mindspore.ops.round

mindspore.ops.round(input, *, decimals=0)[source]

Returns half to even of a tensor element-wise.

\[out_i \approx input_i\]

Note

The input data types supported by the Ascend platform include bfloat16 (Atlas training series products are not supported), float16, float32, float64, int32, and int64.

Parameters

input (Tensor) – The input tensor.

Keyword Arguments

decimals (int, optional) – Number of decimal places to round to (default: 0). If decimals is negative, it specifies the number of positions to the left of the decimal point. It supports converting the single-element tensor to an int. When input type is int32 or int64, the decimals should be 0.

Returns

Tensor, has the same shape and type as the input.

Raises

TypeError – If input is not a Tensor.
RuntimeError – If input type is int32 or int64, the decimals is not 0.

Supported Platforms:: Ascend GPU CPU

Examples

>>> import mindspore
>>> import numpy as np
>>> from mindspore import Tensor, ops
>>> input = Tensor(np.array([0.8, 1.5, 2.3, 2.5, -4.5]), mindspore.float32)
>>> output = ops.round(input)
>>> print(output)
[ 1.  2.  2.  2. -4.]
>>> input = Tensor(np.array([0.81, 1.52, 2.35, 2.53, -4.57]), mindspore.float32)
>>> output = ops.round(input, decimals=1)
>>> print(output)
[ 0.8  1.5  2.4  2.5 -4.6]