如何在caffe中添加新的Layer

本文分为两部分，先写一个入门的教程，然后再给出自己添加maxout与NIN的layer的方法

（一）

其实在Github上已经有答案了（https://github.com/BVLC/caffe/issues/684）

Here's roughly the process I follow.

Add a class declaration for your layer to the appropriate one of

common_layers.hpp

,

data_layers.hpp

,

loss_layers.hpp

,

neuron_layers.hpp

,
or

vision_layers.hpp

.
Include an inline implementation of

type

and
the

*Blobs()

methods
to specify blob number requirements. Omit the

*_gpu

declarations
if you'll only be implementing CPU code.

Implement your layer in

layers/your_layer.cpp

.

SetUp

for
initialization: reading parameters, allocating buffers, etc.

Forward_cpu

for
the function your layer computes

Backward_cpu

for
its gradient

(Optional) Implement the GPU versions

Forward_gpu

and

Backward_gpu

in

layers/your_layer.cu

.

Add your layer to

proto/caffe.proto

,
updating the next available ID. Also declare parameters, if needed, in this file.

Make your layer createable by adding it to

layer_factory.cpp

.

Write tests in

test/test_your_layer.cpp

.
Use

test/test_gradient_check_util.hpp

to
check that your Forward and Backward implementations are in numerical agreement.

上面是一个大致的流程，我就直接翻译过来吧，因为我自己琢磨出来的步骤跟这个是一样的。在这里，我们就添加一个Wtf_Layer，然后作用跟Convolution_Layer一模一样。注意这里的命名方式，Wtf第一个字母大写，剩下的小写，算是一个命名规范吧，强迫症表示很舒服。

1. 首先确定要添加的layer的类型，是common_layer 还是 data_layer 还是loss_layer, neuron_layer, vision_layer ，这里的Wtf_Layer肯定是属vision_layer了，所以打开vision_layers.hpp
然后复制convolution_layer的相关代码，把类名还有构造函数的名字改为WtfLayer，如果没有用到GPU运算，那么把里面的带GPU的函数都删掉

2. 将Wtf_layer.cpp 添加到src\caffe\layers文件夹中，代码内容复制convolution_layer.cpp 把对应的类名修改（可以搜一下conv关键字，然后改为Wtf）

3. 假如有gpu的代码就添加响应的Wtf_layer.cu （这里不添加了）

4. 修改proto/caffe.proto文件，找到LayerType，添加WTF，并更新ID（新的ID应该是34）。假如说Wtf_Layer有参数，比如Convolution肯定是有参数的，那么添加WtfParameter类

5. 在layer_factory.cpp中添加响应的代码，就是一堆if ... else的那片代码

6. 这个可以不做，但是为了结果还是做一个，就是写一个测试文件，检查前向后向传播的数据是否正确。gradient_check的原理可以参考UFLDL教程的对应章节

之后我会更新我自己写的maxout_layer的demo，在这立一个flag以鞭策自己完成吧╮(╯▽╰)╭

（二） 如何添加maxout_layer

表示被bengio的maxout给搞郁闷了，自己摆出一个公式巴拉巴拉说了一堆，结果用到卷积层的maxout却给的另一种方案，吐槽无力，不过后来又想了下应该是bengio没表述清楚的问题。

我的maxout的算法思路是这样的，首先要确定一个group_size变量，表示最大值是在group_size这样一个规模的集合下挑选出来的，简而言之就是给定group_size个数，取最大。确定好group_size变量，然后让卷积层的output_num变为原来的group_size倍，这样输出的featuremap的个数就变为原来的group_size倍，然后以group_size为一组划分这些featuremap，每组里面挑出响应最大的点构成一个新的featuremap，这样就得到了maxout层的输出。



