人工智能作业3

一：利用pytorch实现列题

import torch
 
x1, x2 = torch.Tensor([0.5]), torch.Tensor([0.3])
y1, y2 = torch.Tensor([0.23]), torch.Tensor([-0.07])
print("=====输入值：x1, x2；真实输出值：y1, y2=====")
print(x1, x2, y1, y2)
w1, w2, w3, w4, w5, w6, w7, w8 = torch.Tensor([0.2]), torch.Tensor([-0.4]), torch.Tensor([0.5]), torch.Tensor(
    [0.6]), torch.Tensor([0.1]), torch.Tensor([-0.5]), torch.Tensor([-0.3]), torch.Tensor([0.8])  # 权重初始值
w1.requires_grad = True
w2.requires_grad = True
w3.requires_grad = True
w4.requires_grad = True
w5.requires_grad = True
w6.requires_grad = True
w7.requires_grad = True
w8.requires_grad = True
 
 
def sigmoid(z):
    a = 1 / (1 + torch.exp(-z))
    return a
 
 
def forward_propagate(x1, x2):
    in_h1 = w1 * x1 + w3 * x2
    out_h1 = sigmoid(in_h1)  # out_h1 = torch.sigmoid(in_h1)
    in_h2 = w2 * x1 + w4 * x2
    out_h2 = sigmoid(in_h2)  # out_h2 = torch.sigmoid(in_h2)
 
    in_o1 = w5 * out_h1 + w7 * out_h2
    out_o1 = sigmoid(in_o1)  # out_o1 = torch.sigmoid(in_o1)
    in_o2 = w6 * out_h1 + w8 * out_h2
    out_o2 = sigmoid(in_o2)  # out_o2 = torch.sigmoid(in_o2)
 
    print("正向计算：o1 ,o2")
    print(out_o1.data, out_o2.data)
 
    return out_o1, out_o2
 
 
def loss_fuction(x1, x2, y1, y2):  # 损失函数
    y1_pred, y2_pred = forward_propagate(x1, x2)  # 前向传播
    loss = (1 / 2) * (y1_pred - y1) ** 2 + (1 / 2) * (y2_pred - y2) ** 2  # 考虑 ： t.nn.MSELoss()
    print("损失函数（均方误差）：", loss.item())
    return loss
 
 
def update_w(w1, w2, w3, w4, w5, w6, w7, w8):
    # 步长
    step = 1
    w1.data = w1.data - step * w1.grad.data
    w2.data = w2.data - step * w2.grad.data
    w3.data = w3.data - step * w3.grad.data
    w4.data = w4.data - step * w4.grad.data
    w5.data = w5.data - step * w5.grad.data
    w6.data = w6.data - step * w6.grad.data
    w7.data = w7.data - step * w7.grad.data
    w8.data = w8.data - step * w8.grad.data
    w1.grad.data.zero_()  # 注意：将w中所有梯度清零
    w2.grad.data.zero_()
    w3.grad.data.zero_()
    w4.grad.data.zero_()
    w5.grad.data.zero_()
    w6.grad.data.zero_()
    w7.grad.data.zero_()
    w8.grad.data.zero_()
    return w1, w2, w3, w4, w5, w6, w7, w8
 
if __name__ == "__main__":
 
    print("=====更新前的权值=====")
    print(w1.data, w2.data, w3.data, w4.data, w5.data, w6.data, w7.data, w8.data)
 
    for i in range(1):
        print("=====第" + str(i) + "轮=====")
        L = loss_fuction(x1, x2, y1, y2) # 前向传播，求 Loss，构建计算图
        L.backward()  # 自动求梯度，不需要人工编程实现。反向传播，求出计算图中所有梯度存入w中
        print("\tgrad W: ", round(w1.grad.item(), 2), round(w2.grad.item(), 2), round(w3.grad.item(), 2),
              round(w4.grad.item(), 2), round(w5.grad.item(), 2), round(w6.grad.item(), 2), round(w7.grad.item(), 2),
              round(w8.grad.item(), 2))
        w1, w2, w3, w4, w5, w6, w7, w8 = update_w(w1, w2, w3, w4, w5, w6, w7, w8)
 
    print("更新后的权值")
    print(w1.data, w2.data, w3.data, w4.data, w5.data, w6.data, w7.data, w8.data)
    # print(forward_propagate(x1, x2))

