nnf_group_norm

Applies Group Normalization for last certain number of dimensions.

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_group_norm function

<dl><dt>input</dt>
<dd>the input tensor</dd>
<dt>num_groups</dt>
<dd>number of groups to separate the channels into</dd>
<dt>weight</dt>
<dd>the weight tensor</dd>
<dt>bias</dt>
<dd>the bias tensor</dd>
<dt>eps</dt>
<dd>a value added to the denominator for numerical stability. Default: 1e-5</dd></dl>

Arguments

Group_norm — nnf_group_norm

<dl>

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


<dt>num_groups</dt>
<dd>number of groups to separate the channels into</dd>


<dt>weight</dt>
<dd>the weight tensor</dd>


<dt>bias</dt>
<dd>the bias tensor</dd>


<dt>eps</dt>
<dd>a value added to the denominator for numerical stability. Default: 1e-5</dd>

</dl>

nnf_group_norm: Group_norm

Description

Usage

Arguments