layer_prs

.layer

.out

.is_output

These pronouns provide a cleaner, more readable way to reference layer parameters
in formula-based specifications for <code>nn_module_generator()</code> and related functions.
They work similarly to <code><a href="https://rlang.r-lib.org/reference/dot-data.html">rlang::.data</a></code> and <code><a href="https://rlang.r-lib.org/reference/dot-data.html">rlang::.env</a></code>.

datasets

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_prs function

An object of class <code>layer_pr</code> (inherits from <code>list</code>) of length 0.
An object of class <code>layer_index_pr</code> (inherits from <code>layer_pr</code>, <code>list</code>) of length 0.
An object of class <code>layer_input_pr</code> (inherits from <code>layer_pr</code>, <code>list</code>) of length 0.
An object of class <code>layer_output_pr</code> (inherits from <code>layer_pr</code>, <code>list</code>) of length 0.
An object of class <code>layer_is_output_pr</code> (inherits from <code>layer_pr</code>, <code>list</code>) of length 0.

Format

<div class="sourceCode r"></div><pre><code># Using individual pronouns
layer_arg_fn = ~ list(
 input_size = .in,
 hidden_size = .out,
 num_layers = if (.i == 1) 2L else 1L
)# Using .layer pronoun (alternative syntax)
layer_arg_fn = ~ list(
 input_size = .layer$ind,
 hidden_size = .layer$out,
 is_first = .layer$i == 1
)
</code></pre>

Usage

These pronouns provide a cleaner, more readable way to reference layer parameters
in formula-based specifications for <code>nn_module_generator()</code> and related functions.
They work similarly to <code><a href='https://rlang.r-lib.org/reference/dot-data.html'>rlang::.data</a></code> and <code><a href='https://rlang.r-lib.org/reference/dot-data.html'>rlang::.env</a></code>.

Layer argument pronouns for formula-based specifications — layer_prs

<div class="sourceCode r"><pre><code># Using individual pronouns
layer_arg_fn = ~ list(
 input_size = .in,
 hidden_size = .out,
 num_layers = if (.i == 1) 2L else 1L
)

# Using .layer pronoun (alternative syntax)
layer_arg_fn = ~ list(
 input_size = .layer$ind,
 hidden_size = .layer$out,
 is_first = .layer$i == 1
)
</code></pre></div>

layer_prs: Layer argument pronouns for formula-based specifications

Description

Usage

Arguments

Format

Usage

Details