caffe自定义神经层

来源：互联网发布：交易圣经知乎编辑：程序博客网时间：2024/05/01 20:37

一、步骤：

■1. 创建新定义的头文件include/caffe/layers/my_neuron_layer.hpp

■重新Layer名的方法：virtual inline const char* type() const { return "MyNeuron"; }

■如果只是需要cpu方法的话，可以注释掉forward/backward_gpu()这两个方法

my_neuron_layer.hpp

#ifndef CAFFE_MY_NEURON_LAYER_HPP_
#define CAFFE_MY_NEURON_LAYER_HPP_
#include <vector>
#include "caffe/blob.hpp"
#include "caffe/layer.hpp"
#include "caffe/proto/caffe.pb.h"
#include "caffe/layers/neuron_layer.hpp"

namespace caffe {
template <typename Dtype>

class MyNeuronLayer : public NeuronLayer<Dtype> {
public:

explicit MyNeuronLayer(const LayerParameter& param):NeuronLayer<Dtype>(param) {}
virtual void LayerSetUp(const vector<Blob<Dtype>*>& bottom,const vector<Blob<Dtype>*>& top);

virtual inline const char* type() const { return "MyNeuron"; }

protected:
virtual void Forward_cpu(const vector<Blob<Dtype>*>& bottom,const vector<Blob<Dtype>*>& top);

#virtual void Forward_gpu(const vector<Blob<Dtype>*>& bottom,const vector<Blob<Dtype>*>& top);

virtual void Backward_cpu(const vector<Blob<Dtype>*>& top,const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom);

#virtual void Backward_gpu(const vector<Blob<Dtype>*>& top,const vector<bool>&propagate_down,

const vector<Blob<Dtype>*>& bottom);
Dtype power_;
};
}

#endif // CAFFE_MY_NEURON_LAYER_HPP_

■2. 创建对应src/caffe/layers/my_neuron_layer.cpp的源文件

■重写方法LayerSetUp,实现从能从prototxt读取参数

■重写方法Reshape，如果对继承类没有修改的话，就不需要重写

■重写方法Forward_cpu

■重写方法Backward_cpu(非必须)

■*如果要GPU支持则还需要创建src/caffe/src/my_neuron_layer.cu同理重写方Forward_gpu/Backward_gpu(非必须)

my_neuron_layer.cpp

#include <vector>
#include "caffe/layers/my_neuron_layer.hpp" //需要包含新定义的头文件
#include "caffe/util/math_functions.hpp"

namespace caffe {
template <typename Dtype>
void MyNeuronLayer<Dtype>::LayerSetUp(const vector<Blob<Dtype>*>& bottom,const vector<Blob<Dtype>*>& top){
NeuronLayer<Dtype>::LayerSetUp(bottom,top);
power_ = this->layer_param_.my_neuron_param().power();
}

// Compute y = x^power
template <typename Dtype>

void MyNeuronLayer<Dtype>::Forward_cpu(const vector<Blob<Dtype>*>& bottom,const

vector<Blob<Dtype>*>&top){

Dtype* top_data = top[0]->mutable_cpu_data();
const int count = bottom[0]->count();
caffe_powx(count, bottom[0]->cpu_data(), Dtype(power_), top_data);
}

template <typename Dtype>
void MyNeuronLayer<Dtype>::Backward_cpu(const vector<Blob<Dtype>*>& top,const vector<bool>& propagate_down,const vector<Blob<Dtype>*>& bottom){
const int count = top[0]->count();
const Dtype* top_diff = top[0]->cpu_diff();
if(propagate_down[0]){
const Dtype* bottom_data = bottom[0]->cpu_data();
Dtype* bottom_diff = bottom[0]->mutable_cpu_diff();
caffe_powx(count, bottom_data, Dtype(power_ - 1), bottom_diff);
caffe_scal(count, Dtype(power_), bottom_diff);
caffe_mul(count, bottom_diff, top_diff, bottom_diff);
}
}

