1
 2
 3
 4
 5
 6
 7
 8
 9
10
11

# 生成数据集，其中w = [2, -3.4], b = 4.2，噪声成标准差为1的正态分布
def synthetic_data(w, b, num_examples):  #@save
    """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)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32

# 生成大小为batch_size的小批量
def data_iter(batch_size, features, labels):
    num_examples = len(features)
    indices = list(range(num_examples))
    # 这些样本是随机读取的，没有特定的顺序
    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]

# 初始化参数
w = torch.normal(0, 0.01, size=(2,1), requires_grad=True)
b = torch.zeros(1, requires_grad=True)

# 定义模型
def linreg(X, w, b):  #@save
    """线性回归模型"""
    return torch.matmul(X, w) + b

# 定义损失函数
def squared_loss(y_hat, y):  #@save
    """均方损失"""
    return (y_hat - y.reshape(y_hat.shape)) ** 2 / 2

# 定义优化算法
def sgd(params, lr, batch_size):  #@save
    """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_()

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24

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)  # X和y的小批量损失
        # 因为l形状是(batch_size,1)，而不是一个标量。l中的所有元素被加到一起，
        # 并以此计算关于[w,b]的梯度
        l.sum().backward()
        sgd([w, b], lr, batch_size)  # 使用参数的梯度更新参数
    with torch.no_grad():
        train_l = loss(net(features, w, b), labels)
        print(f'epoch {epoch + 1}, loss {float(train_l.mean()):f}')

# epoch 1, loss 0.037387
# epoch 2, loss 0.000139
# epoch 3, loss 0.000052

# 误差
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}')
# w的估计误差: tensor([ 0.0004, -0.0006], grad_fn=<SubBackward0>)
# b的估计误差: tensor([0.0007], grad_fn=<RsubBackward1>)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49

# 读取数据集
# 调用torch.utils.data中现有api
def load_array(data_arrays, batch_size, is_train=True):  #@save
    """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)
# 可使用next()验证迭代器是否正常工作
next(iter(data_iter))

# 定义模型
# Sequential()将多个层串联到一起
# Linear(2, 1)中两个参数分别为输入和输出特征形状
# nn是神经网络的缩写
from torch import nn
net = nn.Sequential(nn.Linear(2, 1))

# 初始化模型参数
net[0].weight.data.normal_(0, 0.01)
net[0].bias.data.fill_(0)

# 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}')
# epoch 1, loss 0.000248
# epoch 2, loss 0.000103
# epoch 3, loss 0.000103

# 误差
w = net[0].weight.data
print('w的估计误差：', true_w - w.reshape(true_w.shape))
b = net[0].bias.data
print('b的估计误差：', true_b - b)
# w的估计误差： tensor([-0.0010, -0.0003])
# b的估计误差： tensor([-0.0003])

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51

import torch
from IPython import display
from d2l import torch as d2l

# 使用Fashion-MNIST数据集
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)

# 初始化参数
# 展平每个28*28图像，看作784向量，暂不考虑图像空间结构特征
# 输出维度  == 类别数
num_inputs = 784
num_outputs = 10

W = torch.normal(0, 0.01, size=(num_inputs, num_outputs), requires_grad=True)
b = torch.zeros(num_outputs, requires_grad=True)

# 定义softmax
def softmax(X):
    X_exp = torch.exp(X)
    partition = X_exp.sum(1, keepdim=True)
    return X_exp / partition  # 这里应用了广播机制

# 定义模型
def net(X):
    return softmax(torch.matmul(X.reshape((-1, W.shape[0])), W) + b)

# 定义损失函数
# 通过正确的[range(len(y_hat)), y]索引选择所有需要的元素，不需要低效的for循环
def cross_entropy(y_hat, y):
    return - torch.log(y_hat[range(len(y_hat)), y])

# 分类精度

def accuracy(y_hat, y):  #@save
    """计算预测正确的数量"""
    if len(y_hat.shape) > 1 and y_hat.shape[1] > 1:
        y_hat = y_hat.argmax(axis=1) # .argmax(axis=1)用于获取轴1上最大元素的索引
    cmp = y_hat.type(y.dtype) == y
    return float(cmp.type(y.dtype).sum())
# accuracy(y_hat, y) / len(y) 即求得分类精度
# 对数据迭代器求精度
def evaluate_accuracy(net, data_iter):  #@save
    """计算在指定数据集上模型的精度"""
    if isinstance(net, torch.nn.Module):
        net.eval()  # 将模型设置为评估模式
    metric = Accumulator(2)  # 正确预测数、预测总数
    with torch.no_grad():
        for X, y in data_iter:
            metric.add(accuracy(net(X), y), y.numel())
    return metric[0] / metric[1]

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26

import torch
from torch import nn
from d2l import torch as d2l
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)

# 初始化参数
# 在Linear前加一个展平层，用于将图像调整为784
net = nn.Sequential(nn.Flatten(), nn.Linear(784, 10))

def init_weights(m):
    if type(m) == nn.Linear:
        nn.init.normal_(m.weight, std=0.01)

net.apply(init_weights);

# 交叉熵损失
# 这里的底层实现和传统softmax略有不同，避免了上溢和下溢的问题
loss = nn.CrossEntropyLoss(reduction='none')

# 优化算法
trainer = torch.optim.SGD(net.parameters(), lr=0.1)

# 训练
num_epochs = 10
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, trainer)