c++编写神经网络（一）MTCNN内存空间的调用

古城微笑少年丶 2022-04-10 12:28 284阅读 0赞

**背景：**FPGA端程序需要确定的偏移地址，只能有一个指针。我们需要一次性的在DRAM上开辟内存空间然后传给IPcore来运算。所以我们必须从头编写MTCNN的代码。

**目的**：查出原MTCNN代码的内存空间的开辟量。

**目录**

一、旧MTCNN的内存实现

1.1 每个子网络的构建

1.2 mtcnn的构造

1.3 权重的内存实现

1.4 feature的内存实现

1.5 内存实现相关的子函数

二、新MTCNN内存实现的思路

2.1 weight的初始化与权重写入

2.2 feature内存的初始化

Pnet

Rnet，Onet

三、IPcore的接口设计

四、weight的权重大小

网络尺寸表

Pnet

Rnet

Onet

4.1 Pnet weight的大小

Pnet

Rnet

Onet

五、feature的大小

5.1 Rnet

5.2 Onet

5.3 Pnet

六、网络的总尺寸

6.1 权重尺寸

6.2 feature大小

--------------------

# 一、旧MTCNN的内存实现 #

旧MTCNN的weight，input，output分别用malloc开辟新的内存空间。

## 1.1 每个子网络的构建 ##

以Pnet为例

Pnet::Pnet(){
        Pthreshold = 0.9;//0.6;
        firstFlag = true;
    	//in order of [weight] [input] [output]
        
    //the RGB image in pBox format 
        this->rgb = new pBox;
    //conv1,prelu1
        this->conv1_wb = new Weight;
        this->conv1_out = new pBox;//output
        this->conv1_out_pad = new pBox;//output padding
    //pool1
        this->pool1_conv1_wb = new Weight;
        this->pool1_conv1_out = new pBox;//output
    //conv2,relu2
        this->conv2_wb = new Weight;
        this->conv2_out = new pBox;//output
    //conv3,relu3
        this->conv3_wb = new Weight;
        this->conv3_out = new pBox;//output
    //post conv layers
        this->conv4c1_wb = new Weight;
        this->conv4c2_wb = new Weight;//weight
    //    this->score_matrix = new pBox;
        this->score_ = new pBox;
    //    this->location_matrix = new pBox;
        this->location_ = new pBox;    
        
        //weight pointer create,network initialize
        //                                 w           oc  ic  ks s lp  rp 
        long conv1 = initConvAndFc(   this->conv1_wb,  10, 3,  3, 1, 0, 0);
    long pool1_conv1=initConvAndFc(this->pool1_conv1_wb,16,10, 3, 2, 0, 0);
        long conv2 = initConvAndFc(   this->conv2_wb,  32, 16, 3, 1, 0, 0);
        long conv3 = initConvAndFc(   this->conv3_wb,  32, 32, 3, 1, 0, 0);
        long conv4c1 = initConvAndFc(this->conv4c1_wb, 2,  32, 1, 1, 0, 0);
        long conv4c2 = initConvAndFc(this->conv4c2_wb, 4,  32, 1, 1, 0, 0);
        long dataNumber[12] = {conv1,10,pool1_conv1,16,conv2,32,conv3,32,conv4c1,2,conv4c2,4};
        mydataFmt *pointTeam[12] = {this->conv1_wb->pdata, this->conv1_wb->pbias, \
                                this->pool1_conv1_wb->pdata, this->pool1_conv1_wb->pbias, \
                                this->conv2_wb->pdata, this->conv2_wb->pbias, \
                                this->conv3_wb->pdata, this->conv3_wb->pbias, \
                                this->conv4c1_wb->pdata, this->conv4c1_wb->pbias, \
                                this->conv4c2_wb->pdata, this->conv4c2_wb->pbias \
                                };
        string filename = "Pnet.bin";
    	printf("Create Pnet,Read Pnet.bin ,12 pointers \n");
        readData(filename, dataNumber, pointTeam, 12);
    }

[c++的类构造函数与析构函数 http://www.runoob.com/cplusplus/cpp-constructor-destructor.html][c_ http_www.runoob.com_cplusplus_cpp-constructor-destructor.html]

运用构造函数开辟每层的内存存入指针，每层存在一个结构体之中，用initConvandFc函数初始化weight的大小，用convolutioninit这些函数初始化feature的内存。

