Icon

01_​Generate_​Mountain_​Names_​Training

Generate Mountain Names (Training)

This workflow builds, trains, and saves an (many to many) RNN with an LSTM layer to generate new fictive mountain names.

The brown nodes define the network structure. The "Pre-Processing" metdanoe reads original mountain names, index-encodes them, and creates input and output sequences, which are shifted by one character. The Keras Network Learner node trains the network using index-encoded original mountain names. Finally, the trained network is prepared for deployment, transformed into a TensorFlow model, and saved to a file.


Define Network Read and Pre-Process Input Data Train Network Edit and Save Networks Input Shape?, Dictionary SizeRegularizationOutput: Sequence of Hidden StatesActivation: LinearAdd Temperatureand Remove Dropout Keras Input Layer Keras Dropout Layer Pre-Processing Keras LSTM Layer Keras Dense Layer Keras Softmax Layer Keras NetworkLearner DL PythonNetwork Editor TensorFlowNetwork Writer Keras to TensorFlowNetwork Converter Define Network Read and Pre-Process Input Data Train Network Edit and Save Networks Input Shape?, Dictionary SizeRegularizationOutput: Sequence of Hidden StatesActivation: LinearAdd Temperatureand Remove Dropout Keras Input Layer Keras Dropout Layer Pre-Processing Keras LSTM Layer Keras Dense Layer Keras Softmax Layer Keras NetworkLearner DL PythonNetwork Editor TensorFlowNetwork Writer Keras to TensorFlowNetwork Converter

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: kathrinmelcher
Created at: 2018-10-25
On NodePit since: 2020-12-17
Last update: 2024-09-08
Created with KNIME version: v4.2.3
Tags: deep learningkerastext generationRNNLSTMtext analysissequence analysisneural networktext processing

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

Try NodePit Runner!