DL4J Feedforward Predictor (Classification) (legacy)

This node creates a classification prediction using the supplied network and test data. The node is intended to be used with the DL4J Feedforward Learner (Classification) node. The output is a column containing the predicted class value for each example in the input table. If specified, additional columns containing the the probability for each class value will be appended.

The KNIME Deeplearning4J Integration has been marked as legacy with KNIME Analytics Platform 5.0 and will be deprecated in a future version. If you are using this extension in a production workflow, consider switching to one of the other deep learning integrations available in KNIME Analytics Platform.

Options

Change prediction column name?
Whether to change the name of the prediction column. If so enter the new name into the text box.
Append columns with class probabilities?
Whether to append columns containing probabilities for each individual class value.
Probability Column Suffix
Suffix for the probability columns. Their names are like: P(trainingColumn=value).

Input Ports

Icon
Classification Deep Learning Model.
Icon
Data table containing testing data.

Output Ports

Icon
Input data with prediction columns.

Popular Predecessors

Popular Successors

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.

Installation

To use this node in KNIME, install the extension KNIME Deeplearning4J Integration (64bit only) (legacy) from the below update site following our NodePit Product and Node Installation Guide:

v5.3

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

Plugin provider: KNIME AG, Zurich, Switzerland
Plugin version: 5.3.0.v202312081534
On NodePit since: 2024-07-09
Last update: 2024-11-15
KNIME versions: Since v3.6

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!