0 ×

ONNX to TensorFlow Network Converter

KNIME Deep Learning - ONNX Integration version 4.3.0.v202012011121 by KNIME AG, Zurich, Switzerland

Converts an ONNX deep learning model to a TensorFlow model. TensorFlow models can be executed using the TensorFlow Network Executor.
This node uses the Python libraries "onnx" and "onnx-tf". To use this node, make sure that the Python integration is set up correctly (see KNIME Python Integration Installation Guide ) and the libraries "onnx" and "onnx-tf" are installed in the configured Python environment. You can install the libraries into an existing environment by running " pip install onnx onnx-tf ". Alternatively, you can create a new Conda environment with all dependencies of the KNIME Deep Learning Integration on the "Python Deep Learning" preference page (see Setting up Python for KNIME Deep Learning ).

Input Ports

The ONNX deep learning network.

Output Ports

The TensorFlow deep learning network.

Best Friends (Incoming)

Best Friends (Outgoing)



To use this node in KNIME, install KNIME Deep Learning - ONNX Integration from the following update site:


A zipped version of the software site can be downloaded here.

You don't know what to do with this link? Read our NodePit Product and Node Installation Guide that explains you in detail how to install nodes to your KNIME Analytics Platform.

Wait a sec! You want to explore and install nodes even faster? We highly recommend our NodePit for KNIME extension for your KNIME Analytics Platform. Browse NodePit from within KNIME, install nodes with just one click and share your workflows with NodePit Space.


You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.