Icon

01_​Training

Generate Mountain Namesn (Training)
Generate Mountain Names (Training)The workflow builds, trains, and saves an RNN with an LSTM layer to generate new fictive mountain names. The brown nodes define the network structure. The "Pre-Processing" metdanoe readsoriginal mountain names and index-encodes them. The Keras Network Learner node trains the network using index-encoded original mountain names. Finally, the trained network is prepared fordeployment, transformed into a TensorFlow model, and saved to a file.In order to run the example, please make sure you have the following KNIME extensions installed:* KNIME Deep Learning - Keras Integration (Labs)* KNIME Deep Learning - TensorFlow Integration* KNIME Python IntegrationYou also need a local Python installation that includes Keras. Please refer to https://www.knime.com/deeplearning#keras for installation recommendations and further information. Define Network Read and Pre-Process Input Data Train Network Edit and Save Networks Add Temperatureand Remove DropoutInput Shape?, Dictionary SizeRegularizationOutput: Sequence of Hidden StatesActivation: LinearActivation:Softmax DL PythonNetwork Editor Keras NetworkLearner Keras Input Layer Keras Dropout Layer Pre-Processing Keras to TensorFlowNetwork Converter TensorFlowNetwork Writer Keras LSTM Layer Keras Dense Layer Keras Dense Layer Generate Mountain Names (Training)The workflow builds, trains, and saves an RNN with an LSTM layer to generate new fictive mountain names. The brown nodes define the network structure. The "Pre-Processing" metdanoe readsoriginal mountain names and index-encodes them. The Keras Network Learner node trains the network using index-encoded original mountain names. Finally, the trained network is prepared fordeployment, transformed into a TensorFlow model, and saved to a file.In order to run the example, please make sure you have the following KNIME extensions installed:* KNIME Deep Learning - Keras Integration (Labs)* KNIME Deep Learning - TensorFlow Integration* KNIME Python IntegrationYou also need a local Python installation that includes Keras. Please refer to https://www.knime.com/deeplearning#keras for installation recommendations and further information. Define Network Read and Pre-Process Input Data Train Network Edit and Save Networks Add Temperatureand Remove DropoutInput Shape?, Dictionary SizeRegularizationOutput: Sequence of Hidden StatesActivation: LinearActivation:Softmax DL PythonNetwork Editor Keras NetworkLearner Keras Input Layer Keras Dropout Layer Pre-Processing Keras to TensorFlowNetwork Converter TensorFlowNetwork Writer Keras LSTM Layer Keras Dense Layer Keras Dense Layer

Nodes

Extensions

Links