运用此方法构造的Pnet，Rnet，Onet

## 1.2 mtcnn的构造 ##

因为Pnet根据金字塔结构，需要多次构造Pnet；

Rnet，Onet只需要构造一次。

子网络的构建mtcnn的类初始化函数之中实现。

## 1.3 权重的内存实现 ##

网络初始化过程之中，初始化一系列权重指针，然后从文件读入权重。权重之间独立。

//weight pointer create,network initialize
        //                                 w           oc  ic  ks s lp  rp 
        long conv1 = initConvAndFc(   this->conv1_wb,  10, 3,  3, 1, 0, 0);
    long pool1_conv1=initConvAndFc(this->pool1_conv1_wb,16,10, 3, 2, 0, 0);
        long conv2 = initConvAndFc(   this->conv2_wb,  32, 16, 3, 1, 0, 0);
        long conv3 = initConvAndFc(   this->conv3_wb,  32, 32, 3, 1, 0, 0);
        long conv4c1 = initConvAndFc(this->conv4c1_wb, 2,  32, 1, 1, 0, 0);
        long conv4c2 = initConvAndFc(this->conv4c2_wb, 4,  32, 1, 1, 0, 0);
        long dataNumber[12] = {conv1,10,pool1_conv1,16,conv2,32,conv3,32,conv4c1,2,conv4c2,4};
        mydataFmt *pointTeam[12] = {this->conv1_wb->pdata, this->conv1_wb->pbias, \
                                this->pool1_conv1_wb->pdata, this->pool1_conv1_wb->pbias, \
                                this->conv2_wb->pdata, this->conv2_wb->pbias, \
                                this->conv3_wb->pdata, this->conv3_wb->pbias, \
                                this->conv4c1_wb->pdata, this->conv4c1_wb->pbias, \
                                this->conv4c2_wb->pdata, this->conv4c2_wb->pbias \
                                };
        string filename = "Pnet.bin";
    	printf("Create Pnet,Read Pnet.bin ,12 pointers \n");
        readData(filename, dataNumber, pointTeam, 12);

## 1.4 feature的内存实现 ##

权重固定而featreu不固定，所以每次运行网络之前都会初始化feature。

if(firstFlag){
            printf("Pnet buffer init\n");
        //change Mat image to pBox format
            image2MatrixInit(image, this->rgb);
    		//conv1,prelu1
            convolutionInit(this->conv1_wb, this->rgb, this->conv1_out);
            featurePadInit(this->conv1_out, this->conv1_out_pad, 0,1);
    		//pool1
            convolutionInit(this->pool1_conv1_wb, this->conv1_out_pad, this->pool1_conv1_out);
        //conv2,prelu2
            convolutionInit(this->conv2_wb, this->pool1_conv1_out, this->conv2_out);  
        //conv3,prelu3
            convolutionInit(this->conv3_wb, this->conv2_out, this->conv3_out);
        //post conv layers
            convolutionInit(this->conv4c1_wb, this->conv3_out, this->score_);
            convolutionInit(this->conv4c2_wb, this->conv3_out, this->location_);
            firstFlag = false;
        }

以Pnet初始化为例，用相关的Init函数开辟独立的内存以供feature存储。

## 1.5 内存实现相关的子函数 ##

void convolutionInit(const Weight *weightIn, const pBox *pboxParameter, pBox *outpBox){
 	outpBox->channel = weightIn->out_ChannelNum;
 outpBox->width = (pboxParameter->width - weightIn->kernelSize) / weightIn->stride + 1;
 outpBox->height = (pboxParameter->height - weightIn->kernelSize) / weightIn->stride + 1;
 	int outpBoxByteSize=weightIn->out_ChannelNum*outpBox->width*outpBox->height*sizeof(mydataFmt);
 outpBox->pdata = (mydataFmt *)malloc(outpBoxByteSize);
 
 	if(outpBox->pdata==NULL)cout<<"the convolutionInit is failed!!"<<endl;
 memset(outpBox->pdata , 0, outpBoxByteSize);
 }

例如卷积的初始化函数就是独立的开辟出卷积需要的内存大小。

long initConvAndFc(struct Weight *weight, int schannel, int lchannel, int kersize, int stride, int leftPad,int rightPad){
 weight->out_ChannelNum = schannel;
 weight->in_ChannelNum = lchannel;
 weight->kernelSize = kersize;
 weight->stride = stride;
 weight->leftPad = leftPad;
 	 weight->rightPad = rightPad;
 weight->pbias = (mydataFmt *)malloc(schannel*sizeof(mydataFmt));
 if(weight->pbias==NULL)cout<<"In initConvAndFc weight buffer malloc failure!";
 memset(weight->pbias, 0, schannel*sizeof(mydataFmt));
 long byteLenght = weight->out_ChannelNum*weight->in_ChannelNum*weight->kernelSize*weight->kernelSize;
 weight->pdata = (mydataFmt *)malloc(byteLenght*sizeof(mydataFmt));
 if(weight->pdata==NULL)cout<<"In initConvAndFc weight buffer malloc failure!";
 memset(weight->pdata, 0, byteLenght*sizeof(mydataFmt));
 
 return byteLenght;
 }

权重的初始化函数就是开辟出权重需要的大小。

# 二、新MTCNN内存实现的思路 #

按照weight，feature的顺序存储

其中，按照Pnet，Rnet，Onet的顺序存储。每个子网络之中按层的先后顺序来实现。

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl8zNjQ3NDgwOQ_size_16_color_FFFFFF_t_70][]