二：

不相同：

import numpy as np
import matplotlib.pyplot as plt


def sigmoid(z):
    a = 1 / (1 + np.exp(-z))
    return a


def forward_propagate(x1, x2, y1, y2, w1, w2, w3, w4, w5, w6, w7, w8):  # 正向传播
    in_h1 = w1 * x1 + w3 * x2
    out_h1 = sigmoid(in_h1)
    in_h2 = w2 * x1 + w4 * x2
    out_h2 = sigmoid(in_h2)

    in_o1 = w5 * out_h1 + w7 * out_h2
    out_o1 = sigmoid(in_o1)
    in_o2 = w6 * out_h1 + w8 * out_h2
    out_o2 = sigmoid(in_o2)

    error = (1 / 2) * (out_o1 - y1) ** 2 + (1 / 2) * (out_o2 - y2) ** 2

    return out_o1, out_o2, out_h1, out_h2, error


def back_propagate(out_o1, out_o2, out_h1, out_h2):  # 反向传播
    d_o1 = out_o1 - y1
    d_o2 = out_o2 - y2

    d_w5 = d_o1 * out_o1 * (1 - out_o1) * out_h1
    d_w7 = d_o1 * out_o1 * (1 - out_o1) * out_h2
    d_w6 = d_o2 * out_o2 * (1 - out_o2) * out_h1
    d_w8 = d_o2 * out_o2 * (1 - out_o2) * out_h2

    d_w1 = (d_w5 + d_w6) * out_h1 * (1 - out_h1) * x1
    d_w3 = (d_w5 + d_w6) * out_h1 * (1 - out_h1) * x2
    d_w2 = (d_w7 + d_w8) * out_h2 * (1 - out_h2) * x1
    d_w4 = (d_w7 + d_w8) * out_h2 * (1 - out_h2) * x2

    return d_w1, d_w2, d_w3, d_w4, d_w5, d_w6, d_w7, d_w8


def update_w(step, w1, w2, w3, w4, w5, w6, w7, w8):  # 梯度下降，更新权值
    w1 = w1 - step * d_w1
    w2 = w2 - step * d_w2
    w3 = w3 - step * d_w3
    w4 = w4 - step * d_w4
    w5 = w5 - step * d_w5
    w6 = w6 - step * d_w6
    w7 = w7 - step * d_w7
    w8 = w8 - step * d_w8
    return w1, w2, w3, w4, w5, w6, w7, w8


if __name__ == "__main__":
    w1, w2, w3, w4, w5, w6, w7, w8 = 0.2, -0.4, 0.5, 0.6, 0.1, -0.5, -0.3, 0.8  # 可以给随机值，为配合PPT，给的指定值
    x1, x2 = 0.5, 0.3  # 输入值
    y1, y2 = 0.23, -0.07  # 正数可以准确收敛；负数不行。why? 因为用sigmoid输出，y1, y2 在 （0,1）范围内。
    N = 10  # 迭代次数
    step = 10  # 步长

    print("输入值：x1, x2；", x1, x2, "输出值：y1, y2:", y1, y2)
    eli = []
    lli = []
    for i in range(N):
        print("=====第" + str(i) + "轮=====")
        # 正向传播
        out_o1, out_o2, out_h1, out_h2, error = forward_propagate(x1, x2, y1, y2, w1, w2, w3, w4, w5, w6, w7, w8)
        print("正向传播:", round(out_o1, 5), round(out_o2, 5))
        print("损失函数：", round(error, 2))
        # 反向传播
        d_w1, d_w2, d_w3, d_w4, d_w5, d_w6, d_w7, d_w8 = back_propagate(out_o1, out_o2, out_h1, out_h2)
        # 梯度下降，更新权值
        w1, w2, w3, w4, w5, w6, w7, w8 = update_w(step, w1, w2, w3, w4, w5, w6, w7, w8)
        eli.append(i)
        lli.append(error)

    plt.plot(eli, lli，color='red')
    plt.ylabel('Loss')
    plt.xlabel('w')
    plt.show()

