torch_logaddexp2

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_logaddexp2 function

<dl><dt>self</dt>
<dd>(Tensor) the input tensor.</dd>
<dt>other</dt>
<dd>(Tensor) the second input tensor</dd></dl>

Arguments

Logarithm of the sum of exponentiations of the inputs in base-2.
Calculates pointwise \(\log_2\left(2^x + 2^y\right)\). See
<code>torch_logaddexp()</code> for more details.

logaddexp2(input, other, *, out=None) -&gt; Tensor 

Logaddexp2 — torch_logaddexp2

<dl>

<dt>self</dt>
<dd>(Tensor) the input tensor.</dd>


<dt>other</dt>
<dd>(Tensor) the second input tensor</dd>

</dl>

Logarithm of the sum of exponentiations of the inputs in base-2.
Calculates pointwise \(\log_2\left(2^x + 2^y\right)\). See
<code>torch_logaddexp()</code> for more details.

torch_logaddexp2: Logaddexp2

Description

Usage

Arguments

logaddexp2(input, other, *, out=None) -> Tensor

Description

Usage

Arguments

logaddexp2(input, other, *, out=None) -&gt; Tensor

logaddexp2(input, other, *, out=None) -> Tensor