader.h"
//#include <tensor_shape.h>

using namespace tensorflow;

namespace tf_model {

/**
 * ANNFeatureAdapter Implementation
 * */
    ANNFeatureAdapter::ANNFeatureAdapter() {

    }

    ANNFeatureAdapter::~ANNFeatureAdapter() {

    }

/*
 * @brief: Feature Adapter: convert 1-D double vector to Tensor, shape [1, ndim]
 * @param: std::string tname, tensor name;
 * @parma: std::vector<double>*, input vector;
 * */
    void ANNFeatureAdapter::assign(std::string tname, std::vector<double>* vec) {
        //Convert input 1-D double vector to Tensor
        int ndim = vec->size();
        if (ndim == 0) {
            std::cout << "WARNING: Input Vec size is 0 ..." << std::endl;
            return;
        }
        // Create New tensor and set value
        Tensor x(tensorflow::DT_FLOAT, tensorflow::TensorShape({1, ndim})); // New Tensor shape [1, ndim]
        auto x_map = x.tensor<float, 2>();
        for (int j = 0; j < ndim; j++) {
            x_map(0, j) = (*vec)[j];
        }
        // Append <tname, Tensor> to input
        input.push_back(std::pair<std::string, tensorflow::Tensor>(tname, x));
    }

/**
 * ANN Model Loader Implementation
 * */
    ANNModelLoader::ANNModelLoader() {

    }

    ANNModelLoader::~ANNModelLoader() {

    }

/**
 * @brief: load the graph and add to Session
 * @param: Session* session, add the graph to the session
 * @param: model_path absolute path to exported protobuf file *.pb
 * */

    int ANNModelLoader::load(tensorflow::Session* session, const std::string model_path) {
        //Read the pb file into the grapgdef member
        tensorflow::Status status_load = ReadBinaryProto(Env::Default(), model_path, &graphdef);
        if (!status_load.ok()) {
            std::cout << "ERROR: Loading model failed..." << model_path << std::endl;
            std::cout << status_load.ToString() << "\n";
            return -1;
        }

        // Add the graph to the session
        tensorflow::Status status_create = session->Create(graphdef);
        if (!status_create.ok()) {
            std::cout << "ERROR: Creating graph in session failed..." << status_create.ToString() << std::endl;
            return -1;
        }
        return 0;
    }

/**
 * @brief: Making new prediction
 * @param: Session* session
 * @param: FeatureAdapterBase, common interface of input feature
 * @param: std::string, output_node, tensorname of output node
 * @param: double, prediction values
 * */

    int ANNModelLoader::predict(tensorflow::Session* session, const FeatureAdapterBase& input_feature,
                                const std::string output_node, double* prediction) {
        // The session will initialize the outputs
        std::vector<tensorflow::Tensor> outputs;         //shape  [batch_size]

        // @input: vector<pair<string, tensor> >, feed_dict
        // @output_node: std::string, name of the output node op, defined in the protobuf file
        tensorflow::Status status = session->Run(input_feature.input, {output_node}, {}, &outputs);
        if (!status.ok()) {
            std::cout << "ERROR: prediction failed..." << status.ToString() << std::endl;
            return -1;
        }

        //Fetch output value
        std::cout << "Output tensor size:" << outputs.size() << std::endl;
        for (std::size_t i = 0; i < outputs.size(); i++) {
            std::cout << outputs[i].DebugString();
        }
        std::cout << std::endl;

        Tensor t = outputs[0];                   // Fetch the first tensor
        int ndim = t.shape().dims();             // Get the dimension of the tensor
        auto tmap = t.tensor<float, 2>();        // Tensor Shape: [batch_size, target_class_num]
        int output_dim = t.shape().dim_size(1);  // Get the target_class_num from 1st dimension
        std::vector<double> tout;

