我一直试图学习PyTorch . 这里's a tutorial I'一直关注：https://pytorch.org/tutorials/intermediate/char_rnn_classification_tutorial.html，这基本上是一个非常简单的RNN，可以将名称分类为其语言 . 当我在CPU上运行它时，最终的结果是

100000 100% (2m 25s) 0.3983 Tsujimoto / Japanese ✓
Training completed! Time taken: 145.90 seconds.

但是当我在GPU上运行时，我得到了以下内容

100000 100% (5m 56s) 0.1462 Mcgregor / Scottish ✓
Training completed! Time taken: 356.96 seconds.

我唯一改变的是 train 函数，通过将输入张量发送到设备（ device = torch.device("cuda:3" if torch.cuda.is_available() else "cpu") ），当然将rnn本身放到GPU（ rnn = RNN(n_letters, n_hidden, n_categories).to(device ）：

def train(category_tensor, line_tensor):
    hidden = rnn.initHidden().to(device)
    category_tensor, line_tensor = category_tensor.to(device), line_tensor.to(device)
    rnn.zero_grad()
    for i in range(line_tensor.size()[0]):
        output, hidden = rnn(line_tensor[i], hidden)
    loss = F.nll_loss(output, category_tensor)
    loss.backward()
    optimizer.step()
    return output, loss.item()

难道我做错了什么？

提前致谢！

python pytorch