Function Differences with torch.Tensor.item

View Source On Gitee

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

import mindspore as ms
import numpy as np
import torch

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

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

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