要是还不明白我就拿上面的图来说一下，上面一共9张图，相当于卷积层输出9张featuremap，我们每3个为一组，那么maxout层输出9/3=3张featuremap，对于每组featuremaps，比如我们挑出绿色的三张featuremaps，每张大小为w*h，那么声明一个新的output_featuremap大小为w*h，遍历output_featuremap的每个点，要赋的数值为三张绿色featuremap对应点的最大的那个，也就是三个数里面选最大的，这样就输出了一张output_featuremap，剩下的组类似操作。

我觉得到这应该明白maxout的原理跟算法了吧= =，下面就直接贴代码了

新建一个maxout_layer.cpp放到src/caffe/layer文件夹下

[cpp] view
plain copy







#include <cstdio>

#include <vector>

#include "caffe/filler.hpp"

#include "caffe/layer.hpp"

#include "caffe/util/im2col.hpp"

#include "caffe/util/math_functions.hpp"

#include "caffe/vision_layers.hpp"

namespace caffe {

template <typename Dtype>

void MaxoutLayer<Dtype>::SetUp(const vector<Blob<Dtype>*>& bottom,

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

Layer<Dtype>::SetUp(bottom, top);

printf("===============================================================has go into setup !==============================================\n");

MaxoutParameter maxout_param = this->layer_param_.maxout_param();

// maxout_size

//CHECK(!maxout_param.has_num_output())

// << "maxout size are required.";

//if (maxout_param.has_num_output()) {

// num_output_ = maxout_param.num_output();

//}

num_output_ = this->layer_param_.maxout_param().num_output();

CHECK_GT(num_output_, 0) << "output number cannot be zero.";

// bottom ÊÇFEATURE_MAP

num_ = bottom[0]->num();

channels_ = bottom[0]->channels();

height_ = bottom[0]->height();

width_ = bottom[0]->width();

// òËÆÏÂÃæÕâžöif²»»áÅÜœøÈ¥

// TODO: generalize to handle inputs of different shapes.

for (int bottom_id = 1; bottom_id < bottom.size(); ++bottom_id) {

CHECK_EQ(num_, bottom[bottom_id]->num()) << "Inputs must have same num.";

CHECK_EQ(channels_, bottom[bottom_id]->channels())

<< "Inputs must have same channels.";

CHECK_EQ(height_, bottom[bottom_id]->height())

<< "Inputs must have same height.";

CHECK_EQ(width_, bottom[bottom_id]->width())

<< "Inputs must have same width.";

}

// Set the parameters ž³Öµ²ÎÊý

CHECK_EQ(channels_ % num_output_, 0)

<< "Number of channel should be multiples of output number.";

group_size_ = channels_ / num_output_;

// Figure out the dimensions for individual gemms. ŒÆËãŸØÕóµÄÐÐÁÐ

// ÆäʵBengioµÄÂÛÎÄÖжÔÓÚK_µÄŽóС¶šÒåºÜÄ£ºý£¬¶ÔÓÚÍŒÏñœöœöÊÇžøÁËe.g.

// ҲûÓÐ˵µœµ×ʵŒÊÊDz»ÊÇÕâÃŽ²Ù×÷µÄ£¬ÒòΪÈç¹ûÕæµÄÊÇchannelÖ±œÓœøÐбȜÏ

// ÄÇÃŽŸÍžúÀíÂ۵Ĺ«ÊœÎǺϵIJ»ºÃ£¬µ«ÊÇÄܹ»œâÊÍÍŒÏñ£¬±ÈÈç˵Äóö×îºÃµÄÒ»²ã

// ¶øÇÒÍŒÏñžú·ÇÍŒÏñµÄmaxoutµÄ×ö·š²îÌ«¶àÁË°¡¡£ŒÙÈç×öµœŒæÈݵĻ°Ö»ÄÜÈÃÇ°Ò»²ã

// µÄoutput_numÅäºÏmaxout

//for (int top_id = 0; top_id < top->size(); ++top_id) {

(*top)[0]->Reshape(num_, num_output_, height_, width_); // œöœöÊǞıäµÄchannelžöÊý

max_idx_.Reshape(num_, num_output_, height_, width_);

//}

}

template <typename Dtype>

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

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

int featureSize = height_ * width_;

