not_equal

paddle. not_equal ( x, y, name=None ) [source]

Returns the truth value of \(x != y\) elementwise, which is equivalent function to the overloaded operator !=.

Note

The output has no gradient.

Parameters
  • x (Tensor) – First input to compare which is N-D tensor. The input data type should be bool, float32, float64, uint8, int8, int16, int32, int64.

  • y (Tensor) – Second input to compare which is N-D tensor. The input data type should be bool, float32, float64, uint8, int8, int16, int32, int64.

  • name (str, optional) – The default value is None. Normally there is no need for user to set this property. For more information, please refer to Name.

Returns

The output shape is same as input x. The output data type is bool.

Return type

Tensor

Examples

>>> import paddle

>>> x = paddle.to_tensor([1, 2, 3])
>>> y = paddle.to_tensor([1, 3, 2])
>>> result1 = paddle.not_equal(x, y)
>>> print(result1)
Tensor(shape=[3], dtype=bool, place=Place(cpu), stop_gradient=True,
[False, True , True ])