The KNIME deep learning extensions bring new deep learning capabilities to the KNIME Analytics Platform. These deep learning extensions allow users to read, create, edit, train, and execute deep neural networks within KNIME Analytics Platform.
Documentation
Here is the detailed documentation for the KNIME Deep Learning Integration.
KNIME Deep Learning Integrations
KNIME Deep Learning - Keras Integration

The KNIME Deep Learning - Keras Integration utilizes the Keras deep learning framework to enable users to read, write, train, and execute Keras deep learning networks within KNIME. Furthermore, users can also build custom deep learning networks directly in KNIME via the Keras layer nodes.
KNIME Deep Learning - TensorFlow Integration

The KNIME Deep Learning - TensorFlow Integration provides access to the powerful machine learning library TensorFlow* within KNIME. This enables users to read, write, train, and execute TensorFlow networks directly in KNIME. Additionally, users can convert their Keras networks to TensorFlow networks with this extension for even greater flexibility.
* TensorFlow, the TensorFlow logo and any related marks are trademarks of Google Inc.
Python
Advanced users can further customize their deep learning workflows by utilizing the DL Python nodes. These nodes are included with the Keras and TensorFlow integrations.