PyTorch学习（12）——循环神经网络（RNN）-回归

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/github_39611196/article/details/82591431

本篇博客主要介绍采用RNN做回归。

示例代码：

import torch
from torch import nn
import torchvision.datasets as dsets
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
import numpy as np
from torch.autograd import Variable

# 超参数
TIME_STEP = 10
INPUT_SIZE = 1
LR = 0.02

# 生成回归数据并显示
# steps = np.linspace(0, np.pi * 2, 100, dtype=np.float32)
# 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='target (sin)')
# plt.show()


class RNN(nn.Module):
    def __init__(self):
        super(RNN, self).__init__()
        self.rnn = nn.RNN(
            input_size=INPUT_SIZE,
            hidden_size=32,  # hidden state的神经元数目
            num_layers=1,
            batch_first=True,
        )
        self.out = nn.Linear(32, 1)

    def forward(self, x, h_state):
        r_out, h_state = self.rnn(x, h_state)
        outs = []
        # 实现动态图
        for time_step in range(r_out.size(1)):
            outs.append(self.out(r_out[:, time_step, :]))
        return torch.stack(outs, dim=1), h_state

rnn = RNN()
# print(rnn)

# 优化器
optimizer = torch.optim.Adam(rnn.parameters(), lr=LR)
# 损失函数
loss_func = nn.MSELoss()

h_state = None
for step in range(60):
    start, end = step * np.pi, (step + 1) * np.pi  # time steps
    # use sin predicts cos
    steps = np.linspace(start, end, TIME_STEP, dtype=np.float32)
    x_np = np.sin(steps)
    y_np = np.cos(steps)

    x = Variable(torch.from_numpy(x_np[np.newaxis, :, np.newaxis]))
    y = Variable(torch.from_numpy(y_np[np.newaxis, :, np.newaxis]))

    prediction, h_state = rnn(x, h_state)
    h_state = Variable(h_state.data)

    loss = loss_func(prediction, y)
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()

    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()

网络结构：

RNN (
  (rnn): RNN(1, 32, batch_first=True)
  (out): Linear (32 -> 1)
)

数据形式：

训练结果：