人工智能-作业3：例题程序复现 PyTorch版

1.使用pytorch复现课上例题。

结合上次作业的backward（）文件
自动微分的反向传播计算：

import torch
 
w1 = torch.randn(1, requires_grad=True)
w2 = torch.randn(1, requires_grad=True)
w3 = torch.randn(1, requires_grad=True)
w4 = torch.randn(1, requires_grad=True)
 
a = torch.tensor(1.)
print("a = ", a.data)
print("w = ", w1.data, w2.data, w3.data, w4.data)
b = w1 * a
c = w2 * a
d = w3 * b + w4 * c  # compute graph
print("d = ", d.data)
L = (10 - d).sum()  # Loss function
print("L = ", L.data)
L.backward()        # Back propagate
 
print("grad : ",w1.grad, w2.grad, w3.grad, w4.grad)
learning_rate = 1
w1.data = w1.data - learning_rate * w1.grad.data
w2.data = w2.data - learning_rate * w2.grad.data
w3.data = w3.data - learning_rate * w3.grad.data
w4.data = w4.data - learning_rate * w4.grad.data
print("w new = ", w1.data, w2.data, w3.data, w4.data)

计算图：

# calculate: y = 1 / (exp( —( w * x + b )) ＋ 1 )
# x = 1,w = 0,b = 0
 
import math
import torch
x = torch.tensor(1., requires_grad=True)
w = torch.tensor(0., requires_grad=True)
b = torch.tensor(0., requires_grad=True)
h1 = w * x
h2 = h1 + b
h3 = h2 * (-1)
# h4 = math.exp(h3) # 会将Tensor类型转换为float
h4 = torch.exp(h3)
h5 = h4 + 1
h6 = 1 / h5
y = h6
y.backward()
print(f'grad of x: {x.grad}')
print(f'grad of w: {w.grad}')
print(f'grad of b: {b.grad}')

反向传播计算：

# https://blog.csdn.net/qq_41033011/article/details/109325070
# https://github.com/Darwlr/Deep_learning/blob/master/06%20Pytorch%E5%AE%9E%E7%8E%B0%E5%8F%8D%E5%90%91%E4%BC%A0%E6%92%AD.ipynb
# torch.nn.Sigmoid(h_in)

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)

2.对比【作业3】和【作业2】的程序，观察两种方法结果是否相同？如果不同，哪个正确？

初始两种结果不相同，Pytorch计算的正确，修正后结果如下两图所示：
作业二：

作业三：

【作业2】程序更新

import numpy as np


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):
    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)

    print("正向计算：o1 ,o2")
    print(round(out_o1, 5), round(out_o2, 5))

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

    print("损失函数：均方误差")
    print(round(error, 5))

    return out_o1, out_o2, out_h1, out_h2


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
    # print(round(d_o1, 2), round(d_o2, 2))

    d_w5 = d_o1 * out_o1 * (1 - out_o1) * out_h1
    d_w7 = d_o1 * out_o1 * (1 - out_o1) * out_h2
    # print(round(d_w5, 2), round(d_w7, 2))
    d_w6 = d_o2 * out_o2 * (1 - out_o2) * out_h1
    d_w8 = d_o2 * out_o2 * (1 - out_o2) * out_h2
    # print(round(d_w6, 2), round(d_w8, 2))

    d_w1 = (d_w5 + d_w6) * out_h1 * (1 - out_h1) * x1
    d_w3 = (d_w5 + d_w6) * out_h1 * (1 - out_h1) * x2
    # print(round(d_w1, 2), round(d_w3, 2))

    d_w2 = (d_w7 + d_w8) * out_h2 * (1 - out_h2) * x1
    d_w4 = (d_w7 + d_w8) * out_h2 * (1 - out_h2) * x2
    # print(round(d_w2, 2), round(d_w4, 2))
    print("反向传播：误差传给每个权值")
    print(round(d_w1, 5), round(d_w2, 5), round(d_w3, 5), round(d_w4, 5), round(d_w5, 5), round(d_w6, 5),
          round(d_w7, 5), round(d_w8, 5))

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


def update_w(w1, w2, w3, w4, w5, w6, w7, w8):
    # 步长
    step = 5
    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
    x1, x2 = 0.5, 0.3
    y1, y2 = 0.23, -0.07
    print("=====输入值：x1, x2；真实输出值：y1, y2=====")
    print(x1, x2, y1, y2)
    print("=====更新前的权值=====")
    print(round(w1, 2), round(w2, 2), round(w3, 2), round(w4, 2), round(w5, 2), round(w6, 2), round(w7, 2),
          round(w8, 2))

    for i in range(1000):
        print("=====第" + str(i) + "轮=====")
        out_o1, out_o2, out_h1, out_h2 = forward_propagate(x1, x2, y1, y2, w1, w2, w3, w4, w5, w6, w7, w8)
        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)
        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(round(w1, 2), round(w2, 2), round(w3, 2), round(w4, 2), round(w5, 2), round(w6, 2), round(w7, 2),
          round(w8, 2))

