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)
when I do:
for batch_idx, (data, target) in enumerate(train_loader):
data, target = Variable(data), Variable(target)
optimizer.zero_grad()
output = model(data) # error occurs here
I get the fallowing error:
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)
The last error comes from:
output.addmm_(0, 1, input, weight.t())
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?
y = y. long() does the job. There are similar methods for other data types, such as int , char , float and byte . You can check different dtypes here.
How to typecast a float tensor to integer tensor and vice versa in pytorch? This is achieved by using . type(torch. int64) which will return the integer type values, even if the values are in float or in some other data type.
You just need to cast Tensor constant to numpy object,then can access by index. Adding . detach() before . numpy() helped me.
To convert a Python list to a tensor, we are going to use the tf. convert_to_tensor() function and this function will help the user to convert the given object into a tensor. In this example, the object can be a Python list and by using the function will return a tensor.
This is because in PyTorch, you can not do operations between Tensor of different types. Your data is DoubleTensor, but the model parameter are FloatTensor. So you get this error message.
And we see that it is now a PyTorch FloatTensor. The one thing to notice, however, is 6, 2, 8, when we cast or converted the IntTensor back to a FloatTensor, it had not saved anywhere what numbers were past the decimal points.
Trying to convert the model to double is greatly discouraged by PyTorch devs as GPUs are not good at double precision computation. Also, floating point is pretty enough for deep learning.
When feeding data trough the layer a matrix multiplication is applied and this multiplication requires both matrices to be of same data type. Your input which is fed into gen will be converted to float then.
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
.
Hence, do either of the following:
data_utils.TensorDataset(torch.from_numpy(X).float(), torch.from_numpy(Y).float())
or do:
model.double()
Depeding, if you want to cast your model parameters, inputs and targets as Float
or as Double
.
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With