根据具体的卷积算出针对具体卷积的weight，input，output的偏移地址。

weight\_offset=net\_offset+weight\_layer\_offset

input\_offset=feature\_offset+feature\_layer\_offset

## 2.1 weight的初始化与权重写入 ##

一次性开辟所有weight的内存，然后根据Pnet，Rnet，Onet的顺序写入

具体子网络之后用层用从前往后的层顺序。写入weight，

然后从weight文件中读入指针。

## 2.2 feature内存的初始化 ##

###   Pnet ###

因为Pnet按照图像金字塔的结构，所以每层的feature大小都不一样。

按照pyramind的顺序，pyramid之中的feature按照层的顺序。

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl8zNjQ3NDgwOQ_size_16_color_FFFFFF_t_70 1][]

###   Rnet，Onet ###

按照层的顺序进行循环。一次性开辟内存空间反复使用。

#  三、IPcore的接口设计 #

*  接口传入该层参数，
 *  weight，input,output三个偏移量
 *  DRAM地址

//----------------convolution in FPGA-----------------------------------
    void convolution_3x3(int inHight,int inWidth,int inChanNum,int outHight,int outWidth,int OutChanNum,int stride,
        volatile float *SHARED_DRAM, 
        int weight_offset,int input_offset,int output offset){
    #pragma HLS INTERFACE s_axilite register port=inHight bundle=axilite
    #pragma HLS INTERFACE s_axilite register port=inWidth bundle=axilite
    #pragma HLS INTERFACE s_axilite register port=inChanNum bundle=axilite
    #pragma HLS INTERFACE s_axilite register port=outHight bundle=axilite
    #pragma HLS INTERFACE s_axilite register port=outWidth bundle=axilite
    #pragma HLS INTERFACE s_axilite register port=OutChanNum bundle=axilite
    #pragma HLS INTERFACE s_axilite register port=stride bundle=axilite
    #pragma HLS INTERFACE m_axi depth=DRAM_DEPTH port=SHARED_DRAM offset=slave bundle=memorybus
    #pragma HLS INTERFACE s_axilite register port=weight_offset bundle=axilite
    #pragma HLS INTERFACE s_axilite register port=input_offset bundle=axilite
    #pragma HLS INTERFACE s_axilite register port=output offset bundle=axilite

# 四、weight的权重大小 #

###   网络尺寸表 ###

###     Pnet ###

<table> 
 <tbody> 
 <tr> 
 <td> Feature size </td> 
 <td>name</td> 
 <td> Kernel size </td> 
 <td> Stride </td> 
 <td> Padding </td> 
 </tr> 
 <tr> 
 <td> 12*12*3 </td> 
 <td> conv1 ReLU1 </td> 
 <td> 3*3*10 </td> 
 <td> 1 </td> 
 <td>Valid</td> 
 </tr> 
 <tr> 
 <td> 10*10*10 </td> 
 <td>pool1_conv1 pool1_ReLU1 </td> 
 <td> 3*3*16 </td> 
 <td> 2 </td> 
 <td> Same </td> 
 </tr> 
 <tr> 
 <td> 5*5*16 </td> 
 <td> conv2 ReLU2 </td> 
 <td> 3*3*32 </td> 
 <td> 1 </td> 
 <td>Valid</td> 
 </tr> 
 <tr> 
 <td> 3*3*32 </td> 
 <td> conv3 ReLU3 </td> 
 <td> 3*3*32 </td> 
 <td> 1 </td> 
 <td> Valid </td> 
 </tr> 
 <tr> 
 <td> 1*1*32 </td> 
 <td>&nbsp;</td> 
 <td> &nbsp; </td> 
 <td> &nbsp; </td> 
 <td> &nbsp; </td> 
 </tr> 
 </tbody> 
</table>

###     Rnet ###

<table> 
 <tbody> 
 <tr> 
 <td> Feature size </td> 
 <td>name</td> 
 <td> Kernel size </td> 
 <td> Stride </td> 
 <td> Padding </td> 
 </tr> 
 <tr> 
 <td> 24*24*3 </td> 
 <td> conv1 relu1 </td> 
 <td> 3*3*28 </td> 
 <td> 1 </td> 
 <td>Same</td> 
 </tr> 
 <tr> 
 <td> 24*24*28 </td> 
 <td> pool1_conv1 pool1_relu1 </td> 
 <td>3*3*28</td> 
 <td>2</td> 
 <td>Same</td> 
 </tr> 
 <tr> 
 <td>12*12*28</td> 
 <td> conv2 relu2 </td> 
 <td>3*3*48</td> 
 <td>1</td> 
 <td>Same</td> 
 </tr> 
 <tr> 
 <td>12*12*48</td> 
 <td> pool2_conv3 poo2_relu3 </td> 
 <td>3*3*48</td> 
 <td>2</td> 
 <td>Same</td> 
 </tr> 
 <tr> 
 <td>6*6*48</td> 
 <td> conv3 relu3 </td> 
 <td>3*3*64</td> 
 <td>2</td> 
 <td>Same</td> 
 </tr> 
 <tr> 
 <td>3*3*64</td> 
 <td>&nbsp;</td> 
 <td> &nbsp; </td> 
 <td> &nbsp; </td> 
 <td>&nbsp;</td> 
 </tr> 
 </tbody> 
</table>

