The 'fastai' <https://docs.fast.ai/index.html> library
simplifies training fast and accurate neural networks
using modern best practices. It is based on research
in to deep learning best practices undertaken
at 'fast.ai', including 'out of the box' support
for vision, text, tabular, audio, time series, and
collaborative filtering models.

Interface to 'fastai'

package-ubuntu-20.04-r-4.0.5#cran#fastai-2.0.7

Computes the local lr before weight decay is applied

larc_layer_lr(p, lr, trust_coeff, wd, eps, clip = TRUE, ...)

<table summary="R argblock">
<tr valign="top">
<td><code>p</code></td>
<td>
p
</td>
</tr>
<tr valign="top">
<td><code>lr</code></td>
<td>
learning rate
</td>
</tr>
<tr valign="top">
<td><code>trust_coeff</code></td>
<td>
trust_coeff
</td>
</tr>
<tr valign="top">
<td><code>wd</code></td>
<td>
weight decay
</td>
</tr>
<tr valign="top">
<td><code>eps</code></td>
<td>
epsilon
</td>
</tr>
<tr valign="top">
<td><code>clip</code></td>
<td>
clip
</td>
</tr>
<tr valign="top">
<td><code>...</code></td>
<td>
additional arguments to pass
</td>
</tr>
</table>

package-ubuntu-20.04-r-4.0.5#cran#fastai-2.0.7#docs#larc_layer_lr

`p`	p
`lr`	learning rate
`trust_coeff`	trust_coeff
`wd`	weight decay
`eps`	epsilon
`clip`	clip
`...`	additional arguments to pass

larc_layer_lr

Description

Usage

Arguments

Value

fastai

We don't support your browser anymore