4.对比【作业2】与【作业3】的反向传播的实现方法。总结并陈述。

【作业二】为确定损失函数及网络结构后，手动用链式法则计算损失函数对每个参数的梯度。手动求导并转换为程序的过程，非常琐碎并容易出错。

【作业三】利用Pytorch框架包含的backward()自动梯度计算的功能，可以只考虑网络结构并用代码实现，梯度可以自动进行计算，无须人工干预．

5.激活函数Sigmoid用PyTorch自带函数torch.sigmoid()，观察、总结并陈述。

替换后函数：

# https://blog.csdn.net/qq_41033011/article/details/109325070
# https://github.com/Darwlr/Deep_learning/blob/master/06%20Pytorch%E5%AE%9E%E7%8E%B0%E5%8F%8D%E5%90%91%E4%BC%A0%E6%92%AD.ipynb
# torch.nn.Sigmoid(h_in)

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 = torch.sigmoid(in_h1)  # out_h1 = torch.sigmoid(in_h1)
    in_h2 = w2 * x1 + w4 * x2
    out_h2 = torch.sigmoid(in_h2)  # out_h2 = torch.sigmoid(in_h2)

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

sigmoid函数有以下特点：
优点：平滑、易于求导。
缺点：激活函数计算量大，反向传播求误差梯度时，求导涉及除法；反向传播时，很容易就会出现梯度消失的情况，从而无法完成深层网络的训练。

6.激活函数Sigmoid改变为Relu，观察、总结并陈述。

# https://blog.csdn.net/qq_41033011/article/details/109325070
# https://github.com/Darwlr/Deep_learning/blob/master/06%20Pytorch%E5%AE%9E%E7%8E%B0%E5%8F%8D%E5%90%91%E4%BC%A0%E6%92%AD.ipynb
# torch.nn.Sigmoid(h_in)

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 = torch.relu(in_h1)  # out_h1 = torch.sigmoid(in_h1)
    in_h2 = w2 * x1 + w4 * x2
    out_h2 = torch.relu(in_h2)  # out_h2 = torch.sigmoid(in_h2)

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

relu函数表达式为：f(x)=max(0,x)

相比sigmod函数有以下几个优点:
(1)克服梯度消失的问题
(2)加快训练速度

7.损失函数MSE用PyTorch自带函数 t.nn.MSELoss()替代，观察、总结并陈述。

修改部分代码：

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()
    loss_m=torch.nn.MSELoss()
    y_pred = torch.cat((y1_pred,y2_pred),dim=0)
    y = torch.cat((y1,y2),dim=0)
    loss=loss_m(y_pred,y)
    print("损失函数（均方误差）：", loss.item())
    return loss

预测值合并，实际值合并，调用torch.nn.MSELoss()计算结果

8.损失函数MSE改变为交叉熵，观察、总结并陈述。

修改部分代码：

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()
    loss_m=torch.nn.CrossEntropyLoss()
    y_pred = torch.stack([y1_pred,y2_pred],dim=1)
    y = torch.stack([y1,y2],dim=1)
    loss=loss_m(y_pred,y)
    print("损失函数（均方误差）：", loss.item())
    return loss

交叉熵（Cross Entropy）：表示两个概率分布之间的距离，交叉熵越大，两个概率分布距离越远，两个概率分布越相异；交叉熵越小，两个概率分布距离越近，两个概率分布越相似.

9.改变步长，训练次数，观察、总结并陈述。

# https://blog.csdn.net/qq_41033011/article/details/109325070
# https://github.com/Darwlr/Deep_learning/blob/master/06%20Pytorch%E5%AE%9E%E7%8E%B0%E5%8F%8D%E5%90%91%E4%BC%A0%E6%92%AD.ipynb
# torch.nn.Sigmoid(h_in)
import matplotlib.pyplot as plt
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)
    Y=[]
    X=[]

    for i in range(40):
        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)
        Y.append(L.item())
        X.append(i)

    plt.rcParams['font.sans-serif'] = ['SimHei']  # 可以plt绘图过程中中文无法显示的问题
    plt.plot(X,Y)
    plt.xlabel('迭代次数')
    plt.ylabel('Loss，step=1')
    plt.show()
    print("更新后的权值")
    print(w1.data, w2.data, w3.data, w4.data, w5.data, w6.data, w7.data, w8.data)

总结：步长越大，均方误差下降越快

10.权值w1-w8初始值换为随机数，对比【作业2】指定权值结果，观察、总结并陈述。

代码：

#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, w2, w3, w4, w5, w6, w7, w8 = torch.randn(1), torch.randn(1), torch.randn(1), torch.randn(1), \
    torch.randn(1), torch.randn(1), torch.randn(1), torch.randn(1)

更换为随机值：

结果：

更换为随机值后依然能完成收敛，但是收敛速度略微降低

11.全面总结反向传播原理和编码实现，认真写心得体会。

反向传播算法是训练神经网络的经典算法，是深度学习的最重要的基础，适合于多层神经元网络的一种学习算法，它建立在梯度下降法的基础上，通过迭代的方法求出目标损失函数(loss function)的近似最小值。

通俗点讲就是我想更新参数，就得知道参数的更新量，想知道参数的更新量，就得知道偏导，误差函数对本层的输出的偏导。然后，得知道上一层的偏导…输出层的偏导。

因此，在反向传播时，对第l层，有两件事要做：

第一件，根据l层输出的偏导，计算出l层参数的更新量；

第二件，根据l层输出的偏导，计算出l-1层输出的偏导。

以上就是本人对反向传播的大体理解
体会：总体理解与代码实现困难重重，细心理解后，对代码的认知程度也会提升，对代码的编写修改速度也会相应提升。

参考

pytorch的nn.MSELoss损失函数
Tensorflow笔记—5—神经网络优化—MSE损失函数，子定义损失函数和交叉熵损失函数
卷积传播网络反向传播算法