###     Onet ###

<table> 
 <tbody> 
 <tr> 
 <td> Feature size </td> 
 <td>name</td> 
 <td> Kernel size </td> 
 <td> Stride </td> 
 <td> Padding </td> 
 </tr> 
 <tr> 
 <td> 48*48*3 </td> 
 <td> conv1 relu1 </td> 
 <td> 3*3*32 </td> 
 <td> 1 </td> 
 <td> Same </td> 
 </tr> 
 <tr> 
 <td>48*48*32</td> 
 <td> conv2 relu2 </td> 
 <td>3*3*32</td> 
 <td> 2 </td> 
 <td> Same </td> 
 </tr> 
 <tr> 
 <td> 24*24*32 </td> 
 <td> conv3 relu3 </td> 
 <td>3*3*64</td> 
 <td> 1 </td> 
 <td> Same </td> 
 </tr> 
 <tr> 
 <td> 24*24*64 </td> 
 <td> conv4_ relu4_ </td> 
 <td>3*3*64</td> 
 <td> 2 </td> 
 <td> Same </td> 
 </tr> 
 <tr> 
 <td> 12*12*64 </td> 
 <td> conv5_ relu5_ </td> 
 <td>3*3*128</td> 
 <td> 2 </td> 
 <td> Same </td> 
 </tr> 
 <tr> 
 <td> 6*6*128 </td> 
 <td> conv6_ relu6_ </td> 
 <td>3*3*128</td> 
 <td> 2 </td> 
 <td> Same </td> 
 </tr> 
 <tr> 
 <td>3*3*128</td> 
 <td>&nbsp;</td> 
 <td>&nbsp;</td> 
 <td>&nbsp;</td> 
 <td>&nbsp;</td> 
 </tr> 
 </tbody> 
</table>

## 4.1 Pnet weight的大小 ##

----------Pnet conv1---------------------
    -----------Init conv and Fc for weight---------------------
    Current layer weight 1080 byte and bias 40 byte, total= 1120 byte
    ----------Pnet poo1_conv1---------------------
    -----------Init conv and Fc for weight---------------------
    Current layer weight 5760 byte and bias 64 byte, total= 5824 byte
    ----------Pnet conv2---------------------
    -----------Init conv and Fc for weight---------------------
    Current layer weight 18432 byte and bias 128 byte, total= 18560 byte
    ----------Pnet conv3---------------------
    -----------Init conv and Fc for weight---------------------
    Current layer weight 36864 byte and bias 128 byte, total= 36992 byte
    ----------Pnet conv4c1---------------------
    -----------Init conv and Fc for weight---------------------
    Current layer weight 256 byte and bias 8 byte, total= 264 byte
    ----------Pnet conv4c2---------------------
    -----------Init conv and Fc for weight---------------------
    Current layer weight 512 byte and bias 16 byte, total= 528 byte

###   Pnet ###

<table style="width:500px;"> 
 <tbody> 
 <tr> 
 <td> Pnet weight </td> 
 <td>layer name</td> 
 <td>weight data byte</td> 
 <td>weight bias byte</td> 
 <td>total byte</td> 
 </tr> 
 <tr> 
 <td>conv1</td> 
 <td>1080</td> 
 <td>40</td> 
 <td>1120</td> 
 </tr> 
 <tr> 
 <td>pool1_conv1</td> 
 <td>5760</td> 
 <td>64</td> 
 <td>5824</td> 
 </tr> 
 <tr> 
 <td>conv2</td> 
 <td>18432</td> 
 <td>128</td> 
 <td>18560</td> 
 </tr> 
 <tr> 
 <td>conv3</td> 
 <td>36864</td> 
 <td>128</td> 
 <td>36992</td> 
 </tr> 
 <tr> 
 <td>conv4c1</td> 
 <td>256</td> 
 <td>8</td> 
 <td>264</td> 
 </tr> 
 <tr> 
 <td>conv4c2</td> 
 <td>512</td> 
 <td>16</td> 
 <td>528</td> 
 </tr> 
 </tbody> 
</table>

###   Rnet ###

----------Rnet conv1---------------------
    Current layer weight 3024 byte and bias 112 byte, total= 3136 byte
    ----------Rnet pool_conv1---------------------
    Current layer weight 28224 byte and bias 112 byte, total= 28336 byte
    ----------Rnet conv2---------------------
    Current layer weight 48384 byte and bias 192 byte, total= 48576 byte
    ----------Rnet pool2_conv3---------------------
    Current layer weight 82944 byte and bias 192 byte, total= 83136 byte
    ----------Rnet conv3---------------------
    Current layer weight 110592 byte and bias 256 byte, total= 110848 byte
    ----------Rnet fc4---------------------
    Current layer weight 294912 byte and bias 512 byte, total= 295424 byte
    ----------Rnet score---------------------
    Current layer weight 1024 byte and bias 8 byte, total= 1032 byte
    ----------Rnet location---------------------
    Current layer weight 2048 byte and bias 16 byte, total= 2064 byte
    Create Rnet,Read Rnet.bin ,16 pointers

