我正在使用Pytorch处理一个线性回归问题。我使用的数据集是Kaggle的房价数据。在训练模型时，我发现损失没有减少。损失显示出一种不规则的模式。这是我在100个epoch后得到的损失值：

Epoch [10/100], Loss: 222273830912.0000Epoch [20/100], Loss: 348813688832.0000Epoch [30/100], Loss: 85658296320.0000Epoch [40/100], Loss: 290305572864.0000Epoch [50/100], Loss: 59399933952.0000Epoch [60/100], Loss: 80360054784.0000Epoch [70/100], Loss: 90352918528.0000Epoch [80/100], Loss: 534457679872.0000Epoch [90/100], Loss: 256064503808.0000Epoch [100/100], Loss: 102400483328.0000

这是我的代码：

import torchimport numpy as npfrom torch.utils.data import TensorDatasetimport torch.nn as nnfrom torch.utils.data import DataLoaderimport torch.nn.functional as Finputs = normalized_Xtargets = np.array(train_y)# Tensorsinputs = torch.from_numpy(inputs)targets = torch.from_numpy(targets)targets = targets.view(-1, 1)train_ds = TensorDataset(inputs, targets.squeeze())batch_size = 5train_dl = DataLoader(train_ds, batch_size, shuffle=True)model = nn.Linear(10, 1)# Define Loss funcloss_fn = F.mse_loss# Optimizeropt = torch.optim.SGD(model.parameters(), lr = 1e-1)num_epochs = 100model.train()for epoch in range(num_epochs):    # Train with batches of data    for xb, yb in train_dl:        # 1. Generate predictions        pred = model(xb.float())        # 2. Calculate loss        yb = yb.view(yb.size(0), -1)        loss = loss_fn(pred, yb.float())            # 3. Compute gradients        loss.backward()        # 4. Update parameters using gradients        opt.step()        # 5. Reset the gradients to zero        opt.zero_grad()    if (epoch+1) % 10 == 0:        print('Epoch [{}/{}], Loss: {:.4f}'.format(epoch +                                                   1, num_epochs,                                                    loss.item()))

回答：

我运行了您提供的代码，并得到了以下错误：

    p.py:38: UserWarning: Using a target size (torch.Size([50])) that is different to the input size (torch.Size([50, 1])). This will likely lead to incorrect results due to broadcasting. Please ensure they have the same size.

您的问题是由于pred和yb的维度不同引起的。

以下代码展示了如何解决这个问题