pytorch白话入门笔记1.4-回归函数

目录

 

1.设置散点

2.定义network

3.优化神经网络

---

1.设置散点

代码：

import torch
from torch.autograd import Variable
import torch.nn.functional as F
import matplotlib.pyplot as plt

# x = torch.unsqueeze(torch.linspace(-1,1,100),dim = 1)#旧版使用
x = torch.linspace(-1,1,100)#新版使用
y = x.pow(2) + 0.2*torch.rand(x.size())

x,y = Variable(x),Variable(y)

plt.scatter(x.data.numpy(),y.data.numpy())
plt.show()

运行结果：

2.定义network

import torch
from torch.autograd import Variable
import torch.nn.functional as F
import matplotlib.pyplot as plt

x = torch.unsqueeze(torch.linspace(-1,1,100),dim = 1)#旧版使用
# x = torch.linspace(-1,1,100)#新版使用
y = x.pow(2) + 0.2*torch.rand(x.size())

x,y = Variable(x),Variable(y)

# plt.scatter(x.data.numpy(),y.data.numpy())
# plt.show()

# Net __init__()
class Net(torch.nn.Module):#继承module
    def __init__(self,n_features,n_hidden,n_output):
        super(Net,self).__init__()#官方步骤，继承
        self.hidden = torch.nn.Linear(n_features,n_hidden)
        self.predict = torch.nn.Linear(n_hidden,n_output)#预测


    def forward(self,x):
        # 前向传递过程，搭建神经网络
        x = F.relu(self.hidden(x))
        x = self.predict(x)
        return x

net = Net(1,10,1)      #输入、隐藏层、输出分别为1，10，1
print(net)

运行结果：

Net(
  (hidden): Linear(in_features=1, out_features=10, bias=True)
  (predict): Linear(in_features=10, out_features=1, bias=True)
)

Process finished with exit code 0

3.优化神经网络

代码：

import torch
from torch.autograd import Variable
import torch.nn.functional as F
import matplotlib.pyplot as plt

x = torch.unsqueeze(torch.linspace(-1,1,100),dim = 1)#旧版使用
# x = torch.linspace(-1,1,100)#新版使用
y = x.pow(2) + 0.2*torch.rand(x.size())

x,y = Variable(x),Variable(y)

# plt.scatter(x.data.numpy(),y.data.numpy())
# plt.show()

# Net __init__()
class Net(torch.nn.Module):#继承module
    def __init__(self,n_features,n_hidden,n_output):
        super(Net,self).__init__()#官方步骤，继承
        self.hidden = torch.nn.Linear(n_features,n_hidden)
        self.predict = torch.nn.Linear(n_hidden,n_output)#预测


    def forward(self,x):
        # 前向传递过程，搭建神经网络
        x = F.relu(self.hidden(x))
        x = self.predict(x)
        return x

net = Net(1,10,1)      #输入、隐藏层、输出分别为1，10，1
print(net)


plt.ion() #实时打印可视化
plt.show()
# 优化神经网络，SGD梯度下降求解局部最优，传入参数net.parameters()，
# 给定学习效率learning rate一般小于1，学习太快会在梯度下降时导致“跨过”了介于两次优化之间可能最佳的去噪
optimizer = torch.optim.SGD(net.parameters(),lr=0.5)
loss_func = torch.nn.MSELoss()#均方差

for t in range (100):
    prediction = net(x)

    loss = loss_func(prediction,y)

    optimizer.zero_grad()
    loss.backward()
    optimizer.step()

    if t % 5 == 0:
        #打印学习进程
        plt.cla()
        plt.scatter(x.data.numpy(),y.data.numpy())
        plt.plot(x.data.numpy(),prediction.data.numpy(),'r-',lw= 5)
        plt.text(0.5,0,'Loss = %.4f' % loss.data,fontdict={'size':20,'color':'red'})
        plt.pause(0.1)

plt.ioff()
plt.show()

运行结果：

Net(
  (hidden): Linear(in_features=1, out_features=10, bias=True)
  (predict): Linear(in_features=10, out_features=1, bias=True)
)

Process finished with exit code 0