layer-attributes

$.layer_pr

internal

Provides a higher-level interface to the 'torch' package for defining,
training, and fine-tuning neural networks, including its depth, powered by code generation.
This package supports few to several architectures, including feedforward (multi-layer perceptron)
and recurrent neural networks (Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU)),
while also reduces boilerplate 'torch' code while enabling seamless integration with 'torch'. The model methods
to train neural networks from this package also bridges to titanic ML frameworks in R, namely
'tidymodels' ecosystem, which enables the 'parsnip' model specifications, workflows, recipes,
and tuning tools.

Joshua Marie

kindling

Higher-Level Interface of 'torch' Package to Auto-Train Neural
Networks

Antoine Soetewey

layer-attributes function

<dl><dt>x</dt>
<dd>The .layer itself</dd>
<dt>name</dt>
<dd>It could be the following:<ul>
<li><code>i</code>: Layer index (1-based integer)</li>
<li><code>ind</code>: Input dimension for the layer</li>
<li><code>out</code>: Output dimension for the layer</li>
<li><code>is_output</code>: Logical indicating if this is the output layer</li>
</ul></dd></dl>

Arguments

"Layer" attributes — layer-attributes

<dl>

<dt>x</dt>
<dd>The .layer itself</dd>


<dt>name</dt>
<dd>It could be the following:<ul>
<li><code>i</code>: Layer index (1-based integer)</li>
<li><code>ind</code>: Input dimension for the layer</li>
<li><code>out</code>: Output dimension for the layer</li>
<li><code>is_output</code>: Logical indicating if this is the output layer</li>
</ul></dd>

</dl>

layer-attributes: "Layer" attributes

Description

Usage

Value

Arguments