<table style="width:500px;"> 
 <tbody> 
 <tr> 
 <td> Rnet weight </td> 
 <td>layer name</td> 
 <td>weight data byte</td> 
 <td>weight bias byte</td> 
 <td>total byte</td> 
 </tr> 
 <tr> 
 <td>conv1</td> 
 <td>3024</td> 
 <td>112</td> 
 <td>3136</td> 
 </tr> 
 <tr> 
 <td>pool_conv1</td> 
 <td>28224</td> 
 <td>112</td> 
 <td>28336</td> 
 </tr> 
 <tr> 
 <td>conv2</td> 
 <td>48384</td> 
 <td>192</td> 
 <td>48576</td> 
 </tr> 
 <tr> 
 <td>pool2_conv3</td> 
 <td>82944</td> 
 <td>192</td> 
 <td>83136</td> 
 </tr> 
 <tr> 
 <td>conv3</td> 
 <td>110592</td> 
 <td>256</td> 
 <td>110848</td> 
 </tr> 
 <tr> 
 <td>fc4</td> 
 <td>294912</td> 
 <td>512</td> 
 <td>295424</td> 
 </tr> 
 <tr> 
 <td>score</td> 
 <td>1024</td> 
 <td>8</td> 
 <td>1032</td> 
 </tr> 
 <tr> 
 <td>location</td> 
 <td>2048</td> 
 <td>16</td> 
 <td>2064</td> 
 </tr> 
 </tbody> 
</table>

###   Onet ###

----------Onet conv1---------------------
    Current layer weight 3456 byte and bias 128 byte, total= 3584 byte
    ----------Onet conv2---------------------
    Current layer weight 36864 byte and bias 128 byte, total= 36992 byte
    ----------Onet conv3---------------------
    Current layer weight 73728 byte and bias 256 byte, total= 73984 byte
    ----------Onet conv4_---------------------
    Current layer weight 147456 byte and bias 256 byte, total= 147712 byte
    ----------Onet conv5_---------------------
    Current layer weight 294912 byte and bias 512 byte, total= 295424 byte
    ----------Onet conv6_---------------------
    Current layer weight 589824 byte and bias 512 byte, total= 590336 byte
    ----------Onet fc5---------------------
    Current layer weight 1179648 byte and bias 1024 byte, total= 1180672 byte
    ----------Onet score---------------------
    Current layer weight 2048 byte and bias 8 byte, total= 2056 byte
    ----------Onet location---------------------
    Current layer weight 4096 byte and bias 16 byte, total= 4112 byte
    Create Onet,Read Onet.bin ,18 pointers
    Onet buffer init

<table style="width:500px;"> 
 <tbody> 
 <tr> 
 <td> Onet weight </td> 
 <td>layer name</td> 
 <td>weight data byte</td> 
 <td>weight bias byte</td> 
 <td>total byte</td> 
 </tr> 
 <tr> 
 <td>conv1</td> 
 <td>3456</td> 
 <td>128</td> 
 <td>3584</td> 
 </tr> 
 <tr> 
 <td>conv2</td> 
 <td>36864</td> 
 <td>128</td> 
 <td>36992</td> 
 </tr> 
 <tr> 
 <td>conv3</td> 
 <td>73728</td> 
 <td>256</td> 
 <td>73984</td> 
 </tr> 
 <tr> 
 <td>conv4_</td> 
 <td>147456</td> 
 <td>256</td> 
 <td>147712</td> 
 </tr> 
 <tr> 
 <td>conv5_</td> 
 <td>294912</td> 
 <td>512</td> 
 <td>295424</td> 
 </tr> 
 <tr> 
 <td>conv6_</td> 
 <td>589824</td> 
 <td>512</td> 
 <td>590336</td> 
 </tr> 
 <tr> 
 <td>fc5</td> 
 <td>1179648</td> 
 <td>1024</td> 
 <td>1180672</td> 
 </tr> 
 <tr> 
 <td>score</td> 
 <td>2048</td> 
 <td>8</td> 
 <td>2056</td> 
 </tr> 
 <tr> 
 <td>location</td> 
 <td>4096</td> 
 <td>16</td> 
 <td>4112</td> 
 </tr> 
 </tbody> 
</table>

