1. 正弦数据生成

曲线如下图：

代码如下图：

• 50个点构成一个正弦曲线
• 随机生成一个0~3之间的一个值（随机的原因是防止每次都从相同的点开始，50个点的正弦曲线一样，被模型记住），值的范围区间是[start, start+10]
• 输入x范围[0,48]，预测值y范围是[1,49]

2. 构建网络

下图是构建的网络，注意out维度扩展出一个维度，是为了和y维度一致

3. 训练

loss计算采用均方差MSE，优化器采用Adam
注意：hidden_prev的自更新

4. 预测

预测是循环一个点一个点的预测，每次预测的点的结果作为下次点的输入，直到预测出全部点，放到predictions中。
input = x[:,0,:] 去掉了x[1,seq,1]中的seq维度，变成[1,1]

5. 完整代码

import  numpy as np
import  torch
import  torch.nn as nn
import  torch.optim as optim
from    matplotlib import pyplot as pltnum_time_steps = 50
input_size = 1
hidden_size = 16
output_size = 1
lr=0.01class Net(nn.Module):def __init__(self, ):super(Net, self).__init__()self.rnn = nn.RNN(input_size=input_size,hidden_size=hidden_size,num_layers=1,batch_first=True,)for p in self.rnn.parameters():nn.init.normal_(p, mean=0.0, std=0.001)self.linear = nn.Linear(hidden_size, output_size)def forward(self, x, hidden_prev):out, hidden_prev = self.rnn(x, hidden_prev)# [b, seq, h]out = out.view(-1, hidden_size)out = self.linear(out)out = out.unsqueeze(dim=0)return out, hidden_prevmodel = Net()
criterion = nn.MSELoss()
optimizer = optim.Adam(model.parameters(), lr)hidden_prev = torch.zeros(1, 1, hidden_size)for iter in range(6000):start = np.random.randint(3, size=1)[0]time_steps = np.linspace(start, start + 10, num_time_steps)data = np.sin(time_steps)data = data.reshape(num_time_steps, 1)x = torch.tensor(data[:-1]).float().view(1, num_time_steps - 1, 1)y = torch.tensor(data[1:]).float().view(1, num_time_steps - 1, 1)output, hidden_prev = model(x, hidden_prev)hidden_prev = hidden_prev.detach()loss = criterion(output, y)model.zero_grad()loss.backward()# for p in model.parameters():#     print(p.grad.norm())# torch.nn.utils.clip_grad_norm_(p, 10)optimizer.step()if iter % 100 == 0:print("Iteration: {} loss {}".format(iter, loss.item()))start = np.random.randint(3, size=1)[0]
time_steps = np.linspace(start, start + 10, num_time_steps)
data = np.sin(time_steps)
data = data.reshape(num_time_steps, 1)
x = torch.tensor(data[:-1]).float().view(1, num_time_steps - 1, 1)
y = torch.tensor(data[1:]).float().view(1, num_time_steps - 1, 1)predictions = []
input = x[:, 0, :]
for _ in range(x.shape[1]):input = input.view(1, 1, 1)(pred, hidden_prev) = model(input, hidden_prev)input = predpredictions.append(pred.detach().numpy().ravel()[0])x = x.data.numpy().ravel()
y = y.data.numpy()
plt.scatter(time_steps[:-1], x.ravel(), s=90)
plt.plot(time_steps[:-1], x.ravel())plt.scatter(time_steps[1:], predictions)
plt.show()

6. 结果展示

图中黄色点是预测点，蓝色为实际点，前面的曲线是start不随机预测的效果，说明曲线已经被模型记住了；后面的曲线是start随机预测的效果，基本趋势和真实点是一致的。