- 08 线性回归09 Softmax51 序列模型
文章目录
动手学深度学习 PyTorch版 李沐视频课笔记一、序列模型
1. 使用正弦函数和一些可加性噪声来生成序列数据,时间步为1,2,...,10002. 将数据映射为数据对 y t = x t y_t=x_t yt=xt和 x t = [ x t − τ , . . . , x t − 1 ] x_t=[x_{t-tau},...,x_{t-1}] xt=[xt−τ,...,xt−1]3. 使用一个相当简单的架构训练模型:⼀个拥有两个全连接层的多层感知机,ReLU激活函数和平方损失4. 训练模型5. 模型预测下一个时间步6. 进行多步预测7. 进行k步预测
一、序列模型 1. 使用正弦函数和一些可加性噪声来生成序列数据,时间步为1,2,…,1000
Code:
%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))
Result:
2. 将数据映射为数据对 y t = x t y_t=x_t yt=xt和 x t = [ x t − τ , . . . , x t − 1 ] x_t=[x_{t-tau},...,x_{t-1}] xt=[xt−τ,...,xt−1]Code:
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)
3. 使用一个相当简单的架构训练模型:⼀个拥有两个全连接层的多层感知机,ReLU激活函数和平方损失
Code:
# 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')
4. 训练模型
Code:
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)
Result:
5. 模型预测下一个时间步Code:
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))
Result:
6. 进行多步预测Code:
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))
Result:
7. 进行k步预测Code:
max_steps = 64 features = torch.zeros((T - tau - max_steps + 1, tau + max_steps)) # 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))
Result:



