ngraph.unique(data: Union[_pyngraph.Node, int, float, numpy.ndarray], axis: Optional[Union[_pyngraph.Node, int, float, numpy.ndarray]] = None, sorted: Optional[bool] = True, index_element_type: Optional[str] = 'i64', count_element_type: Optional[str] = 'i64', name: Optional[str] = None) _pyngraph.Node

Operator which selects and returns unique elements or unique slices of the input tensor.

  • data – Input data tensor.

  • axis – (Optional) An input tensor containing the axis value. If not provided or None, data input is considered as a flattened tensor. Default value: None.

  • sorted – (Optional) Controls the order of the returned unique values, sorts ascendingly when true. Default value: True.

  • index_element_type – (Optional) The data type set for outputs containing indices. Default value: “i64”.

  • count_element_type – (Optional) The data type set for the output with repetition count. Default value: “i64”.

  • name – (Optional) A name for the output node. Default value: None.


Node representing Unique operation.