nnf_ctc_loss

The Connectionist Temporal Classification loss.

Provides functionality to define and train neural networks similar to
'PyTorch' by Paszke et al (2019) <doi:10.48550/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

Sebastian Fischer

Maximilian Pichler

 RStudio

nnf_ctc_loss function

<dl><dt>log_probs</dt>
<dd>\((T, N, C)\) where C = number of characters in alphabet including blank,
T = input length, and N = batch size. The logarithmized probabilities of
the outputs (e.g. obtained with nnf_log_softmax).</dd>
<dt>targets</dt>
<dd>\((N, S)\) or <code>(sum(target_lengths))</code>. Targets cannot be blank.
In the second form, the targets are assumed to be concatenated.</dd>
<dt>input_lengths</dt>
<dd>\((N)\). Lengths of the inputs (must each be \(\leq T\))</dd>
<dt>target_lengths</dt>
<dd>\((N)\). Lengths of the targets</dd>
<dt>blank</dt>
<dd>(int, optional) Blank label. Default \(0\).</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>
<dt>zero_infinity</dt>
<dd>(bool, optional) Whether to zero infinite losses and the
associated gradients. Default: <code>FALSE</code> Infinite losses mainly occur when the
inputs are too short to be aligned to the targets.</dd></dl>

Arguments

Ctc_loss — nnf_ctc_loss

<dl>

<dt>log_probs</dt>
<dd>\((T, N, C)\) where C = number of characters in alphabet including blank,
T = input length, and N = batch size. The logarithmized probabilities of
the outputs (e.g. obtained with nnf_log_softmax).</dd>


<dt>targets</dt>
<dd>\((N, S)\) or <code>(sum(target_lengths))</code>. Targets cannot be blank.
In the second form, the targets are assumed to be concatenated.</dd>


<dt>input_lengths</dt>
<dd>\((N)\). Lengths of the inputs (must each be \(\leq T\))</dd>


<dt>target_lengths</dt>
<dd>\((N)\). Lengths of the targets</dd>


<dt>blank</dt>
<dd>(int, optional) Blank label. Default \(0\).</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>


<dt>zero_infinity</dt>
<dd>(bool, optional) Whether to zero infinite losses and the
associated gradients. Default: <code>FALSE</code> Infinite losses mainly occur when the
inputs are too short to be aligned to the targets.</dd>

</dl>

Ctc_loss

Data Engineering and BI courses are free this week!

nnf_ctc_loss: Ctc_loss

Description

Usage

Arguments