nn_prune_head.tabnet_fit

nn_prune_head.tabnet_pretrain

Prune <code>head_size</code> last layers of a tabnet network in order to
use the pruned module as a sequential embedding module.

Implements the 'TabNet' model by Sercan O. Arik et al. (2019) <arXiv:1908.07442>
and provides a consistent interface for fitting and creating predictions. It's
also fully compatible with the 'tidymodels' ecosystem.

Christophe Regouby

tabnet

Fit 'TabNet' Models for Classification and Regression

Daniel Falbel

 RStudio

Egill Fridgeirsson

Philipp Haarmeyer

nn_prune_head.tabnet_fit function

<dl><dt>x</dt>
<dd>nn_network to prune</dd>
<dt>head_size</dt>
<dd>number of nn_layers to prune, should be less than 2</dd></dl>

Arguments

Prune top layer(s) of a tabnet network — nn_prune_head.tabnet_fit

<dl>

<dt>x</dt>
<dd>nn_network to prune</dd>


<dt>head_size</dt>
<dd>number of nn_layers to prune, should be less than 2</dd>

</dl>

nn_prune_head.tabnet_fit: Prune top layer(s) of a tabnet network

Description

Usage

Value

Arguments