This workflow shows how a model created with Keras can be converted to be used with the TensorFlow 2 integration. This demonstrated by using a very small Keras network build with the Keras layer nodes. However, this method works for every Keras Network (trained or untrained). After the model is converted to TensorFlow 2 it can make use of the feature only available for TensorFlow 2 like adding custom layers and TensorFlow Hub layers. In order to run the example, please make sure you have the following KNIME extensions installed: * KNIME Deep Learning - TensorFlow 2 Integration (Labs) * KNIME Deep Learning - Keras Integration (Labs) You also need a local Python installation that includes TensorFlow 2 and a local Python installation that includes Keras. TensorFlow 2 must be selected to be used for the "DL Python" nodes on the "Python Deep Learning" preference page. Please refer to https://docs.knime.com/latest/deep_learning_installation_guide/#dl_python_setup for installation recommendations and further information.
This is a companion discussion topic for the original entry at https://kni.me/w/2s1Q1r1dzYfPDUvz