This workflow shows the different options of training and executing a network using TF2 on the example of an autoencoder: Option 1: Define network using Keras Layer nodes, train and execute using TF2 Option 2: Define network using Python code, train and execute using TF2 Option 3. Define and train the network using Keras, convert and save as TF2 model, read TF2 model, and execute network using TF2.
Used extensions & nodes
Created with KNIME Analytics Platform version 4.2.0
Loading ad hoc jobs
By using or downloading the workflow, you agree to our terms and conditions.