This repository is maintained by the KNIME Team Rakete.
KNIME Analytics Platform - Deeplearning4J Integration enables you to use deep neural networks in KNIME. The extension consists of a set of new nodes which allow you to modularly assemble a deep neural network architecture, train the network on data, and use the trained network for predictions.
The integration is based on Deeplearning4J, which is an open-source Deep Learning library that runs on the JVM.
Please note: The KNIME - Deeplearning4J Integration is contained in KNIME Labs.
This repository contains the source code for the KNIME - Deeplearning4J Integration. The code is organized as follows:
- org.knime.ext.dl4j.base: Deeplearning4J Integration nodes
- org.knime.ext.dl4j.bin.*: CPU/GPU backend fragments
- org.knime.ext.dl4j.libs: DL4J Library, dependencies, and OSGi plugin activator
- org.knime.ext.dl4j.testing : Deeplearning4J Integration testing nodes
The KNIME - Deeplearning4J Integration contains two additional extensions for text and image processing:
- KNIME Analytics Platform - Deeplearning4J Text Processing Extension: Provides nodes to train and use Word Vector Models (Word2Vec & Doc2Vec).
- KNIME Analytics Platform - Deeplearning4J Image Processing Extension: Provides converters which allows you to use images from KNIME Analytics Platform - Image Processing Extension as input for deep networks. See project repository on GitHub.
You can find instructions on how to work with our code or develop extensions for KNIME Analytics Platform in the knime-sdk-setup repository on BitBucket or GitHub.