mindspore.ops.logit

mindspore.ops.logit(input, eps=None)

Calculate the logit of a tensor element-wise. When eps is not None, element in input is clamped to [eps, 1-eps]. When eps is None, input input is not clamped.

$$\begin{array}{r}\begin{array}{rl}{y}_i& =\ln (\frac{z_i}{1-z_i})\\ z_i& =\{\begin{array}{ll}inpu{t}_i& \text{if eps is None}\\ \text{eps}& \text{if }inpu{t}_i<\text{eps}\\ inpu{t}_i& \text{if }\text{eps}\le inpu{t}_i\le 1-\text{eps}\\ 1-\text{eps}& \text{if }inpu{t}_i>1-\text{eps}\end{array}\end{array}\end{array}$$

Parameters

• input (Tensor) – The input tensor of type float16, float32 or float64.

• eps (float, optional) – The epsilon. If eps is not None, the input clamp bound is defined as [eps, 1-eps], otherwise, the input input is not clamped. Default: None .

Returns

Tensor, with the same shape and dtype as the input.

Raises

• TypeError – If eps is not a float.

• TypeError – If input is not a Tensor.

• TypeError – If dtype of input is not float16, float32 or float64.

Supported Platforms:

Ascend GPU CPU

Examples

>>> import numpy as np
>>> from mindspore import Tensor, ops
>>> x = Tensor(np.array([0.1, 0.2, 0.3]).astype(np.float32))
>>> output = ops.logit(x, eps=1e-5)
>>> print(output)
[-2.1972246 -1.3862944 -0.8472978]