# 五、feature的大小 #

###   5.1 Rnet ###

//input image to pBox format
    	RnetImage2MatrixInit(rgb);
    	featurePadInit(this->rgb, this->rgb_pad, 1, 1);
        //conv1
    	convolutionInit(this->conv1_wb, this->rgb_pad, this->conv1_out);
    	featurePadInit(this->conv1_out, this->conv1_out_pad, 0, 1);
        //pool1
    	convolutionInit(this->pool_conv1_wb, this->conv1_out_pad, this->pool_conv1_out);
    	featurePadInit(this->pool_conv1_out, this->pool_conv1_out_pad, 1, 1);
        //conv2
    	convolutionInit(this->conv2_wb, this->pool_conv1_out_pad, this->conv2_out);
    	featurePadInit(this->conv2_out, this->conv2_out_pad, 0, 1);
        //pool2
    	convolutionInit(this->pool2_conv3_wb, this->conv2_out_pad, this->pool2_conv3_out);
    	featurePadInit(this->pool2_conv3_out, this->pool2_conv3_out_pad, 0, 1);
        //conv3
    	convolutionInit(this->conv3_wb, this->pool2_conv3_out_pad, this->conv3_out);
        //post conv precess
    	fullconnectInit(this->fc4_wb, this->fc4_out);
    	fullconnectInit(this->score_wb, this->score_);
    	fullconnectInit(this->location_wb, this->location_);

据此生成的大小为：

Create Rnet,Read Rnet.bin ,16 pointers
    Rnet weight buffer init SUCCESS!Start init feature buffer
    -------Rnet image2Matrix buffer byte size 6912 -------
    --------Feature pad buffer byte size 8112 -------
    --------convolution buffer byte size 64512 -------
    --------Feature pad buffer byte size 70000 -------
    --------convolution buffer byte size 16128 -------
    --------Feature pad buffer byte size 21952 -------
    --------convolution buffer byte size 27648 -------
    --------Feature pad buffer byte size 32448 -------
    --------convolution buffer byte size 6912 -------
    --------Feature pad buffer byte size 9408 -------
    --------convolution buffer byte size 2304 -------
    --------fullconnect buffer byte size 512 -------
    --------fullconnect buffer byte size 8 -------
    --------fullconnect buffer byte size 16 -------

<table style="width:500px;"> 
 <tbody> 
 <tr> 
 <td> Rnet feature </td> 
 <td>feature name</td> 
 <td>bytesize</td> 
 </tr> 
 <tr> 
 <td>rgb</td> 
 <td>6912</td> 
 </tr> 
 <tr> 
 <td>rgb_pad</td> 
 <td>8112</td> 
 </tr> 
 <tr> 
 <td>conv1_out</td> 
 <td>64512</td> 
 </tr> 
 <tr> 
 <td>conv1_out_pad</td> 
 <td>70000</td> 
 </tr> 
 <tr> 
 <td>pool_conv1_out</td> 
 <td>16128</td> 
 </tr> 
 <tr> 
 <td>pool_conv1_out_pad</td> 
 <td>21952</td> 
 </tr> 
 <tr> 
 <td>conv2_out</td> 
 <td>27648</td> 
 </tr> 
 <tr> 
 <td>conv2_out_pad</td> 
 <td>32448</td> 
 </tr> 
 <tr> 
 <td>pool2_conv3_out</td> 
 <td>6912</td> 
 </tr> 
 <tr> 
 <td>pool2_conv3_out_pad</td> 
 <td>9408</td> 
 </tr> 
 <tr> 
 <td>conv3_out</td> 
 <td>2304</td> 
 </tr> 
 <tr> 
 <td>fc4_out</td> 
 <td>512</td> 
 </tr> 
 <tr> 
 <td>score_</td> 
 <td>8</td> 
 </tr> 
 <tr> 
 <td>location_</td> 
 <td>16</td> 
 </tr> 
 </tbody> 
</table>

## 5.2 Onet ##

//Init the network
    	printf("Onet weight buffer init SUCCESS! Start init feature buffer \n");
    	  //change image to pBox format
        OnetImage2MatrixInit(rgb);
        featurePadInit(this->rgb, this->rgb_pad, 1, 1);//s=1
    	  //conv1
        convolutionInit(this->conv1_wb, this->rgb_pad, this->conv1_out);
        featurePadInit(this->conv1_out, this->conv1_out_pad, 0, 1);//s=2
    	  //conv2
        convolutionInit(this->conv2_wb, this->conv1_out_pad, this->conv2_out);
        featurePadInit(this->conv2_out, this->conv2_out_pad, 1, 1);//s=1
        //conv3
        convolutionInit(this->conv3_wb, this->conv2_out_pad, this->conv3_out);
        featurePadInit(this->conv3_out, this->conv3_out_pad, 0, 1);//s=2
        //conv4_
        convolutionInit(this->conv4_wb, this->conv3_out_pad, this->conv4_out);
        featurePadInit(this->conv4_out, this->conv4_out_pad, 0, 1);//s=2
        //conv5_
        convolutionInit(this->conv5_wb, this->conv4_out_pad, this->conv5_out);
        featurePadInit(this->conv5_out, this->conv5_out_pad, 0, 1);//s=2
        //conv6_
        convolutionInit(this->conv6_wb, this->conv5_out_pad, this->conv6_out);
        //post conv precess
    	  fullconnectInit(this->fc5_wb, this->fc5_out);
        fullconnectInit(this->score_wb, this->score_);
        fullconnectInit(this->location_wb, this->location_);

