运行pytorch的RNN进行训练的代码

下面是一个使用PyTorch实现的RNN进行训练的代码示例：

import torch
import torch.nn as nn
import torch.optim as optim

# 定义RNN模型
class RNN(nn.Module):
    def __init__(self, input_size, hidden_size, output_size):
        super(RNN, self).__init__()
        self.hidden_size = hidden_size
        self.i2h = nn.Linear(input_size + hidden_size, hidden_size)
        self.i2o = nn.Linear(input_size + hidden_size, output_size)
        self.softmax = nn.LogSoftmax(dim=1)

    def forward(self, input, hidden):
        combined = torch.cat((input, hidden), 1)
        hidden = self.i2h(combined)
        output = self.i2o(combined)
        output = self.softmax(output)
        return output, hidden

    def initHidden(self):
        return torch.zeros(1, self.hidden_size)

# 定义训练函数
def train(input_tensor, target_tensor, rnn, criterion, optimizer):
    hidden = rnn.initHidden()
    optimizer.zero_grad()
    loss = 0

    for i in range(input_tensor.size(0)):
        output, hidden = rnn(input_tensor[i], hidden)
        loss += criterion(output, target_tensor[i])

    loss.backward()
    optimizer.step()

    return output, loss.item()

# 定义参数
input_size = 10
hidden_size = 20
output_size = 5
learning_rate = 0.01
num_epochs = 1000

# 初始化模型、损失函数、优化器
rnn = RNN(input_size, hidden_size, output_size)
criterion = nn.NLLLoss()
optimizer = optim.SGD(rnn.parameters(), lr=learning_rate)

# 训练模型
for epoch in range(num_epochs):
    input_tensor = torch.randn(5, input_size)
    target_tensor = torch.LongTensor(5).random_(0, output_size)
    output, loss = train(input_tensor, target_tensor, rnn, criterion, optimizer)

    if epoch % 100 == 0:
        print('Epoch:', epoch, 'Loss:', loss)

在这个示例中，我们首先定义了一个简单的RNN模型，然后定义了一个用于训练模型的函数。在训练函数中，我们使用了随机生成的输入张量和目标张量来训练模型。最后，我们使用SGD优化器对模型进行优化，并在每一百个epoch时打印出当前的损失。