mindspore.ops.RightShift

class mindspore.ops.RightShift[source]

Shift the value of each position of Tensor input_x to the right by corresponding bits in Tensor input_y. The inputs are two tensors, dtypes of them must be consistent, and the shapes of them could be broadcast.

\[\begin{aligned} &out_{i} =x_{i} >> y_{i} \end{aligned}\]

Warning

This is an experimental API that is subject to change or deletion.

Inputs:

input_x (Tensor) - The target tensor, will be shifted to the right by input_y bits element-wise. Support all int and uint types.
input_y (Tensor) - Number of bits shifted, the tensor must have the same type as input_x.

Outputs:

output (Tensor) - The output tensor, has the same type as input_x.

Raises

TypeError – If input_x or input_y is not tensor.
TypeError – If input_x and input_y could not be broadcast.

Supported Platforms:: Ascend GPU CPU

Examples

>>> import numpy as np
>>> from mindspore import Tensor, ops
>>> rightshift = ops.RightShift()
>>> input_x = Tensor(np.array([1, 2, 3]).astype(np.uint8))
>>> input_y = Tensor(np.array([1, 1, 1]).astype(np.uint8))
>>> output = rightshift(input_x, input_y)
>>> print(output)
[0 1 1]