set_hparams

This function is used to define hyper-parameters before calling <code>fit</code> for
<code>luz_modules</code>.

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

set_hparams function

<dl><dt>module</dt>
<dd>An <code>nn_module</code> that has been <code>setup()</code>.</dd>
<dt>...</dt>
<dd>The parameters set here will be used to initialize the <code>nn_module</code>, ie they
are passed unchanged to the <code>initialize</code> method of the base <code>nn_module</code>.</dd></dl>

Arguments

Set hyper-parameter of a module — set_hparams

<dl>

<dt>module</dt>
<dd>An <code>nn_module</code> that has been <code>setup()</code>.</dd>


<dt>...</dt>
<dd>The parameters set here will be used to initialize the <code>nn_module</code>, ie they
are passed unchanged to the <code>initialize</code> method of the base <code>nn_module</code>.</dd>

</dl>

set_hparams: Set hyper-parameter of a module

Description

Usage

Value

Arguments

See Also