torch_frac

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_frac function

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

Arguments

Computes the fractional portion of each element in <code>input</code>.
$$
 \mbox{out}_{i} = \mbox{input}_{i} - \left\lfloor |\mbox{input}_{i}| \right\rfloor * \mbox{sgn}(\mbox{input}_{i})
$$

frac(input, out=NULL) -&gt; Tensor 

Frac — torch_frac

<dl>

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

</dl>

Computes the fractional portion of each element in <code>input</code>.
$$
 \mbox{out}_{i} = \mbox{input}_{i} - \left\lfloor |\mbox{input}_{i}| \right\rfloor * \mbox{sgn}(\mbox{input}_{i})
$$

torch_frac: Frac

Description

Usage

Arguments

frac(input, out=NULL) -> Tensor

Examples

Description

Usage

Arguments

frac(input, out=NULL) -&gt; Tensor

Examples

frac(input, out=NULL) -> Tensor