0 ×

Keras Freeze Layers

KNIME Deep Learning - Keras Integration version 4.3.0.v202012011122 by KNIME AG, Zurich, Switzerland

Freezes the parameters of the selected layers. If the model is trained afterwards, the parameters of the selected layers are not updated. All other layers are set to trainable.

Options

Freeze Layers

Not trainable layers
The list contains the layer names of the layers that should not be trainable in the output network.
Enforce inclusion
Select to force the list of not trainable layers not to change. Even if other layers are added to the input network. Other layers are then added to the trainable layers list.
Trainable layers
The list contains the layer names of the layers that should be trainable in the output network.
Enforce exclusion
Select to force the list of trainable layers not to change. Even if other layers are added to the input network. Other layers are then added to the not trainable layers list.
Wildcard/Regex Selection
Use a wildcard or regular expression to select the layers which should be not trainable.

Input Ports

Icon
The Keras deep learning network.

Output Ports

Icon
The Keras deep learning network with the selected layers set to not-trainable and all other layers set to trainable.

Best Friends (Incoming)

Best Friends (Outgoing)

Workflows

Installation

To use this node in KNIME, install KNIME Deep Learning - Keras Integration from the following update site:

KNIME 4.3

A zipped version of the software site can be downloaded here.

You don't know what to do with this link? Read our NodePit Product and Node Installation Guide that explains you in detail how to install nodes to your KNIME Analytics Platform.

Wait a sec! You want to explore and install nodes even faster? We highly recommend our NodePit for KNIME extension for your KNIME Analytics Platform. Browse NodePit from within KNIME, install nodes with just one click and share your workflows with NodePit Space.

Developers

You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.