TensorFlow 的 c ++ 实践及各种坑!

前言

Tensorflow当前官网仅包含python、C、Java、Go的发布包,并无C++ release包,并且tensorflow官网也注明了并不保证除python以外库的稳定性,在功能方面python也是最完善的。众所周知,python在开发效率、易用性上有着巨大的优势,但作为一个解释性语言,在性能方面还是存在比较大的缺陷,在各类AI服务化过程中,采用python作为模型快速构建工具,使用高级语言(如C++,java)作为服务化程序实现是大势所趋。本文重点介绍tensorflow C++服务化过程中实现方式及遇到的各种问题。

实现方案

对于tensorflow c++库的使用,有两种方法:

(1) 最佳方式当然是直接用C++构建graph,但是当前c++tensorflow库并不像python api那样full-featured。可参照builds a small graph in c++ here, C++ tensorflow api中还包含cpu和gpu的数字内核实现的类,可用以添加新的op。可参照https://www.tensorflow.org/extend/adding_an_op

(2) 常用的方式,c++调用python生成好的graph。本文主要介绍该方案。

实现步骤

(1) 编译tensorflow源码C++ so

(2) 模型训练输出结果

(3) 模型固化

(4) 模型加载及运行

(5) 运行问题

(1) 源码编译

环境要求: 公司tlinux2.2版本, GCC版本 >= 4.8.5

安装组件: protobuf 3.3.0 bazel 0.5.0 python 2.7 java8

机器要求: 4GB内存

a. 安装java8

yum install java

b. 安装protobuf 3.3.0

下载 下载https://github.com/google/protobuf/archive/v3.3.0.zip

./configure && make && make install

c. 安装bazel

download https://github.com/bazelbuild/bazel/releases

sh bazel-0.5.0-installer-linux-x86_64.sh

d. 编译源码

最好采用最新release版本:https://github.com/tensorflow/tensorflow/releases

bazel build //tensorflow:libtensorflow_cc.so

编译过程中可能遇到的问题:

问题一: fatal error: unsupported/Eigen/CXX11/Tensor: No such file or directory

安装Eigen3.3或以上版本

问题二: java.io.IOException: Cannot run program "patch"

yum install patch

问题三: 内存不够

(2) 模型训练与输出

模型训练输出可参照改用例去实践https://blog.metaflow.fr/tensorflow-saving-restoring-and-mixing-multiple-models-c4c94d5d7125 , google上也很多,模型训练保存好得到下面文件:

(3) 模型固化

模型固化方式有三种:

a. freeze_graph 工具

bazel build tensorflow/python/tools:freeze_graph && bazel-bin/tensorflow/python/tools/freeze_graph 
        --input_graph=graph.pb 
        --input_checkpoint=checkpoint 
        --output_graph=./frozen_graph.pb 
        --output_node_names=output/output/scores

b. 利用freeze_graph.py工具

# We save out the graph to disk, and then call the const conversion# routine.checkpoint_state_name = "checkpoint"
input_graph_name = "graph.pb"
output_graph_name = "frozen_graph.pb"

input_graph_path = os.path.join(FLAGS.model_dir, input_graph_name)
input_saver_def_path = ""
input_binary = False
input_checkpoint_path = os.path.join(FLAGS.checkpoint_dir, 'saved_checkpoint') + "-0"# Note that we this normally should be only "output_node"!!!output_node_names = "output/output/scores" 
restore_op_name = "save/restore_all"
filename_tensor_name = "save/Const:0"
output_graph_path = os.path.join(FLAGS.model_dir, output_graph_name)
clear_devices = False

freeze_graph.freeze_graph(input_graph_path, input_saver_def_path,
                          input_binary, input_checkpoint_path,
                          output_node_names, restore_op_name,
                          filename_tensor_name, output_graph_path,
                          clear_devices)

c. 利用tensorflow python

import os, argparseimport tensorflow as tffrom tensorflow.python.framework import graph_util

dir = os.path.dirname(os.path.realpath(__file__))def freeze_graph(model_folder):
    # We retrieve our checkpoint fullpath
    checkpoint = tf.train.get_checkpoint_state(model_folder)
    input_checkpoint = checkpoint.model_checkpoint_path    # We precise the file fullname of our freezed graph
    absolute_model_folder = "/".join(input_checkpoint.split('/')[:-1])
    output_graph = absolute_model_folder + "/frozen_model.pb"
    print output_graph    # Before exporting our graph, we need to precise what is our output node
    # This is how TF decides what part of the Graph he has to keep and what part it can dump
    # NOTE: this variable is plural, because you can have multiple output nodes
    output_node_names = "output/output/scores"

