mindspore.nn.Softmin

class mindspore.nn.Softmin(axis=-1)[source]

Softmin activation function, which is a two-category function mindspore.nn.Sigmoid in the promotion of multi-classification. Its purpose is to show the results of multi-classification in the form of probability.

Calculates the value of the exponential function for the elements of the input Tensor on the axis, and then normalizes to lie in the range [0, 1] and sum up to 1.

Warning

Non-backward-compatible change after version 2.9.0: axis will be renamed to dim, and the default value will change.

Softmin is defined as:

\[\text{softmin}(x_{i}) = \frac{\exp(-x_i)}{\sum_{j=0}^{n-1}\exp(-x_j)},\]

where \(x_{i}\) is the \(i\)-th slice in the given dimension of the input Tensor.

Parameters:: axis (Union[int, tuple[int]], optional) – The axis to apply Softmin operation, if the dimension of input x is x.ndim, the range of axis is \([-x.ndim, x.ndim)\). -1 means the last dimension. Default: -1 . In CPU environment, axis only supports int type.

Inputs:

x (Tensor) - Tensor for computing Softmin functions with data type of float16 or float32.

Outputs:

Tensor, which has the same type and shape as x with values in the range \([0, 1]\).

Raises:

TypeError – If axis is neither an int nor a tuple.
TypeError – If dtype of x is neither float16 nor float32.
ValueError – If axis is a tuple whose length is less than 1.
ValueError – If axis is a tuple whose elements are not all in the range \([-x.ndim, x.ndim)\).

Supported Platforms:: Ascend GPU CPU

Examples

>>> import mindspore
>>> from mindspore import Tensor, nn
>>> import numpy as np
>>> # axis = -1(default), and the sum of return value is 1.0.
>>> x = Tensor(np.array([-1, -2, 0, 2, 1]), mindspore.float16)
>>> softmin = nn.Softmin()
>>> output = softmin(x)
>>> print(output)
[0.2341  0.636  0.0862  0.01165  0.03168 ]