沐神的 《动手学深度学习》 3.3. 线性回归的简洁实现
有很多需要学习的地方。
模型分为,数据输入,转换为tensorData, 加载打乱(data)
## 造数据
import torch
from torch.utils import data
from torch import nn
def synthetic_data(w,b,num_examples):
X = torch.normal(0,1,(num_examples,len(w)))
y = torch.matmul(X, w) + b
y += torch.normal(0,0.01,y.shape)
return X,y.reshape((-1,1))
true_w = torch.tensor([2, -3.4])
true_b = 4.2
features, labels = synthetic_data(true_w, true_b, 1000)
def load_array(arrays,batch_size,is_train=True):
dataset = data.TensorDataset(*arrays)
return data.DataLoader(dataset,batch_size,is_train)
#定义模型
net = nn.Sequential(nn.Linear(2,1))
## 初始化超参数
net[0].weight.data.normal_(0, 0.01)
net[0].bias.data.fill_(0)
## 初始化模型参数
learn_rate = 0.03
epochs = 3
##定义损失函数
loss = nn.MSELoss()
##定义优化算法
trainer = torch.optim.SGD(net.parameters(), lr=0.03)
## 训练
num_epochs = 3
for epoch in range(num_epochs):
for X, y in data_iter:
l = loss(net(X) ,y)
trainer.zero_grad()
l.backward()
trainer.step()
l = loss(net(features), labels)
print(f'epoch {epoch + 1}, loss {l:f}')