caffe自定义layer

caffe自带layers：

http://caffe.berkeleyvision.org/tutorial/layers.html

Layers:

• Image Data - read raw images.
• Database - read data from LEVELDB or LMDB.
• HDF5 Input - read HDF5 data, allows data of arbitrary dimensions.
• HDF5 Output - write data as HDF5.
• Input - typically used for networks that are being deployed.
• Window Data - read window data file.
• Memory Data - read data directly from memory.
• Dummy Data - for static data and debugging.

Note that the Python Layer can be useful for create custom data layers.

自定义caffe layers：

https://chrischoy.github.io/research/making-caffe-layer/

模型文件的参数在/src/caffe/proto/caffe.proto中，caffe.proto文件编译后以.h文件的方式被include/caffe/zss_layers.hpp引用，如下：

#include "caffe/proto/caffe.pb.h"

 

protobuf：

https://developers.google.com/protocol-buffers/docs/cpptutorial

syntax = "proto2";

package tutorial;

message Person {
  required string name = 1;
  required int32 id = 2;
  optional string email = 3;

  enum PhoneType {
    MOBILE = 0;
    HOME = 1;
    WORK = 2;
  }

  message PhoneNumber {
    required string number = 1;
    optional PhoneType type = 2 [default = HOME];
  }

  repeated PhoneNumber phones = 4;
}

message AddressBook {
  repeated Person people = 1;
}

1、2、16、3、4表示变量的编码，编码为1-15的比编码大于16的变量存储时少用1个字节的空间，因此使用频率较高的变量应当给予1-15的编码

required——慎用

optional——可以赋默认值

repeated——长度不固定，可以用来存动态数组之类的

源码阅读过程中遇到的一些c++知识：

1、explicit关键字，禁止构造函数隐式转换

https://blog.csdn.net/qq_35524916/article/details/58178072

2、在类、对象之后的 . :: : ->的作用

https://blog.csdn.net/k_koris/article/details/80469956

3、函数后:的作用——构造函数初始化列表

http://www.cnblogs.com/BlueTzar/articles/1223169.html

4、c++模板

template <class identifier> function_declaration;
template <typename identifier> function_declaration;

https://blog.csdn.net/qq_35637562/article/details/55194097