luz_load_model_weights

luz_save_model_weights

This can be useful when you have saved model checkpoints during training and
want to reload the best checkpoint in the end.

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) <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'

 RStudio

luz_load_model_weights function

<dl><dt>obj</dt>
<dd>luz object to which you want to copy the new weights.</dd>
<dt>path</dt>
<dd>path to saved model in disk.</dd>
<dt>...</dt>
<dd>other arguments passed to <code>torch_load()</code>.</dd></dl>

Arguments

<code>luz_save_model_weights</code> operates inplace, ie modifies the model object to contain the
new weights.

Warning

Loads model weights into a fitted object. — luz_load_model_weights

<dl>

<dt>obj</dt>
<dd>luz object to which you want to copy the new weights.</dd>


<dt>path</dt>
<dd>path to saved model in disk.</dd>


<dt>...</dt>
<dd>other arguments passed to <code>torch_load()</code>.</dd>

</dl>

<code>luz_save_model_weights</code> operates inplace, ie modifies the model object to contain the
new weights.

luz_load_model_weights: Loads model weights into a fitted object.

Description

Usage

Value

Arguments

Warning