Dtype* mask = NULL;

mask = max_idx_.mutable_cpu_data();

//printf("1.maxout_forward\n");

const int top_count = (*top)[0]->count();

caffe_set(top_count, Dtype(0), mask);

//printf("2.maxout_forward\n");

for (int i = 0; i < bottom.size(); ++i) {

const Dtype* bottom_data = bottom[i]->cpu_data();

Dtype* top_data = (*top)[i]->mutable_cpu_data();

for (int n = 0; n < num_; n ++) {

// È¡µÚnÕÅÍŒÏñ

for (int o = 0; o < num_output_; o ++) {

for (int g = 0; g < group_size_; g ++) {

if (g == 0) {

for (int h = 0; h < height_; h ++) { // Áœ²ãÑ­»·Óеã¶ù†ªàÂ

for (int w = 0; w < width_; w ++) {

int index = w + h * width_;

top_data[index] = bottom_data[index];

mask[index] = index;

}

}

}

else {

for (int h = 0; h < height_; h ++) {

for (int w = 0; w < width_; w ++) {

int index0 = w + h * width_;

int index1 = index0 + g * featureSize;

if (top_data[index0] < bottom_data[index1]) {

top_data[index0] = bottom_data[index1];

mask[index0] = index1;

}

}

}

}

}

bottom_data += featureSize * group_size_;

top_data += featureSize;

mask += featureSize;

}

}

}

return Dtype(0.);

}

template <typename Dtype>

void MaxoutLayer<Dtype>::Backward_cpu(const vector<Blob<Dtype>*>& top,

const vector<bool>& propagate_down, vector<Blob<Dtype>*>* bottom) {

if (!propagate_down[0]) {

return;

}

const Dtype* top_diff = top[0]->cpu_diff();

Dtype* bottom_diff = (*bottom)[0]->mutable_cpu_diff();

caffe_set((*bottom)[0]->count(), Dtype(0), bottom_diff);

const Dtype* mask = max_idx_.mutable_cpu_data();

int featureSize = height_ * width_;

for (int i = 0; i < top.size(); i ++) {

const Dtype* top_diff = top[i]->cpu_diff();

Dtype* bottom_diff = (*bottom)[i]->mutable_cpu_diff();

for (int n = 0; n < num_; n ++) {

// È¡µÚnÕÅÍŒÏñ

for (int o = 0; o < num_output_; o ++) {

for (int h = 0; h < height_; h ++) { // Áœ²ãÑ­»·Óеã¶ù†ªàÂ

for (int w = 0; w < width_; w ++) {

int index = w + h * width_;

int bottom_index = mask[index];

bottom_diff[bottom_index] += top_diff[index];

}

}

bottom_diff += featureSize * group_size_;

top_diff += featureSize;

mask += featureSize;

}

}

}

}

//#ifdef CPU_ONLY

//STUB_GPU(MaxoutLayer);

//#endif

INSTANTIATE_CLASS(MaxoutLayer);

} // namespace caffe

里面的乱码是中文，到了linux里面就乱码了，不影响，还一个printf是测试用的（要被笑话用printf了= =）

vision_layers.hpp 里面添加下面的代码

[cpp] view
plain copy







/* MaxoutLayer

*/

template <typename Dtype>

class MaxoutLayer : public Layer<Dtype> {

public:

explicit MaxoutLayer(const LayerParameter& param)

: Layer<Dtype>(param) {}

virtual void SetUp(const vector<Blob<Dtype>*>& bottom,

vector<Blob<Dtype>*>* top); // 为什么需要bottom与top，肯定的啊，

//要初始化bottom top的形状

virtual inline LayerParameter_LayerType type() const {

return LayerParameter_LayerType_MAXOUT;

}

protected:

virtual Dtype Forward_cpu(const vector<Blob<Dtype>*>& bottom,

vector<Blob<Dtype>*>* top);

