mindsponge.common.rots_to_tensor

mindsponge.common.rots_to_tensor(rots, use_numpy=False)[source]

Translate rots represented by vectors to tensor, inverse of ‘rots_from_tensor’.

Parameters

rots (Tuple) – Rots represented by vectors, shape is \((xx, xy, xz, yx, yy, yz, zx, zy, zz)\) .
use_numpy (bool) – Whether to use numpy to calculate. Default: False.

Returns

Tensor, concat the tensor in last dims, shape \((N_{res}, 3, 3)\).

Supported Platforms:: Ascend GPU

Examples

>>> import numpy as np
>>> import mindspore as ms
>>> from mindspore import Tensor
>>> from mindsponge.common.geometry import rots_to_tensor
>>> inputs = [Tensor(np.ones((256,)), ms.float32) for i in range(9)]
>>> output = rots_to_tensor(inputs)
>>> print(output.shape)
(256, 3, 3)