KNIME Deep Learning - Keras Integration version 3.6.0.v201807091039 by KNIME AG, Zurich, Switzerland
The softmax function is commonly used as the last layer in a classification network. It transforms an unconstrained n-dimensional vector into a valid probability distribution. Note that the input to a softmax must have at least one dimension in addition to the batch dimension. Corresponds to the Keras Softmax Layer.
To use this node in KNIME, install KNIME Deep Learning - Keras Integration from the following update site: