vaeac_get_model_from_checkp

Function to load a <code>vaeac</code> model and set it in the right state and mode

internal

Complex machine learning models are often hard to interpret. However, in
many situations it is crucial to understand and explain why a model made a specific
prediction. Shapley values is the only method for such prediction explanation framework
with a solid theoretical foundation. Previously known methods for estimating the Shapley
values do, however, assume feature independence. This package implements methods which accounts for any feature
dependence, and thereby produces more accurate estimates of the true Shapley values.
An accompanying 'Python' wrapper ('shaprpy') is available through the GitHub repository.

Martin Jullum

shapr

Prediction Explanation with Dependence-Aware Shapley Values

Lars Henry Berge Olsen

Annabelle Redelmeier

Jon Lachmann

Nikolai Sellereite

Anders Løland

Jens Christian Wahl

Camilla Lingjærde

Norsk Regnesentral 

vaeac_get_model_from_checkp function

<dl><dt>checkpoint</dt>
<dd>List. This must be a loaded <code>vaeac</code> save object. That is, <code>torch::torch_load('vaeac_save_path')</code>.</dd>
<dt>cuda</dt>
<dd>Logical (default is <code>FALSE</code>). If <code>TRUE</code>, then the <code>vaeac</code> model will be trained using cuda/GPU.
If <code>torch::cuda_is_available()</code> is <code>FALSE</code>, the we fall back to use CPU. If <code>FALSE</code>, we use the CPU. Using a GPU
for smaller tabular dataset often do not improve the efficiency.
See <code><a href="https://torch.mlverse.org/docs/articles/installation.html">vignette("installation", package = "torch")</a></code> fo help to enable running on the GPU (only Linux and Windows).</dd>
<dt>mode_train</dt>
<dd>Logical. If <code>TRUE</code>, the returned <code>vaeac</code> model is set to be in training mode.
If <code>FALSE</code>, the returned <code>vaeac</code> model is set to be in evaluation mode.</dd></dl>

Arguments

Author

Function to load a vaeac model and set it in the right state and mode — vaeac_get_model_from_checkp

<dl>

<dt>checkpoint</dt>
<dd>List. This must be a loaded <code>vaeac</code> save object. That is, <code>torch::torch_load('vaeac_save_path')</code>.</dd>


<dt>cuda</dt>
<dd>Logical (default is <code>FALSE</code>). If <code>TRUE</code>, then the <code>vaeac</code> model will be trained using cuda/GPU.
If <code>torch::cuda_is_available()</code> is <code>FALSE</code>, the we fall back to use CPU. If <code>FALSE</code>, we use the CPU. Using a GPU
for smaller tabular dataset often do not improve the efficiency.
See <code><a href='https://torch.mlverse.org/docs/articles/installation.html'>vignette("installation", package = "torch")</a></code> fo help to enable running on the GPU (only Linux and Windows).</dd>


<dt>mode_train</dt>
<dd>Logical. If <code>TRUE</code>, the returned <code>vaeac</code> model is set to be in training mode.
If <code>FALSE</code>, the returned <code>vaeac</code> model is set to be in evaluation mode.</dd>

</dl>

Function to load a <code>vaeac</code> model and set it in the right state and mode

vaeac_get_model_from_checkp: Function to load a `vaeac` model and set it in the right state and mode

Description

Usage

Value

Arguments

Author