    # We clear devices to allow TensorFlow to control on which device it will load operations
    clear_devices = True

    # We import the meta graph and retrieve a Saver
    saver = tf.train.import_meta_graph(input_checkpoint + '.meta', clear_devices=clear_devices)    # We retrieve the protobuf graph definition
    graph = tf.get_default_graph()
    input_graph_def = graph.as_graph_def()    # fix batch norm nodes
    for node in input_graph_def.node:        if node.op == 'RefSwitch':
            node.op = 'Switch'
            for index in xrange(len(node.input)):                if 'moving_' in node.input[index]:
                    node.input[index] = node.input[index] + '/read'
        elif node.op == 'AssignSub':
            node.op = 'Sub'
            if 'use_locking' in node.attr: del node.attr['use_locking']    # We start a session and restore the graph weights
    with tf.Session() as sess:
        saver.restore(sess, input_checkpoint)        # We use a built-in TF helper to export variables to constants
        output_graph_def = graph_util.convert_variables_to_constants(
            sess, # The session is used to retrieve the weights
            input_graph_def, # The graph_def is used to retrieve the nodes 
            output_node_names.split(",") # The output node names are used to select the usefull nodes
        ) 

        # Finally we serialize and dump the output graph to the filesystem
        with tf.gfile.GFile(output_graph, "wb") as f:
            f.write(output_graph_def.SerializeToString())
        print("%d ops in the final graph." % len(output_graph_def.node))if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument("--model_folder", type=str, help="Model folder to export")
    args = parser.parse_args()

    freeze_graph(args.model_folder)

坑 BatchNorm bug

在具体实际项目,用方式一与方式二将生成的模型利用tensorflow c++ api加载,报以上错误,采用tensorflow python加载模型报同样错:

原因是模型中用到了BatchNorm,修复方式如上面c中给出的方案

(4) 模型加载及运行

构建输入输出

模型输入输出主要就是构造输入输出矩阵,相比python的numpy库,tensorflow提供的Tensor和Eigen::Tensor还是非常难用的,特别是动态矩阵创建,如果你的编译器支持C++14,可以用xTensor库,和numpy一样强大,并且用法机器类似。如果是C++11版本就好好看看eigen库和tensorflow::Tensor文档吧。例举集中简单的用法:

矩阵赋值:

tensorflow::Tensor four_dim_plane(DT_FLOAT, tensorflow::TensorShape({1, MODEL_X_AXIS_LEN, MODEL_Y_AXIS_LEN, fourth_dim_size}));
auto plane_tensor = four_dim_plane.tensor<float, 4>();for (uint32_t k = 0; k < array_plane.size(); ++k)
{    for (uint32_t j = 0; j < MODEL_Y_AXIS_LEN; ++j)
    {        for (uint32_t i = 0; i < MODEL_X_AXIS_LEN; ++i)
        {
            plane_tensor(0, i, j, k) = array_plane[k](i, j); 
        }
    }
}

SOFTMAX:

Eigen::Tensor<float, 1> ModelApp::TensorSoftMax(const Eigen::Tensor<float, 1>& tensor)
{
    Eigen::Tensor<float, 0> max = tensor.maximum();    auto e_x = (tensor - tensor.constant(max())).exp();
    Eigen::Tensor<float, 0> e_x_sum = e_x.sum();    return e_x / e_x_sum();
}

模型加载及session初始化:

int32_t ModelApp::Init(const std::string& graph_file, Logger *logger)
{
    auto status = NewSession(SessionOptions(), &m_session); 
    if (!status.ok())
    {
        LOG_ERR(logger, "New session failed! %s", status.ToString().c_str());        return Error::ERR_FAILED_NEW_TENSORFLOW_SESSION;
    }

    GraphDef graph_def;
    status = ReadBinaryProto(Env::Default(), graph_file, &graph_def);    if (!status.ok()) 
    {
        LOG_ERR(logger, "Read binary proto failed! %s", status.ToString().c_str());        return Error::ERR_FAILED_READ_BINARY_PROTO;
    }

    status = m_session->Create(graph_def);    if (!status.ok()) 
    {
        LOG_ERR(logger, "Session create failed! %s", status.ToString().c_str());        return Error::ERR_FAILED_CREATE_TENSORFLOW_SESSION;
    }    return Error::Success;
}

