giagrad.Tensor.elu#
- Tensor.elu(alpha=1.0) Tensor [source]#
Creates a new Tensor applying Exponential Linear Unit (ELU) function to data. See ELU.
\[\begin{split}out_i = \begin{cases} data_i \ \ if \ \ data_i > 0 \\ \text{alpha}(\exp(data_i) - 1) \ \ if \ \ x \leq 0 \\ \end{cases}\end{split}\]- Parameters:
alpha¶ (float) – The \(\alpha\) value for the ELU formulation.
Examples
>>> t = Tensor.empty(2, 3).uniform(-100, 100) >>> t tensor: [[-49.970577 35.522175 -14.944364] [ 32.187164 -66.65264 48.01228 ]] >>> t.elu() tensor: [[-1. 35.522175 -0.9999997] [32.187164 -1. 48.01228 ]] fn: ELU(alpha=1.0)