序列模型api整理

README.md

 <div align=center><img src="./picture/01.svg"/></div>
-
 # Edge-Engine
 
 ## Edge : 一个开源的科学计算引擎
@@ -62,6 +61,20 @@ make install
 ➜  edge-computing-engine git:(master) ✗ ./main
 ```
 
+序贯模型api使用方法:
+
+edge_network(int input, int num_neuron)
+
+作为序列模型api
+
+edge_network作为一个类型存在,位于matrix_grad.h中结构体类型的数据
+
+定义了前向传播函数,前向传播无激活版,反向传播,末层反向传播,四大最常用的函数主体.
+
+完整的序列模型:
+
+![image-20200128154352842](/Users/zhangyiji/Documents/code/cpp_demo/my_os/Edge-Computing-Engine/image-20200128154352842.png)
+
 ## 新的demo程序实现5层全连接层,可自定义神经元和激活函数,损失函数
 
 全连接层使用方法:
@@ -500,7 +513,6 @@ Something :
 <div align = center><img src = './picture/星月.svg'></div>
 
 
-
  个人小站:[极度空间](http://likedge.top/)
 
 作者邮箱:zk@likedge.top | edge@ibooker.org.cn

main.cpp

@@ -32,25 +32,13 @@ int main()
 {
 	cout<<"------------autodiff for neraul network-----------"<<endl;
 	Matrix data_mine = CreateMatrix(2,1);
-	change_va(data_mine,0,0,0.55);
-	change_va(data_mine,1,0,0.2);
 	cout<<"data mine"<<endl;
 	cout_mat(data_mine);
 	cout<<"data mine"<<endl;
 	Matrix label = CreateRandMat(2,1);
-    change_va(label,0,0,0.4);
-	change_va(label,1,0,0.8);
 	Matrix weight1 = CreateRandMat(2,2);
-	change_va(weight1,0,0,0.1);
-	change_va(weight1,0,1,0.2);
-	change_va(weight1,1,0,0.2);
-	change_va(weight1,1,1,0.4);
 	Matrix bais1 = ones(2,1);
 	Matrix weight2 = CreateRandMat(2,2);
-	change_va(weight2,0,0,0.5);
-	change_va(weight2,1,0,0.6);
-    change_va(weight2,0,1,0.7);
-	change_va(weight2,1,1,0.8);
 	Matrix bais2 = ones(2,1);
 	for(int epoch = 0;epoch<1;epoch++)
 	{