Pytorch:将 FloatTensor 转换为 DoubleTensor [英] Pytorch: Convert FloatTensor into DoubleTensor

问题描述

我有 2 个 numpy 数组，我将它们转换为张量以使用 TensorDataset 对象.

I have 2 numpy arrays, which I convert into tensors to use the TensorDataset object.

import torch.utils.data as data_utils

X = np.zeros((100,30))
Y = np.zeros((100,30))

train = data_utils.TensorDataset(torch.from_numpy(X).double(), torch.from_numpy(Y))
train_loader = data_utils.DataLoader(train, batch_size=50, shuffle=True)

当我这样做时:

for batch_idx, (data, target) in enumerate(train_loader):
    data, target = Variable(data), Variable(target)
    optimizer.zero_grad()
    output = model(data)               # error occurs here

我收到了以下错误:

TypeError: addmm_ 收到了一个无效的参数组合 - 得到了 (int, int, torch.DoubleTensor, torch.FloatTensor)，但需要以下之一:[...]
*(浮动 beta，浮动 alpha，torch.DoubleTensor mat1，torch.DoubleTensor mat2)不匹配，因为某些参数的类型无效:(int, int, torch.DoubleTensor, torch.FloatTensor)
*(浮动 beta，浮动 alpha，torch.SparseDoubleTensor mat1，torch.DoubleTensor mat2)不匹配，因为某些参数的类型无效:(int, int, torch.DoubleTensor, torch.FloatTensor)

TypeError: addmm_ received an invalid combination of arguments - got (int, int, torch.DoubleTensor, torch.FloatTensor), but expected one of: [...]
* (float beta, float alpha, torch.DoubleTensor mat1, torch.DoubleTensor mat2) didn't match because some of the arguments have invalid types: (int, int, torch.DoubleTensor, torch.FloatTensor)
* (float beta, float alpha, torch.SparseDoubleTensor mat1, torch.DoubleTensor mat2) didn't match because some of the arguments have invalid types: (int, int, torch.DoubleTensor, torch.FloatTensor)

最后一个错误来自:

output.addmm_(0, 1, input, weight.t())

output.addmm_(0, 1, input, weight.t())

正如您在我的代码中看到的，我尝试使用 .double() 转换张量 - 但这不起作用.为什么他将一个数组转换为 FloatTensor 对象，而将另一个数组转换为 DoubleTensor?有什么想法吗?

As you see in my code I tried converting the tensor by using .double() - but this did not work. Why is he casting one array into a FloatTensor object and the other into a DoubleTensor? Any ideas?

推荐答案

您的 numpy 数组是 64 位浮点，将被转换为 torch.DoubleTensor 标准.现在，如果您将它们与您的模型一起使用，您需要确保您的模型参数也是 Double.或者你需要确保你的 numpy 数组被转换为 Float，因为模型参数被标准转换为 float.

Your numpy arrays are 64-bit floating point and will be converted to torch.DoubleTensor standardly. Now, if you use them with your model, you'll need to make sure that your model parameters are also Double. Or you need to make sure, that your numpy arrays are cast as Float, because model parameters are standardly cast as float.

因此，请执行以下任一操作:

Hence, do either of the following:

data_utils.TensorDataset(torch.from_numpy(X).float(), torch.from_numpy(Y).float())

或者做:

model.double()

Depeding，如果您想将模型参数、输入和目标转换为 Float 或 Double.

Depeding, if you want to cast your model parameters, inputs and targets as Float or as Double.

这篇关于Pytorch:将 FloatTensor 转换为 DoubleTensor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IT屋！