mindspore.ops.atan2

mindspore.ops.atan2(input, other)[source]

Returns arctangent of input/other element-wise.

It returns \(\theta\ \in\ [-\pi, \pi]\) such that \(input = r*\sin(\theta), other = r*\cos(\theta)\), where \(r = \sqrt{input^2 + other^2}\).

Note

  • Arg input and other comply with the implicit type conversion rules to make the data types consistent. If they have different data types, the lower precision data type will be converted to relatively the highest precision data type.

  • At least one of the input and other args is Tensor.

Parameters

  • input (Tensor, Number.number) – The input tensor or scalar. The data type should be one of the following types: float16, float32, float64

  • other (Tensor, Number.number) – The input tensor or scalar. It has the same shape with input or its shape is able to broadcast with input.

Returns

Tensor or scalar, the shape is the same as the one after broadcasting, and the data type is same as input.

Raises

  • TypeError – If input or other is not a Tensor or scalar.

  • RuntimeError – If the data type of input and other conversion of Parameter is required when data type conversion of Parameter is not supported.

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore
>>> import numpy as np
>>> from mindspore import Tensor, ops
>>> input = Tensor(np.array([0, 1]), mindspore.float32)
>>> other = Tensor(np.array([1, 1]), mindspore.float32)
>>> output = ops.atan2(input, other)
>>> print(output)
[0.        0.7853982]