Function Differences with torch.Tensor.item

torch.Tensor.item

torch.Tensor.item()

For more information, see torch.Tensor.item.

mindspore.Tensor.item

mindspore.Tensor.item(index=None)

For more information, see torch.Tensor.item.

Differences

PyTorch: Returns the value of this tensor, applicable to tensors with only one element.

MindSpore：Returns the value corresponding to the specified index in the tensor, applicable to tensors with one or more elements.

Code Examplefrom mindspore import Tensor
import numpy as np
import torch

x = Tensor(np.array([[1,2,3],[4,5,6]], dtype=np.float32))
print(x.item((0,1)))
# Out：
# 2.0

y = Tensor([1.0])
print(y.item())
# Out:
# [1.]

z = torch.tensor([1.0])
print(z.item())
# Out:
# 1.0