5RNN_regression

RNN 迴歸

以下內容是根據torch官網和莫煩python學習所得
用 sin 的曲線預測出 cos 的曲線.

使用函數

• 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)
  

  prediction.data.numpy().flatten() 的作用，

  • prediction

  • tensor([[[0.9894], [0.7702], [0.5155], [0.4985], [0.4289], [0.5299], [0.5842], [0.6685], [0.8230], [0.9050]]], grad_fn=)

  • prediction.data
    Out[18]: tensor([[[0.9894], [0.7702], [0.5155], [0.4985], [0.4289], [0.5299], [0.5842], [0.6685], [0.8230], [0.9050]]])
  • prediction.data.numpy()
    Out[19]: array([[[ 0.98939151], [ 0.77023441], [ 0.51547438], [ 0.49851495], [ 0.42892569], [ 0.52992851], [ 0.58420801], [ 0.6685465 ], [ 0.82303888], [ 0.90499824]]], dtype=float32)
  • prediction.data.numpy().flatten()
    Out[20]: array([ 0.98939151, 0.77023441, 0.51547438, 0.49851495, 0.42892569,
    0.52992851, 0.58420801, 0.6685465 , 0.82303888, 0.90499824], dtype=float32)

  h_state 的值

  tensor([[[ 0.1971, 0.0377, -0.1762, -0.0389, 0.0437, 0.1591, -0.9546,
  0.9859, -0.7511, 0.6297, 0.6038, 0.6584, -0.5129, -0.2273,
  0.2661, 0.6085, 0.0599, -0.8674, -0.2799, -0.2373, 0.2681,
  -0.2986, -0.4462, -0.1166, 0.0302, 0.1772, 0.1731, -0.7297,
  0.1891, 0.3121, 0.6803, -0.5887]]], grad_fn=)

  有32個數據，對應RNN網絡的隱藏層數

源代碼

import torch
from torch import nn
import numpy as np
import matplotlib.pyplot as plt

# torch.manual_seed(1)    # reproducible

# Hyper Parameters
TIME_STEP = 10      # rnn time step
INPUT_SIZE = 1      # rnn input size
LR = 0.02           # learning rate

# show data
steps = np.linspace(0, np.pi*2, 100, dtype=np.float32)  # float32 for converting torch FloatTensor
x_np = np.sin(steps)
y_np = np.cos(steps)
plt.plot(steps, y_np, 'r-', label='target (cos)')
plt.plot(steps, x_np, 'b-', label='input (sin)')
plt.legend(loc='best')
plt.show()


class RNN(nn.Module):
    def __init__(self):
        super(RNN, self).__init__()
        self.rnn = nn.RNN(
            input_size=INPUT_SIZE,
            hidden_size=32,     # rnn hidden unit
            num_layers=1,       # number of rnn layer
            batch_first=True,   # input & output will has batch size as 1s dimension. e.g. (batch, time_step, input_size)
        )
        self.out = nn.Linear(32, 1)

    def forward(self, x, h_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)

        outs = []    # save all predictions
        for time_step in range(r_out.size(1)):    # calculate output for each time step
            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)

optimizer = torch.optim.Adam(rnn.parameters(), lr=LR)   # optimize all cnn parameters
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()