調用caffe進行網絡訓練（caffe.cpp 解析）

 caffe.cpp 文件爲調用caffe進行網絡訓練的主要代碼，內包含 train,test,time等函數對網絡進行訓練，微調，測試，時間計算。

 caffe.cpp文件位於： /caffe-master/tools/caffe.cpp

使用方法：

    train.sh

#!/usr/bin/env sh

TOOLS=/usr/local/caffe-master/build/tools
GLOG_logtostderr=0 GLOG_log_dir=Log/ \
$TOOLS/caffe train \
  --solver=./solver.prototxt # \
  --snapshot=snapshot_iter_1100000.solverstate

參考博文： http://blog.sina.com.cn/s/blog_9a3e0f110102w9r1.html

#ifdef WITH_PYTHON_LAYER
#include "boost/python.hpp"
namespace bp = boost::python;
#endif

#include <gflags/gflags.h>  //簡化命令行參數解析庫
#include <glog/logging.h>

#include <cstring>
#include <map>
#include <string>
#include <vector>

#include "boost/algorithm/string.hpp"
#include "caffe/caffe.hpp"
#include "caffe/util/signal_handler.h"

using caffe::Blob;
using caffe::Caffe;
using caffe::Net;
using caffe::Layer;
using caffe::Solver;
using caffe::shared_ptr;
using caffe::string;
using caffe::Timer;
using caffe::vector;
using std::ostringstream;

//定義函數參數：參數名，默認值，--help時的說明文字
//使用方法：--iterations=60
DEFINE_string(gpu, "",
    "Optional; run in GPU mode on given device IDs separated by ','."
    "Use '-gpu all' to run on all available GPUs. The effective training "
    "batch size is multiplied by the number of devices.");
DEFINE_string(solver, "",
    "The solver definition protocol buffer text file.");
DEFINE_string(model, "",
    "The model definition protocol buffer text file.");
DEFINE_string(snapshot, "",
    "Optional; the snapshot solver state to resume training.");
DEFINE_string(weights, "",
    "Optional; the pretrained weights to initialize finetuning, "
    "separated by ','. Cannot be set simultaneously with snapshot.");
DEFINE_int32(iterations, 50,
    "The number of iterations to run.");
DEFINE_string(sigint_effect, "stop",  //中斷信號
             "Optional; action to take when a SIGINT signal is received: "
              "snapshot, stop or none.");
DEFINE_string(sighup_effect, "snapshot",   //終止信號
             "Optional; action to take when a SIGHUP signal is received: "
             "snapshot, stop or none.");

// A simple registry for caffe commands.
typedef int (*BrewFunction)();  //定義函數指針類型
typedef std::map<caffe::string, BrewFunction> BrewMap;  //C++標準map容器,容器類型名爲BrewMap
BrewMap g_brew_map;  //聲明map容器變量

// 宏定義，比如RegisterBrewFunction（train）時，相當於在容器g_brew_map中註冊了train函數的函數指針和其對應的名字“train”.
//在C/C++的宏中，”#”的功能是將其後面的宏參數進行字符串化操作(Stringfication)，簡單說就是在對它所引用的宏變量通過替換後在其左右各加上一個雙引號。
//”##”被稱爲連接符(concatenator)，用來將兩個子串Token連接爲一個Token。注意這裏連接的對象是Token就行，而不一定是宏的變量。
#define RegisterBrewFunction(func) \
namespace { \
class __Registerer_##func { \
 public: /* NOLINT */ \
  __Registerer_##func() { \
    g_brew_map[#func] = &func; \
  } \
}; \
__Registerer_##func g_registerer_##func; \
}

//在g_brew_map容器中查找對應函數指針並返回
//LOG來源於google的glog庫，控制程序的日誌輸出消息和測試消息
static BrewFunction GetBrewFunction(const caffe::string& name) {
  if (g_brew_map.count(name)) {
    return g_brew_map[name];
  } else {
    LOG(ERROR) << "Available caffe actions:";
    for (BrewMap::iterator it = g_brew_map.begin();
         it != g_brew_map.end(); ++it) {
      LOG(ERROR) << "\t" << it->first;
    }
    LOG(FATAL) << "Unknown action: " << name;
    return NULL;  // not reachable, just to suppress old compiler warnings.
  }
}

// Parse GPU ids or use all available devices
//解析可用GPU，使用所有硬件 
static void get_gpus(vector<int>* gpus) {
  if (FLAGS_gpu == "all") {
    int count = 0;
#ifndef CPU_ONLY
    CUDA_CHECK(cudaGetDeviceCount(&count));
#else
    NO_GPU;
#endif
    for (int i = 0; i < count; ++i) {
      gpus->push_back(i);
    }
  } else if (FLAGS_gpu.size()) {
    vector<string> strings;
    boost::split(strings, FLAGS_gpu, boost::is_any_of(","));
    for (int i = 0; i < strings.size(); ++i) {
      gpus->push_back(boost::lexical_cast<int>(strings[i]));
    }
  } else {
    CHECK_EQ(gpus->size(), 0);
  }
}

