Different options to train an autoencoder using TensorFlow 2

Workflow

Different options to train an autoencoder using TensorFlow 2

autoencoder Keras neural network deep learning fraud detection +3

Last edited:

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.

Legal

By using or downloading the workflow, you agree to our terms and conditions.

Different options to train an autoencoder using TensorFlow 2

Used extensions & nodes

KNIME Base nodes Trusted extension

KNIME Deep Learning - Keras Integration Trusted extension

KNIME Deep Learning - TensorFlow 2 Integration Trusted extension

KNIME Expressions Trusted extension

KNIME JavaScript Views (Labs) Trusted extension

KNIME Javasnippet Trusted extension

KNIME Math Expression (JEP) Trusted extension

KNIME Optimization extension Trusted extension

Legal

Discussion

KNIME Base nodes

KNIME Deep Learning - Keras Integration

KNIME Deep Learning - TensorFlow 2 Integration

KNIME Expressions

KNIME JavaScript Views (Labs)

KNIME Javasnippet

KNIME Math Expression (JEP)

KNIME Optimization extension