刘二大人《Pytorch深度学习》第七讲作业

sigmoid函数（课程中的方法）：

import numpy as np
import torch
xy=np.loadtxt('E:\study\PyTorch\diabetes.csv',delimiter=',',dtype=np.float32)
x_data=torch.from_numpy(xy[:,:-1])#-1加[]保证运算结果为矩阵而非向量
y_data=torch.from_numpy(xy[:,[-1]])#from_numpy根据数值创建两个tensor出来

class Model(torch.nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.linear1 = torch.nn.Linear(8, 6)
        self.linear2 = torch.nn.Linear(6, 4)
        self.linear3 = torch.nn.Linear(4, 1)
        self.sigmoid = torch.nn.Sigmoid()
 
    def forward(self, x):
        x = self.sigmoid(self.linear1(x))
        x = self.sigmoid(self.linear2(x))
        x = self.sigmoid(self.linear3(x))
        return x
model=Model()

criterion=torch.nn.BCELoss(reduction='mean')
optimizer=torch.optim.SGD(model.parameters(),lr=0.1)

loss_list=[]
for epoch in range(10000):
    #Forward
    y_pred=model(x_data)
    loss=criterion(y_pred,y_data)
    print(epoch,loss.item())
    loss_list.append(loss.item())
    
    #Backward
    optimizer.zero_grad()
    loss.backward()
    
    #Update
    optimizer.step()

import matplotlib.pyplot as plt
epoch_list=[i for i in range(10000)]
plt.plot(epoch_list,loss_list)
plt.xlabel('epoch')
plt.ylabel('loss')
plt.show()

运行结果：

 作业：

 1.Heaviside

官方文档：https://pytorch.org/docs/stable/generated/torch.heaviside.html#torch.heaviside

Model部分，其余同上：

class Model(torch.nn.Module):
    def __init__(self):
        super(Model,self).__init__()
        self.linear1=torch.nn.Linear(8,6)#8维->6维
        self.linear2=torch.nn.Linear(6,4)
        self.linear3=torch.nn.Linear(4,1)
        self.sigmoid=torch.nn.Sigmoid()
    def forward(self,x):
        x=torch.heaviside(self.linear1(x).clone().detach(),torch.tensor([0.5]))
        x=torch.heaviside(self.linear2(x).clone().detach(),torch.tensor([0.5]))
        x=self.sigmoid(self.linear3(x))
        return x
model=Model()

运行结果：

2.Sign

官方文档：https://pytorch.org/docs/stable/generated/torch.sign.html?highlight=sign#torch.sign

class Model(torch.nn.Module):
    def __init__(self):
        super(Model,self).__init__()
        self.linear1=torch.nn.Linear(8,6)#8维->6维
        self.linear2=torch.nn.Linear(6,4)
        self.linear3=torch.nn.Linear(4,1)
        self.sigmoid=torch.nn.Sigmoid()
    def forward(self,x):
        x=torch.sign(self.linear1(x).clone().detach())
        x=torch.sign(self.linear2(x).clone().detach())
        x=self.sigmoid(self.linear3(x))
        return x
model=Model()

运行结果：

​

3.linear

即f(x)=x,其实输出着玩儿~，所以直接去掉激活函数就可以。(刘二大人原话[doge])

class Model(torch.nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.linear1 = torch.nn.Linear(8, 6)
        self.linear2 = torch.nn.Linear(6, 4)
        self.linear3 = torch.nn.Linear(4, 1)
        #self.sigmoid = torch.nn.Sigmoid()
 
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        x = self.sigmoid(self.linear3(x))
        return x
model=Model()

运行结果：

4.piece-wise linear（Hardsigmoid）

官方文档：https://pytorch.org/docs/stable/generated/torch.nn.Hardsigmoid.html#torch.nn.Hardsigmoid

class Model(torch.nn.Module):
    def __init__(self):
        super(Model,self).__init__()
        self.linear1=torch.nn.Linear(8,6)#8维->6维
        self.linear2=torch.nn.Linear(6,4)
        self.linear3=torch.nn.Linear(4,1)
        self.sigmoid=torch.nn.Sigmoid()
        self.activate=torch.nn.Hardsigmoid()
    def forward(self,x):
        x=self.activate(self.linear1(x))
        x=self.activate(self.linear2(x))
        x=self.sigmoid(self.linear3(x))
        return x
model=Model()

运行结果：

​(这个曲线长得好生神奇。。。)

5.hyperbolic tangent（tanh）：

官方文档：https://pytorch.org/docs/stable/generated/torch.nn.Tanh.html#torch.nn.Tanh 

class Model(torch.nn.Module):
    def __init__(self):
        super(Model,self).__init__()
        self.linear1=torch.nn.Linear(8,6)
        self.linear2=torch.nn.Linear(6,4)
        self.linear3=torch.nn.Linear(4,1)
        self.sigmoid=torch.nn.Sigmoid()
        self.activate=torch.nn.Tanh()
    def forward(self,x):
        x=self.activate(self.linear1(x))
        x=self.activate(self.linear2(x))
        x=self.sigmoid(self.linear3(x))
        return x
model=Model()

运行结果：

​

 6.ReLu:

官方文档：https://pytorch.org/docs/stable/generated/torch.nn.ReLU.html#torch.nn.ReLU

class Model(torch.nn.Module):
    def __init__(self):
        super(Model,self).__init__()
        self.linear1=torch.nn.Linear(8,6)
        self.linear2=torch.nn.Linear(6,4)
        self.linear3=torch.nn.Linear(4,1)
        self.sigmoid=torch.nn.Sigmoid()
        self.activate=torch.nn.ReLU()
    def forward(self,x):
        x=self.activate(self.linear1(x))
        x=self.activate(self.linear2(x))
        x=self.sigmoid(self.linear3(x))
        return x
model=Model()

​

 7.softplus

官方文档：https://pytorch.org/docs/stable/generated/torch.nn.Softplus.html#torch.nn.Softplus

class Model(torch.nn.Module):
    def __init__(self):
        super(Model,self).__init__()
        self.linear1=torch.nn.Linear(8,6)#8维->6维
        self.linear2=torch.nn.Linear(6,4)
        self.linear3=torch.nn.Linear(4,1)
        self.sigmoid=torch.nn.Sigmoid()
        self.activate=torch.nn.Softplus()
    def forward(self,x):
        x=self.activate(self.linear1(x))
        x=self.activate(self.linear2(x))
        x=self.sigmoid(self.linear3(x))
        return x
model=Model()

​