torch_celu

Provides functionality to define and train neural networks similar to
'PyTorch' by Paszke et al (2019) <arXiv:1912.01703> but written entirely in R
using the 'libtorch' library. Also supports low-level tensor operations and
'GPU' acceleration.

Daniel Falbel

torch

Tensors and Neural Networks with 'GPU' Acceleration

Javier Luraschi

Dmitriy Selivanov

Athos Damiani

Christophe Regouby

Krzysztof Joachimiak

Hamada S. Badr

 RStudio

torch_celu function

<dl><dt>self</dt>
<dd>the input tensor</dd>
<dt>alpha</dt>
<dd>the alpha value for the CELU formulation. Default: 1.0</dd></dl>

Arguments

See <code>nnf_celu()</code> for more info.

celu(input, alpha=1.) -&gt; Tensor 

Celu — torch_celu

<dl>

<dt>self</dt>
<dd>the input tensor</dd>


<dt>alpha</dt>
<dd>the alpha value for the CELU formulation. Default: 1.0</dd>

</dl>

See <code>nnf_celu()</code> for more info.

torch_celu: Celu

Description

Usage

Arguments

celu(input, alpha=1.) -> Tensor

Description

Usage

Arguments

celu(input, alpha=1.) -&gt; Tensor

celu(input, alpha=1.) -> Tensor