【darknet】添加新层详细版

灰太狼 2022-05-18 09:19 213阅读 0赞

[darknet中depthwiselayer的github][darknet_depthwiselayer_github]  
[darknet卷积源码解读github][darknet_github]

一、添加一个新的网络层

(1)parse.c文件中函数string\_to\_layer\_type，添加网络层类型解析：

if (strcmp(type, "[depthwise_convolutional]") == 0) return DEPTHWISE_CONVOLUTIONAL;

(2)darknet.h文件中枚举类型LAYER\_TYPE，添加网络层枚举类型：

DEPTHWISE_CONVOLUTIONAL；

(3)parse.c文件中函数parse\_network\_cfg添加网络层解析后进行构建：

LAYER_TYPE lt = string_to_layer_type(s->type); 
         if (lt == DEPTHWISE_CONVOLUTIONAL) { 
         l = parse_depthwise_convolutional(options, params); //自己编写的函数，主要调用了make layer 
         } 
         else if(lt == CONVOLUTIONAL){ 
         l = parse_convolutional(options, params);

(4)parse.c 添加参数读取网络层加载文件

A、添加网络层读取参数函数

void load_weights_upto(network *net, char *filename, int start, int cutoff) 
         load depthwise weights；

B、把参数读取到内存上:

void load_depthwise_convolutional_weights(layer l, FILE *fp)；

C、以及修改depthwise\_convolutional\_kenel.cu把读取后的cpu参数拷贝到显存上：

void push_depthwise_convolutional_layer(depthwise_convolutional_layer layer)；

(5)parse.c添加参数保存功能：

void save_weights_upto(network net, char *filename, int cutoff)： 
         void save_depthwise_convolutional_weights (layer l, FILE *fp)； 
         void pull_depthwise_convolutional_layer (depthwise_convolutional_layer layer)；

(6)添加network.c中网络层:

int resize_network(network *net, int w, int h)的resize： 
         if (l.type==DEPTHWISE_CONVOLUTIONAL) 
         { 
         resize_depthwise_convolutional_layer(&l, w, h); 
         }

(7)另外在多卡异步训练的时候，network\_kernels.cu的好几个函数也要添加depth\_convolutional参数相关的更新设置。

总结为一句话：直接搜索项目中调用：CONVOLUTIONAL的关键子

有调用到卷积层枚举类型的地方，可分离卷积层也要添加相对应的功能。

(8)darknet使用须知：darknet的网络配置文件中的学习率、batch并不是我们平时所说的学习率、batch\_size。网络更新所用的学习率为：learning\_rate/batch\_size,所以学习率不能太小，比如如果学习率设置为0.01，batch=128，那么实际计算的学习率就是0.000078，非常小的一个数值，基本上就是更新不了

二、编写网络层代码:depthwise\_convolutional\_kernels.cu、depthwise\_convolutional\_layer.c、depthwise\_convolutional\_layer.h

三、编写mobilenet网络结构文件：

[net] 
         batch= 32 
         subdivisions= 1 
         height= 224 
         width= 224 
         channels= 3 
         momentum= 0.9 
         decay= 0.000 
         max_crop= 320 
         
         learning_rate= 0.1 
         policy=poly 
         power= 3 
         max_batches= 1600000 
         
         #conv1 
         [convolutional] 
         batch_normalize= 1 
         filters= 32 
         size= 3 
         stride= 2 
         pad= 1 
         activation=relu 
         
         #conv2_1/dw 
         [depthwise_convolutional] 
         batch_normalize= 1 
         size= 3 
         stride= 1 
         pad= 1 
         activation=relu 
         
         #conv2_1/sep 
         [convolutional] 
         batch_normalize= 1 
         filters= 64 
         size= 1 
         stride= 1 
         pad= 0 
         activation=relu 
         
         
         #conv2_2/dw 
         [depthwise_convolutional] 
         batch_normalize= 1 
         size= 3 
         stride= 2 
         pad= 1 
         activation=relu 
         
         #conv2_2/sep 
         [convolutional] 
         batch_normalize= 1 
         filters= 128 
         size= 1 
         stride= 1 
         pad= 0 
         activation=relu 
         
         #conv3_1/dw 
         [depthwise_convolutional] 
         batch_normalize= 1 
         size= 3 
         stride= 1 
         pad= 1 
         activation=relu 
         
         
         #conv3_1/sep 
         [convolutional] 
         batch_normalize= 1 
         filters= 128 
         size= 1 
         stride= 1 
         pad= 0 
         activation=relu 
         
