model_to_json

model_from_json

Save and re-load models configurations as JSON. Note that the representation
does not include the weights, only the architecture.

Interface to 'Keras' <https://keras.io>, a high-level neural
networks 'API'. 'Keras' was developed with a focus on enabling fast experimentation,
supports both convolution based networks and recurrent networks (as well as
combinations of the two), and runs seamlessly on both 'CPU' and 'GPU' devices.

Tomasz Kalinowski

keras

R Interface to 'Keras'

Daniel Falbel

JJ Allaire

François Chollet

RStudio 

Google 

Yuan Tang

Wouter Van Der Bijl

Martin Studer

Sigrid Keydana

model_to_json function

<dl><dt>object</dt>
<dd>Model object to save</dd>
<dt>json</dt>
<dd>JSON with model configuration</dd>
<dt>custom_objects</dt>
<dd>Optional named list mapping names to custom classes or
functions to be considered during deserialization.</dd></dl>

Arguments

Model configuration as JSON — model_to_json

<dl>

<dt>object</dt>
<dd>Model object to save</dd>


<dt>json</dt>
<dd>JSON with model configuration</dd>


<dt>custom_objects</dt>
<dd>Optional named list mapping names to custom classes or
functions to be considered during deserialization.</dd>

</dl>

Model configuration as JSON

model_to_json: Model configuration as JSON

Description

Usage

Arguments

See Also