三：激活函数Sigmoid用PyTorch自带函数torch.sigmoid()

pyTorch的Tensor这种数据结构，在前向传播中动态构建计算图，使用计算图的最后一个张量节点loss的backward()方法自动计算计算图中所有参数梯度。

	def sigmoid(z):
    a = 1 / (1 + torch.exp(-z))
    return a


def forward_propagate(x1, x2):
    in_h1 = w1 * x1 + w3 * x2
    out_h1 = sigmoid(in_h1)  # out_h1 = torch.sigmoid(in_h1)
    in_h2 = w2 * x1 + w4 * x2
    out_h2 = sigmoid(in_h2)  # out_h2 = torch.sigmoid(in_h2)

    in_o1 = w5 * out_h1 + w7 * out_h2
    out_o1 = sigmoid(in_o1)  # out_o1 = torch.sigmoid(in_o1)
    in_o2 = w6 * out_h1 + w8 * out_h2
    out_o2 = sigmoid(in_o2)  # out_o2 = torch.sigmoid(in_o2)

    print("正向计算：o1 ,o2")
    print(out_o1.data, out_o2.data)

    return out_o1, out_o2

修改为：

def forward_propagate(x1, x2):
 in_h1 = w1 * x1 + w3 * x2
 out_h1 = torch.sigmoid(in_h1)
 in_h2 = w2 * x1 + w4 * x2
 out_h2 = torch.sigmoid(in_h2)

 in_o1 = w5 * out_h1 + w7 * out_h2
 out_o1 = torch.sigmoid(in_o1)
 in_o2 = w6 * out_h1 + w8 * out_h2
 out_o2 = torch.sigmoid(in_o2)

 print("正向计算：o1 ,o2")
 print(out_o1.data, out_o2.data)

 return out_o1, out_o2

四：激活函数Sigmoid改变为Relu

def forward_propagate(x1, x2):
    in_h1 = w1 * x1 + w3 * x2
    out_h1 = torch.relu(in_h1)
    in_h2 = w2 * x1 + w4 * x2
    out_h2 = torch.relu(in_h2)


    in_o1 = w5 * out_h1 + w7 * out_h2
    out_o1 = torch.relu(in_o1)
    in_o2 = w6 * out_h1 + w8 * out_h2
    out_o2 = torch.relu(in_o2)

    print("正向计算：o1 ,o2")
    print(out_o1.data, out_o2.data)

    return out_o1, out_o2

五：更换损失函数

def loss_fuction(x1, x2, y1, y2):  # 损失函数
	# y1_pred, y2_pred = forward_propagate(x1, x2)  # 前向传播
    y_pred = torch.cat(forward_propagate(x1, x2), dim=0) 
    y = torch.cat((y1, y2), dim=0)
    
    loss = torch.nn.MSELoss(reduction='mean')
    l = loss(y_pred, y)
    print("损失函数（均方误差）：", l.item())
    return l

更改后：

def loss_fuction(x1, x2, y1, y2):  # 损失函数
   y1_pred, y2_pred = forward_propagate(x1, x2)  # 前向传播
   y_pred = torch.stack([y1_pred, y2_pred], dim=1)  # 将两个预测值放在一个矩阵中
   y = torch.stack([y1, y2], dim=1)
   
   loss = torch.nn.CrossEntropyLoss()
   l = loss(y_pred, y)
   print("损失函数（均方误差）：", l.item())
   return l

六：更改步长

step:10

step:9

step:5:

step:1