nnf_pixel_shuffle

Rearranges elements in a tensor of shape \((*, C \times r^2, H, W)\) to a
tensor of shape \((*, C, H \times r, W \times r)\).

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_pixel_shuffle function

<dl><dt>input</dt>
<dd>(Tensor) the input tensor</dd>
<dt>upscale_factor</dt>
<dd>(int) factor to increase spatial resolution by</dd></dl>

Arguments

Pixel_shuffle — nnf_pixel_shuffle

<dl>

<dt>input</dt>
<dd>(Tensor) the input tensor</dd>


<dt>upscale_factor</dt>
<dd>(int) factor to increase spatial resolution by</dd>

</dl>

nnf_pixel_shuffle: Pixel_shuffle

Description

Usage

Arguments