nnf_affine_grid

Generates a 2D or 3D flow field (sampling grid), given a batch of
affine matrices <code>theta</code>.

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_affine_grid function

<dl><dt>theta</dt>
<dd>(Tensor) input batch of affine matrices with shape
(\(N \times 2 \times 3\)) for 2D or (\(N \times 3 \times 4\)) for 3D</dd>
<dt>size</dt>
<dd>(torch.Size) the target output image size. (\(N \times C \times H \times W\)
for 2D or \(N \times C \times D \times H \times W\) for 3D)
Example: torch.Size((32, 3, 24, 24))</dd>
<dt>align_corners</dt>
<dd>(bool, optional) if <code>True</code>, consider <code>-1</code> and <code>1</code>
to refer to the centers of the corner pixels rather than the image corners.
Refer to <code>nnf_grid_sample()</code> for a more complete description. A grid generated by
<code>nnf_affine_grid()</code> should be passed to <code>nnf_grid_sample()</code> with the same setting for
this option. Default: <code>False</code></dd></dl>

Arguments

Affine_grid — nnf_affine_grid

<dl>

<dt>theta</dt>
<dd>(Tensor) input batch of affine matrices with shape
(\(N \times 2 \times 3\)) for 2D or (\(N \times 3 \times 4\)) for 3D</dd>


<dt>size</dt>
<dd>(torch.Size) the target output image size. (\(N \times C \times H \times W\)
for 2D or \(N \times C \times D \times H \times W\) for 3D)
Example: torch.Size((32, 3, 24, 24))</dd>


<dt>align_corners</dt>
<dd>(bool, optional) if <code>True</code>, consider <code>-1</code> and <code>1</code>
to refer to the centers of the corner pixels rather than the image corners.
Refer to <code>nnf_grid_sample()</code> for a more complete description. A grid generated by
<code>nnf_affine_grid()</code> should be passed to <code>nnf_grid_sample()</code> with the same setting for
this option. Default: <code>False</code></dd>

</dl>

nnf_affine_grid: Affine_grid

Description

Usage

Arguments