时间戳

首页 > 解决方案 > 如何修复 RuntimeError“标量类型 Float 的预期对象，但参数的标量类型 Double”？

python - 如何修复 RuntimeError“标量类型 Float 的预期对象，但参数的标量类型 Double”？

问题描述

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

RuntimeError: 标量类型 Float 的预期对象，但参数 #4 'mat1' 的标量类型 Double

以下是我的代码的关键部分：

# 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

标签： pythonneural-networkdeep-learningclassificationpytorch

解决方案

参考来自这个 github 问题。

当错误出现时RuntimeError: Expected object of scalar type Float but got scalar type Double for argument #4 'mat1'，您需要使用该.float()功能，因为它说Expected object of scalar type Float。

因此，解决方案正在更改y_pred = model(X_trainTensor)为y_pred = model(X_trainTensor.float())。

同样，当您收到另一个错误时loss = loss_fn(y_pred, y_trainTensor)，您需要y_trainTensor.long()因为错误消息显示Expected object of scalar type Long.

您也可以model.double()按照@Paddy 的建议进行操作。

推荐阅读