Hub
WorkflowWorkflow

Different options to train an autoencoder using TensorFlow 2

Autoencoder Keras Neural network Deep learning Fraud detection
+3

Last edited: 

Drag & drop
Like
Download workflow
Copy short link
Workflow preview
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
  • KNIME Base nodes Trusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.2.0

    knime
  • KNIME Deep Learning - Keras Integration Trusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.2.0

    knime
  • KNIME Deep Learning - TensorFlow 2 Integration Trusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.2.0

    knime
  • KNIME Expressions Trusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.2.0

    knime
  • KNIME JavaScript Views (Labs) Trusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.2.0

    knime
  • KNIME Javasnippet Trusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.2.0

    knime
  • KNIME Math Expression (JEP) Trusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.2.0

    knime
  • KNIME Optimization extension Trusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.2.0

    knime
Discussion