python pytorch 纯算法实现前馈神经网络训练（数据集随机生成）-续

上一次的代码博主看了，有两个小问题其实，一个是，SGD优化的时候，那个梯度应该初始化为0，还一个是我并没有用到随机生成batch。
博主修改了代码，并且加入了accuracy图像绘制的代码。代码如下：

#coding=gbk

import torch
from torch.autograd import Variable
from torch.utils import data
import matplotlib.pyplot as plt


dim=5
batch=32
neuron_num=10
def generate_data():
    torch.manual_seed(3)
    X1=torch.randint(0,4,(1000,dim))
    X2=torch.randint(6,10,(1000,dim))

    Y1=torch.randint(0,1,(1000,))
    Y2=torch.randint(1,2,(1000,))
    print(X1)
    print(X2)
    print(Y1)
    print(Y2)
    X_data=torch.cat([X1,X2],0)
    Y_label=torch.cat([Y1,Y2],0)
    print(X_data)
    print(Y_label)
    return X_data,Y_label

def sampling(X_data,Y_label,batch):
    data_size=Y_label.size()
    #print(data_size)
    index_sequense=torch.randperm(data_size[0])
    return index_sequense


def loss_function_crossEntropy(Y_predict,Y_real):
    if Y_real==1:
        return -torch.log(Y_predict)
    else:
         return -torch.log(1-Y_predict)



X_data,Y_label=generate_data()
index_sequense=sampling(X_data,Y_label,batch)



def test():
    l=loss_function_crossEntropy(torch.tensor([0.1]),torch.tensor([1]))
    print(l)



def neuron_net(X,W,b):
    result=torch.matmul(X.type(dtype=torch.float32),W)+b
    result=torch.relu(result).reshape(1,result.size(0))

    #print(result)
    
    #print(result.size())
    return result


def grad(X,W,b,y_predict,y_real,W2,b2):
    g1=y_real/y_predict+(y_real-1)/(1-y_predict)
    result=torch.matmul(X.type(dtype=torch.float32),W)+b
    result=torch.relu(result).reshape(1,result.size(0))
   
    g2=y_predict*(1-y_predict)
    g3=neuron_net(X,W,b)
    g4=W2
    C=torch.matmul(X.type(dtype=torch.float32),W)+b
    a=[]
    for i in C:
        if i<=0:
            a.append(0)
        else:
            a.append(1)
    g5=torch.tensor(a)

    g6=X
    grad_w=g1*g2*g3
    grad_b=g1*g2
    #print("grad_w",grad_w)
    #print(grad_b)
    grad_w2=g1*g2*g4
    grad_w2=grad_w2.reshape(1,10)
   
    grad_w2=grad_w2*g5
  #  print(grad_w2.size())
    grad_w2=grad_w2.reshape(10,1)
  
    g6=g6.reshape(1,5)
    
    grad_b2=grad_w2
    grad_w2=torch.matmul(grad_w2.type(dtype=torch.float32),g6.type(dtype=torch.float32))
   # print(grad_b2.size())

    return grad_w,grad_b,grad_w2,grad_b2

    #print(g1,g2,g3,g4,g5,g6)
    
    #print(grad_w2)
    #print(grad_b2)
  
   

def flat_dense(X,W,b):
    return torch.sigmoid(torch.matmul(X.type(dtype=torch.float32),W)+b)


W=torch.randn(dim,neuron_num)
b=torch.randn(neuron_num)
W2=torch.randn(neuron_num,1)
b2=torch.randn(1)


def net(X,W,b,W2,b2):
    result=neuron_net(X,W,b)

    ans=flat_dense(result,W2,b2)
    return  ans


y_predict=net(X_data[0],W,b,W2,b2)
print(y_predict)

grad_w,grad_b,grad_w2,grad_b2=grad(X_data[0],W,b,y_predict,Y_label[0],W2,b2)

loss_list=[]
accuracy_list=[]
learn_rating=0.01
epoch=2000
def train():
    
    index=0
    global W,W2,b,b2
    for i in range(epoch):
       
        W_g=torch.zeros(dim,neuron_num)
        b_g=torch.zeros(neuron_num)
        W2_g=torch.zeros(neuron_num,1)
        b2_g=torch.zeros(1)
        loss=torch.tensor([0.0])
        co=0
        for j in range(32):
            try:
                y_predict=net(X_data[index_sequense[index]],W,b,W2,b2)
                grad_w,grad_b,grad_w2,grad_b2=grad(X_data[index_sequense[index]],W,b,y_predict,Y_label[index_sequense[index]],W2,b2)
             #   print(grad_w2.size(),W_g.size())
                grad_w2=torch.t(grad_w2)
                W_g=W_g+grad_w2
                grad_b2=grad_b2.reshape(10)
                #print("b_g",b_g)
                #print("grad_b2",grad_b2)
                b_g=grad_b2+b_g
             
                W2_g=W2_g+torch.t(grad_w)
                b2_g=b2_g+torch.t(grad_b)
                
             #   print("fdafaf",grad_w,grad_b,grad_w2,grad_b2)
                loss=loss+loss_function_crossEntropy(y_predict,Y_label[index_sequense[index]])
               # print( Y_label[index],y_predict[0][0])
                if (Y_label[index_sequense[index]]==1) &( y_predict[0][0]>0.5):
                    co=co+1
                if (Y_label[index_sequense[index]]==0) &( y_predict[0][0]<=0.5):
                    co=co+1
                index=index+1
            except:
                index=0

        print("loss:",loss[0])
        print("accuracy:",co/32)
        loss_list.append(loss[0])
        accuracy_list.append(co/32)
        W_g=W_g/batch
        b_g=b_g/batch
        W2_g=W2_g/batch
        b2_g=b2_g/batch
        #print(W.size())
        #print(b.size())
        #print(W2.size())
        #print(b2.size())

        W=W+learn_rating*W_g
     #   print("b*********************",b,b_g)
        b=b+learn_rating*(b_g)
        #print(W2_g.size())
        #print(b2_g.size())
        W2=W2+learn_rating*W2_g
        b2=b2+learn_rating*b2_g
        #print(W.size())
        #print(b.size())
        #print(W2.size())
        #print(b2.size())



train()
epoch_list=list(range(epoch))
plt.plot(epoch_list,loss_list,label='SGD')
plt.title("loss")
plt.legend()

plt.show()

epoch_list=list(range(epoch))
plt.plot(epoch_list,accuracy_list,label='SGD')
plt.title("loss")
plt.legend()
plt.show()

可一下跑出的结果：


可以看到这样看下来，效果就很不错了。