nn_mixup_loss

In the training phase, computes individual losses with regard to two targets, weights them item-wise,
and averages the linear combinations to yield the mean batch loss.
For validation and testing, defers to the passed-in loss.

A high level interface for 'torch' providing utilities to reduce the
the amount of code needed for common tasks, abstract away torch details and
make the same code work on both the 'CPU' and 'GPU'. It's flexible enough to
support expressing a large range of models. It's heavily inspired by 'fastai' by
Howard et al. (2020) <doi:10.48550/arXiv.2002.04688>, 'Keras' by Chollet et al. (2015) and
'PyTorch Lightning' by Falcon et al. (2019) <doi:10.5281/zenodo.3828935>.

Daniel Falbel

Higher Level 'API' for 'torch'

Christophe Regouby

 RStudio

nn_mixup_loss function

<dl><dt>loss</dt>
<dd>the underlying loss <code>nn_module</code> to call. It must
support the <code>reduction</code> field. During training the attribute will be changed to
<code>'none'</code> so we get the loss for individual observations. See for for example
documentation for the <code>reduction</code> argument in <code>torch::nn_cross_entropy_loss()</code>.</dd></dl>

Arguments

Loss to be used with callbacks_mixup(). — nn_mixup_loss

<dl>

<dt>loss</dt>
<dd>the underlying loss <code>nn_module</code> to call. It must
support the <code>reduction</code> field. During training the attribute will be changed to
<code>'none'</code> so we get the loss for individual observations. See for for example
documentation for the <code>reduction</code> argument in <code>torch::nn_cross_entropy_loss()</code>.</dd>

</dl>

nn_mixup_loss: Loss to be used with `callbacks_mixup()`.

Description

Usage

Arguments

Details

See Also