        // Argmax: Get Final Prediction Label and Probability
        int output_class_id = -1;
        double output_prob = 0.0;
        for (int j = 0; j < output_dim; j++) {
            std::cout << "Class " << j << " prob:" << tmap(0, j) << "," << std::endl;
            if (tmap(0, j) >= output_prob) {
                output_class_id = j;
                output_prob = tmap(0, j);
            }
        }

        // Log
        std::cout << "Final class id: " << output_class_id << std::endl;
        std::cout << "Final value is: " << output_prob << std::endl;

        (*prediction) = output_prob;   // Assign the probability to prediction
        return 0;
    }

}

main.cpp：

#include <iostream>
#include "tensorflow/core/public/session.h"
#include "tensorflow/core/platform/env.h"
#include "ann_model_loader.h"

using namespace tensorflow;

int main(int argc, char* argv[]) {
    if (argc != 2) {
        std::cout << "WARNING: Input Args missing" << std::endl;
        return 0;
    }
    std::string model_path = argv[1];  // Model_path *.pb file

    // TensorName pre-defined in python file, Need to extract values from tensors
    std::string input_tensor_name = "inputs";
    std::string output_tensor_name = "outputs";

    // Create New Session
    Session* session;
    Status status = NewSession(SessionOptions(), &session);
    if (!status.ok()) {
        std::cout << status.ToString() << "\n";
        return 0;
    }

    // Create prediction demo
    tf_model::ANNModelLoader model;  //Create demo for prediction
    if (0 != model.load(session, model_path)) {
        std::cout << "Error: Model Loading failed..." << std::endl;
        return 0;
    }

    // Define Input tensor and Feature Adapter
    // Demo example: [1.0, 1.0, 1.0, 1.0, 1.0] for Iris Example, including bias
    int ndim = 5;
    std::vector<double> input;
    for (int i = 0; i < ndim; i++) {
        input.push_back(1.0);
    }

    // New Feature Adapter to convert vector to tensors dictionary
    tf_model::ANNFeatureAdapter input_feat;
    input_feat.assign(input_tensor_name, &input);   //Assign vec<double> to tensor

    // Make New Prediction
    double prediction = 0.0;
    if (0 != model.predict(session, input_feat, output_tensor_name, &prediction)) {
        std::cout << "WARNING: Prediction failed..." << std::endl;
    }
    std::cout << "Output Prediction Value:" << prediction << std::endl;

    return 0;
}

将这四个文件放在同一个路径下，然后还需要添加一个Cmake的txt文件：


cmake_minimum_required(VERSION 2.8)
project(cpptensorflow)
set(CMAKE_CXX_STANDARD 11)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -std=gnu++0x -g -fopenmp -fno-strict-aliasing")
link_directories(/home/xxx/tensorflow/bazel-bin/tensorflow)
include_directories(
        /home/xxx/tensorflow
        /home/xxx/tensorflow/bazel-genfiles
        /home/xxx/tensorflow/bazel-bin/tensorflow
        /home/xxx/tools/eigen3
)
add_executable(cpptensorflow main.cpp ann_model_loader.h model_loader_base.h ann_model_loader.cpp)
target_link_libraries(cpptensorflow tensorflow_cc tensorflow_framework)

这里注意cmake_minimum_required(VERSION 2.8)要和自己系统的cmake最低版本相符合。

然后在当前目录下建立一个build的空文件夹：
这里写图片描述

mkdir  build
cd  build
cmake ..
make 
生成cpptensorflow执行文件，后接保存的模型pb文件路径：
./cpptensorflow /Users/zhoumeixu/Documents/python/credit-nlp-ner/model/liner.pb
Final value is: 14.9985
Output Prediction Value:14.9985

到此基本就结束了，最后感谢下作者[1]，我真是差点被搞疯了。。。

原文：https://blog.csdn.net/gzt940726/article/details/81053378

posted @ 2018-08-22 11:15 瘋耔阅读(1172) 评论(0) 编辑收藏举报

会员力量，点亮园子希望

刷新页面返回顶部