//virtual Dtype Forward_gpu(const vector<Blob<Dtype>*>& bottom,

// vector<Blob<Dtype>*>* top);

virtual void Backward_cpu(const vector<Blob<Dtype>*>& top,

const vector<bool>& propagate_down, vector<Blob<Dtype>*>* bottom);

//virtual void Backward_gpu(const vector<Blob<Dtype>*>& top,

// const vector<bool>& propagate_down, vector<Blob<Dtype>*>* bottom);

int num_output_;

int num_;

int channels_;

int height_;

int width_;

int group_size_;

Blob<Dtype> max_idx_;

};

剩下的是layer_factory.cpp 的改动，不说明了，然后是proto文件的改动

[cpp] view
plain copy







message MaxoutParameter {

optional uint32 num_output = 1; // The number of outputs for the layer

}

额，当然还有proto文件的其他改动也不说明了，还有test文件，我没写，因为我自己跑了下demo，没啥问题，所以代码可以说是正确的。

不过要说明的是，目前的代码不能接在全连接层后面，是我里面有几句代码写的有问题，之后我会改动一下，问题不大。

然后就是NIN的实现了，表示自己写的渣一样的代码啊，效率目测很低。哦对了，这些都是CPU算的，GPU不大会，还没打算写。

NIN_layer 的实现

我之前一直以为Github上的network in network 是有问题的，事实证明，我最后也写成了Github上面的样子= =所以大家自行搜索caffe+network in network吧……不过得翻墙下载，所以我就把网络格式的代码直接贴出来（cifar10数据库的网络结构）

[plain] view
plain copy







layers {

name: "cifar"

type: DATA

top: "data"

top: "label"

data_param {

source: "cifar-train-leveldb"

batch_size: 128

}

include: { phase: TRAIN }

}

layers {

name: "cifar"

type: DATA

top: "data"

top: "label"

data_param {

source: "cifar-test-leveldb"

batch_size: 100

}

include: { phase: TEST }

}

layers {

name: "conv1"

type: CONVOLUTION

bottom: "data"

top: "conv1"

blobs_lr: 1

blobs_lr: 2

weight_decay: 1.

weight_decay: 0.

convolution_param {

num_output: 192

pad: 2

kernel_size: 5

weight_filler {

type: "gaussian"

std: 0.05

}

bias_filler {

type: "constant"

}

}

}

layers {

name: "relu1"

type: RELU

bottom: "conv1"

top: "conv1"

}

layers {

name: "cccp1"

type: CONVOLUTION

bottom: "conv1"

top: "cccp1"

blobs_lr: 1

blobs_lr: 2

weight_decay: 1

weight_decay: 0

convolution_param {

num_output: 160

group: 1

kernel_size: 1

weight_filler {

type: "gaussian"

std: 0.05

}

bias_filler {

type: "constant"

value: 0

}

}

}

layers {

name: "relu_cccp1"

type: RELU

bottom: "cccp1"

top: "cccp1"

}

layers {

name: "cccp2"

type: CONVOLUTION

bottom: "cccp1"

top: "cccp2"

blobs_lr: 1

blobs_lr: 2

weight_decay: 1

weight_decay: 0

convolution_param {

num_output: 96

group: 1

kernel_size: 1

weight_filler {

type: "gaussian"

std: 0.05

}

bias_filler {

type: "constant"

value: 0

}

}

}

layers {

name: "relu_cccp2"

type: RELU

bottom: "cccp2"

top: "cccp2"

}

layers {

name: "pool1"

type: POOLING

bottom: "cccp2"

top: "pool1"

pooling_param {

pool: MAX

kernel_size: 3

stride: 2

}

}

layers {

name: "drop3"

type: DROPOUT

bottom: "pool1"

top: "pool1"

dropout_param {

dropout_ratio: 0.5

}

}

layers {

name: "conv2"

type: CONVOLUTION

bottom: "pool1"

top: "conv2"

blobs_lr: 1

blobs_lr: 2

weight_decay: 1.

weight_decay: 0.