//caffe 命令的調用方法：caffe <command> <args>
// caffe commands to call by
//     caffe <command> <args>
//
// To add a command, define a function "int command()" and register it with
// RegisterBrewFunction(action);

// Device Query: show diagnostic information for a GPU device.
//查詢GPU信息
int device_query() {
  LOG(INFO) << "Querying GPUs " << FLAGS_gpu;
  vector<int> gpus;
  get_gpus(&gpus);
  for (int i = 0; i < gpus.size(); ++i) {
    caffe::Caffe::SetDevice(gpus[i]);
    caffe::Caffe::DeviceQuery();
  }
  return 0;
}
RegisterBrewFunction(device_query);

// Load the weights from the specified caffemodel(s) into the train and
// test nets.
//加載特定模型的權重到網絡中
void CopyLayers(caffe::Solver<float>* solver, const std::string& model_list) {
  std::vector<std::string> model_names;
  boost::split(model_names, model_list, boost::is_any_of(",") );
  for (int i = 0; i < model_names.size(); ++i) {
    LOG(INFO) << "Finetuning from " << model_names[i];
    solver->net()->CopyTrainedLayersFrom(model_names[i]);
    for (int j = 0; j < solver->test_nets().size(); ++j) {
      solver->test_nets()[j]->CopyTrainedLayersFrom(model_names[i]);
    }
  }
}

// Translate the signal effect the user specified on the command-line to the
// corresponding enumeration.
//獲取請求操作
caffe::SolverAction::Enum GetRequestedAction(
    const std::string& flag_value) {
  if (flag_value == "stop") {
    return caffe::SolverAction::STOP;
  }
  if (flag_value == "snapshot") {
    return caffe::SolverAction::SNAPSHOT;
  }
  if (flag_value == "none") {
    return caffe::SolverAction::NONE;
  }
  LOG(FATAL) << "Invalid signal effect \""<< flag_value << "\" was specified";
}

// Train / Finetune a model.
//訓練，微調一個網絡模型
int train() {
  // google的glog庫，檢查--solver、--snapshot和--weight並輸出消息；必須有指定solver，snapshot和weight兩者指定其一；
  CHECK_GT(FLAGS_solver.size(), 0) << "Need a solver definition to train.";
  CHECK(!FLAGS_snapshot.size() || !FLAGS_weights.size())
      << "Give a snapshot to resume training or weights to finetune "
      "but not both.";

  caffe::SolverParameter solver_param;  //實例化SolverParameter類，該類保存solver參數和相應的方法
  caffe::ReadSolverParamsFromTextFileOrDie(FLAGS_solver, &solver_param); //將-solver指定solver.prototxt文件內容解析到solver_param中

  // If the gpus flag is not provided, allow the mode and device to be set
  // in the solver prototxt.
  // 根據命令參數-gpu或者solver.prototxt提供的信息設置GPU
  if (FLAGS_gpu.size() == 0
      && solver_param.solver_mode() == caffe::SolverParameter_SolverMode_GPU) {
      if (solver_param.has_device_id()) {
          FLAGS_gpu = "" +
              boost::lexical_cast<string>(solver_param.device_id());  
      } else {  // Set default GPU if unspecified
          FLAGS_gpu = "" + boost::lexical_cast<string>(0);  // boost::lexical_cast(0)是將數值0轉換爲字符串'“0”；
      }
  }

  // 多GPU下，將GPU編號存入vector容器中（get_gpus()函數通過FLAGS_gpu獲取）；
  vector<int> gpus;
  get_gpus(&gpus);
  if (gpus.size() == 0) {
    LOG(INFO) << "Use CPU.";
    Caffe::set_mode(Caffe::CPU);
  } else {
    ostringstream s;
    for (int i = 0; i < gpus.size(); ++i) {
      s << (i ? ", " : "") << gpus[i];
    }
    LOG(INFO) << "Using GPUs " << s.str();
#ifndef CPU_ONLY
    cudaDeviceProp device_prop;
    for (int i = 0; i < gpus.size(); ++i) {
      cudaGetDeviceProperties(&device_prop, gpus[i]);
      LOG(INFO) << "GPU " << gpus[i] << ": " << device_prop.name;
    }
#endif
    solver_param.set_device_id(gpus[0]);
    Caffe::SetDevice(gpus[0]);
    Caffe::set_mode(Caffe::GPU);
    Caffe::set_solver_count(gpus.size());
  }
  
