mindspore.ops.logit

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

Calculate the logit of a tensor element-wise.

The formula is defined as:

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

Parameters

• input (Tensor) – The input tensor.

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

Returns

Tensor

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore
>>> x = mindspore.tensor([0.1, 0.2, 0.3], mindspore.float32)
>>> output = mindspore.ops.logit(x, eps=1e-5)
>>> print(output)
[-2.1972246 -1.3862944 -0.8472978]