运行:

0.10以上的tensorflow库是线程安全的,因此可多线程调用predict

int32_t ModelApp::Predict(const Action& action, std::vector<int>* info, Logger *logger)
{
    ...
    auto tensor_x = m_writer->Generate(action, logger);

    Tensor phase_train(DT_BOOL, TensorShape());
    phase_train.scalar<bool>()() = false;
    std::vector<std::pair<std::string, Tensor>> inputs = {
        {"input_x", tensor_x},
        {"phase_train", phase_train}
    }; 

    std::vector<Tensor> result;
    auto status = m_session->Run(inputs, {"output/output/scores"}, {}, &result);    if (!status.ok())
    {
        LOG_ERR(logger, "Session run failed! %s", status.ToString().c_str());        return Error::ERR_FAILED_TENSORFLOW_EXECUTION;
    }
    ...
    auto scores = result[0].flat<float>() ;
    ...    return Error::SUCCESS;
}

(5) 运行问题

问题一:运行告警

2017-08-16 14:11:14.393295: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.2017-08-16 14:11:14.393324: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2017-08-16 14:11:14.393331: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.2017-08-16 14:11:14.393338: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.

是因为在编译tensorflow so库的时候没有把这些CPU加速指令编译进去,因此可以在编译的时候加入加速指令,在没有GPU条件下,加入这些库实测可以将CPU计算提高10%左右。

bazel build -c opt --copt=-mavx --copt=-mfma --copt=-mfpmath=both --copt=-msse4.2 -k //tensorflow:libtensorflow_cc.so

需要注意的是并不是所有CPU都支持这些指令,一定要实机测试,以免abort。

问题二: C++ libtensorflow和python tensorflow混用

为验证C++加载模型调用的准确性,利用swig将c++ api封装成了python库供python调用,在同时import tensorflow as tf和import封装好的python swig接口时,core dump

该问题tensorflow官方并不打算解决

本文来自 全球人工智能 微信公众号

原创声明,本文系作者授权云+社区发表,未经许可,不得转载。

如有侵权,请联系 yunjia_community@tencent.com 删除。

编辑于

我来说两句

0 条评论
登录 后参与评论

相关文章

来自专栏CreateAMind

多目标的强化学习教程-两篇均有代码

902
来自专栏Python小屋

Win10系统配置Python3.6+OpenGL环境详细步骤

1、首先登录https://www.opengl.org/resources/libraries/glut/,下载下图箭头所指的文件 ? 2、解压缩,如下图所示...

3747
来自专栏小鹏的专栏

ubuntu下C++如何调用matlab程序

实验平台:   ubuntu  matlab R2016b   g++ 步骤: 1.    设置matlab的编译器 在命令行窗口下,输入并执行如下命令:m...

25610
来自专栏GIS讲堂

dojo chart生成函数

893
来自专栏何俊林

一种JNI方法实现图片压缩,压缩率极高

直接使用项目或直接复制libs中的so库到项目中即可(当前只构建了armeabi),需要其他ABI可检下项目另外使用CMake构建即可。

1483
来自专栏Fish

CUDA C最佳实践-CUDA Best Practices(三)

10. 运行配置优化 10.1. 占用 10.1.1. 计算占用 10.2. 同步Kernel执行 10.3. 多上下文 10.4. 隐藏寄存器依赖 10.5....

21810
来自专栏编程札记

数据库内部排序算法之两阶段多路归并排序算法实现

5103
来自专栏曾子骄的专栏

Tensorflow c++ 实践及各种坑

众所周知,python 在开发效率、易用性上有着巨大的优势,但作为一个解释性语言,在性能方面还是存在比较大的缺陷,在各类AI服务化过程中,采用 python 作...

9.8K4
来自专栏生信宝典

Python学习教程 (六)

作业(三) 使 “作业(二)” 中的程序都能接受命令行参数 import sys sys.argv import optparse 用到的知识点 2.备注...

2239
来自专栏CreateAMind

A3C run torcs

check: https://github.com/bn2302/rl_torcs/issues

1063

扫码关注云+社区