There are several ways to convert arrays to torch tensors.
import torch
import numpy as np
data = np.array([1,2,3,4,5,6])
option1 = torch.Tensor(arr)
option2 = torch.tensor(arr)
option3 = torch.as_tensor(arr)
option4 = torch.from_numpy(arr)
| Option | Description |
|---|---|
| 1 | Make a Copy and convert array to torch Tensor’s default data type (float.32) |
| 2 | Make a Copy and inherit original array’s data type |
| 3 | Share the same memory allocation with the original array, and inherit original array’s data type |
| 4 | Share the same memory allocation with the original array, and inherit original array’s data type. BUT, only works for numpy arrays |
