Icon

03_​Generate_​Music

Deploy RNN to Generate Music

This workflows uses a trained RNN to generate new music.

Read trained network, define outputs, and convert network toTensorFlow model Apply network, sample first note and startcollection cells for generated sequences Predict the next values in the squence using the last predicted values & hidden states andupdate the collection cells for the generated sequences To execute this workflow you need a conda environment with keras,music21, and tensorflow-mkl. This Conda Environment Propagationnode creates a new environment with all necessary packages. Remove network inputsOutput: Collections of predicted valuesApply dictionaryOffset_diff to offsetRead trained networkDefine outputsRead note dictionarySample first noteCreate midi fileCreate Conda Env Create start tokensand hidden states Recursive LoopStart (deprecated) Recursive LoopEnd (deprecated) TensorFlowNetwork Executor Column Filter Column Appender Post-processing Sample note andupdate inputs Keras NetworkReader Keras SetOutput Layers Keras to TensorFlowNetwork Converter TensorFlowNetwork Executor Table Reader Start collection cellsfor all sequences Please select the outputlocation and file name Python Script Conda EnvironmentPropagation Read trained network, define outputs, and convert network toTensorFlow model Apply network, sample first note and startcollection cells for generated sequences Predict the next values in the squence using the last predicted values & hidden states andupdate the collection cells for the generated sequences To execute this workflow you need a conda environment with keras,music21, and tensorflow-mkl. This Conda Environment Propagationnode creates a new environment with all necessary packages. Remove network inputsOutput: Collections of predicted valuesApply dictionaryOffset_diff to offsetRead trained networkDefine outputsRead note dictionarySample first noteCreate midi fileCreate Conda EnvCreate start tokensand hidden states Recursive LoopStart (deprecated) Recursive LoopEnd (deprecated) TensorFlowNetwork Executor Column Filter Column Appender Post-processing Sample note andupdate inputs Keras NetworkReader Keras SetOutput Layers Keras to TensorFlowNetwork Converter TensorFlowNetwork Executor Table Reader Start collection cellsfor all sequences Please select the outputlocation and file name Python Script Conda EnvironmentPropagation

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: 2021-03-26
On NodePit since: 2021-09-16
Last update: 2024-04-25
Created with KNIME version: v4.6.0
Tags: Music GenerationRNN

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

Try NodePit Runner!