nnf_one_hot

Takes LongTensor with index values of shape <code>(*)</code> and returns a tensor
of shape <code>(*, num_classes)</code> that have zeros everywhere except where the
index of last dimension matches the corresponding value of the input tensor,
in which case it will be 1.

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_one_hot function

<dl><dt>tensor</dt>
<dd>(LongTensor) class values of any shape.</dd>
<dt>num_classes</dt>
<dd>(int) Total number of classes. If set to -1, the number
of classes will be inferred as one greater than the largest class value in
the input tensor.</dd></dl>

Arguments

One_hot — nnf_one_hot

<dl>

<dt>tensor</dt>
<dd>(LongTensor) class values of any shape.</dd>


<dt>num_classes</dt>
<dd>(int) Total number of classes. If set to -1, the number
of classes will be inferred as one greater than the largest class value in
the input tensor.</dd>

</dl>

nnf_one_hot: One_hot

Description

Usage

Arguments

Details