<table style="width:500px;"> 
 <tbody> 
 <tr> 
 <td> Onet feature </td> 
 <td>feature name</td> 
 <td>bytesize</td> 
 </tr> 
 <tr> 
 <td>rgb</td> 
 <td>27648</td> 
 </tr> 
 <tr> 
 <td>rgb_pad</td> 
 <td>30000</td> 
 </tr> 
 <tr> 
 <td>conv1_out</td> 
 <td>294912</td> 
 </tr> 
 <tr> 
 <td>conv1_out_pad</td> 
 <td>307328</td> 
 </tr> 
 <tr> 
 <td>conv2_out</td> 
 <td>73728</td> 
 </tr> 
 <tr> 
 <td>conv2_out_pad</td> 
 <td>86528</td> 
 </tr> 
 <tr> 
 <td>conv3_out</td> 
 <td>147456</td> 
 </tr> 
 <tr> 
 <td>conv3_out_pad</td> 
 <td>160000</td> 
 </tr> 
 <tr> 
 <td>conv4_out</td> 
 <td>36864</td> 
 </tr> 
 <tr> 
 <td>conv4_out_pad</td> 
 <td>43264</td> 
 </tr> 
 <tr> 
 <td>conv5_out</td> 
 <td>18432</td> 
 </tr> 
 <tr> 
 <td>conv5_out_pad</td> 
 <td>25088</td> 
 </tr> 
 <tr> 
 <td>conv6_out</td> 
 <td>4608</td> 
 </tr> 
 <tr> 
 <td>fc5_out</td> 
 <td>1024</td> 
 </tr> 
 <tr> 
 <td>score_</td> 
 <td>8</td> 
 </tr> 
 <tr> 
 <td>location_</td> 
 <td>16</td> 
 </tr> 
 </tbody> 
</table>