  // 處理snapshot, stop or none信號，其聲明在include/caffe/util/signal_Handler.h中；
  // GetRequestedAction在caffe.cpp中，將‘stop’，‘snapshot’，‘none’轉換爲標準信號，即解析；
  caffe::SignalHandler signal_handler(
        GetRequestedAction(FLAGS_sigint_effect),
        GetRequestedAction(FLAGS_sighup_effect));

  //指向caffe::Solver對象，該對象由CreateSolver創建
  shared_ptr<caffe::Solver<float> >
      solver(caffe::SolverRegistry<float>::CreateSolver(solver_param));

  //solver設置操作函數
  solver->SetActionFunction(signal_handler.GetActionFunction());

  // 從snapshot或caffemodel中恢復train；
  if (FLAGS_snapshot.size()) {
    LOG(INFO) << "Resuming from " << FLAGS_snapshot;
    solver->Restore(FLAGS_snapshot.c_str());
  } else if (FLAGS_weights.size()) {
    CopyLayers(solver.get(), FLAGS_weights);
  }

  if (gpus.size() > 1) {
    caffe::P2PSync<float> sync(solver, NULL, solver->param());
    sync.Run(gpus);
  } else {
    LOG(INFO) << "Starting Optimization";
    solver->Solve();   // // 初始化完成，開始優化網絡
  }
  LOG(INFO) << "Optimization Done.";
  return 0;
}
RegisterBrewFunction(train);


// Test: score a model.
//測試網絡模型
int test() {
  CHECK_GT(FLAGS_model.size(), 0) << "Need a model definition to score.";
  CHECK_GT(FLAGS_weights.size(), 0) << "Need model weights to score.";

  // Set device id and mode
  vector<int> gpus;
  get_gpus(&gpus);
  if (gpus.size() != 0) {
    LOG(INFO) << "Use GPU with device ID " << gpus[0];
#ifndef CPU_ONLY
    cudaDeviceProp device_prop;
    cudaGetDeviceProperties(&device_prop, gpus[0]);
    LOG(INFO) << "GPU device name: " << device_prop.name;
#endif
    Caffe::SetDevice(gpus[0]);
    Caffe::set_mode(Caffe::GPU);
  } else {
    LOG(INFO) << "Use CPU.";
    Caffe::set_mode(Caffe::CPU);
  }
  // Instantiate the caffe net.  
  //實例化caffe網絡
  Net<float> caffe_net(FLAGS_model, caffe::TEST);
  caffe_net.CopyTrainedLayersFrom(FLAGS_weights);
  LOG(INFO) << "Running for " << FLAGS_iterations << " iterations.";

  vector<int> test_score_output_id;
  vector<float> test_score;
  float loss = 0;
  for (int i = 0; i < FLAGS_iterations; ++i) {
    float iter_loss;
    const vector<Blob<float>*>& result =
        caffe_net.Forward(&iter_loss);
    loss += iter_loss;
    int idx = 0;
    for (int j = 0; j < result.size(); ++j) {
      const float* result_vec = result[j]->cpu_data();
      for (int k = 0; k < result[j]->count(); ++k, ++idx) {
        const float score = result_vec[k];
        if (i == 0) {
          test_score.push_back(score);
          test_score_output_id.push_back(j);
        } else {
          test_score[idx] += score;
        }
        const std::string& output_name = caffe_net.blob_names()[
            caffe_net.output_blob_indices()[j]];
        LOG(INFO) << "Batch " << i << ", " << output_name << " = " << score;
      }
    }
  }
  loss /= FLAGS_iterations;
  LOG(INFO) << "Loss: " << loss;
  for (int i = 0; i < test_score.size(); ++i) {
    const std::string& output_name = caffe_net.blob_names()[
        caffe_net.output_blob_indices()[test_score_output_id[i]]];
    const float loss_weight = caffe_net.blob_loss_weights()[
        caffe_net.output_blob_indices()[test_score_output_id[i]]];
    std::ostringstream loss_msg_stream;
    const float mean_score = test_score[i] / FLAGS_iterations;
    if (loss_weight) {
      loss_msg_stream << " (* " << loss_weight
                      << " = " << loss_weight * mean_score << " loss)";
    }
    LOG(INFO) << output_name << " = " << mean_score << loss_msg_stream.str();
  }

  return 0;
}
RegisterBrewFunction(test);


// Time: benchmark the execution time of a model.
//測試網絡模型的執行時間
int time() {
  CHECK_GT(FLAGS_model.size(), 0) << "Need a model definition to time.";

  // Set device id and mode
  vector<int> gpus;
  get_gpus(&gpus);
  if (gpus.size() != 0) {
    LOG(INFO) << "Use GPU with device ID " << gpus[0];
    Caffe::SetDevice(gpus[0]);
    Caffe::set_mode(Caffe::GPU);
  } else {
    LOG(INFO) << "Use CPU.";
    Caffe::set_mode(Caffe::CPU);
  }
  // Instantiate the caffe net.
  Net<float> caffe_net(FLAGS_model, caffe::TRAIN);

