两个rnn实例，可直接运行

仅作为记录，大佬请跳过。

参考

感谢大佬博主文章

实例1传送门

实例2传送门

实例一完整代码

简介：输入了这个正弦曲线，输出一个移位的正弦曲线

代码：

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

plt.figure(figsize=(8, 5))

# how many time steps/data pts are in one batch of data
seq_length = 20

# generate evenly spaced data pts
time_steps = np.linspace(0, np.pi, seq_length + 1)
data = np.sin(time_steps)
data.resize((seq_length + 1, 1))  # size becomes (seq_length+1, 1), adds an input_size dimension

x = data[:-1]  # all but the last piece of data
y = data[1:]  # all but the first

# # display the data
# plt.plot(time_steps[1:], x, 'r.', label='input, x')  # x
# plt.plot(time_steps[1:], y, 'b.', label='target, y')  # y
#
# plt.legend(loc='best')
# plt.show()


class RNN(nn.Module):
    def __init__(self, input_size, output_size, hidden_dim, n_layers):
        super(RNN, self).__init__()

        self.hidden_dim = hidden_dim

        # define an RNN with specified parameters
        # batch_first means that the first dim of the input and output will be the batch_size
        self.rnn = nn.RNN(input_size, hidden_dim, n_layers, batch_first=True)

        # last, fully-connected layer
        self.fc = nn.Linear(hidden_dim, output_size)

    def forward(self, x, hidden):
        # x (batch_size, seq_length, input_size)
        # hidden (n_layers, batch_size, hidden_dim)
        # r_out (batch_size, time_step, hidden_size)
        batch_size = x.size(0)

        # get RNN outputs
        r_out, hidden = self.rnn(x, hidden)
        # shape output to be (batch_size*seq_length, hidden_dim)
        r_out = r_out.view(-1, self.hidden_dim)

        # get final output
        output = self.fc(r_out)

        return output, hidden


# **********************#
# 检查输入和输出维度
# **********************#

# test that dimensions are as expected
test_rnn = RNN(input_size=1, output_size=1, hidden_dim=10, n_layers=2)

# generate evenly spaced, test data pts
time_steps = np.linspace(0, np.pi, seq_length)
data = np.sin(time_steps)
data.resize((seq_length, 1))

test_input = torch.Tensor(data).unsqueeze(0)  # give it a batch_size of 1 as first dimension
print('Input size: ', test_input.size())

# test out rnn sizes
test_out, test_h = test_rnn(test_input, None)
print('Output size: ', test_out.size())
print(