Menu
I created a permutation of the numbers from 1 to 3.
th> y = torch.randperm(3 ); th> y 3 2 1 [torch.DoubleTensor of size 3] Now, I want to convert y to a Torch.LongTensor. How can I do that?
785
A PyTorch tensor is homogenous, i.e., all the elements of a tensor are of the same data type. We can access the data type of a tensor using the ". dtype" attribute of the tensor. It returns the data type of the tensor.
To convert this FloatTensor to a double, define the variable double_x = x. double(). We can check the type and we see that whereas before this PyTorch tensor was a FloatTensor, we now have a PyTorch tensor that is a DoubleTensor.
A torch.Tensor is a multi-dimensional matrix containing elements of a single data type.
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.
85
use .to method of torch as follows:
y = y.to(torch.long) More details about torch tensor type/ops can be found here
https://pytorch.org/docs/stable/tensors.html
45
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