  // Do a clean forward and backward pass, so that memory allocation are done
  // and future iterations will be more stable.
  LOG(INFO) << "Performing Forward";
  // Note that for the speed benchmark, we will assume that the network does
  // not take any input blobs.
  float initial_loss;
  caffe_net.Forward(&initial_loss);
  LOG(INFO) << "Initial loss: " << initial_loss;
  LOG(INFO) << "Performing Backward";
  caffe_net.Backward();

  const vector<shared_ptr<Layer<float> > >& layers = caffe_net.layers();
  const vector<vector<Blob<float>*> >& bottom_vecs = caffe_net.bottom_vecs();
  const vector<vector<Blob<float>*> >& top_vecs = caffe_net.top_vecs();
  const vector<vector<bool> >& bottom_need_backward =
      caffe_net.bottom_need_backward();
  LOG(INFO) << "*** Benchmark begins ***";
  LOG(INFO) << "Testing for " << FLAGS_iterations << " iterations.";
  Timer total_timer;
  total_timer.Start();
  Timer forward_timer;
  Timer backward_timer;
  Timer timer;
  std::vector<double> forward_time_per_layer(layers.size(), 0.0);
  std::vector<double> backward_time_per_layer(layers.size(), 0.0);
  double forward_time = 0.0;
  double backward_time = 0.0;
  for (int j = 0; j < FLAGS_iterations; ++j) {
    Timer iter_timer;
    iter_timer.Start();
    forward_timer.Start();
    for (int i = 0; i < layers.size(); ++i) {
      timer.Start();
      layers[i]->Forward(bottom_vecs[i], top_vecs[i]);
      forward_time_per_layer[i] += timer.MicroSeconds();
    }
    forward_time += forward_timer.MicroSeconds();
    backward_timer.Start();
    for (int i = layers.size() - 1; i >= 0; --i) {
      timer.Start();
      layers[i]->Backward(top_vecs[i], bottom_need_backward[i],
                          bottom_vecs[i]);
      backward_time_per_layer[i] += timer.MicroSeconds();
    }
    backward_time += backward_timer.MicroSeconds();
    LOG(INFO) << "Iteration: " << j + 1 << " forward-backward time: "
      << iter_timer.MilliSeconds() << " ms.";
  }
  LOG(INFO) << "Average time per layer: ";
  for (int i = 0; i < layers.size(); ++i) {
    const caffe::string& layername = layers[i]->layer_param().name();
    LOG(INFO) << std::setfill(' ') << std::setw(10) << layername <<
      "\tforward: " << forward_time_per_layer[i] / 1000 /
      FLAGS_iterations << " ms.";
    LOG(INFO) << std::setfill(' ') << std::setw(10) << layername  <<
      "\tbackward: " << backward_time_per_layer[i] / 1000 /
      FLAGS_iterations << " ms.";
  }
  total_timer.Stop();
  LOG(INFO) << "Average Forward pass: " << forward_time / 1000 /
    FLAGS_iterations << " ms.";
  LOG(INFO) << "Average Backward pass: " << backward_time / 1000 /
    FLAGS_iterations << " ms.";
  LOG(INFO) << "Average Forward-Backward: " << total_timer.MilliSeconds() /
    FLAGS_iterations << " ms.";
  LOG(INFO) << "Total Time: " << total_timer.MilliSeconds() << " ms.";
  LOG(INFO) << "*** Benchmark ends ***";
  return 0;
}
RegisterBrewFunction(time);

int main(int argc, char** argv) {
  // Print output to stderr (while still logging).
  //打印標準錯誤
  FLAGS_alsologtostderr = 1;
  // Set version
  gflags::SetVersionString(AS_STRING(CAFFE_VERSION));
  // Usage message.
  // gflags庫中爲main函數設置usage信息：
  gflags::SetUsageMessage("command line brew\n"
      "usage: caffe <command> <args>\n\n"
      "commands:\n"
      "  train           train or finetune a model\n"
      "  test            score a model\n"
      "  device_query    show GPU diagnostic information\n"
      "  time            benchmark model execution time");
  // Run tool or show usage.
  caffe::GlobalInit(&argc, &argv);
  if (argc == 2) {
#ifdef WITH_PYTHON_LAYER
    try {
#endif
      return GetBrewFunction(caffe::string(argv[1]))();
#ifdef WITH_PYTHON_LAYER
    } catch (bp::error_already_set) {
      PyErr_Print();
      return 1;
    }
#endif
  } else {
    gflags::ShowUsageWithFlagsRestrict(argv[0], "tools/caffe");
  }
}