李沐视频课笔记其他文章目录链接(不定时更新)
y = X w + b + ϵ y=Xw+b+\epsilon y=Xw+b+ϵ
Code:
%matplotlib inline
import random
import torch
from d2l import torch as d2l
def synthetic_data(w, b, num_examples):
"""生成y=Xw+b+噪声。"""
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)
print('features:', features[0], '\nlabel:', labels[0])
Result:
Code:
d2l.set_figsize()
d2l.plt.scatter(features[:, -1].detach().numpy(),
labels.detach().numpy(), 1)
Result:
Code:
def data_iter(batch_size, features, labels):
num_examples = len(features)
indices = list(range(num_examples))
# 样本随机读取,没有特定顺序
random.shuffle(indices)
for i in range(0, num_examples, batch_size):
batch_indices = torch.tensor(
indices[i:min(i + batch_size, num_examples)])
yield features[batch_indices], labels[batch_indices]
batch_size = 10
for X, y in data_iter(batch_size, features, labels):
print(X, '\n', y)
break
Result:
Code:
w = torch.normal(0, 0.01, size=(2, 1), requires_grad=True)
b = torch.zeros(1, requires_grad=True)
Code:
def linreg(X, w, b):
"""线性回归模型"""
return torch.matmul(X, w) + b
Code:
def squared_loss(y_hat, y):
"""均方损失"""
return (y_hat - y.reshape(y_hat.shape))**2 / 2
Code:
def sgd(params, lr, batch_size):
"""小批量随机梯度下降"""
with torch.no_grad():
for param in params:
param -= lr * param.grad / batch_size
param.grad.zero_()
Code:
lr = 0.03
num_epochs = 3
net = linreg
loss = squared_loss
for epoch in range(num_epochs):
for X, y in data_iter(batch_size, features, labels):
l = loss(net(X, w, b), y) # 小批量损失
l.sum().backward()
sgd([w, b], lr, batch_size)
with torch.no_grad():
train_l = loss(net(features, w, b), labels)
print(f'epoch {epoch + 1}, loss{float(train_l.mean()):f}')
Result:
Code:
print(f'w的估计误差:{true_w - w.reshape(true_w.shape)}')
print(f'b的估计误差:{true_b - b}')
Result:
Code:
import numpy as np
import torch
from torch.utils import data
from d2l import torch as d2l
true_w = torch.tensor([2, -3.4])
true_b = 4.2
features, labels = d2l.synthetic_data(true_w, true_b, 1000)
Result:
Code:
def load_array(data_arrays, batch_size, is_train=True):
"""g构造一个PyTorch数据迭代器"""
dataset = data.TensorDataset(*data_arrays)
return data.DataLoader(dataset, batch_size, shuffle=is_train)
batch_size = 10
data_iter = load_array((features, labels), batch_size)
next(iter(data_iter))
Result:
Code:
from torch import nn
net = nn.Sequential(nn.Linear(2, 1))
Code:
net[0].weight.data.normal_(0, 0.01)
net[0].bias.data.fill_(0)
Code:
loss = nn.MSELoss()
Code:
trainer = torch.optim.SGD(net.parameters(), lr=0.03)
Code:
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}')
Result: