nnf_instance_norm

Applies Instance Normalization for each channel in each data sample in a
batch.

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_instance_norm function

<dl><dt>input</dt>
<dd>the input tensor</dd>
<dt>running_mean</dt>
<dd>the running_mean tensor</dd>
<dt>running_var</dt>
<dd>the running var tensor</dd>
<dt>weight</dt>
<dd>the weight tensor</dd>
<dt>bias</dt>
<dd>the bias tensor</dd>
<dt>use_input_stats</dt>
<dd>whether to use input stats</dd>
<dt>momentum</dt>
<dd>a double for the momentum</dd>
<dt>eps</dt>
<dd>an eps double for numerical stability</dd></dl>

Arguments

Instance_norm — nnf_instance_norm

<dl>

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


<dt>running_mean</dt>
<dd>the running_mean tensor</dd>


<dt>running_var</dt>
<dd>the running var tensor</dd>


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


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


<dt>use_input_stats</dt>
<dd>whether to use input stats</dd>


<dt>momentum</dt>
<dd>a double for the momentum</dd>


<dt>eps</dt>
<dd>an eps double for numerical stability</dd>

</dl>

nnf_instance_norm: Instance_norm

Description

Usage

Arguments