如何修复 RuntimeError“标量类型 Float 的预期对象，但参数为 Double 的标量类型"?

问题描述

我正在尝试通过 PyTorch 训练分类器.但是，当我为模型提供训练数据时，我遇到了训练问题.我在 y_pred = model(X_trainTensor) 上收到此错误:

I'm trying to train a classifier via PyTorch. However, I am experiencing problems with training when I feed the model with training data.I get this error on y_pred = model(X_trainTensor):

运行时错误:标量类型为 Float 的预期对象，但参数 #4 'mat1' 的标量类型为 Double

以下是我的代码的关键部分:

Here are key parts of my code:

# Hyper-parameters
D_in = 47  # there are 47 parameters I investigate
H = 33
D_out = 2  # output should be either 1 or 0

# Format and load the data
y = np.array( df['target'] )
X = np.array( df.drop(columns = ['target'], axis = 1) )
X_train, X_test, y_train, y_test = train_test_split(X, y, train_size = 0.8)  # split training/test data

X_trainTensor = torch.from_numpy(X_train) # convert to tensors
y_trainTensor = torch.from_numpy(y_train)
X_testTensor = torch.from_numpy(X_test)
y_testTensor = torch.from_numpy(y_test)

# Define the model
model = torch.nn.Sequential(
    torch.nn.Linear(D_in, H),
    torch.nn.ReLU(),
    torch.nn.Linear(H, D_out),
    nn.LogSoftmax(dim = 1)
)

# Define the loss function
loss_fn = torch.nn.NLLLoss()

for i in range(50):
    y_pred = model(X_trainTensor)
    loss = loss_fn(y_pred, y_trainTensor)
    model.zero_grad()
    loss.backward()
    with torch.no_grad():
        for param in model.parameters():
            param -= learning_rate * param.grad

推荐答案

参考来自 this github issue.

当错误是 RuntimeError: Expected object of scalar type Float 但得到标量类型 Double 作为参数 #4 'mat1' 时，您需要使用 .float()code> 函数，因为它说 预期的标量类型 Float 对象.

When the error is RuntimeError: Expected object of scalar type Float but got scalar type Double for argument #4 'mat1', you would need to use the .float() function since it says Expected object of scalar type Float.

因此，解决方案是将 y_pred = model(X_trainTensor) 更改为 y_pred = model(X_trainTensor.float()).

Therefore, the solution is changing y_pred = model(X_trainTensor) to y_pred = model(X_trainTensor.float()).

同样，当您收到 loss = loss_fn(y_pred, y_trainTensor) 的另一个错误时，您需要 y_trainTensor.long() 因为错误消息说 Expected标量类型 Long 对象.

Likewise, when you get another error for loss = loss_fn(y_pred, y_trainTensor), you need y_trainTensor.long() since the error message says Expected object of scalar type Long.

您也可以按照@Paddy 的建议执行 model.double().

You could also do model.double(), as suggested by @Paddy.

这篇关于如何修复 RuntimeError“标量类型 Float 的预期对象，但参数为 Double 的标量类型"?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！