import torch
from torch import nn
import numpy as np
import matplotlib.pyplot as plt
# 超参数
# Hyper Parameters
TIME_STEP = 10 # rnn time step
INPUT_SIZE = 1 # rnn input size
LR = 0.02 # learning rate
# 生成数据
# show data
steps = np.linspace(0, np.pi * 2, 100, dtype=np.float32) # float32 for converting torch FloatTensor
x_np = np.sin(steps) # 输入
y_np = np.cos(steps) # 目标
plt.plot(steps, y_np, 'r-', label='target (cos)')
plt.plot(steps, x_np, 'b-', label='input (sin)')
plt.legend(loc='best')
plt.show()
# 定义神经网络
# 对每一个 r_out 都得放到 Linear 中去计算出预测的 output, 所以能用一个 for loop 来循环计算.
class RNN(nn.Module):
def __init__(self):
super(RNN, self).__init__() # 继承 __init__ 功能
self.rnn = nn.RNN( # 一个普通的 RNN
input_size=INPUT_SIZE,
hidden_size=32, # rnn hidden unit 32个神经元
num_layers=1, # number of rnn layer # 有几层 RNN layers
batch_first=True, # input & output will has batch size as 1s dimension. e.g. (batch, time_step, input_size) # input & output 会是以 batch size 为第一维度的特征集 e.g. (batch, time_step, input_size)
)
self.out = nn.Linear(32, 1)
def forward(self, x, h_state): # 因为 hidden state 是连续的, 所以要一直传递这一个 state
# x (batch, time_step, input_size)
# h_state (n_layers, batch, hidden_size)
# r_out (batch, time_step, hidden_size)
r_out, h_state = self.rnn(x, h_state) # h_state 也要作为 RNN 的一个输入
outs = [] # save all predictions # 保存所有时间点的预测值
for time_step in range(r_out.size(1)): # calculate output for each time step # 对每一个时间点计算 output
outs.append(self.out(r_out[:, time_step, :]))
return torch.stack(outs, dim=1), h_state
# instead, for simplicity, you can replace above codes by follows
# r_out = r_out.view(-1, 32)
# outs = self.out(r_out)
# outs = outs.view(-1, TIME_STEP, 1)
# return outs, h_state
# or even simpler, since nn.Linear can accept inputs of any dimension
# and returns outputs with same dimension except for the last
# outs = self.out(r_out)
# return outs
rnn = RNN()
print(rnn)
# 选择优化器
optimizer = torch.optim.Adam(rnn.parameters(), lr=LR) # optimize all cnn parameters
# 选择损失函数
loss_func = nn.MSELoss()
h_state = None # for initial hidden state
plt.figure(1, figsize=(12, 5))
plt.ion() # continuously plot
for step in range(100):
start, end = step * np.pi, (step + 1) * np.pi # time range
# use sin predicts cos
steps = np.linspace(start, end, TIME_STEP, dtype=np.float32,
endpoint=False) # float32 for converting torch FloatTensor
x_np = np.sin(steps)
y_np = np.cos(steps)
x = torch.from_numpy(x_np[np.newaxis, :, np.newaxis]) # shape (batch, time_step, input_size)
y = torch.from_numpy(y_np[np.newaxis, :, np.newaxis])
prediction, h_state = rnn(x, h_state) # rnn output
# !! next step is important !!
h_state = h_state.data # repack the hidden state, break the connection from last iteration
loss = loss_func(prediction, y) # calculate loss
optimizer.zero_grad() # clear gradients for this training step
loss.backward() # backpropagation, compute gradients
optimizer.step() # apply gradients
# plotting
plt.plot(steps, y_np.flatten(), 'r-')
plt.plot(steps, prediction.data.numpy().flatten(), 'b-')
plt.draw();
plt.pause(0.05)
plt.ioff()
plt.show()