## 5.3 Pnet ##

Pnet的feature较多，有很多个pyramid，每个pyramid的尺寸都不一样。

//scales 0.400000  h:116  w:142
    //scales 0.340000  h:98  w:120
    //scales 0.289000  h:84  w:102
    //scales 0.245650  h:72  w:88
    //scales 0.208803  h:62  w:74
    //scales 0.177482  h:52  w:64
    //scales 0.150860  h:44  w:54
    //scales 0.128231  h:38  w:46
    //scales 0.108996  h:32  w:40
    //scales 0.092647  h:28  w:34
    //scales 0.078750  h:24  w:28
    //scales 0.066937  h:20  w:24
    //scales 0.056897  h:18  w:22
    //scales 0.048362  h:14  w:18
    Create Pnet,Read Pnet.bin ,12 pointers
    ------Start find Face function
    scales 0.400000  h:116  w:142
    Start run Pnet
    Pnet feature buffer init
    ----------image to matrix buffer byte size 197664 ----------------
    --------convolution buffer byte size 638400 -------
    --------Feature pad buffer byte size 648600 -------
    --------convolution buffer byte size 255360 -------
    --------convolution buffer byte size 478720 -------
    --------convolution buffer byte size 447744 -------
    --------convolution buffer byte size 27984 -------
    --------convolution buffer byte size 55968 -------
    scales 0.340000  h:98  w:120
    Start run Pnet
    Pnet feature buffer init
    ----------image to matrix buffer byte size 141120 ----------------
    --------convolution buffer byte size 453120 -------
    --------Feature pad buffer byte size 461720 -------
    --------convolution buffer byte size 181248 -------
    --------convolution buffer byte size 335616 -------
    --------convolution buffer byte size 309760 -------
    --------convolution buffer byte size 19360 -------
    --------convolution buffer byte size 38720 -------
    scales 0.289000  h:84  w:102
    Start run Pnet
    Pnet feature buffer init
    ----------image to matrix buffer byte size 102816 ----------------
    --------convolution buffer byte size 328000 -------
    --------Feature pad buffer byte size 335320 -------
    --------convolution buffer byte size 131200 -------
    --------convolution buffer byte size 239616 -------
    --------convolution buffer byte size 217856 -------
    --------convolution buffer byte size 13616 -------
    --------convolution buffer byte size 27232 -------
    scales 0.245650  h:72  w:88
    Start run Pnet
    Pnet feature buffer init
    ----------image to matrix buffer byte size 76032 ----------------
    --------convolution buffer byte size 240800 -------
    --------Feature pad buffer byte size 247080 -------
    --------convolution buffer byte size 96320 -------
    --------convolution buffer byte size 173184 -------
    --------convolution buffer byte size 154752 -------
    --------convolution buffer byte size 9672 -------
    --------convolution buffer byte size 19344 -------
    scales 0.208803  h:62  w:74
    Start run Pnet
    Pnet feature buffer init
    ----------image to matrix buffer byte size 55056 ----------------
    --------convolution buffer byte size 172800 -------
    --------Feature pad buffer byte size 178120 -------
    --------convolution buffer byte size 69120 -------
    --------convolution buffer byte size 121856 -------
    --------convolution buffer byte size 106496 -------
    --------convolution buffer byte size 6656 -------
    --------convolution buffer byte size 13312 -------
    scales 0.177482  h:52  w:64
    Start run Pnet
    Pnet feature buffer init
    ----------image to matrix buffer byte size 39936 ----------------
    --------convolution buffer byte size 124000 -------
    --------Feature pad buffer byte size 128520 -------
    --------convolution buffer byte size 49600 -------
    --------convolution buffer byte size 85376 -------
    --------convolution buffer byte size 72576 -------
    --------convolution buffer byte size 4536 -------
    --------convolution buffer byte size 9072 -------
    scales 0.150860  h:44  w:54
    Start run Pnet
    Pnet feature buffer init
    ----------image to matrix buffer byte size 28512 ----------------
    --------convolution buffer byte size 87360 -------
    --------Feature pad buffer byte size 91160 -------
    --------convolution buffer byte size 34944 -------
    --------convolution buffer byte size 58368 -------
    --------convolution buffer byte size 47872 -------
    --------convolution buffer byte size 2992 -------
    --------convolution buffer byte size 5984 -------
    scales 0.128231  h:38  w:46
    Start run Pnet
    Pnet feature buffer init
    ----------image to matrix buffer byte size 20976 ----------------
    --------convolution buffer byte size 63360 -------
    --------Feature pad buffer byte size 66600 -------
    --------convolution buffer byte size 25344 -------
    --------convolution buffer byte size 40960 -------
    --------convolution buffer byte size 32256 -------
    --------convolution buffer byte size 2016 -------
    --------convolution buffer byte size 4032 -------
    scales 0.108996  h:32  w:40
    Start run Pnet
    Pnet feature buffer init
    ----------image to matrix buffer byte size 15360 ----------------
    --------convolution buffer byte size 45600 -------
    --------Feature pad buffer byte size 48360 -------
    --------convolution buffer byte size 18240 -------
    --------convolution buffer byte size 28288 -------
    --------convolution buffer byte size 21120 -------
    --------convolution buffer byte size 1320 -------
    --------convolution buffer byte size 2640 -------
    scales 0.092647  h:28  w:34
    Start run Pnet
    Pnet feature buffer init
    ----------image to matrix buffer byte size 11424 ----------------
    --------convolution buffer byte size 33280 -------
    --------Feature pad buffer byte size 35640 -------
    --------convolution buffer byte size 13312 -------
    --------convolution buffer byte size 19712 -------
    --------convolution buffer byte size 13824 -------
    --------convolution buffer byte size 864 -------
    --------convolution buffer byte size 1728 -------
    scales 0.078750  h:24  w:28
    Start run Pnet
    Pnet feature buffer init
    ----------image to matrix buffer byte size 8064 ----------------
    --------convolution buffer byte size 22880 -------
    --------Feature pad buffer byte size 24840 -------
    --------convolution buffer byte size 9152 -------
    --------convolution buffer byte size 12672 -------
    --------convolution buffer byte size 8064 -------
    --------convolution buffer byte size 504 -------
    --------convolution buffer byte size 1008 -------
    scales 0.066937  h:20  w:24
    Start run Pnet
    Pnet feature buffer init
    ----------image to matrix buffer byte size 5760 ----------------
    --------convolution buffer byte size 15840 -------
    --------Feature pad buffer byte size 17480 -------
    --------convolution buffer byte size 6336 -------
    --------convolution buffer byte size 8064 -------
    --------convolution buffer byte size 4480 -------
    --------convolution buffer byte size 280 -------
    --------convolution buffer byte size 560 -------
    scales 0.056897  h:18  w:22
    Start run Pnet
    Pnet feature buffer init
    ----------image to matrix buffer byte size 4752 ----------------
    --------convolution buffer byte size 12800 -------
    --------Feature pad buffer byte size 14280 -------
    --------convolution buffer byte size 5120 -------
    --------convolution buffer byte size 6144 -------
    --------convolution buffer byte size 3072 -------
    --------convolution buffer byte size 192 -------
    --------convolution buffer byte size 384 -------
    scales 0.048362  h:14  w:18
    Start run Pnet
    Pnet feature buffer init
    ----------image to matrix buffer byte size 3024 ----------------
    --------convolution buffer byte size 7680 -------
    --------Feature pad buffer byte size 8840 -------
    --------convolution buffer byte size 3072 -------
    --------convolution buffer byte size 3072 -------
    --------convolution buffer byte size 1024 -------
    --------convolution buffer byte size 64 -------
    --------convolution buffer byte size 128 -------

# 六、网络的总尺寸 #

## 6.1 权重尺寸 ##

## 6.2 feature大小 ##

[c_ http_www.runoob.com_cplusplus_cpp-constructor-destructor.html]: http://www.runoob.com/cplusplus/cpp-constructor-destructor.html
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl8zNjQ3NDgwOQ_size_16_color_FFFFFF_t_70]: /images/20220330/976a290b01d842bc8f525e41ead04a1e.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl8zNjQ3NDgwOQ_size_16_color_FFFFFF_t_70 1]: /images/20220330/8b3bc2266a7d45a69997d9258ed86f4b.png