mindspore.ops.cdist

mindspore.ops.cdist(x1, x2, p=2.0)[source]

Computes p-norm distance between each pair of row vectors of two input Tensors.

Note

  • On Ascend, the supported dtypes are float16 and float32.

  • On CPU, the supported dtypes are float16 and float32.

  • On GPU, the supported dtypes are float32 and float64.

Parameters
  • x1 (Tensor) – Input tensor of shape \((B, P, M)\). Letter \(B\) represents 0 or positive int number. When \(B\) is equal to 0, it means this dimension can be ignored, i.e. shape of the tensor is \((P, M)\).

  • x2 (Tensor) – Input tensor of shape \((B, R, M)\), has the same dtype as x1.

  • p (float, optional) – P value for the p-norm distance to calculate between each vector pair, P >= 0. Default: 2.0 .

Returns

Tensor, p-norm distance, has the same dtype as x1, its shape is \((B, P, R)\).

Raises
  • TypeError – If x1 or x2 is not Tensor.

  • TypeError – If dtype of x1 or x2 is not listed in the "Note" above.

  • TypeError – If p is not float32.

  • ValueError – If p is negative.

  • ValueError – If dimension of x1 is not the same as x2.

  • ValueError – If dimension of x1 or x2 is neither 2 nor 3.

  • ValueError – If the batch dim of x1 and x2 can not broadcast.

  • ValueError – If the number of columns of x1 is not the same as that of x2.

Supported Platforms:

Ascend GPU CPU

Examples

>>> import numpy as np
>>> from mindspore import Tensor, ops
>>> x = Tensor(np.array([[[1.0, 1.0], [2.0, 2.0]]]).astype(np.float32))
>>> y = Tensor(np.array([[[3.0, 3.0], [3.0, 3.0]]]).astype(np.float32))
>>> output = ops.cdist(x, y, 2.0)
>>> print(output)
[[[2.8284273 2.8284273]
  [1.4142137 1.4142137]]]