pytorch 张量

data = np.array([1, 2, 3, 4])
t1 = torch.Tensor(data)
t2 = torch.tensor(data)
t3 = torch.as_tensor(data)
t4 = torch.from_numpy(data)

data[0] = 0
data[1] = 0

t1–t4的结果

tensor([1., 2., 3., 4.])
tensor([1, 2, 3, 4], dtype=torch.int32)
tensor([0, 0, 3, 4], dtype=torch.int32)
tensor([0, 0, 3, 4], dtype=torch.int32)

share data	copy data
torch.as_tensor()	torch.tensor()
torch.from_numpy()	torch.Tensor()