Keras Set Output Layers

Allows to manipulate the network architecture of a Keras deep learning model by choosing a new set of output tensors of the model. Of the original layers of the model, only those that are relevant to produce the selected outputs are retained. The new outputs must be selected in the node configuration.

Options

Output Selection

Add output

Add an output tensor to the list of selected outputs. A dialog will be shown that allows to select which tensor should be added.

Remove

Remove the particular output from the list of selected outputs.

Input Ports

The Keras deep learning network.

Output Ports

A Keras deep learning network with the selected outputs.

Best Friends (Incoming)

• Keras Dense Layer (28 %) 
• Keras Network Learner (17 %) 
• Keras Dropout Layer (13 %) 
• Keras Softmax Layer (4 %) 
• Keras Flatten Layer (4 %) 
• Show all 21 recommendations

Best Friends (Outgoing)

• Keras Network Learner (58 %) 
• Keras Network Executor (14 %) Streamable
• Keras Freeze Layers (6 %) 
• Keras Network Writer (5 %) 
• Keras Dense Layer (5 %) 
• Show all 9 recommendations

Workflows

• Train-VGG16-binary (KNIME Hub) 

Installation

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

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.

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.