torch_threshold_

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_threshold_ function

<dl><dt>self</dt>
<dd>input tensor</dd>
<dt>threshold</dt>
<dd>The value to threshold at</dd>
<dt>value</dt>
<dd>The value to replace with</dd></dl>

Arguments

In-place version of <code>torch_threshold</code>.

threshold_(input, threshold, value) -&gt; Tensor 

Threshold_ — torch_threshold_

<dl>

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


<dt>threshold</dt>
<dd>The value to threshold at</dd>


<dt>value</dt>
<dd>The value to replace with</dd>

</dl>

In-place version of <code>torch_threshold</code>.

torch_threshold_: Threshold_

Description

Usage

Arguments

threshold_(input, threshold, value) -> Tensor

Description

Usage

Arguments

threshold_(input, threshold, value) -&gt; Tensor

threshold_(input, threshold, value) -> Tensor