一、使用pytorch复现课上例题。
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)
二、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?
作业2运行结果
作业3运行结果
对比可得,作业3的答案正确
三、【作业2】程序更新(保留【作业2中】的错误答案,留作对比。新程序到作业3。)
新的代码
import numpy as np
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 x0, x1:", x1, x2)
print("输出值 y0, y1:", y1, y2)
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,隐藏层h1 ,h2:", end="")
print(round(out_h1, 5), round(out_h2, 5))
print("正向计算,预测值o1 ,o2:", end="")
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):",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
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_o1 * out_h1 * (1 - out_h1) * w5 + d_o2 * out_o2 * (1 - out_o2) * w6) * out_h1 * (1 - out_h1) * x1
d_w3 = (d_o1 * out_h1 * (1 - out_h1) * w5 + d_o2 * out_o2 * (1 - out_o2) * w6) * out_h1 * (1 - out_h1) * x2
d_w2 = (d_o1 * out_h1 * (1 - out_h1) * w7 + d_o2 * out_o2 * (1 - out_o2) * w8) * out_h2 * (1 - out_h2) * x1
d_w4 = (d_o1 * out_h1 * (1 - out_h1) * w7 + d_o2 * out_o2 * (1 - out_o2) * w8) * out_h2 * (1 - out_h2) * x2
print("w的梯度:",round(d_w1, 2), round(d_w2, 2), round(d_w3, 2), round(d_w4, 2), round(d_w5, 2), round(d_w6, 2),
round(d_w7, 2), round(d_w8, 2))
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 = 1
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__":
print("权值w0-w7:",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(1):
print("=====第" + str(i+1) + "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w:",round(w1, 2), round(w2, 2), round(w3, 2), round(w4, 2), round(w5, 2), round(w6, 2), round(w7, 2),
round(w8, 2))
四、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2是通过手动用链式法则推公式方式实现的,容易出错,而作业3是通过计算图,backward()自动梯度计算实现的,方便很多。
五、激活函数Sigmoid用PyTorch自带函数torch.sigmoid(),观察、总结并陈述。
运行结果
将激活函数更换后,运行后结果并没有发生变化,所以直接调用torch.sigmoid可以节省很多操作
六、激活函数Sigmoid改变为Relu,观察、总结并陈述。
改变代码
运行结果
七、损失函数MSE用PyTorch自带函数 t.nn.MSELoss()替代,观察、总结并陈述。
替换损失函数
def loss_fuction(x1, x2, y1, y2): # 损失函数
y1_pred, y2_pred = forward_propagate(x1, x2) # 前向传播
#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
运行结果
八、损失函数MSE改变为交叉熵,观察、总结并陈述。
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.
替换代码为
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
运行结果
九、改变步长,训练次数,观察、总结并陈述。
# 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)
十、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。
更换为随机值
更换为随机值后相比作业2收敛速度降低。
十一、全面总结反向传播原理和编码实现,认真写心得体会。
反向传播算法主要由两个环节(激励传播、权重更新)反复循环迭代,直到网络的对输入的响应达到预定的目标范围为止。它的学习过程由正向传播过程和反向传播过程组成。在正向传播过程中,输入信息通过输入层经隐含层,逐层处理并传向输出层。如果在输出层得不到期望的输出值,则取输出与期望的误差的平方和作为目标函数,转入反向传播,逐层求出目标函数对各神经元权值的偏导数,构成目标函数对权值向量的梯量,作为修改权值的依据,网络的学习在权值修改过程中完成。误差达到所期望值时,网络学习结束。另外如果激活函数使用的不是sigmoid函数而是ReLU,LeakyReLU或者是其它,只要对新的激活函数的一般形式进行求导,然后将求导结果应用到反向传播算法中即可。