Analysis of prototxt file in caffe

Net represents a complete CNN model in caffe. It contains several Layer instances. A Net corresponds to a *.prototxt file, and the *.prototxt file corresponds to ProtoBuffer data. The analysis of *.prototxt files is similar to that of ProtoBuffer files with a .bin suffix. The read and write functions of caffe specific prototxt files are in /caffe/utils/io.cpp.

// 从txt读取proto的定义
bool ReadProtoFromTextFile(const char* filename, Message* proto);
// 从text读取proto的定义
inline bool ReadProtoFromTextFile(const string& filename, Message* proto) {
  return ReadProtoFromTextFile(filename.c_str(), proto);
}
// 从text读取proto的定义,只是增加了检查而已
inline void ReadProtoFromTextFileOrDie(const char* filename, Message* proto) {
  CHECK(ReadProtoFromTextFile(filename, proto));
}
// 从text读取proto的定义,只是增加了检查而已
inline void ReadProtoFromTextFileOrDie(const string& filename, Message* proto) {
  ReadProtoFromTextFileOrDie(filename.c_str(), proto);
}
// 将proto写入到txt文件
void WriteProtoToTextFile(const Message& proto, const char* filename);
inline void WriteProtoToTextFile(const Message& proto, const string& filename) {
  WriteProtoToTextFile(proto, filename.c_str());
}

Take the parsing of the cifar10_full.prototxt file under caffe-master/examples/cifar10/ in caffe as an example:

#include <iostream>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <unistd.h>

#include <google/protobuf/io/coded_stream.h>
#include <google/protobuf/io/zero_copy_stream_impl.h>
#include <google/protobuf/text_format.h>

#include "caffe.pb.h"

using namespace std;
using namespace caffe;
using google::protobuf::io::FileInputStream;
using google::protobuf::io::FileOutputStream;
using google::protobuf::io::ZeroCopyInputStream;
using google::protobuf::io::CodedInputStream;
using google::protobuf::io::ZeroCopyOutputStream;
using google::protobuf::io::CodedOutputStream;
using google::protobuf::Message;

bool ReadProtoFromTextFile(const char* filename, Message* proto)
{
  int fd = open(filename, O_RDONLY);
  FileInputStream* input = new FileInputStream(fd);
  bool success = google::protobuf::TextFormat::Parse(input, proto);//TextFormat::Parse函数从指定文本文件中读取protobuf数据
  delete input;
  close(fd);
  return success;
}

void WriteProtoToTextFile(const Message& proto, const char* filename) {
  int fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC, 0644);
  FileOutputStream* output = new FileOutputStream(fd);
  google::protobuf::TextFormat::Print(proto, output); //TextFormat::Print函数把protobuf数据写入到指定文本文件中
  delete output;
  close(fd);
}

int main()
{
    std::string fileName = "cifar10_full.prototxt";

    caffe::NetParameter *protoMsgPtr = new caffe::NetParameter;

    ReadProtoFromTextFile(fileName.c_str(), protoMsgPtr);
    std::cout<<protoMsgPtr->DebugString()<<std::endl;
    std::string writeFile = "cifar10_full_write.prototxt";
    WriteProtoToTextFile(*protoMsgPtr, writeFile.c_str());
    delete protoMsgPtr;
    return 0;
}

operation result

name: "CIFAR10_full_deploy"
layer {
  name: "data"
  type: "Input"
  top: "data"
  input_param {
    shape {
      dim: 1
      dim: 3
      dim: 32
      dim: 32
    }
  }
}
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 32
    pad: 2
    kernel_size: 5
    stride: 1
  }
}
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "conv1"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "pool1"
  top: "pool1"
}
layer {
  name: "norm1"
  type: "LRN"
  bottom: "pool1"
  top: "norm1"
  lrn_param {
    local_size: 3
    alpha: 5e-05
    beta: 0.75
    norm_region: WITHIN_CHANNEL
  }
}
layer {
  name: "conv2"
  type: "Convolution"
  bottom: "norm1"
  top: "conv2"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 32
    pad: 2
    kernel_size: 5
    stride: 1
  }
}
layer {
  name: "relu2"
  type: "ReLU"
  bottom: "conv2"
  top: "conv2"
}
layer {
  name: "pool2"
  type: "Pooling"
  bottom: "conv2"
  top: "pool2"
  pooling_param {
    pool: AVE
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "norm2"
  type: "LRN"
  bottom: "pool2"
  top: "norm2"
  lrn_param {
    local_size: 3
    alpha: 5e-05
    beta: 0.75
    norm_region: WITHIN_CHANNEL
  }
}
layer {
  name: "conv3"
  type: "Convolution"
  bottom: "norm2"
  top: "conv3"
  convolution_param {
    num_output: 64
    pad: 2
    kernel_size: 5
    stride: 1
  }
}
layer {
  name: "relu3"
  type: "ReLU"
  bottom: "conv3"
  top: "conv3"
}
layer {
  name: "pool3"
  type: "Pooling"
  bottom: "conv3"
  top: "pool3"
  pooling_param {
    pool: AVE
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "ip1"
  type: "InnerProduct"
  bottom: "pool3"
  top: "ip1"
  param {
    lr_mult: 1
    decay_mult: 250
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 10
  }
}
layer {
  name: "prob"
  type: "Softmax"
  bottom: "ip1"
  top: "prob"
}

Press <RETURN> to close this window...