nnf_pairwise_distance

Computes the batchwise pairwise distance between vectors using the p-norm.

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

nnf_pairwise_distance function

<dl><dt>x1</dt>
<dd>(Tensor) First input.</dd>
<dt>x2</dt>
<dd>(Tensor) Second input (of size matching x1).</dd>
<dt>p</dt>
<dd>the norm degree. Default: 2</dd>
<dt>eps</dt>
<dd>(float, optional) Small value to avoid division by zero.
Default: 1e-8</dd>
<dt>keepdim</dt>
<dd>Determines whether or not to keep the vector dimension. Default: False</dd></dl>

Arguments

Pairwise_distance — nnf_pairwise_distance

<dl>

<dt>x1</dt>
<dd>(Tensor) First input.</dd>


<dt>x2</dt>
<dd>(Tensor) Second input (of size matching x1).</dd>


<dt>p</dt>
<dd>the norm degree. Default: 2</dd>


<dt>eps</dt>
<dd>(float, optional) Small value to avoid division by zero.
Default: 1e-8</dd>


<dt>keepdim</dt>
<dd>Determines whether or not to keep the vector dimension. Default: False</dd>

</dl>

nnf_pairwise_distance: Pairwise_distance

Description

Usage

Arguments