mindchemistry.e3.o3.Norm

View Source On Gitee
class mindchemistry.e3.o3.Norm(irreps_in, squared=False, dtype=float32, ncon_dtype=float32)[source]

Norm of each irrep in a direct sum of irreps.

Parameters

  • irreps_in (Union[str, Irrep, Irreps]) – Irreps for the input.

  • squared (bool) – whether to return the squared norm. Default: False.

  • dtype (mindspore.dtype) – The type of input tensor. Default: mindspore.float32 .

  • ncon_dtype (mindspore.dtype) – The type of input tensors of ncon computation module. Default: mindspore.float32 .

Inputs:

  • v (Tensor) - The shape of Tensor is \((..., irreps\_in.dim)\) .

Outputs:

  • output (Tensor) - The shape of Tensor is \((..., irreps\_out.dim)\) .

Supported Platforms:

Ascend

Examples

>>> import mindspore as ms
>>> import numpy as np
>>> from mindchemistry.e3.o3 import Norm
>>> n = Norm('3x1o')
>>> v = ms.Tensor(np.linspace(1., 2., n.irreps_in.dim), dtype=ms.float32)
>>> n(v).shape
(1, 3)