pytorch入门程序1

一、构建三层神经分类网络

输入维度为1000，隐藏层为100维，输出层为10维。激活函数使用ReLU函数，本程序的写法有两个，为了对比体现，现贴出两个的代码，供对比学习。

1、使用Sequential构建神经网络

import torch

#N为一个batch_size 
N,D_in,H,D_out=64,1000,100,10
x=torch.randn(N,D_in)
y=torch.randn(N,D_out)

model=torch.nn.Sequential(
    torch.nn.Linear(D_in,H),
    torch.nn.ReLU(),
    torch.nn.Linear(H,D_out)
)

loss_fn=torch.nn.MSELoss(reduction='sum')
learning_rate=1e-4
optimizer=torch.optim.Adam(model.parameters(),lr=learning_rate)

for t in range(500):
    y_pred=model(x)
    
    loss=loss_fn(y_pred,y)
    model.zero_grad()
    loss.backward()
    print(t,loss.item())
    optimizer.step()

2、继承nn.Module构建神经网络

import torch

#N为一个batch_size 
N,D_in,H,D_out=64,1000,100,10
x=torch.randn(N,D_in)
y=torch.randn(N,D_out)

class Net(torch.nn.Module):
    def __init__(self,D_in,H,D_out):
        super(Net,self).__init__()
        self.linear1=torch.nn.Linear(D_in,H)
        self.relu=torch.nn.ReLU()
        self.linear2=torch.nn.Linear(H,D_out)
        
    def forward(self,x):
        #h=self.linear1(x).clamp(min=0)
        h=self.linear1(x)
        h_relu=self.relu(h)
        y_pred=self.linear2(h_relu)
        return y_pred

model=Net(D_in,H,D_out)    
loss_fn=torch.nn.MSELoss(reduction='sum')
learning_rate=1e-4
optimizer=torch.optim.SGD(model.parameters(),lr=learning_rate)

for t in range(500):
    y_pred=model(x)
    
    loss=loss_fn(y_pred,y)
    #梯度清零
    model.zero_grad()
    #反向传播
    loss.backward()
    print(t,loss.item())
    #逐步优化
    optimizer.step()