Is There A Verctorized Approach In Pytorch To Get This Result?
I would like to get this result with torch functions. Do you have suggestions? import torch test_tensor=torch.tensor([[1, 2, 3, 4, 5, 6], [7, 8, 9, 1
Solution 1:
Using standard Python stride notation
import torch
test_tensor=torch.tensor([[1, 2, 3, 4, 5, 6],
[7, 8, 9, 10, 11, 12]]
)
t1 = test_tensor[:, :3].sum(dim=1)
print(t1)
t2 = test_tensor[:, ::2].sum(dim=1)
print(t2)
Post a Comment for "Is There A Verctorized Approach In Pytorch To Get This Result?"