//#ifdef CPU_ONLY
//STUB_GPU(MyNeuronLayer);
//#endif
INSTANTIATE_CLASS(MyNeuronLayer);
REGISTER_LAYER_CLASS(MyNeuron);

}

my_neuron_layer.cu

#include <vector>
#include "caffe/layers/mysquare_layer.hpp"
#include "caffe/util/math_functions.hpp"
#include <iostream>
using namespace std;

namespace caffe {
template <typename Dtype>
void MyNeuronLayer<Dtype>::Forward_gpu(
const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) {
const int count = top[0]->count();
Dtype* top_data = top[0]->mutable_gpu_data();
caffe_gpu_powx(count, bottom[0]->gpu_data(), Dtype(power_), top_data);
}

template <typename Dtype>
void MyNeuronLayer<Dtype>::Backward_gpu(const vector<Blob<Dtype>*>& top,
const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom) {
const int count = top[0]->count();
const Dtype* top_diff = top[0]->gpu_diff();
if (propagate_down[0]) {
const Dtype* bottom_data = bottom[0]->gpu_data();
Dtype* bottom_diff = bottom[0]->mutable_gpu_diff();
const Dtype* bottom_data_w = bottom[0]->cpu_data();
const Dtype* bottom_diff_w = bottom[0]->cpu_diff();

cout << "bottom_data[0]: " << bottom_data_w[0] << endl;
cout << "bottom_diff[0]: " << bottom_diff_w[0] << endl;

caffe_gpu_powx(count, bottom_data, Dtype(power_ - 1), bottom_diff);

bottom_diff = bottom[0]->mutable_gpu_diff();
bottom_data_w = bottom[0]->cpu_data();
bottom_diff_w = bottom[0]->cpu_diff();
cout << "bottom_data[0]: " << bottom_data_w[0] << endl;
cout << "bottom_diff[0]: " << bottom_diff_w[0] << endl;

caffe_gpu_scal(count, Dtype(power_), bottom_diff);

bottom_diff = bottom[0]->mutable_gpu_diff();
bottom_data_w = bottom[0]->cpu_data();
bottom_diff_w = bottom[0]->cpu_diff();
cout << "bottom_data[0]: " << bottom_data_w[0] << endl;
cout << "bottom_diff[0]: " << bottom_diff_w[0] << endl;
caffe_gpu_mul(count, bottom_diff, top_diff, bottom_diff);
bottom_diff = bottom[0]->mutable_gpu_diff();
bottom_data_w = bottom[0]->cpu_data();
bottom_diff_w = bottom[0]->cpu_diff();
cout << "bottom_data[0]: " << bottom_data_w[0] << endl;
cout << "bottom_diff[0]: " << bottom_diff_w[0] << endl;
}
}

INSTANTIATE_LAYER_GPU_FUNCS(MyNeuronLayer);
}

■3. proto/caffe.proto注册新的Layer

message LayerParameter{

...

++ optional MyNeuronParameter my_neuron_param = 150;

...

}

...

++ message MyNeuronParameter {

++ optional float power = 1 [default = 2];

}

...

message V1LayerParameter{

...

++ MYNEURON = 40;

...

}

■4. my_neuron_layer.cpp添加注册的宏定义

INSTANTIATE_CLASS(MyNeuronLayer);

REGISTER_LAYER_CLASS(MyNeuron);

如果有my_neuron_layer.cu,则添加

INSTANTIATE_LAYER_GPU_FUNCS(MyNeuronLayer);

■5. 重新编译和install

# cd caffe/build/

# cmake -D CPU_ONLY=ON -D CMAKE_PREFIX_INSTALL=/usr/local ..

# make all

# make install

二、测试自定义的Layer

■定义deploy.prototxt

name: "CaffeNet"

input: "data"

input_shape {

dim: 1 # batchsize

dim: 1 # number of colour channels - rgb

dim: 28 # width

dim: 28 # height

}

layer {

name: "myneuron"

type: "MyNeuron"

bottom: "data"

top: "data_out"

my_neuron_param {

power : 2

}

■运行测试程序：
test_my_neuron.py

阅读全文

0 0