序列模型的核心概念就是有n个有顺序因果关系的数据构成的模型,通常有两种策略实现:自回归模型(只需要满足某个长度为𝜏的时间跨度, 即使用观测序列𝑥𝑡−1,…,𝑥𝑡−𝜏。),以及隐变量自回归模型(由于ℎ𝑡从未被观测到)。
区别:
hidden variable:现实中存在,但我们未观察到的东西
latent variable:现实中可以不存在,但我们人为加上去,比如类别。。。
马尔可夫模型:就是假设一个数据的结果只与前𝜏个数据相关。
# 代码来自动手学深度学习 by 李沐
%matplotlib inline
import torch
from torch import nn
from d2l import torch as d2l
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))
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))
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))
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)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)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))