nnf_poisson_nll_loss

Poisson negative log likelihood loss.

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_poisson_nll_loss function

<dl><dt>input</dt>
<dd>tensor (N,*) where ** means, any number of additional dimensions</dd>
<dt>target</dt>
<dd>tensor (N,*) , same shape as the input</dd>
<dt>log_input</dt>
<dd>if <code>TRUE</code> the loss is computed as \(\exp(\mbox{input}) - \mbox{target} * \mbox{input}\),
if <code>FALSE</code> then loss is \(\mbox{input} - \mbox{target} * \log(\mbox{input}+\mbox{eps})\).
Default: <code>TRUE</code>.</dd>
<dt>full</dt>
<dd>whether to compute full loss, i. e. to add the Stirling approximation
term. Default: <code>FALSE</code>.</dd>
<dt>eps</dt>
<dd>(float, optional) Small value to avoid evaluation of \(\log(0)\) when
<code>log_input</code>=<code>FALSE</code>. Default: 1e-8</dd>
<dt>reduction</dt>
<dd>(string, optional) – Specifies the reduction to apply to the
output: 'none' | 'mean' | 'sum'. 'none': no reduction will be applied, 'mean':
the sum of the output will be divided by the number of elements in the output,
'sum': the output will be summed. Default: 'mean'</dd></dl>

Arguments

Poisson_nll_loss — nnf_poisson_nll_loss

<dl>

<dt>input</dt>
<dd>tensor (N,*) where ** means, any number of additional dimensions</dd>


<dt>target</dt>
<dd>tensor (N,*) , same shape as the input</dd>


<dt>log_input</dt>
<dd>if <code>TRUE</code> the loss is computed as \(\exp(\mbox{input}) - \mbox{target} * \mbox{input}\),
if <code>FALSE</code> then loss is \(\mbox{input} - \mbox{target} * \log(\mbox{input}+\mbox{eps})\).
Default: <code>TRUE</code>.</dd>


<dt>full</dt>
<dd>whether to compute full loss, i. e. to add the Stirling approximation
term. Default: <code>FALSE</code>.</dd>


<dt>eps</dt>
<dd>(float, optional) Small value to avoid evaluation of \(\log(0)\) when
<code>log_input</code>=<code>FALSE</code>. Default: 1e-8</dd>


<dt>reduction</dt>
<dd>(string, optional) – Specifies the reduction to apply to the
output: 'none' | 'mean' | 'sum'. 'none': no reduction will be applied, 'mean':
the sum of the output will be divided by the number of elements in the output,
'sum': the output will be summed. Default: 'mean'</dd>

</dl>

nnf_poisson_nll_loss: Poisson_nll_loss

Description

Usage

Arguments