convolution_param {

num_output: 192

pad: 2

kernel_size: 5

weight_filler {

type: "gaussian"

std: 0.05

}

bias_filler {

type: "constant"

}

}

}

layers {

name: "relu2"

type: RELU

bottom: "conv2"

top: "conv2"

}

layers {

name: "cccp3"

type: CONVOLUTION

bottom: "conv2"

top: "cccp3"

blobs_lr: 1

blobs_lr: 2

weight_decay: 1

weight_decay: 0

convolution_param {

num_output: 192

group: 1

kernel_size: 1

weight_filler {

type: "gaussian"

std: 0.05

}

bias_filler {

type: "constant"

value: 0

}

}

}

layers {

name: "relu_cccp3"

type: RELU

bottom: "cccp3"

top: "cccp3"

}

layers {

name: "cccp4"

type: CONVOLUTION

bottom: "cccp3"

top: "cccp4"

blobs_lr: 1

blobs_lr: 2

weight_decay: 1

weight_decay: 0

convolution_param {

num_output: 192

group: 1

kernel_size: 1

weight_filler {

type: "gaussian"

std: 0.05

}

bias_filler {

type: "constant"

value: 0

}

}

}

layers {

name: "relu_cccp4"

type: RELU

bottom: "cccp4"

top: "cccp4"

}

layers {

name: "pool2"

type: POOLING

bottom: "cccp4"

top: "pool2"

pooling_param {

pool: AVE

kernel_size: 3

stride: 2

}

}

layers {

name: "drop6"

type: DROPOUT

bottom: "pool2"

top: "pool2"

dropout_param {

dropout_ratio: 0.5

}

}

layers {

name: "conv3"

type: CONVOLUTION

bottom: "pool2"

top: "conv3"

blobs_lr: 1.

blobs_lr: 2.

weight_decay: 1.

weight_decay: 0.

convolution_param {

num_output: 192

pad: 1

kernel_size: 3

weight_filler {

type: "gaussian"

std: 0.05

}

bias_filler {

type: "constant"

}

}

}

layers {

name: "relu3"

type: RELU

bottom: "conv3"

top: "conv3"

}

layers {

name: "cccp5"

type: CONVOLUTION

bottom: "conv3"

top: "cccp5"

blobs_lr: 1

blobs_lr: 2

weight_decay: 1

weight_decay: 0

convolution_param {

num_output: 192

group: 1

kernel_size: 1

weight_filler {

type: "gaussian"

std: 0.05

}

bias_filler {

type: "constant"

value: 0

}

}

}

layers {

name: "relu_cccp5"

type: RELU

bottom: "cccp5"

top: "cccp5"

}

layers {

name: "cccp6"

type: CONVOLUTION

bottom: "cccp5"

top: "cccp6"

blobs_lr: 0.1

blobs_lr: 0.1

weight_decay: 1

weight_decay: 0

convolution_param {

num_output: 10

group: 1

kernel_size: 1

weight_filler {

type: "gaussian"

std: 0.05

}

bias_filler {

type: "constant"

value: 0

}

}

}

layers {

name: "relu_cccp6"

type: RELU

bottom: "cccp6"

top: "cccp6"

}

layers {

name: "pool3"

type: POOLING

bottom: "cccp6"

top: "pool3"

pooling_param {

pool: AVE

kernel_size: 8

stride: 1

}

}

layers {

name: "accuracy"

type: ACCURACY

bottom: "pool3"

bottom: "label"

top: "accuracy"

include: { phase: TEST }

}

layers {

name: "loss"

type: SOFTMAX_LOSS

bottom: "pool3"

bottom: "label"

top: "loss"

}

训练参数

[plain] view
plain copy







test_iter: 100

test_interval: 500

base_lr: 0.1

momentum: 0.9

weight_decay: 0.0001

lr_policy: "step"

gamma: 0.1

stepsize: 100000

display: 100

max_iter: 120000

snapshot: 10000

snapshot_prefix: "cifar10_nin"



该文章算是告一段落了，剩下的任务就是如何训练得到state-of-the-art了