mindspore.ops.Rsqrt

class mindspore.ops.Rsqrt[source]

Computes reciprocal of square root of input tensor element-wise.

\[out_{i} = \frac{1}{\sqrt{x_{i}}}\]
Inputs:
  • x (Tensor) - The input of Rsqrt. Each element must be a non-negative number. \((N,*)\) where \(*\) means, any number of additional dimensions, its rank should less than 8.

Outputs:

Tensor, has the same type and shape as x.

Raises

TypeError – If dtype of x is neither float16 nor float32.

Supported Platforms:

Ascend GPU

Examples

>>> input_tensor = Tensor([[4, 4], [9, 9]], mindspore.float32)
>>> rsqrt = ops.Rsqrt()
>>> output = rsqrt(input_tensor)
>>> print(output)
[[0.5        0.5       ]
 [0.33333334 0.33333334]]