实现基本循环神经网络模型循环单元为nnRNN或GRU输出层的全连接使用RNN所有时间步的输出隐状态初始值为0测试前向传播如果采用顺序划分需梯度截断训练：损失函数为平均交叉熵预测：给定一个前缀进行单步预测和K步预测。

import torch import torch.nn as nn

class RNNModel(nn.Module): def init(self, input_size, hidden_size, output_size, num_layers, rnn_type='gru'): super(RNNModel, self).init() self.input_size = input_size self.hidden_size = hidden_size self.output_size = output_size self.num_layers = num_layers self.rnn_type = rnn_type

    if self.rnn_type == 'gru':
        self.rnn = nn.GRU(input_size, hidden_size, num_layers, batch_first=True)
    else:
        self.rnn = nn.RNN(input_size, hidden_size, num_layers, batch_first=True)
    
    self.fc = nn.Linear(hidden_size, output_size)

def forward(self, input, hidden=None):
    if hidden is None:
        hidden = torch.zeros(self.num_layers, input.size(0), self.hidden_size)
    
    output, hidden = self.rnn(input, hidden)
    output = self.fc(output.reshape(-1, self.hidden_size))
    
    return output, hidden

def init_hidden(self, batch_size):
    return torch.zeros(self.num_layers, batch_size, self.hidden_size