Keras Softmax Layer
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.
- Type: DLKerasNetworkPortObjectBase The Keras deep learning network to which to add a <tt>Softmax</tt> layer.
- Type: DLKerasNetworkPortObjectBase The Keras deep learning network with an added <tt>Softmax</tt> layer.
KNIME Labs > Deep Learning > Keras > Layers > Advanced Activations
Make sure to have this extension installed:
KNIME Deep Learning - Keras Integration
Update site for KNIME Analytics Platform 3.7:
KNIME Analytics Platform 3.7 Update Site