mindspore.mint.argsort

mindspore.mint.argsort(input, dim=- 1, descending=False, stable=False)[source]

Return the indices that sort the tensor along the specified dimension.

Warning

  • This is an experimental API that may change or be removed.

  • After version 2.9.0, axis will be renamed to dim, and stable will be added to the public mindspore.ops.argsort signature.

Parameters

  • input (Tensor) – The input tensor.

  • dim (int, optional) – Specify the dimension to sort along. Default -1. The Ascend backend only supports sorting the last dimension.

  • descending (bool, optional) – Sort order(ascending or descending). Default False.

  • stable (bool, optional) – Control the relative order of equivalent elements. Default False.

Returns

Tensor

Supported Platforms:

Ascend

Examples

>>> import mindspore
>>> x = mindspore.tensor([[8, 2, 1], [5, 9, 3], [4, 6, 7]], mindspore.float16)
>>> sort = mindspore.mint.argsort(x)
>>> print(sort)
[[2 1 0]
 [2 0 1]
 [0 1 2]]