mindspore.ops.pdist

mindspore.ops.pdist(x, p=2.0)

Computes the p-norm distance between each pair of row vectors in the input. If x is a 2D Tensor of shape $(N,M)$, then output must be a 1D Tensor of shape $(N\ast (N-1)/2,)$. If x is a Tensor of shape $(\ast B,N,M)$, then output must be a Tensor of shape $(\ast B,N\ast (N-1)/2)$.

$$y[n]=\sqrt[p]{{\mid x_i-x_j\mid }^p}$$

where $x_i,x_j$ are two different row vectors in the input.

Parameters

• x (Tensor) – Input tensor of shape $(\ast B,N,M)$. $\ast B$ is batch size, one-dim or multi-dim. dtype: float16, float32 or float64.

• p (float) – p value for the p-norm distance to calculate between each vector pair. $p\in [0,\infty ]$. Default: 2.0.

Returns

Tensor, has the same dtype as x.

Raises

• TypeError – If x is not a Tensor.

• TypeError – If dtype of x is not float16, float32 or float64.

• TypeError – If p is not a float.

• ValueError – If p is a negative float.

• ValueError – If dimension of x is less than 2.

Supported Platforms:

CPU

Examples

>>> x = Tensor(np.array([[1.0, 1.0], [2.0, 2.0], [3.0, 3.0]]).astype(np.float32))
>>> y = ops.pdist(x, p=2.0)
>>> print(y)
[1.4142135 2.828427 1.4142135]