Icon

Map Softmax Output to Class Names Example

This workflow shows how to map softmax output of a classification network to class names.

Create mapping of class index to class name (they are the same in this case because we predict numbers) MNIST imagesMNIST imagessimple, untrainedCNNinput: untrained net andtraining images with labelsoutput: trained net- -5 epochs(increase to improve accuracy)Find prediction with highest probability Preparetraining data Prepare test data DL PythonNetwork Creator Keras NetworkLearner Keras NetworkExecutor Column Expressions ExtractColumn Header Transpose Column Filter Counter Generation Column Rename Joiner RowID Create mapping of class index to class name (they are the same in this case because we predict numbers) MNIST imagesMNIST imagessimple, untrainedCNNinput: untrained net andtraining images with labelsoutput: trained net- -5 epochs(increase to improve accuracy)Find prediction with highest probabilityPreparetraining data Prepare test data DL PythonNetwork Creator Keras NetworkLearner Keras NetworkExecutor Column Expressions ExtractColumn Header Transpose Column Filter Counter Generation Column Rename Joiner RowID

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: marcel
Created at: 2017-07-05
On NodePit since: 2020-04-22
Last update: 2024-12-24
Created with KNIME version: v4.1.2
Tags: deep learningKerasimage classification

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

Try NodePit Runner!