nnf_nll_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_nll_loss function

<dl><dt>input</dt>
<dd>\((N, C)\) where <code>C = number of classes</code> or \((N, C, H, W)\) in
case of 2D Loss, or \((N, C, d_1, d_2, ..., d_K)\) where \(K \geq 1\) in
the case of K-dimensional loss.</dd>
<dt>target</dt>
<dd>\((N)\) where each value is \(0 \leq \mbox{targets}[i] \leq C-1\),
or \((N, d_1, d_2, ..., d_K)\) where \(K \geq 1\) for K-dimensional loss.</dd>
<dt>weight</dt>
<dd>(Tensor, optional) a manual rescaling weight given to each class.
If given, has to be a Tensor of size <code>C</code></dd>
<dt>ignore_index</dt>
<dd>(int, optional) Specifies a target value that is ignored and
does not contribute to the input gradient.</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

Nll_loss — nnf_nll_loss

<dl>

<dt>input</dt>
<dd>\((N, C)\) where <code>C = number of classes</code> or \((N, C, H, W)\) in
case of 2D Loss, or \((N, C, d_1, d_2, ..., d_K)\) where \(K \geq 1\) in
the case of K-dimensional loss.</dd>


<dt>target</dt>
<dd>\((N)\) where each value is \(0 \leq \mbox{targets}[i] \leq C-1\),
or \((N, d_1, d_2, ..., d_K)\) where \(K \geq 1\) for K-dimensional loss.</dd>


<dt>weight</dt>
<dd>(Tensor, optional) a manual rescaling weight given to each class.
If given, has to be a Tensor of size <code>C</code></dd>


<dt>ignore_index</dt>
<dd>(int, optional) Specifies a target value that is ignored and
does not contribute to the input gradient.</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>

Nll_loss

Get 50% off unlimited learning

nnf_nll_loss: Nll_loss

Description

Usage

Arguments