Since Numpy array is Float64 by default. How do I convert to PyTorch tensor to give a FLoat32 type and not 64?
I tried torch.from_numpy and it gave a Float64 type.
Asked
Active
Viewed 1,753 times
3
-
1`torch.from_numpy(arr).type(torch.FloatTensor)` – Michael Szczesny Feb 06 '22 at 18:12
-
Many thanks, this solved it – Lamosh Feb 06 '22 at 18:17
-
Or you can call `float`: `torch.from_numpy(x).float()` – Ivan Feb 07 '22 at 09:53