Keras Freeze Layers

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.

Views

This node has no views

Workflows

Links

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.