【动手学深度学习pytorch】学习笔记 8.1 序列模型

书籍免费下载，有网页版，有Jupyter源代码版，有视频看，讲解清晰，有理论有实践。

感觉DL的东西，必须写代码跑跑看，读完书总感觉差点意思。

生成数据：

构建模型：

两个全连接层的多层感知机，ReLU激活函数和平方损失

net = nn.Sequential(nn.Linear(4, 10),
nn.ReLU(),
nn.Linear(10, 1))
net.apply(init_weights)

loss = nn.MSELoss(reduction='none')

训练模型：

def train(net, train_iter, loss, epochs, lr):
trainer = torch.optim.Adam(net.parameters(), lr)
for epoch in range(epochs):
for X, y in train_iter:
trainer.zero_grad()
l = loss(net(X), y)
l.sum().backward()
trainer.step()
print(f'epoch {epoch + 1}, '
f'loss: {d2l.evaluate_loss(net, train_iter, loss):f}')

net = get_net()
train(net, train_iter, loss, 5, 0.01)

预测：

单步预测预测下一个时间步

多步预测使用自己的预测（而不是原始数据）

k

源代码：

import torch
from torch import nn
from d2l import torch as d2l
import matplotlib.pyplot as plt

T = 1000  # 总共产生1000个点
time = torch.arange(1, T + 1, dtype=torch.float32)
x = torch.sin(0.01 * time) + torch.normal(0, 0.2, (T,))
d2l.plot(time, [x], 'time', 'x', xlim=[1, 1000], figsize=(6, 3))
plt.show()

tau = 4
features = torch.zeros((T - tau, tau))
for i in range(tau):
    features[:, i] = x[i: T - tau + i]
labels = x[tau:].reshape((-1, 1))

batch_size, n_train = 16, 600  # 只有前n_train个样本用于训练
train_iter = d2l.load_array((features[:n_train], labels[:n_train]), batch_size, is_train=True)


# 初始化网络权重的函数
def init_weights(m):
    if type(m) == nn.Linear:
        nn.init.xavier_uniform_(m.weight)


# 一个简单的多层感知机
def get_net():
    net = nn.Sequential(nn.Linear(4, 10),
                        nn.ReLU(),
                        nn.Linear(10, 1))
    net.apply(init_weights)
    return net


# 平方损失。注意：MSELoss计算平方误差时不带系数1/2
loss = nn.MSELoss(reduction='none')


def train(net, train_iter, loss, epochs, lr):
    trainer = torch.optim.Adam(net.parameters(), lr)
    for epoch in range(epochs):
        for X, y in train_iter:
            trainer.zero_grad()
            l = loss(net(X), y)
            l.sum().backward()
            trainer.step()
        print(f'epoch {epoch + 1}, '
              f'loss: {d2l.evaluate_loss(net, train_iter, loss):f}')


net = get_net()
train(net, train_iter, loss, 5, 0.01)

onestep_preds = net(features)
d2l.plot([time, time[tau:]],
         [x.detach().numpy(), onestep_preds.detach().numpy()], 'time',
         'x', legend=['data', '1-step preds'], xlim=[1, 1000],
         figsize=(6, 3))
plt.show()

multistep_preds = torch.zeros(T)
multistep_preds[: n_train + tau] = x[: n_train + tau]
for i in range(n_train + tau, T):
    multistep_preds[i] = net(
        multistep_preds[i - tau:i].reshape((1, -1)))

d2l.plot([time, time[tau:], time[n_train + tau:]],
         [x.detach().numpy(), onestep_preds.detach().numpy(),
          multistep_preds[n_train + tau:].detach().numpy()], 'time',
         'x', legend=['data', '1-step preds', 'multistep preds'],
         xlim=[1, 1000], figsize=(6, 3))
plt.show()

max_steps = 64
features = torch.zeros((T - tau - max_steps + 1, tau + max_steps))
# 列i（i<tau）是来自x的观测，其时间步从（i+1）到（i+T-tau-max_steps+1）
for i in range(tau):
    features[:, i] = x[i: i + T - tau - max_steps + 1]

# 列i（i>=tau）是来自（i-tau+1）步的预测，其时间步从（i+1）到（i+T-tau-max_steps+1）
for i in range(tau, tau + max_steps):
    features[:, i] = net(features[:, i - tau:i]).reshape(-1)

steps = (1, 4, 16, 64)
d2l.plot([time[tau + i - 1: T - max_steps + i] for i in steps],
         [features[:, (tau + i - 1)].detach().numpy() for i in steps], 'time', 'x',
         legend=[f'{i}-step preds' for i in steps], xlim=[5, 1000],
         figsize=(6, 3))
plt.show()