Logit

Usage

torch_logit(self, eps = NULL)

Arguments

self

(Tensor) the input tensor.

eps

(float, optional) the epsilon for input clamp bound. Default: None

logit(input, eps=None, *, out=None) -> Tensor

Returns a new tensor with the logit of the elements of input. input is clamped to [eps, 1 - eps] when eps is not None. When eps is None and input < 0 or input > 1, the function will yields NaN.

$$\begin{gathered} y_i=\ln (\frac{z_i}{1-z_i}) \\ {z}_i=\begin{array}{ll}{x}_i& \text{if eps is None}\\ \text{eps}& \text{if }{x}_i<\text{eps}\\ x_i& \text{if }\text{eps}\le x_i\le 1-\text{eps}\\ 1-\text{eps}& \text{if }{x}_i>1-\text{eps}\end{array} \end{gathered}$$

Examples

if (torch_is_installed()) {

a <- torch_rand(5)
a
torch_logit(a, eps=1e-6)
}
#> torch_tensor
#>  0.0053
#>  0.3823
#>  1.3913
#>  1.2776
#>  2.6703
#> [ CPUFloatType{5} ]