the same operation, but different results---The difference between pytorch.tensor and numpy.array

import numpy as np
import torch
from torch.autograd import Variable

a=np.array([[0,0,1,2],[0,0,0,0],[2,3,4,5],[2,3,2,2]])
bbox=a
k=((bbox[:,2]-bbox[:,0])>0).nonzero()
k

result:
(array([0, 2]),)

bbox=torch.tensor(a)
bbox=Variable(bbox,requires_grad=False)
k=((bbox[:,2]-bbox[:,0])>0).nonzero()
k

result:
tensor([[0],
[2]])