import torch.nn as nn
import torch
import numpy as np
import matplotlib
matplotlib.use('TkAgg')
from matplotlib import pyplot as plt
# net = nn.RNN(100,10) #100个单词,每个单词10个维度
# print(net._parameters.keys())
#序列时间点预测num_time_steps =50
input_size =1
hidden_size =16
output_size = 1
lr=0.01
class 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, #[b,seq,feature] batch_first=False [seq,b,feature] ,)self.linear = nn.Linear(hidden_size,output_size)def forward(self,x,hidden_prev):# hidden_prev=h0 表示最后一个Ht的输出,out是表示[h0,h1,h2,h3....]每一个时间t的输出out,hidden_prev = self.rnn(x,hidden_prev)#[1,seq,h] => [seq,h]out = out.view(-1,hidden_size)out = self.linear(out) #[seq,h] => [seq,1]out = out.unsqueeze(dim=0) #=>[1,seq,1]return out,hidden_prevmodel =Net()
criterion = nn.MSELoss()
optimizer = torch.optim.Adam(model.parameters(),lr)hidden_prev = torch.zeros(1,1,hidden_size) #[b,1,10]for iter in range(6000):start = np.random.randint(10,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()optimizer.step()if iter%100 == 0:print("Iteration:{} loss{}".format(iter,loss.item()))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],predictions)plt.scatter(time_steps[1:],predictions)
plt.show()