首先了解几个pytorch
模块:
- torch,utils.data:提供有关数据处理的工具
- torch.nn:定义大量的神经网络的层
- torch.nn.init:定义各种初始化方法
- torch.optim:提供各种优化算法
下面是具体程序:
- 导入必要的包
import torch
import numpy as np
- 建立数据集
num_inputs=2
num_examples=1000
true_w=[2,-3.4]
true_b=4.2
features=torch.tensor(np.random.normal(0,1,(num_examples,num_inputs)),dtype=torch.float32)
lables=true_w[0] * features[:,0] + true_w[1]*features[:,1] +true_b
lables += torch.tensor(np.random.normal(0,0.01,size=lables.size()),dtype=torch.float32)
- 读取数据
import torch.utils.data as Data
batch_size=10
dataset =Data.TensorDataset(features,lables)
data_iter=Data.DataLoader(dataset,batch_size,shuffle=True)
for X,y in data_iter:
print(X,'\n',y)
break
- 定义模型
from torch import nn
class LinearNet(nn.Module):
def __init__(self,n_feature):
super(LinearNet,self).__init__()
self.linear=nn.Linear(n_feature,1)
# 前向传播
def forward(self,x):
y=self.linear(x)
return y
net=LinearNet(num_inputs)
print(net)
net=nn.Sequential(
nn.Linear(num_inputs,1)
)
for param in net.parameters():
print(param)
- 初始化模型参数
from torch.nn import init
init.normal_(net[0].weight,mean=0,std=0.01)
init.constant_(net[0].bias,val=0)
- 定义损失函数
loss=nn.MSELoss()
- 定义优化算法
import torch.optim as optim
optimizer=optim.SGD(net.parameters(),lr=0.03)
print(optimizer)
- 训练模型
num_epochs=3
for epoch in range(1,num_epochs+1):
for X,y in data_iter:
output=net(X)
l=loss(output,y.view(-1,1))
optimizer.zero_grad()
l.backward()
optimizer.step()
print('epoch %d, loss :%f' % (epoch,l.item()))
- 对比设置的参数和学习到的数据
dense=net[0]
print(true_w,dense.weight)
print(true_b,dense.bias)