mindspore.ops.nextafter

mindspore.ops.nextafter(input, other)[source]

Returns the next representable floating-point value after input towards other element-wise.

\begin{array}{r} o u t_{i} = {\begin{cases} i n p u t_{i} + e p s, & if i n p u t_{i} < o t h e r_{i} \\ i n p u t_{i} - e p s, & if i n p u t_{i} > o t h e r_{i} \\ i n p u t_{i}, & if i n p u t_{i} = o t h e r_{i} \end{cases} \end{array}

Where eps is the smallest representable increment value for the input tensor's dtype.

For more detailed information, refer to A Self Regularized Non-Monotonic Neural Activation Function.

Parameters

input (Tensor) – The first input tensor.
other (Tensor) – The second input tensor.

Returns

Tensor

Supported Platforms:: Ascend GPU CPU

Examples

>>> import mindspore
>>> input = mindspore.tensor([0.0], mindspore.float32)
>>> other = mindspore.tensor([0.1], mindspore.float32)
>>> output = mindspore.ops.nextafter(input, other)
>>> print(output)
[1.e-45]