         #conv3_2/dw 
         [depthwise_convolutional] 
         batch_normalize= 1 
         size= 3 
         stride= 2 
         pad= 1 
         activation=relu 
         
         #conv3_2/sep 
         [convolutional] 
         batch_normalize= 1 
         filters= 256 
         size= 1 
         stride= 1 
         pad= 0 
         activation=relu 
         
         #conv4_1/dw 
         [depthwise_convolutional] 
         batch_normalize= 1 
         size= 3 
         stride= 1 
         pad= 1 
         activation=relu 
         
         #conv4_1/sep 
         [convolutional] 
         batch_normalize= 1 
         filters= 256 
         size= 1 
         stride= 1 
         pad= 0 
         activation=relu 
         
         #conv4_2/dw 
         [depthwise_convolutional] 
         batch_normalize= 1 
         size= 3 
         stride= 2 
         pad= 1 
         activation=relu 
         
         #conv4_2/sep 
         [convolutional] 
         batch_normalize= 1 
         filters= 512 
         size= 1 
         stride= 1 
         pad= 0 
         activation=relu 
         
         #conv5_1/dw 
         [depthwise_convolutional] 
         batch_normalize= 1 
         size= 3 
         stride= 1 
         pad= 1 
         activation=relu 
         
         #conv5_1/sep 
         [convolutional] 
         batch_normalize= 1 
         filters= 512 
         size= 1 
         stride= 1 
         pad= 0 
         activation=relu 
         
         #conv5_2/dw 
         [depthwise_convolutional] 
         batch_normalize= 1 
         size= 3 
         stride= 1 
         pad= 1 
         activation=relu 
         
         #conv5_2/sep 
         [convolutional] 
         batch_normalize= 1 
         filters= 512 
         size= 1 
         stride= 1 
         pad= 0 
         activation=relu 
         
         #conv5_3/dw 
         [depthwise_convolutional] 
         batch_normalize= 1 
         size= 3 
         stride= 1 
         pad= 1 
         activation=relu 
         
         #conv5_3/sep 
         [convolutional] 
         batch_normalize= 1 
         filters= 512 
         size= 1 
         stride= 1 
         pad= 0 
         activation=relu 
         
         #conv5_4/dw 
         [depthwise_convolutional] 
         batch_normalize= 1 
         size= 3 
         stride= 1 
         pad= 1 
         activation=relu 
         
         #conv5_4/sep 
         [convolutional] 
         batch_normalize= 1 
         filters= 512 
         size= 1 
         stride= 1 
         pad= 0 
         activation=relu 
         
         #conv5_5/dw 
         [depthwise_convolutional] 
         batch_normalize= 1 
         size= 3 
         stride= 1 
         pad= 1 
         activation=relu 
         
         #conv5_5/sep 
         [convolutional] 
         batch_normalize= 1 
         filters= 512 
         size= 1 
         stride= 1 
         pad= 0 
         activation=relu 
         
         #conv5_6/dw 
         [depthwise_convolutional] 
         batch_normalize= 1 
         size= 3 
         stride= 2 
         pad= 1 
         activation=relu 
         
         #conv5_6/sep 
         [convolutional] 
         batch_normalize= 1 
         filters= 1024 
         size= 1 
         stride= 1 
         pad= 0 
         activation=relu 
         
         #conv6/dw 
         [depthwise_convolutional] 
         batch_normalize= 1 
         size= 3 
         stride= 1 
         pad= 1 
         activation=relu 
         
         #conv6/sep 
         [convolutional] 
         batch_normalize= 1 
         filters= 1024 
         size= 1 
         stride= 1 
         pad= 0 
         activation=relu 
         
         #pool6 
         [avgpool] 
         
         #fc7 
         [convolutional] 
         filters= 1000 
         size= 1 
         stride= 1 
         pad= 0 
         activation=leaky 
         
         [softmax] 
         groups= 1 
         
         [cost]

四、imagenet训练实验

1、训练一天后,经过两轮多的epoch后,精度:

![20170727133643993][]

2、训练两天后,迭代第二天结果:

![20170803105357650][]

3\\又训练了一天多:

![20170804151700223][]

[darknet_depthwiselayer_github]: https://github.com/hjimce/darknet_mobilenet
[darknet_github]: https://github.com/hgpvision/darknet
[20170727133643993]: /images/20220518/06b30bf138bb4035a7e283973bd92a74.png
[20170803105357650]: /images/20220518/d5b87cfae6cb4b4b912de633df6ea30e.png
[20170804151700223]: /images/20220518/74661ba95ebb481d93a9122c7597a22c.png