Icon

04_​Edit_​MNIST_​SavedModel

Edit MNIST SavedModel

This workflow shows how to edit a TensorFlow model using the TensorFlow Python API by adding an additional output to a model.
The loaded model does classification on MNIST but only outputs the probabilities for each class. We edit the model such that it outputs the class as well.

In order to run the example, please make sure you have the following KNIME extensions installed:

* KNIME Deep Learning - TensorFlow Integration (Labs)
* KNIME Image Processing (Community Contributions Trusted)
* KNIME Image Processing - Deep Learning Extension (Community Contributions Trusted)

Acknowledgements:

The architecture of the used network was taken but slightly changed from https://www.tensorflow.org/tutorials/layers.

The enclosed pictures are from the MNIST dataset (http://yann.lecun.com/exdb/mnist/) [1].

[1] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. "Gradient-based learning applied to document recognition." Proceedings of the IEEE, 86(11):2278-2324, November 1998.

KNIME Deep Learning - TensorFlow - Edit MNIST SavedModelThis workflow shows how to edit a TensorFlow model using the TensorFlowPython API by adding an additional output to a model.The loaded model does classification on MNIST but only outputs theprobabilities for each class. We edit the model such that it outputs the classas well. Execute ontest dataMNIST imagesopenView: Confusion MatrixRead a modelwhich has been trainedon MNISTAdd ouput layerfor predicted classOnly keep maxprobability DL Network Executor(deprecated) Prepare test data Scorer Image Viewer TensorFlowNetwork Reader DL PythonNetwork Editor Column Aggregator KNIME Deep Learning - TensorFlow - Edit MNIST SavedModelThis workflow shows how to edit a TensorFlow model using the TensorFlowPython API by adding an additional output to a model.The loaded model does classification on MNIST but only outputs theprobabilities for each class. We edit the model such that it outputs the classas well. Execute ontest dataMNIST imagesopenView: Confusion MatrixRead a modelwhich has been trainedon MNISTAdd ouput layerfor predicted classOnly keep maxprobabilityDL Network Executor(deprecated) Prepare test data Scorer Image Viewer TensorFlowNetwork Reader DL PythonNetwork Editor Column Aggregator

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: bw
Created at: 2018-06-25
On NodePit since: 2019-07-12
Last update: 2024-04-26
Created with KNIME version: v4.1.0
Tags: deep learningTensorFlowimage classification

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!