mindspore.Tensor.logit
- Tensor.logit(eps=None)[source]
Calculate the logit of a tensor element-wise. When eps is not None, element in ‘x’ is clamped to [eps, 1-eps]. When eps is None, input ‘x’ is not clamped.
x refers to self tensor.
\[\begin{split}\begin{align} y_{i} & = \ln(\frac{z_{i}}{1 - z_{i}}) \\ z_{i} & = \begin{cases} x_{i} & \text{if eps is None} \\ \text{eps} & \text{if } x_{i} \lt \text{eps} \\ x_{i} & \text{if } \text{eps} \leq x_{i} \leq 1 - \text{eps} \\ 1 - \text{eps} & \text{if } x_{i} \gt 1 - \text{eps} \end{cases} \end{align}\end{split}\]- Parameters
eps (float, optional) – The epsilon. The input clamp bound is defined as [eps, 1-eps]. Default: None.
- Returns
Tensor, with the same shape as the x.
- Raises
- Supported Platforms:
GPU
Examples
>>> x = Tensor(np.array([0.1, 0.2, 0.3]).astype(np.float32)) >>> output = x.logit(eps=1e-5) >>> print(output) [-2.1972246 -1.3862944 -0.8472978]