mindspore.Tensor.ne

Tensor.ne(other) → Tensor

Computes the non-equivalence of two tensors element-wise.

Note

  • self and other comply with the implicit type conversion rules to make the data types consistent.

  • The other can be a tensor or a scalar.

  • When other is a tensor, the shapes of self and other could be broadcast.

  • When other is a scalar, it could only be a constant.

  • Broadcasting is supported.

\[\begin{split}out_{i} =\begin{cases} & \text{True, if } tensor_{i} \ne other_{i} \\ & \text{False, if } tensor_{i} = other_{i} \end{cases}\end{split}\]
Parameters

other (Union[Tensor, number.Number, bool]) – other is a number.Number or a bool or a tensor whose data type is number.Number and bool.

Returns

Tensor, the shape is the same as the one after broadcasting, and the data type is bool.

Raises

TypeError – If other is not one of the following: Tensor, Number, bool.

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore
>>> from mindspore import Tensor
>>> x = Tensor([1, 2, 3], mindspore.float32)
>>> output = x.ne(2.0)
>>> print(output)
[ True False  True]
>>>
>>> x = Tensor([1, 2, 3], mindspore.int32)
>>> y = Tensor([1, 2, 4], mindspore.int32)
>>> output = x.ne(y)
>>> print(output)
[False False  True]