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

Basic 11 Layer - 1D resnet builder

create_resnet(
  ni,
  nout,
  kss = c(9, 5, 3),
  conv_sizes = c(64, 128, 128),
  stride = 1
)

<table summary="R argblock">
<tr valign="top">
<td><code>ni</code></td>
<td>
number of input channels
</td>
</tr>
<tr valign="top">
<td><code>nout</code></td>
<td>
output shape
</td>
</tr>
<tr valign="top">
<td><code>kss</code></td>
<td>
kernel size
</td>
</tr>
<tr valign="top">
<td><code>conv_sizes</code></td>
<td>
convolution sizes
</td>
</tr>
<tr valign="top">
<td><code>stride</code></td>
<td>
stride
</td>
</tr>
</table>

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

create_resnet

Description

Usage

Arguments

Value

fastai

We don't support your browser anymore

`ni`	number of input channels
`nout`	output shape
`kss`	kernel size
`conv_sizes`	convolution sizes
`stride`	stride